https://wiki.linux-nfs.org/wiki/index.php?title=Special:Contributions/65.172.181.6&feed=atom&limit=50&target=65.172.181.6&year=&month=
Linux NFS - User contributions [en]
2024-03-28T08:09:10Z
From Linux NFS
MediaWiki 1.16.5
https://wiki.linux-nfs.org/wiki/index.php/Main_Page
Main Page
2005-11-15T23:32:31Z
<p>65.172.181.6: </p>
<hr />
<div>NFS is a critical service in many organizations, and even a simple error can lead to major problems. NFSv4 promises to bring several key new features, but clearly it will be imperative to users that the new version of NFS be robust, that it perform well, and that it interoperate easily with other technologies.<br />
<br />
{|{|cellpadding="5" cellspacing="3" class="mainpagetable" width="100%"<br />
|- + <br />
|valign="top" style="padding: .5em 1em 1em; color: #000000; background-color: #d7e4f4; width: 33%"| <br />
'''General''' <br />
* [[NFSv4_Introduction|End user documentation]] <br />
* [[Comparison of NFS vs. others]] <br />
* [[Design|Design documentation]]<br />
* Active Directory<br />
** [[http://nfsworld.blogspot.com/2005/06/using-active-directory-as-your-kdc-for.html Linux, AD, and NetApp filers]] <br />
* [[How to get involved]] <br />
|valign="top"| <br />
'''Troubleshooting''' <br />
* [[General troubleshooting recommendations]] <br />
* Common error messages <br />
* Tools for troubleshooting <br />
* Problems exporting <br />
* Problems mounting<br />
* Problems automounting <br />
* Problems with Kerberos Authentication <br />
* [[Reporting bugs]] <br />
|valign="top" style="padding: .5em 1em 1em; color: #000000; background-color: #d7e4f4; width:33%"| <br />
'''Testing''' <br />
* [[Testing tools]]<br />
* [[Emulating tools]]<br />
* [[Functional testing]]<br />
* [[Interoperability testing]]<br />
* [[Performance testing]]<br />
* [[Robustness testing]]<br />
* [[Security testing]] <br />
* [[Tests needed]]<br />
* [[Testing methodologies]]<br />
* [[Test_matrix|Test matrix]]<br />
* [[Testing forecast roadmap]]<br />
|}<br />
==Testing ==<br />
<br />
The Linux NFSv4 Testing effort seeks to ensure that the Linux<br />
implementation of NFSv4 succeeds on all these counts. The purpose of the testing is threefold:<br />
* To prove that the features are implemented correctly according to spec.<br />
* To locate and identify bugs, and verify the fixes. <br />
* To give confidence to users that upgrading to NFSv4 on Linux is of benefit.</div>
65.172.181.6
https://wiki.linux-nfs.org/wiki/index.php/Main_Page
Main Page
2005-11-15T17:48:14Z
<p>65.172.181.6: Spam revert</p>
<hr />
<div>NFS is a critical service in many organizations, and even a simple error can lead to major problems. NFSv4 promises to bring several key new features, but clearly it will be imperative to users that the new version of NFS be robust, that it perform well, and that it interoperate easily with other technologies.<br />
<br />
{|{|cellpadding="5" cellspacing="3" class="mainpagetable" width="100%"<br />
|- + <br />
|valign="top" style="padding: .5em 1em 1em; color: #000000; background-color: #d7e4f4; width: 33%"| <br />
'''General''' <br />
* [[NFSv4_Introduction|End user documentation]] <br />
* [[Comparison of NFS vs. others]] <br />
* [[Design|Design documentation]]<br />
* Active Directory<br />
** [[http://nfsworld.blogspot.com/2005/06/using-active-directory-as-your-kdc-for.html Linux, AD, and NetApp filers]] <br />
* [[How to get involved]] <br />
|valign="top"| <br />
'''Troubleshooting''' <br />
* [[General troubleshooting recommendations]] <br />
* Common error messages <br />
* Tools for troubleshooting <br />
* Problems exporting <br />
* Problems mounting<br />
* Problems automounting <br />
* Problems with Kerberos Authentication <br />
* [[Reporting bugs]] <br />
|valign="top" style="padding: .5em 1em 1em; color: #000000; background-color: #d7e4f4; width:33%"| <br />
'''Testing''' <br />
* [[Testing tools]]<br />
* [[Emulating tools]]<br />
* [[Functional testing]]<br />
* [[Interoperability testing]]<br />
* [[Performance testing]]<br />
* [[Robustness testing]]<br />
* [[Security testing]] <br />
* [[Tests needed]]<br />
* [[Testing methodologies]]<br />
* [[Test_matrix|Test matrix]]<br />
* [[Testing forecast roadmap]]<br />
|}<br />
==Testing ==<br />
<br />
The Linux NFSv4 Testing effort seeks to ensure that the Linux<br />
implementation of NFSv4 succeeds on all these counts. The purpose of the testing is threefold:<br />
* To prove that the features are implemented correctly according to spec.<br />
* To locate and identify bugs, and verify the fixes. <br />
* To give confidence to users that upgrading to NFSv4 on Linux is of benefit.</div>
65.172.181.6
https://wiki.linux-nfs.org/wiki/index.php/Testing_forecast_roadmap
Testing forecast roadmap
2005-10-04T22:52:38Z
<p>65.172.181.6: /* Milestone 4: Enterprise Readiness */</p>
<hr />
<div>Linux NFSv4 Testing Roadmap<br />
---------------------------<br />
<br />
As of May 2005, we've completed a detailed itemization of testing work<br />
necessary for NFSv4, in a spreadsheet "Test Matrix", identifying items<br />
as High, Medium, and Low.<br />
<br />
This document seeks to divide the high priority work into achievable<br />
chunks that we as a community can strive to attain.<br />
<br />
I tried to prioritize for things that look reasonably easy to complete<br />
in the near term, that have owners, and/or are most likely to reveal<br />
issues that developers want to know about.<br />
<br />
<br />
==Milestone 0: Developer Testing Support==<br />
<br />
These testing tasks seek to put into place tools and practices that will<br />
help support development activities (including testing) on an ongoing<br />
basis.<br />
<br />
Functionality:<br />
I.B.1 [X] [OSDL] Automate running applicable existing functionality<br />
tests on codebase periodically: cthon, pynfs,<br />
iozone<br />
I.B.3 [X] [OSDL] Automate cross-compile testing for major platforms<br />
on each NFSv4 patchset<br />
I.C.2 [ ] [ ] Test install on Fedora Core of NFSv4 server &<br />
client, krb5, ldap, et al<br />
I.E.9 [ ] [ ] Verify ability to force operations (close files,<br />
change states, unmount)<br />
I.G.5 [ ] [Bull] Test compilation and functionality on IA-64<br />
I.G.7 [ ] [Bull] Test compilation and functionality on PPC-64<br />
I.K.2 [ ] [ ] Check that NFS HOWTO is updated with sufficient<br />
nfsv4 info<br />
<br />
Interop:<br />
II.A.1 [ ] [Bull] Kerberos (MIT) - verify basic functionality. Mount<br />
w/ krb5, etc.<br />
<br />
Robustness:<br />
III.A.3 [ ] [OSDL] Run NFS server for 2 wks with random configuration<br />
changes<br />
III.C.1 [ ] [Bull] Run LTP NFS fstress in a std config on each release<br />
<br />
Performance:<br />
IV.A.1 [ ] [Bull] Time to perform sequence of unique read/write<br />
operations<br />
IV.A.2 [ ] [Bull] Time to perform sequence of cacheable read/write<br />
operations<br />
IV.F.4 [ ] [Bull] Measure memory/network/CPU efficiency of client for<br />
fixed workload<br />
IV.G.3 [ ] [Bull] Measure effects of scaling up number of<br />
connections with exportfs/mount. Measure number of <br />
mounts per second on client and server.<br />
IV.J.2 [ ] [Bull] Measure performance when operating with Kerberos 5<br />
integrity and privacy<br />
<br />
Security:<br />
V.A.6 [ ] [ ] Audit the mountd code<br />
V.B.4 [ ] [OSDL] Run sparse as regression test periodically<br />
V.L.1 [ ] [ ] Ensure there is high level design documentation of<br />
NFSv4 security<br />
V.L.2 [ ] [ ] Ensure there is inline documentation for security<br />
related code in kernel<br />
V.L.3 [ ] [ ] Ensure there is inline documentation for GSS API<br />
(libgssapi, librpcsecgss)<br />
<br />
Misc:<br />
* [X] [OSDL] Establish bug tracking process for NFSv4<br />
<br />
==Milestone 1: Distro Quality Assurance==<br />
<br />
This milestone strives to attain a "Top Ten" list of testing that is<br />
felt will emphasize that NFSv4 is stable enough to be included in all<br />
enterprise distros. The focus is robustness, and items that would cause<br />
distros the most headaches if they're busted.<br />
<br />
I.A.5 [ ] [ ] Protocol implementation interoperability between<br />
Linux server and client<br />
I.C.5 [ ] [ ] Test install on SLES of NFSv4 server & client,<br />
krb5, ldap, et al<br />
I.C.6 [ ] [ ] Test install on RHEL of NFSv4 server & client,<br />
krb5, ldap, et al<br />
I.H.1 [ ] [ ] Verify compatibility with glibc<br />
I.H.9 [ ] [ IBM] Verify compatibility with automounter<br />
I.H.11 [ ] [ ] Verify compatibility with basic system tools<br />
(file utils, core utils, util-linux, mount, sar,<br />
iostat, etc.)<br />
I.K.4 [ ] [ ] Check that Network Admin Guide at tldp.org is<br />
updated for nfsv4<br />
II.E.2 [ ] [ ] Verify features of the Ext3 file system work under<br />
NFSv4<br />
III.A.1 [ ] [Bull] Run iozone for 2 wks on basic client/server<br />
operations<br />
III.A.2 [ ] [ ] Run automounter use case for 2 wks on amd, autofs,<br />
and autong<br />
III.A.4 [ ] [ ] Run connectathon locking tests against NFS server<br />
for 2 weeks<br />
III.E.1 [ ] [OSDL] Test short & long term local network failure<br />
(unplugged cable, ifdown eth0, etc.)<br />
III.E.2 [ ] [OSDL] Test short & long duration remote network partition<br />
III.E.3 [ ] [OSDL] Test behavior during crash/reboot of server with<br />
clients holding various states<br />
V.D.1 [ ] [ ] Review Authentication/ACL feature design<br />
V.E.1 [ ] [ ] Ensure a functionality test sufficiently tests<br />
Authentication/ACL<br />
<br />
==Milestone 2: Drill Down for One Use Case==<br />
<br />
This milestone strives to push NFSv4 through one complete use case, to<br />
give it some thorough exercise and scaling, and to establish a "case<br />
study" we can use as an example of NFSv4's value.<br />
<br />
I.E.5 [ ] [ ] Verify sufficient monitoring functionality within<br />
Ethereal<br />
I.F.1 [ ] [ ] Client notification to server of locking, write,<br />
read, etc.<br />
I.P.1 [ ] [OSDL] Database functionality on NFS<br />
I.L.1 [ ] [ ] Test compatibility with TCP protocol<br />
IV.A.7 [ ] [ ] NFSv3 vs. v4: Metadata - open/close intensive<br />
workload<br />
IV.A.8 [ ] [ ] NFSv3 vs. v4: Metadata - directory scanning<br />
IV.A.9 [ ] [ ] NFSv3 vs. v4: Metadata - create/delete<br />
IV.A.10 [ ] [ ] NFSv3 vs. v4: Metadata - changing attributes<br />
(chown, chmod) while dir scanning<br />
IV.E.1 [ ] [Bull] Test performance with large numbers of small (<4k)<br />
files<br />
IV.E.2 [ ] [Bull] Test performance with a few very large (>1G) files<br />
IV.F.4 [ ] [Bull] Measure memory/network/CPU efficiency of client<br />
for fixed workload<br />
IV.G.1 [ ] [ ] Verify server scalability with clients generating<br />
various basic requests (ACCESS, GETATTR, et al)<br />
IV.G.2 [ ] [ ] Verify server scalability with clients using<br />
compound requests<br />
V.D.6 [ ] [ ] Penetration testing for client callback<br />
implementation<br />
V.E.6 [ ] [ ] Ensure a functionality test sufficiently covers<br />
penetration testing for client callback<br />
implementation<br />
<br />
==Milestone 3: Enterprise Usability==<br />
<br />
This milestone focuses on testing that verifies "basic" usability of<br />
NFSv4 in data centers. It strives to establish that NFSv4 is able to<br />
perform basic functions in enterprise-class deployments.<br />
<br />
I.F.2 [ ] [ ] Reboot recovery<br />
I.F.4 [ ] [ ] Open with shares / deny<br />
I.F.5 [ ] [ ] Bumping a sequence ID<br />
I.F.6 [ ] [ ] Network partition recovery<br />
I.F.8 [ ] [ ] Locking (Non-blocking locks)<br />
I.H.3 [ ] [ ] Verify compatibility with Kerberos<br />
I.H.4 [ ] [ ] Verify compatibility with Ipsec<br />
I.H.5 [ ] [ ] Verify compatibility with POSIX ACLs<br />
I.H.6 [ ] [ ] Verify compatibility with NFS ACLs<br />
II.B.1 [ ] [Bull] Interoperability between 32-bit and 64-bit for<br />
client and server: IA32/AIX-PPC, IA32/Linux-PPC<br />
II.B.2 [ ] [Bull] Interoperability between little endian and big<br />
endian<br />
II.C.1 [ ] [Bull] Interoperability for Linux IA-32 client ? Solaris<br />
10 server<br />
II.C.4 [ ] [Bull] Interoperability for Linux IA-32 client ? AIX 5.3<br />
server<br />
III.D.7 [ ] [ ] Test correctness of NFS client when backed by a<br />
large (>100GB) cachefs<br />
IV.E.5 [ ] [ ] NFS "Cluster" scenario with 1000+ clients and<br />
several servers<br />
V.A.7 [ ] [ ] Audit the RPC authentication code (gssd, authsys,<br />
etc.)<br />
V.D.2 [ ] [ ] Review each security flavor feature design:<br />
Krb5, Spkm<br />
V.E.2 [ ] [ ] Ensure a functionality test sufficiently covers<br />
each security flavor<br />
<br />
<br />
==Milestone 4: Enterprise Readiness==<br />
<br />
This milestone builds on the previous one by ensuring that NFSv4 will<br />
behave well and perform robustly under typical enterprise-class loads.<br />
<br />
III.B.2 [ ] [ ] Test stability of client in out of memory<br />
situation<br />
III.B.3 [ ] [ ] Test stability of client in out of disk space on<br />
server situation<br />
III.B.4 [ ] [ ] Test stability of client in out of inode situation<br />
III.B.5 [ ] [ ] Test stability of client in out of swap space<br />
situation<br />
III.B.6 [ ] [ ] Test stability of server in out of pid situation<br />
III.B.7 [ ] [ ] Test stability of server in out of memory<br />
situation<br />
III.B.8 [ ] [ ] Test stability of server in out of disk space<br />
situation<br />
III.B.9 [ ] [ ] Test stability of server in out of inode situation<br />
III.B.10 [ ] [ ] Test stability of server in out of swap space<br />
situation<br />
III.D.1 [ ] [ ] Find maximum number of connections to Linux IA-32<br />
server<br />
III.D.4 [ ] [Bull] Find maximum number of mounted file systems on<br />
client<br />
III.E.4 [ ] [ ] Test multiple clients using, locking, etc. same<br />
files<br />
III.E.5 [ ] [ ] Test behavior of server with failed storage device<br />
III.E.6 [ ] [ ] Test behavior during crash of client with open<br />
delegations and locks<br />
III.E.7 [ ] [ ] Test recovery from denied permission<br />
III.E.8 [ ] [ ] Test recovery from JUKEBOX/DELAY<br />
III.E.9 [ ] [ ] Test recovery from ESTALE<br />
III.E.10 [ ] [ ] Test server callback mechanism (c.f. III.E.1,<br />
III.E.2)<br />
III.G.2 [ ] [ ] Test concurrent access tests for races in<br />
automounter<br />
IV.G.4 [ ] [Bull] Measure effects of increasing number of files<br />
IV.G.5 [ ] [Bull] Measure effects of increasing file size<br />
(with/without cache)<br />
IV.G.6 [ ] [Bull] Measure effects when increasing size of<br />
on-the-wire NFS read or write operations<br />
V.J.1 [ ] [Bull] Identify security issues assuming attack from<br />
client-side</div>
65.172.181.6
https://wiki.linux-nfs.org/wiki/index.php/Testing_forecast_roadmap
Testing forecast roadmap
2005-10-04T22:51:56Z
<p>65.172.181.6: /* Milestone 2: Drill Down for One Use Case */</p>
<hr />
<div>Linux NFSv4 Testing Roadmap<br />
---------------------------<br />
<br />
As of May 2005, we've completed a detailed itemization of testing work<br />
necessary for NFSv4, in a spreadsheet "Test Matrix", identifying items<br />
as High, Medium, and Low.<br />
<br />
This document seeks to divide the high priority work into achievable<br />
chunks that we as a community can strive to attain.<br />
<br />
I tried to prioritize for things that look reasonably easy to complete<br />
in the near term, that have owners, and/or are most likely to reveal<br />
issues that developers want to know about.<br />
<br />
<br />
==Milestone 0: Developer Testing Support==<br />
<br />
These testing tasks seek to put into place tools and practices that will<br />
help support development activities (including testing) on an ongoing<br />
basis.<br />
<br />
Functionality:<br />
I.B.1 [X] [OSDL] Automate running applicable existing functionality<br />
tests on codebase periodically: cthon, pynfs,<br />
iozone<br />
I.B.3 [X] [OSDL] Automate cross-compile testing for major platforms<br />
on each NFSv4 patchset<br />
I.C.2 [ ] [ ] Test install on Fedora Core of NFSv4 server &<br />
client, krb5, ldap, et al<br />
I.E.9 [ ] [ ] Verify ability to force operations (close files,<br />
change states, unmount)<br />
I.G.5 [ ] [Bull] Test compilation and functionality on IA-64<br />
I.G.7 [ ] [Bull] Test compilation and functionality on PPC-64<br />
I.K.2 [ ] [ ] Check that NFS HOWTO is updated with sufficient<br />
nfsv4 info<br />
<br />
Interop:<br />
II.A.1 [ ] [Bull] Kerberos (MIT) - verify basic functionality. Mount<br />
w/ krb5, etc.<br />
<br />
Robustness:<br />
III.A.3 [ ] [OSDL] Run NFS server for 2 wks with random configuration<br />
changes<br />
III.C.1 [ ] [Bull] Run LTP NFS fstress in a std config on each release<br />
<br />
Performance:<br />
IV.A.1 [ ] [Bull] Time to perform sequence of unique read/write<br />
operations<br />
IV.A.2 [ ] [Bull] Time to perform sequence of cacheable read/write<br />
operations<br />
IV.F.4 [ ] [Bull] Measure memory/network/CPU efficiency of client for<br />
fixed workload<br />
IV.G.3 [ ] [Bull] Measure effects of scaling up number of<br />
connections with exportfs/mount. Measure number of <br />
mounts per second on client and server.<br />
IV.J.2 [ ] [Bull] Measure performance when operating with Kerberos 5<br />
integrity and privacy<br />
<br />
Security:<br />
V.A.6 [ ] [ ] Audit the mountd code<br />
V.B.4 [ ] [OSDL] Run sparse as regression test periodically<br />
V.L.1 [ ] [ ] Ensure there is high level design documentation of<br />
NFSv4 security<br />
V.L.2 [ ] [ ] Ensure there is inline documentation for security<br />
related code in kernel<br />
V.L.3 [ ] [ ] Ensure there is inline documentation for GSS API<br />
(libgssapi, librpcsecgss)<br />
<br />
Misc:<br />
* [X] [OSDL] Establish bug tracking process for NFSv4<br />
<br />
==Milestone 1: Distro Quality Assurance==<br />
<br />
This milestone strives to attain a "Top Ten" list of testing that is<br />
felt will emphasize that NFSv4 is stable enough to be included in all<br />
enterprise distros. The focus is robustness, and items that would cause<br />
distros the most headaches if they're busted.<br />
<br />
I.A.5 [ ] [ ] Protocol implementation interoperability between<br />
Linux server and client<br />
I.C.5 [ ] [ ] Test install on SLES of NFSv4 server & client,<br />
krb5, ldap, et al<br />
I.C.6 [ ] [ ] Test install on RHEL of NFSv4 server & client,<br />
krb5, ldap, et al<br />
I.H.1 [ ] [ ] Verify compatibility with glibc<br />
I.H.9 [ ] [ IBM] Verify compatibility with automounter<br />
I.H.11 [ ] [ ] Verify compatibility with basic system tools<br />
(file utils, core utils, util-linux, mount, sar,<br />
iostat, etc.)<br />
I.K.4 [ ] [ ] Check that Network Admin Guide at tldp.org is<br />
updated for nfsv4<br />
II.E.2 [ ] [ ] Verify features of the Ext3 file system work under<br />
NFSv4<br />
III.A.1 [ ] [Bull] Run iozone for 2 wks on basic client/server<br />
operations<br />
III.A.2 [ ] [ ] Run automounter use case for 2 wks on amd, autofs,<br />
and autong<br />
III.A.4 [ ] [ ] Run connectathon locking tests against NFS server<br />
for 2 weeks<br />
III.E.1 [ ] [OSDL] Test short & long term local network failure<br />
(unplugged cable, ifdown eth0, etc.)<br />
III.E.2 [ ] [OSDL] Test short & long duration remote network partition<br />
III.E.3 [ ] [OSDL] Test behavior during crash/reboot of server with<br />
clients holding various states<br />
V.D.1 [ ] [ ] Review Authentication/ACL feature design<br />
V.E.1 [ ] [ ] Ensure a functionality test sufficiently tests<br />
Authentication/ACL<br />
<br />
==Milestone 2: Drill Down for One Use Case==<br />
<br />
This milestone strives to push NFSv4 through one complete use case, to<br />
give it some thorough exercise and scaling, and to establish a "case<br />
study" we can use as an example of NFSv4's value.<br />
<br />
I.E.5 [ ] [ ] Verify sufficient monitoring functionality within<br />
Ethereal<br />
I.F.1 [ ] [ ] Client notification to server of locking, write,<br />
read, etc.<br />
I.P.1 [ ] [OSDL] Database functionality on NFS<br />
I.L.1 [ ] [ ] Test compatibility with TCP protocol<br />
IV.A.7 [ ] [ ] NFSv3 vs. v4: Metadata - open/close intensive<br />
workload<br />
IV.A.8 [ ] [ ] NFSv3 vs. v4: Metadata - directory scanning<br />
IV.A.9 [ ] [ ] NFSv3 vs. v4: Metadata - create/delete<br />
IV.A.10 [ ] [ ] NFSv3 vs. v4: Metadata - changing attributes<br />
(chown, chmod) while dir scanning<br />
IV.E.1 [ ] [Bull] Test performance with large numbers of small (<4k)<br />
files<br />
IV.E.2 [ ] [Bull] Test performance with a few very large (>1G) files<br />
IV.F.4 [ ] [Bull] Measure memory/network/CPU efficiency of client<br />
for fixed workload<br />
IV.G.1 [ ] [ ] Verify server scalability with clients generating<br />
various basic requests (ACCESS, GETATTR, et al)<br />
IV.G.2 [ ] [ ] Verify server scalability with clients using<br />
compound requests<br />
V.D.6 [ ] [ ] Penetration testing for client callback<br />
implementation<br />
V.E.6 [ ] [ ] Ensure a functionality test sufficiently covers<br />
penetration testing for client callback<br />
implementation<br />
<br />
==Milestone 3: Enterprise Usability==<br />
<br />
This milestone focuses on testing that verifies "basic" usability of<br />
NFSv4 in data centers. It strives to establish that NFSv4 is able to<br />
perform basic functions in enterprise-class deployments.<br />
<br />
I.F.2 [ ] [ ] Reboot recovery<br />
I.F.4 [ ] [ ] Open with shares / deny<br />
I.F.5 [ ] [ ] Bumping a sequence ID<br />
I.F.6 [ ] [ ] Network partition recovery<br />
I.F.8 [ ] [ ] Locking (Non-blocking locks)<br />
I.H.3 [ ] [ ] Verify compatibility with Kerberos<br />
I.H.4 [ ] [ ] Verify compatibility with Ipsec<br />
I.H.5 [ ] [ ] Verify compatibility with POSIX ACLs<br />
I.H.6 [ ] [ ] Verify compatibility with NFS ACLs<br />
II.B.1 [ ] [Bull] Interoperability between 32-bit and 64-bit for<br />
client and server: IA32/AIX-PPC, IA32/Linux-PPC<br />
II.B.2 [ ] [Bull] Interoperability between little endian and big<br />
endian<br />
II.C.1 [ ] [Bull] Interoperability for Linux IA-32 client ? Solaris<br />
10 server<br />
II.C.4 [ ] [Bull] Interoperability for Linux IA-32 client ? AIX 5.3<br />
server<br />
III.D.7 [ ] [ ] Test correctness of NFS client when backed by a<br />
large (>100GB) cachefs<br />
IV.E.5 [ ] [ ] NFS "Cluster" scenario with 1000+ clients and<br />
several servers<br />
V.A.7 [ ] [ ] Audit the RPC authentication code (gssd, authsys,<br />
etc.)<br />
V.D.2 [ ] [ ] Review each security flavor feature design:<br />
Krb5, Spkm<br />
V.E.2 [ ] [ ] Ensure a functionality test sufficiently covers<br />
each security flavor<br />
<br />
<br />
==Milestone 4: Enterprise Readiness==<br />
<br />
This milestone builds on the previous one by ensuring that NFSv4 will<br />
behave well and perform robustly under typical enterprise-class loads.<br />
<br />
III.B.2 [ ] [ ] Test stability of client in out of memory<br />
situation<br />
III.B.3 [ ] [ ] Test stability of client in out of disk space on<br />
server situation<br />
III.B.4 [ ] [ ] Test stability of client in out of inode situation<br />
III.B.5 [ ] [ ] Test stability of client in out of swap space<br />
situation<br />
III.B.6 [ ] [ ] Test stability of server in out of pid situation<br />
III.B.7 [ ] [ ] Test stability of server in out of memory<br />
situation<br />
III.B.8 [ ] [ ] Test stability of server in out of disk space<br />
situation<br />
III.B.9 [ ] [ ] Test stability of server in out of inode situation<br />
III.B.10 [ ] [ ] Test stability of server in out of swap space<br />
situation<br />
III.D.1 [ ] [ ] Find maximum number of connections to Linux IA-32<br />
server<br />
III.D.4 [ ] [ ] Find maximum number of mounted file systems on<br />
client<br />
III.E.4 [ ] [ ] Test multiple clients using, locking, etc. same<br />
files<br />
III.E.5 [ ] [ ] Test behavior of server with failed storage device<br />
III.E.6 [ ] [ ] Test behavior during crash of client with open<br />
delegations and locks<br />
III.E.7 [ ] [ ] Test recovery from denied permission<br />
III.E.8 [ ] [ ] Test recovery from JUKEBOX/DELAY<br />
III.E.9 [ ] [ ] Test recovery from ESTALE<br />
III.E.10 [ ] [ ] Test server callback mechanism (c.f. III.E.1,<br />
III.E.2)<br />
III.G.2 [ ] [ ] Test concurrent access tests for races in<br />
automounter<br />
IV.G.4 [ ] [ ] Measure effects of increasing number of files<br />
IV.G.5 [ ] [ ] Measure effects of increasing file size<br />
(with/without cache)<br />
IV.G.6 [ ] [ ] Measure effects when increasing size of<br />
on-the-wire NFS read or write operations<br />
V.J.1 [ ] [ ] Identify security issues assuming attack from<br />
client-side</div>
65.172.181.6
https://wiki.linux-nfs.org/wiki/index.php/Testing_forecast_roadmap
Testing forecast roadmap
2005-10-04T22:51:26Z
<p>65.172.181.6: /* Milestone 1: Distro Quality Assurance */</p>
<hr />
<div>Linux NFSv4 Testing Roadmap<br />
---------------------------<br />
<br />
As of May 2005, we've completed a detailed itemization of testing work<br />
necessary for NFSv4, in a spreadsheet "Test Matrix", identifying items<br />
as High, Medium, and Low.<br />
<br />
This document seeks to divide the high priority work into achievable<br />
chunks that we as a community can strive to attain.<br />
<br />
I tried to prioritize for things that look reasonably easy to complete<br />
in the near term, that have owners, and/or are most likely to reveal<br />
issues that developers want to know about.<br />
<br />
<br />
==Milestone 0: Developer Testing Support==<br />
<br />
These testing tasks seek to put into place tools and practices that will<br />
help support development activities (including testing) on an ongoing<br />
basis.<br />
<br />
Functionality:<br />
I.B.1 [X] [OSDL] Automate running applicable existing functionality<br />
tests on codebase periodically: cthon, pynfs,<br />
iozone<br />
I.B.3 [X] [OSDL] Automate cross-compile testing for major platforms<br />
on each NFSv4 patchset<br />
I.C.2 [ ] [ ] Test install on Fedora Core of NFSv4 server &<br />
client, krb5, ldap, et al<br />
I.E.9 [ ] [ ] Verify ability to force operations (close files,<br />
change states, unmount)<br />
I.G.5 [ ] [Bull] Test compilation and functionality on IA-64<br />
I.G.7 [ ] [Bull] Test compilation and functionality on PPC-64<br />
I.K.2 [ ] [ ] Check that NFS HOWTO is updated with sufficient<br />
nfsv4 info<br />
<br />
Interop:<br />
II.A.1 [ ] [Bull] Kerberos (MIT) - verify basic functionality. Mount<br />
w/ krb5, etc.<br />
<br />
Robustness:<br />
III.A.3 [ ] [OSDL] Run NFS server for 2 wks with random configuration<br />
changes<br />
III.C.1 [ ] [Bull] Run LTP NFS fstress in a std config on each release<br />
<br />
Performance:<br />
IV.A.1 [ ] [Bull] Time to perform sequence of unique read/write<br />
operations<br />
IV.A.2 [ ] [Bull] Time to perform sequence of cacheable read/write<br />
operations<br />
IV.F.4 [ ] [Bull] Measure memory/network/CPU efficiency of client for<br />
fixed workload<br />
IV.G.3 [ ] [Bull] Measure effects of scaling up number of<br />
connections with exportfs/mount. Measure number of <br />
mounts per second on client and server.<br />
IV.J.2 [ ] [Bull] Measure performance when operating with Kerberos 5<br />
integrity and privacy<br />
<br />
Security:<br />
V.A.6 [ ] [ ] Audit the mountd code<br />
V.B.4 [ ] [OSDL] Run sparse as regression test periodically<br />
V.L.1 [ ] [ ] Ensure there is high level design documentation of<br />
NFSv4 security<br />
V.L.2 [ ] [ ] Ensure there is inline documentation for security<br />
related code in kernel<br />
V.L.3 [ ] [ ] Ensure there is inline documentation for GSS API<br />
(libgssapi, librpcsecgss)<br />
<br />
Misc:<br />
* [X] [OSDL] Establish bug tracking process for NFSv4<br />
<br />
==Milestone 1: Distro Quality Assurance==<br />
<br />
This milestone strives to attain a "Top Ten" list of testing that is<br />
felt will emphasize that NFSv4 is stable enough to be included in all<br />
enterprise distros. The focus is robustness, and items that would cause<br />
distros the most headaches if they're busted.<br />
<br />
I.A.5 [ ] [ ] Protocol implementation interoperability between<br />
Linux server and client<br />
I.C.5 [ ] [ ] Test install on SLES of NFSv4 server & client,<br />
krb5, ldap, et al<br />
I.C.6 [ ] [ ] Test install on RHEL of NFSv4 server & client,<br />
krb5, ldap, et al<br />
I.H.1 [ ] [ ] Verify compatibility with glibc<br />
I.H.9 [ ] [ IBM] Verify compatibility with automounter<br />
I.H.11 [ ] [ ] Verify compatibility with basic system tools<br />
(file utils, core utils, util-linux, mount, sar,<br />
iostat, etc.)<br />
I.K.4 [ ] [ ] Check that Network Admin Guide at tldp.org is<br />
updated for nfsv4<br />
II.E.2 [ ] [ ] Verify features of the Ext3 file system work under<br />
NFSv4<br />
III.A.1 [ ] [Bull] Run iozone for 2 wks on basic client/server<br />
operations<br />
III.A.2 [ ] [ ] Run automounter use case for 2 wks on amd, autofs,<br />
and autong<br />
III.A.4 [ ] [ ] Run connectathon locking tests against NFS server<br />
for 2 weeks<br />
III.E.1 [ ] [OSDL] Test short & long term local network failure<br />
(unplugged cable, ifdown eth0, etc.)<br />
III.E.2 [ ] [OSDL] Test short & long duration remote network partition<br />
III.E.3 [ ] [OSDL] Test behavior during crash/reboot of server with<br />
clients holding various states<br />
V.D.1 [ ] [ ] Review Authentication/ACL feature design<br />
V.E.1 [ ] [ ] Ensure a functionality test sufficiently tests<br />
Authentication/ACL<br />
<br />
==Milestone 2: Drill Down for One Use Case==<br />
<br />
This milestone strives to push NFSv4 through one complete use case, to<br />
give it some thorough exercise and scaling, and to establish a "case<br />
study" we can use as an example of NFSv4's value.<br />
<br />
I.E.5 [ ] [ ] Verify sufficient monitoring functionality within<br />
Ethereal<br />
I.F.1 [ ] [ ] Client notification to server of locking, write,<br />
read, etc.<br />
I.P.1 [ ] [OSDL] Database functionality on NFS<br />
I.L.1 [ ] [ ] Test compatibility with TCP protocol<br />
IV.A.7 [ ] [ ] NFSv3 vs. v4: Metadata - open/close intensive<br />
workload<br />
IV.A.8 [ ] [ ] NFSv3 vs. v4: Metadata - directory scanning<br />
IV.A.9 [ ] [ ] NFSv3 vs. v4: Metadata - create/delete<br />
IV.A.10 [ ] [ ] NFSv3 vs. v4: Metadata - changing attributes<br />
(chown, chmod) while dir scanning<br />
IV.E.1 [ ] [Bull] Test performance with large numbers of small (<4k)<br />
files<br />
IV.E.2 [ ] [ ] Test performance with a few very large (>1G) files<br />
IV.F.4 [ ] [Bull] Measure memory/network/CPU efficiency of client<br />
for fixed workload<br />
IV.G.1 [ ] [ ] Verify server scalability with clients generating<br />
various basic requests (ACCESS, GETATTR, et al)<br />
IV.G.2 [ ] [ ] Verify server scalability with clients using<br />
compound requests<br />
V.D.6 [ ] [ ] Penetration testing for client callback<br />
implementation<br />
V.E.6 [ ] [ ] Ensure a functionality test sufficiently covers<br />
penetration testing for client callback<br />
implementation<br />
<br />
==Milestone 3: Enterprise Usability==<br />
<br />
This milestone focuses on testing that verifies "basic" usability of<br />
NFSv4 in data centers. It strives to establish that NFSv4 is able to<br />
perform basic functions in enterprise-class deployments.<br />
<br />
I.F.2 [ ] [ ] Reboot recovery<br />
I.F.4 [ ] [ ] Open with shares / deny<br />
I.F.5 [ ] [ ] Bumping a sequence ID<br />
I.F.6 [ ] [ ] Network partition recovery<br />
I.F.8 [ ] [ ] Locking (Non-blocking locks)<br />
I.H.3 [ ] [ ] Verify compatibility with Kerberos<br />
I.H.4 [ ] [ ] Verify compatibility with Ipsec<br />
I.H.5 [ ] [ ] Verify compatibility with POSIX ACLs<br />
I.H.6 [ ] [ ] Verify compatibility with NFS ACLs<br />
II.B.1 [ ] [Bull] Interoperability between 32-bit and 64-bit for<br />
client and server: IA32/AIX-PPC, IA32/Linux-PPC<br />
II.B.2 [ ] [Bull] Interoperability between little endian and big<br />
endian<br />
II.C.1 [ ] [Bull] Interoperability for Linux IA-32 client ? Solaris<br />
10 server<br />
II.C.4 [ ] [Bull] Interoperability for Linux IA-32 client ? AIX 5.3<br />
server<br />
III.D.7 [ ] [ ] Test correctness of NFS client when backed by a<br />
large (>100GB) cachefs<br />
IV.E.5 [ ] [ ] NFS "Cluster" scenario with 1000+ clients and<br />
several servers<br />
V.A.7 [ ] [ ] Audit the RPC authentication code (gssd, authsys,<br />
etc.)<br />
V.D.2 [ ] [ ] Review each security flavor feature design:<br />
Krb5, Spkm<br />
V.E.2 [ ] [ ] Ensure a functionality test sufficiently covers<br />
each security flavor<br />
<br />
<br />
==Milestone 4: Enterprise Readiness==<br />
<br />
This milestone builds on the previous one by ensuring that NFSv4 will<br />
behave well and perform robustly under typical enterprise-class loads.<br />
<br />
III.B.2 [ ] [ ] Test stability of client in out of memory<br />
situation<br />
III.B.3 [ ] [ ] Test stability of client in out of disk space on<br />
server situation<br />
III.B.4 [ ] [ ] Test stability of client in out of inode situation<br />
III.B.5 [ ] [ ] Test stability of client in out of swap space<br />
situation<br />
III.B.6 [ ] [ ] Test stability of server in out of pid situation<br />
III.B.7 [ ] [ ] Test stability of server in out of memory<br />
situation<br />
III.B.8 [ ] [ ] Test stability of server in out of disk space<br />
situation<br />
III.B.9 [ ] [ ] Test stability of server in out of inode situation<br />
III.B.10 [ ] [ ] Test stability of server in out of swap space<br />
situation<br />
III.D.1 [ ] [ ] Find maximum number of connections to Linux IA-32<br />
server<br />
III.D.4 [ ] [ ] Find maximum number of mounted file systems on<br />
client<br />
III.E.4 [ ] [ ] Test multiple clients using, locking, etc. same<br />
files<br />
III.E.5 [ ] [ ] Test behavior of server with failed storage device<br />
III.E.6 [ ] [ ] Test behavior during crash of client with open<br />
delegations and locks<br />
III.E.7 [ ] [ ] Test recovery from denied permission<br />
III.E.8 [ ] [ ] Test recovery from JUKEBOX/DELAY<br />
III.E.9 [ ] [ ] Test recovery from ESTALE<br />
III.E.10 [ ] [ ] Test server callback mechanism (c.f. III.E.1,<br />
III.E.2)<br />
III.G.2 [ ] [ ] Test concurrent access tests for races in<br />
automounter<br />
IV.G.4 [ ] [ ] Measure effects of increasing number of files<br />
IV.G.5 [ ] [ ] Measure effects of increasing file size<br />
(with/without cache)<br />
IV.G.6 [ ] [ ] Measure effects when increasing size of<br />
on-the-wire NFS read or write operations<br />
V.J.1 [ ] [ ] Identify security issues assuming attack from<br />
client-side</div>
65.172.181.6
https://wiki.linux-nfs.org/wiki/index.php/Testing_forecast_roadmap
Testing forecast roadmap
2005-10-04T22:51:04Z
<p>65.172.181.6: /* Milestone 0: Developer Testing Support */</p>
<hr />
<div>Linux NFSv4 Testing Roadmap<br />
---------------------------<br />
<br />
As of May 2005, we've completed a detailed itemization of testing work<br />
necessary for NFSv4, in a spreadsheet "Test Matrix", identifying items<br />
as High, Medium, and Low.<br />
<br />
This document seeks to divide the high priority work into achievable<br />
chunks that we as a community can strive to attain.<br />
<br />
I tried to prioritize for things that look reasonably easy to complete<br />
in the near term, that have owners, and/or are most likely to reveal<br />
issues that developers want to know about.<br />
<br />
<br />
==Milestone 0: Developer Testing Support==<br />
<br />
These testing tasks seek to put into place tools and practices that will<br />
help support development activities (including testing) on an ongoing<br />
basis.<br />
<br />
Functionality:<br />
I.B.1 [X] [OSDL] Automate running applicable existing functionality<br />
tests on codebase periodically: cthon, pynfs,<br />
iozone<br />
I.B.3 [X] [OSDL] Automate cross-compile testing for major platforms<br />
on each NFSv4 patchset<br />
I.C.2 [ ] [ ] Test install on Fedora Core of NFSv4 server &<br />
client, krb5, ldap, et al<br />
I.E.9 [ ] [ ] Verify ability to force operations (close files,<br />
change states, unmount)<br />
I.G.5 [ ] [Bull] Test compilation and functionality on IA-64<br />
I.G.7 [ ] [Bull] Test compilation and functionality on PPC-64<br />
I.K.2 [ ] [ ] Check that NFS HOWTO is updated with sufficient<br />
nfsv4 info<br />
<br />
Interop:<br />
II.A.1 [ ] [Bull] Kerberos (MIT) - verify basic functionality. Mount<br />
w/ krb5, etc.<br />
<br />
Robustness:<br />
III.A.3 [ ] [OSDL] Run NFS server for 2 wks with random configuration<br />
changes<br />
III.C.1 [ ] [Bull] Run LTP NFS fstress in a std config on each release<br />
<br />
Performance:<br />
IV.A.1 [ ] [Bull] Time to perform sequence of unique read/write<br />
operations<br />
IV.A.2 [ ] [Bull] Time to perform sequence of cacheable read/write<br />
operations<br />
IV.F.4 [ ] [Bull] Measure memory/network/CPU efficiency of client for<br />
fixed workload<br />
IV.G.3 [ ] [Bull] Measure effects of scaling up number of<br />
connections with exportfs/mount. Measure number of <br />
mounts per second on client and server.<br />
IV.J.2 [ ] [Bull] Measure performance when operating with Kerberos 5<br />
integrity and privacy<br />
<br />
Security:<br />
V.A.6 [ ] [ ] Audit the mountd code<br />
V.B.4 [ ] [OSDL] Run sparse as regression test periodically<br />
V.L.1 [ ] [ ] Ensure there is high level design documentation of<br />
NFSv4 security<br />
V.L.2 [ ] [ ] Ensure there is inline documentation for security<br />
related code in kernel<br />
V.L.3 [ ] [ ] Ensure there is inline documentation for GSS API<br />
(libgssapi, librpcsecgss)<br />
<br />
Misc:<br />
* [X] [OSDL] Establish bug tracking process for NFSv4<br />
<br />
==Milestone 1: Distro Quality Assurance==<br />
<br />
This milestone strives to attain a "Top Ten" list of testing that is<br />
felt will emphasize that NFSv4 is stable enough to be included in all<br />
enterprise distros. The focus is robustness, and items that would cause<br />
distros the most headaches if they're busted.<br />
<br />
I.A.5 [ ] [ ] Protocol implementation interoperability between<br />
Linux server and client<br />
I.C.5 [ ] [ ] Test install on SLES of NFSv4 server & client,<br />
krb5, ldap, et al<br />
I.C.6 [ ] [ ] Test install on RHEL of NFSv4 server & client,<br />
krb5, ldap, et al<br />
I.H.1 [ ] [ ] Verify compatibility with glibc<br />
I.H.9 [ ] [ IBM] Verify compatibility with automounter<br />
I.H.11 [ ] [ ] Verify compatibility with basic system tools<br />
(file utils, core utils, util-linux, mount, sar,<br />
iostat, etc.)<br />
I.K.4 [ ] [ ] Check that Network Admin Guide at tldp.org is<br />
updated for nfsv4<br />
II.E.2 [ ] [ ] Verify features of the Ext3 file system work under<br />
NFSv4<br />
III.A.1 [ ] [ ] Run iozone for 2 wks on basic client/server<br />
operations<br />
III.A.2 [ ] [ ] Run automounter use case for 2 wks on amd, autofs,<br />
and autong<br />
III.A.4 [ ] [ ] Run connectathon locking tests against NFS server<br />
for 2 weeks<br />
III.E.1 [ ] [OSDL] Test short & long term local network failure<br />
(unplugged cable, ifdown eth0, etc.)<br />
III.E.2 [ ] [OSDL] Test short & long duration remote network partition<br />
III.E.3 [ ] [OSDL] Test behavior during crash/reboot of server with<br />
clients holding various states<br />
V.D.1 [ ] [ ] Review Authentication/ACL feature design<br />
V.E.1 [ ] [ ] Ensure a functionality test sufficiently tests<br />
Authentication/ACL<br />
<br />
<br />
==Milestone 2: Drill Down for One Use Case==<br />
<br />
This milestone strives to push NFSv4 through one complete use case, to<br />
give it some thorough exercise and scaling, and to establish a "case<br />
study" we can use as an example of NFSv4's value.<br />
<br />
I.E.5 [ ] [ ] Verify sufficient monitoring functionality within<br />
Ethereal<br />
I.F.1 [ ] [ ] Client notification to server of locking, write,<br />
read, etc.<br />
I.P.1 [ ] [OSDL] Database functionality on NFS<br />
I.L.1 [ ] [ ] Test compatibility with TCP protocol<br />
IV.A.7 [ ] [ ] NFSv3 vs. v4: Metadata - open/close intensive<br />
workload<br />
IV.A.8 [ ] [ ] NFSv3 vs. v4: Metadata - directory scanning<br />
IV.A.9 [ ] [ ] NFSv3 vs. v4: Metadata - create/delete<br />
IV.A.10 [ ] [ ] NFSv3 vs. v4: Metadata - changing attributes<br />
(chown, chmod) while dir scanning<br />
IV.E.1 [ ] [Bull] Test performance with large numbers of small (<4k)<br />
files<br />
IV.E.2 [ ] [ ] Test performance with a few very large (>1G) files<br />
IV.F.4 [ ] [Bull] Measure memory/network/CPU efficiency of client<br />
for fixed workload<br />
IV.G.1 [ ] [ ] Verify server scalability with clients generating<br />
various basic requests (ACCESS, GETATTR, et al)<br />
IV.G.2 [ ] [ ] Verify server scalability with clients using<br />
compound requests<br />
V.D.6 [ ] [ ] Penetration testing for client callback<br />
implementation<br />
V.E.6 [ ] [ ] Ensure a functionality test sufficiently covers<br />
penetration testing for client callback<br />
implementation<br />
<br />
==Milestone 3: Enterprise Usability==<br />
<br />
This milestone focuses on testing that verifies "basic" usability of<br />
NFSv4 in data centers. It strives to establish that NFSv4 is able to<br />
perform basic functions in enterprise-class deployments.<br />
<br />
I.F.2 [ ] [ ] Reboot recovery<br />
I.F.4 [ ] [ ] Open with shares / deny<br />
I.F.5 [ ] [ ] Bumping a sequence ID<br />
I.F.6 [ ] [ ] Network partition recovery<br />
I.F.8 [ ] [ ] Locking (Non-blocking locks)<br />
I.H.3 [ ] [ ] Verify compatibility with Kerberos<br />
I.H.4 [ ] [ ] Verify compatibility with Ipsec<br />
I.H.5 [ ] [ ] Verify compatibility with POSIX ACLs<br />
I.H.6 [ ] [ ] Verify compatibility with NFS ACLs<br />
II.B.1 [ ] [Bull] Interoperability between 32-bit and 64-bit for<br />
client and server: IA32/AIX-PPC, IA32/Linux-PPC<br />
II.B.2 [ ] [Bull] Interoperability between little endian and big<br />
endian<br />
II.C.1 [ ] [Bull] Interoperability for Linux IA-32 client ? Solaris<br />
10 server<br />
II.C.4 [ ] [Bull] Interoperability for Linux IA-32 client ? AIX 5.3<br />
server<br />
III.D.7 [ ] [ ] Test correctness of NFS client when backed by a<br />
large (>100GB) cachefs<br />
IV.E.5 [ ] [ ] NFS "Cluster" scenario with 1000+ clients and<br />
several servers<br />
V.A.7 [ ] [ ] Audit the RPC authentication code (gssd, authsys,<br />
etc.)<br />
V.D.2 [ ] [ ] Review each security flavor feature design:<br />
Krb5, Spkm<br />
V.E.2 [ ] [ ] Ensure a functionality test sufficiently covers<br />
each security flavor<br />
<br />
<br />
==Milestone 4: Enterprise Readiness==<br />
<br />
This milestone builds on the previous one by ensuring that NFSv4 will<br />
behave well and perform robustly under typical enterprise-class loads.<br />
<br />
III.B.2 [ ] [ ] Test stability of client in out of memory<br />
situation<br />
III.B.3 [ ] [ ] Test stability of client in out of disk space on<br />
server situation<br />
III.B.4 [ ] [ ] Test stability of client in out of inode situation<br />
III.B.5 [ ] [ ] Test stability of client in out of swap space<br />
situation<br />
III.B.6 [ ] [ ] Test stability of server in out of pid situation<br />
III.B.7 [ ] [ ] Test stability of server in out of memory<br />
situation<br />
III.B.8 [ ] [ ] Test stability of server in out of disk space<br />
situation<br />
III.B.9 [ ] [ ] Test stability of server in out of inode situation<br />
III.B.10 [ ] [ ] Test stability of server in out of swap space<br />
situation<br />
III.D.1 [ ] [ ] Find maximum number of connections to Linux IA-32<br />
server<br />
III.D.4 [ ] [ ] Find maximum number of mounted file systems on<br />
client<br />
III.E.4 [ ] [ ] Test multiple clients using, locking, etc. same<br />
files<br />
III.E.5 [ ] [ ] Test behavior of server with failed storage device<br />
III.E.6 [ ] [ ] Test behavior during crash of client with open<br />
delegations and locks<br />
III.E.7 [ ] [ ] Test recovery from denied permission<br />
III.E.8 [ ] [ ] Test recovery from JUKEBOX/DELAY<br />
III.E.9 [ ] [ ] Test recovery from ESTALE<br />
III.E.10 [ ] [ ] Test server callback mechanism (c.f. III.E.1,<br />
III.E.2)<br />
III.G.2 [ ] [ ] Test concurrent access tests for races in<br />
automounter<br />
IV.G.4 [ ] [ ] Measure effects of increasing number of files<br />
IV.G.5 [ ] [ ] Measure effects of increasing file size<br />
(with/without cache)<br />
IV.G.6 [ ] [ ] Measure effects when increasing size of<br />
on-the-wire NFS read or write operations<br />
V.J.1 [ ] [ ] Identify security issues assuming attack from<br />
client-side</div>
65.172.181.6
https://wiki.linux-nfs.org/wiki/index.php/Matrix_interop_section
Matrix interop section
2005-10-04T22:48:13Z
<p>65.172.181.6: /* Test ACL interoperability of Linux client for non-Linux servers */</p>
<hr />
<div>==Interoperability with other protocols==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|II.A.1<br />
|Kerberos – verify basic functionality. Mount w/ krb5, etc.<br><br />
MIT implementation Open Bull Bull plans to do in 2005<br><br />
Heimdal implementation Open Bull Bull plans to do in 2005<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.A.2<br />
|Active Directory<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.A.3<br />
|IpSec – basic functionality w/ various VPNs, establishment, policies, best practices Unknown <br><br />
IpSec v4 Open Bull Bull plans to do in 2005 <br><br />
IpSec v6 New Not clear who will be using it<br><br />
CCM – very new, low priority New Very new, low priority<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.A.4<br />
|SPKM – Interoperability with key management New<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.A.5<br />
|Interoperability of RPCSEC_GSS in general DONE CITI Trond and Bruce have tested this at Connectathon and NFSv4 Bakeathon<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|}<br />
<br />
== Specific architectural/platform interoperability issues ==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|II.B.1<br />
|Interoperability for Linux IA-32 client - Linux PPC 32 bit server<br />
|<br />
|'''Open'''<br />
|'''Bull'''<br />
|<br />
|-<br />
|II.B.2<br />
|Interoperability for Linux IA-32 client - Linux PPC 64 bit server<br />
|<br />
|'''Open'''<br />
|'''Bull'''<br />
|<br />
|-<br />
|II.B.3<br />
|Interoperability for Linux IA-32 client - IA-64 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.B.4<br />
|Interoperability for Linux IA-32 client - x86_64 server<br />
|<br />
|'''Open'''<br />
|'''Bull'''<br />
|<br />
|-<br />
|II.B.5<br />
|Interoperability for Linux PPC 32 bit client - Linux IA-32 server<br />
|<br />
|'''Open'''<br />
|'''Bull'''<br />
|<br />
|-<br />
|II.B.6<br />
|Interoperability for Linux PPC 64 bit client - Linux IA-32 server<br />
|<br />
|'''Open'''<br />
|'''Bull'''<br />
|<br />
|-<br />
|II.B.7<br />
|Interoperability for Linux IA-64 server - Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.B.8<br />
|Interoperability for Linux x86_64 server - Linux IA-32 server<br />
|<br />
|'''Open'''<br />
|'''Bull'''<br />
|<br />
|-<br />
|}<br />
<br />
== Client Interoperability with target architectures/platforms ==<br />
<br />
Need to define how to do interoperability testing – need more than just connectathon<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|II.C.1<br />
|Interoperability for Linux IA-32 client – Solaris 10 server <br />
|<br />
|'''Open'''<br />
|'''Bull'''<br />
|<br />
|-<br />
|II.C.2<br />
|Interoperability for Linux IA-32 client – NetApp Filer server <br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.C.3<br />
|Interoperability for Linux IA-32 client – EMC Filer server <br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.C.4<br />
|Interoperability for Linux IA-32 client – AIX 5.3 server <br />
|<br />
|'''Done'''<br />
|'''Bull'''<br />
|<br />
|-<br />
|II.C.5<br />
|Interoperability for Linux IA-32 client – AMD x86_64 server <br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.C.6<br />
|Interoperability for Linux IA-32 client – PolyServe clustered products <br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.C.7<br />
|Interoperability for Linux IA-32 client – Hummingbird server <br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.C.9<br />
|Interoperability for Linux IA-32 client – HP server <br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.C.10<br />
|Interoperability for Linux IA-32 client – SGI server <br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.C.11<br />
|Interoperability for Linux IA-32 client – Spinniker server <br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|}<br />
<br />
== Server Interoperability with target architectures/platforms ==<br />
<br />
Need to define how to do interoperability testing – need more than just connectathon<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|II.D.1<br />
|Interoperability for Solaris 10 client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.D.2<br />
|Interoperability for NetApp client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.D.3<br />
|Interoperability for EMC client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.D.4<br />
|Interoperability for AIX 5.3 client – Linux IA-32 server<br />
|<br />
|''' Open'''<br />
|''' Bull'''<br />
|<br />
|-<br />
|II.D.5<br />
|Interoperability for AMD x86_64 client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.D.6<br />
|Interoperability for Polyserve client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.D.7<br />
|Interoperability for Hummingbird client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.D.8<br />
|Interoperability for HP client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.D.9<br />
|Interoperability for SGI client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.D.10<br />
|Interoperability for Spinniker client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|}<br />
<br />
== File systems ==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|II.E.1<br />
|Verify features of cachefs for NFSv4<br />
|<br />
|'''New'''<br />
|<br />
|Not currently NFSv4 ready; needs additional development<br />
|-<br />
|II.E.2<br />
|Verify features of the Ext3 file system work under NFSv4<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.E.3<br />
|Verify features of the XFS file system work under NFSv4<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.E.4<br />
|Verify features of the Reiser file system work under NFSv4<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.E.5<br />
|Verify features of the GFS file system work under NFSv4<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.E.6<br />
|Verify features of cluster file systems (e.g. GFS) work under NFSv4<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.E.7<br />
|Verify features of the Luster file system work under NFSv4<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.E.8<br />
|Verify features of the GPFS file system work under NFSv4<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.E.9<br />
|Verify features of the Sanfs file system work under NFSv4<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.E.10<br />
|Verify features of the Polyserve file system work under NFSv4<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.E.11<br />
|Verify features of the Netcache file system work under NFSv4<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.E.12<br />
|Verify features of the Rainfinity file system work under NFSv4<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.E.13<br />
|Analyze file system configuration issues, such as:<br><br />
Logical volume manager behind server<br><br />
RAID-5 problem with small write workloads (may be performance issue?)<br><br />
Compiling POSIX ACL's in and out<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|}<br />
<br />
== Test ACL interoperability of Linux client for non-Linux servers ==<br />
See I.R.3; need test<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|II.F.1<br />
|ACL compatibility for Linux IA-32 client - Solaris 10 client<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.F.2<br />
|ACL compatibility for Linux IA-32 client - NetApp server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.F.3<br />
|ACL compatibility for Linux IA-32 client - EMC server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.F.4<br />
|ACL compatibility for Linux IA-32 client - AIX 5.3 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.F.5<br />
|ACL compatibility for Linux IA-32 client – AMD x86_64 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.F.6<br />
|ACL compatibility for Linux IA-32 client - Polyserve server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.F.7<br />
|ACL compatibility for Linux IA-32 client – Hummingbird server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.F.8<br />
|ACL compatibility for Linux IA-32 client – HP server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.F.9<br />
|ACL compatibility for Linux IA-32 client – SGI server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.F.10<br />
|ACL compatibility for Linux IA-32 client – Spinniker server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|}<br />
<br />
== Test ACL interoperability of Linux server with non-Linux clients ==<br />
See I.R.3; need test<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|II.G.1<br />
|ACL compatibility for Solaris 10 client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.G.2<br />
|ACL compatibility for NetApp client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.G.3<br />
|ACL compatibility for EMC client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.G.4<br />
|ACL compatibility for AIX 5.3 client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.G.5<br />
|ACL compatibility for AMD client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.G.6<br />
|ACL compatibility for Polyserve client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.G.7<br />
|ACL compatibility for Hummingbird client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.G.8<br />
|ACL compatibility for HP client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.G.9<br />
|ACL compatibility for SGI client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.G.10<br />
|ACL compatibility for Spinniker client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|}<br />
<br />
== Automounter interoperability ==<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|II.H.1<br />
|Verify amd will work as a drop-in automounter service with nfsv4<br />
|<br />
|'''Open'''<br />
|IBM<br />
|<br />
|-<br />
|II.H.2<br />
|Verify autong will work as a drop-in automounter service with nfsv4<br />
|<br />
|'''Open'''<br />
|IBM<br />
|<br />
|-<br />
|II.H.3<br />
|Verify autofs4 will work as a drop-in automounter service with nfsv4<br />
|<br />
|'''Open'''<br />
|IBM<br />
|<br />
|-<br />
|II.H.4<br />
|Verify interoperability of nfsv4 and automounter with various map sources:<br><br />
- Flat file Connectathon<br><br />
- Program file Connectathon<br><br />
- NIS Connectathon<br><br />
- NIS+<br><br />
- LDAP using NIS style maps (RFC2307)<br><br />
- LDAP using Linux style automounter maps<br><br />
- LDAP using Yet-Another schema (RFC2307bis, deleted, but used by solaris 9 last I checked)<br />
|<br />
|'''Open'''<br />
|IBM<br />
|<br />
|-<br />
|}</div>
65.172.181.6
https://wiki.linux-nfs.org/wiki/index.php/Matrix_interop_section
Matrix interop section
2005-10-04T22:47:43Z
<p>65.172.181.6: /* Server Interoperability with target architectures/platforms */</p>
<hr />
<div>==Interoperability with other protocols==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|II.A.1<br />
|Kerberos – verify basic functionality. Mount w/ krb5, etc.<br><br />
MIT implementation Open Bull Bull plans to do in 2005<br><br />
Heimdal implementation Open Bull Bull plans to do in 2005<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.A.2<br />
|Active Directory<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.A.3<br />
|IpSec – basic functionality w/ various VPNs, establishment, policies, best practices Unknown <br><br />
IpSec v4 Open Bull Bull plans to do in 2005 <br><br />
IpSec v6 New Not clear who will be using it<br><br />
CCM – very new, low priority New Very new, low priority<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.A.4<br />
|SPKM – Interoperability with key management New<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.A.5<br />
|Interoperability of RPCSEC_GSS in general DONE CITI Trond and Bruce have tested this at Connectathon and NFSv4 Bakeathon<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|}<br />
<br />
== Specific architectural/platform interoperability issues ==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|II.B.1<br />
|Interoperability for Linux IA-32 client - Linux PPC 32 bit server<br />
|<br />
|'''Open'''<br />
|'''Bull'''<br />
|<br />
|-<br />
|II.B.2<br />
|Interoperability for Linux IA-32 client - Linux PPC 64 bit server<br />
|<br />
|'''Open'''<br />
|'''Bull'''<br />
|<br />
|-<br />
|II.B.3<br />
|Interoperability for Linux IA-32 client - IA-64 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.B.4<br />
|Interoperability for Linux IA-32 client - x86_64 server<br />
|<br />
|'''Open'''<br />
|'''Bull'''<br />
|<br />
|-<br />
|II.B.5<br />
|Interoperability for Linux PPC 32 bit client - Linux IA-32 server<br />
|<br />
|'''Open'''<br />
|'''Bull'''<br />
|<br />
|-<br />
|II.B.6<br />
|Interoperability for Linux PPC 64 bit client - Linux IA-32 server<br />
|<br />
|'''Open'''<br />
|'''Bull'''<br />
|<br />
|-<br />
|II.B.7<br />
|Interoperability for Linux IA-64 server - Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.B.8<br />
|Interoperability for Linux x86_64 server - Linux IA-32 server<br />
|<br />
|'''Open'''<br />
|'''Bull'''<br />
|<br />
|-<br />
|}<br />
<br />
== Client Interoperability with target architectures/platforms ==<br />
<br />
Need to define how to do interoperability testing – need more than just connectathon<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|II.C.1<br />
|Interoperability for Linux IA-32 client – Solaris 10 server <br />
|<br />
|'''Open'''<br />
|'''Bull'''<br />
|<br />
|-<br />
|II.C.2<br />
|Interoperability for Linux IA-32 client – NetApp Filer server <br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.C.3<br />
|Interoperability for Linux IA-32 client – EMC Filer server <br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.C.4<br />
|Interoperability for Linux IA-32 client – AIX 5.3 server <br />
|<br />
|'''Done'''<br />
|'''Bull'''<br />
|<br />
|-<br />
|II.C.5<br />
|Interoperability for Linux IA-32 client – AMD x86_64 server <br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.C.6<br />
|Interoperability for Linux IA-32 client – PolyServe clustered products <br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.C.7<br />
|Interoperability for Linux IA-32 client – Hummingbird server <br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.C.9<br />
|Interoperability for Linux IA-32 client – HP server <br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.C.10<br />
|Interoperability for Linux IA-32 client – SGI server <br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.C.11<br />
|Interoperability for Linux IA-32 client – Spinniker server <br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|}<br />
<br />
== Server Interoperability with target architectures/platforms ==<br />
<br />
Need to define how to do interoperability testing – need more than just connectathon<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|II.D.1<br />
|Interoperability for Solaris 10 client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.D.2<br />
|Interoperability for NetApp client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.D.3<br />
|Interoperability for EMC client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.D.4<br />
|Interoperability for AIX 5.3 client – Linux IA-32 server<br />
|<br />
|''' Open'''<br />
|''' Bull'''<br />
|<br />
|-<br />
|II.D.5<br />
|Interoperability for AMD x86_64 client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.D.6<br />
|Interoperability for Polyserve client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.D.7<br />
|Interoperability for Hummingbird client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.D.8<br />
|Interoperability for HP client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.D.9<br />
|Interoperability for SGI client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.D.10<br />
|Interoperability for Spinniker client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|}<br />
<br />
== File systems ==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|II.E.1<br />
|Verify features of cachefs for NFSv4<br />
|<br />
|'''New'''<br />
|<br />
|Not currently NFSv4 ready; needs additional development<br />
|-<br />
|II.E.2<br />
|Verify features of the Ext3 file system work under NFSv4<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.E.3<br />
|Verify features of the XFS file system work under NFSv4<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.E.4<br />
|Verify features of the Reiser file system work under NFSv4<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.E.5<br />
|Verify features of the GFS file system work under NFSv4<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.E.6<br />
|Verify features of cluster file systems (e.g. GFS) work under NFSv4<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.E.7<br />
|Verify features of the Luster file system work under NFSv4<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.E.8<br />
|Verify features of the GPFS file system work under NFSv4<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.E.9<br />
|Verify features of the Sanfs file system work under NFSv4<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.E.10<br />
|Verify features of the Polyserve file system work under NFSv4<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.E.11<br />
|Verify features of the Netcache file system work under NFSv4<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.E.12<br />
|Verify features of the Rainfinity file system work under NFSv4<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.E.13<br />
|Analyze file system configuration issues, such as:<br><br />
Logical volume manager behind server<br><br />
RAID-5 problem with small write workloads (may be performance issue?)<br><br />
Compiling POSIX ACL's in and out<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|}<br />
<br />
== Test ACL interoperability of Linux client for non-Linux servers ==<br />
See I.R.3; need test<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|II.F.1<br />
|ACL compatibility for Linux IA-32 client - Solaris 10 client<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.F.2<br />
|ACL compatibility for Linux IA-32 client - NetApp server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.F.3<br />
|ACL compatibility for Linux IA-32 client - EMC server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.F.4<br />
|ACL compatibility for Linux IA-32 client - AIX 5.3 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.F.5<br />
|ACL compatibility for Linux IA-32 client – AMD server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.F.6<br />
|ACL compatibility for Linux IA-32 client - Polyserve server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.F.7<br />
|ACL compatibility for Linux IA-32 client – Hummingbird server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.F.8<br />
|ACL compatibility for Linux IA-32 client – HP server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.F.9<br />
|ACL compatibility for Linux IA-32 client – SGI server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.F.10<br />
|ACL compatibility for Linux IA-32 client – Spinniker server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|}<br />
<br />
== Test ACL interoperability of Linux server with non-Linux clients ==<br />
See I.R.3; need test<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|II.G.1<br />
|ACL compatibility for Solaris 10 client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.G.2<br />
|ACL compatibility for NetApp client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.G.3<br />
|ACL compatibility for EMC client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.G.4<br />
|ACL compatibility for AIX 5.3 client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.G.5<br />
|ACL compatibility for AMD client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.G.6<br />
|ACL compatibility for Polyserve client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.G.7<br />
|ACL compatibility for Hummingbird client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.G.8<br />
|ACL compatibility for HP client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.G.9<br />
|ACL compatibility for SGI client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.G.10<br />
|ACL compatibility for Spinniker client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|}<br />
<br />
== Automounter interoperability ==<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|II.H.1<br />
|Verify amd will work as a drop-in automounter service with nfsv4<br />
|<br />
|'''Open'''<br />
|IBM<br />
|<br />
|-<br />
|II.H.2<br />
|Verify autong will work as a drop-in automounter service with nfsv4<br />
|<br />
|'''Open'''<br />
|IBM<br />
|<br />
|-<br />
|II.H.3<br />
|Verify autofs4 will work as a drop-in automounter service with nfsv4<br />
|<br />
|'''Open'''<br />
|IBM<br />
|<br />
|-<br />
|II.H.4<br />
|Verify interoperability of nfsv4 and automounter with various map sources:<br><br />
- Flat file Connectathon<br><br />
- Program file Connectathon<br><br />
- NIS Connectathon<br><br />
- NIS+<br><br />
- LDAP using NIS style maps (RFC2307)<br><br />
- LDAP using Linux style automounter maps<br><br />
- LDAP using Yet-Another schema (RFC2307bis, deleted, but used by solaris 9 last I checked)<br />
|<br />
|'''Open'''<br />
|IBM<br />
|<br />
|-<br />
|}</div>
65.172.181.6
https://wiki.linux-nfs.org/wiki/index.php/Matrix_interop_section
Matrix interop section
2005-10-04T22:47:22Z
<p>65.172.181.6: /* Client Interoperability with target architectures/platforms */</p>
<hr />
<div>==Interoperability with other protocols==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|II.A.1<br />
|Kerberos – verify basic functionality. Mount w/ krb5, etc.<br><br />
MIT implementation Open Bull Bull plans to do in 2005<br><br />
Heimdal implementation Open Bull Bull plans to do in 2005<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.A.2<br />
|Active Directory<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.A.3<br />
|IpSec – basic functionality w/ various VPNs, establishment, policies, best practices Unknown <br><br />
IpSec v4 Open Bull Bull plans to do in 2005 <br><br />
IpSec v6 New Not clear who will be using it<br><br />
CCM – very new, low priority New Very new, low priority<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.A.4<br />
|SPKM – Interoperability with key management New<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.A.5<br />
|Interoperability of RPCSEC_GSS in general DONE CITI Trond and Bruce have tested this at Connectathon and NFSv4 Bakeathon<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|}<br />
<br />
== Specific architectural/platform interoperability issues ==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|II.B.1<br />
|Interoperability for Linux IA-32 client - Linux PPC 32 bit server<br />
|<br />
|'''Open'''<br />
|'''Bull'''<br />
|<br />
|-<br />
|II.B.2<br />
|Interoperability for Linux IA-32 client - Linux PPC 64 bit server<br />
|<br />
|'''Open'''<br />
|'''Bull'''<br />
|<br />
|-<br />
|II.B.3<br />
|Interoperability for Linux IA-32 client - IA-64 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.B.4<br />
|Interoperability for Linux IA-32 client - x86_64 server<br />
|<br />
|'''Open'''<br />
|'''Bull'''<br />
|<br />
|-<br />
|II.B.5<br />
|Interoperability for Linux PPC 32 bit client - Linux IA-32 server<br />
|<br />
|'''Open'''<br />
|'''Bull'''<br />
|<br />
|-<br />
|II.B.6<br />
|Interoperability for Linux PPC 64 bit client - Linux IA-32 server<br />
|<br />
|'''Open'''<br />
|'''Bull'''<br />
|<br />
|-<br />
|II.B.7<br />
|Interoperability for Linux IA-64 server - Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.B.8<br />
|Interoperability for Linux x86_64 server - Linux IA-32 server<br />
|<br />
|'''Open'''<br />
|'''Bull'''<br />
|<br />
|-<br />
|}<br />
<br />
== Client Interoperability with target architectures/platforms ==<br />
<br />
Need to define how to do interoperability testing – need more than just connectathon<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|II.C.1<br />
|Interoperability for Linux IA-32 client – Solaris 10 server <br />
|<br />
|'''Open'''<br />
|'''Bull'''<br />
|<br />
|-<br />
|II.C.2<br />
|Interoperability for Linux IA-32 client – NetApp Filer server <br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.C.3<br />
|Interoperability for Linux IA-32 client – EMC Filer server <br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.C.4<br />
|Interoperability for Linux IA-32 client – AIX 5.3 server <br />
|<br />
|'''Done'''<br />
|'''Bull'''<br />
|<br />
|-<br />
|II.C.5<br />
|Interoperability for Linux IA-32 client – AMD x86_64 server <br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.C.6<br />
|Interoperability for Linux IA-32 client – PolyServe clustered products <br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.C.7<br />
|Interoperability for Linux IA-32 client – Hummingbird server <br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.C.9<br />
|Interoperability for Linux IA-32 client – HP server <br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.C.10<br />
|Interoperability for Linux IA-32 client – SGI server <br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.C.11<br />
|Interoperability for Linux IA-32 client – Spinniker server <br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|}<br />
<br />
== Server Interoperability with target architectures/platforms ==<br />
<br />
Need to define how to do interoperability testing – need more than just connectathon<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|II.D.1<br />
|Interoperability for Solaris 10 client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.D.2<br />
|Interoperability for NetApp client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.D.3<br />
|Interoperability for EMC client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.D.4<br />
|Interoperability for AIX 5.3 client – Linux IA-32 server<br />
|<br />
|''' Open'''<br />
|''' Bull'''<br />
|<br />
|-<br />
|II.D.5<br />
|Interoperability for AMD client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.D.6<br />
|Interoperability for Polyserve client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.D.7<br />
|Interoperability for Hummingbird client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.D.8<br />
|Interoperability for HP client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.D.9<br />
|Interoperability for SGI client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.D.10<br />
|Interoperability for Spinniker client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|}<br />
<br />
== File systems ==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|II.E.1<br />
|Verify features of cachefs for NFSv4<br />
|<br />
|'''New'''<br />
|<br />
|Not currently NFSv4 ready; needs additional development<br />
|-<br />
|II.E.2<br />
|Verify features of the Ext3 file system work under NFSv4<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.E.3<br />
|Verify features of the XFS file system work under NFSv4<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.E.4<br />
|Verify features of the Reiser file system work under NFSv4<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.E.5<br />
|Verify features of the GFS file system work under NFSv4<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.E.6<br />
|Verify features of cluster file systems (e.g. GFS) work under NFSv4<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.E.7<br />
|Verify features of the Luster file system work under NFSv4<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.E.8<br />
|Verify features of the GPFS file system work under NFSv4<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.E.9<br />
|Verify features of the Sanfs file system work under NFSv4<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.E.10<br />
|Verify features of the Polyserve file system work under NFSv4<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.E.11<br />
|Verify features of the Netcache file system work under NFSv4<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.E.12<br />
|Verify features of the Rainfinity file system work under NFSv4<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.E.13<br />
|Analyze file system configuration issues, such as:<br><br />
Logical volume manager behind server<br><br />
RAID-5 problem with small write workloads (may be performance issue?)<br><br />
Compiling POSIX ACL's in and out<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|}<br />
<br />
== Test ACL interoperability of Linux client for non-Linux servers ==<br />
See I.R.3; need test<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|II.F.1<br />
|ACL compatibility for Linux IA-32 client - Solaris 10 client<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.F.2<br />
|ACL compatibility for Linux IA-32 client - NetApp server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.F.3<br />
|ACL compatibility for Linux IA-32 client - EMC server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.F.4<br />
|ACL compatibility for Linux IA-32 client - AIX 5.3 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.F.5<br />
|ACL compatibility for Linux IA-32 client – AMD server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.F.6<br />
|ACL compatibility for Linux IA-32 client - Polyserve server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.F.7<br />
|ACL compatibility for Linux IA-32 client – Hummingbird server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.F.8<br />
|ACL compatibility for Linux IA-32 client – HP server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.F.9<br />
|ACL compatibility for Linux IA-32 client – SGI server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.F.10<br />
|ACL compatibility for Linux IA-32 client – Spinniker server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|}<br />
<br />
== Test ACL interoperability of Linux server with non-Linux clients ==<br />
See I.R.3; need test<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|II.G.1<br />
|ACL compatibility for Solaris 10 client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.G.2<br />
|ACL compatibility for NetApp client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.G.3<br />
|ACL compatibility for EMC client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.G.4<br />
|ACL compatibility for AIX 5.3 client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.G.5<br />
|ACL compatibility for AMD client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.G.6<br />
|ACL compatibility for Polyserve client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.G.7<br />
|ACL compatibility for Hummingbird client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.G.8<br />
|ACL compatibility for HP client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.G.9<br />
|ACL compatibility for SGI client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.G.10<br />
|ACL compatibility for Spinniker client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|}<br />
<br />
== Automounter interoperability ==<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|II.H.1<br />
|Verify amd will work as a drop-in automounter service with nfsv4<br />
|<br />
|'''Open'''<br />
|IBM<br />
|<br />
|-<br />
|II.H.2<br />
|Verify autong will work as a drop-in automounter service with nfsv4<br />
|<br />
|'''Open'''<br />
|IBM<br />
|<br />
|-<br />
|II.H.3<br />
|Verify autofs4 will work as a drop-in automounter service with nfsv4<br />
|<br />
|'''Open'''<br />
|IBM<br />
|<br />
|-<br />
|II.H.4<br />
|Verify interoperability of nfsv4 and automounter with various map sources:<br><br />
- Flat file Connectathon<br><br />
- Program file Connectathon<br><br />
- NIS Connectathon<br><br />
- NIS+<br><br />
- LDAP using NIS style maps (RFC2307)<br><br />
- LDAP using Linux style automounter maps<br><br />
- LDAP using Yet-Another schema (RFC2307bis, deleted, but used by solaris 9 last I checked)<br />
|<br />
|'''Open'''<br />
|IBM<br />
|<br />
|-<br />
|}</div>
65.172.181.6
https://wiki.linux-nfs.org/wiki/index.php/Test_matrix
Test matrix
2005-09-30T22:30:22Z
<p>65.172.181.6: /* Interoperability Testing */</p>
<hr />
<div>This pages summarizes testing efforts for NFSv4, and identify testing gaps. Email nfsv4@linux-nfs.org with feedback or to take ownership of a task. If you are doing NFSv4 testing, please let us know!<br />
<br />
==[[Matrix_functional_section|Functional Testing]]==<br />
Ability to do what it's supposed to do. Standards compliance, regression, compatibility, static code analysis, etc.<br />
{|border="1" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|<br />
!style="background: #ececec;"|'''New'''<br />
!style="background: #ececec;"|'''Open'''<br />
!style="background: #ececec;"|'''In progress'''<br />
!style="background: #ececec;"|'''Near Done'''<br />
!style="background: #ececec;"|'''Done'''<br />
!style="background: #ececec;"|'''High'''<br />
!style="background: #ececec;"|'''Medium'''<br />
!style="background: #ececec;"|'''Low'''<br />
|-<br />
|current status<br />
|102<br />
|30<br />
|1<br />
|0<br />
|5<br />
|43<br />
|72<br />
|22<br />
|}<br />
<br />
==[[Matrix_interop_section|Interoperability Testing]]==<br />
<br />
Ability to work with other versions of NFS, other operating systems and other software/filesystems/etc. generally associated with NFS<br />
<br />
{|border="1" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|<br />
!style="background: #ececec;"|'''New'''<br />
!style="background: #ececec;"|'''Open'''<br />
!style="background: #ececec;"|'''In progress'''<br />
!style="background: #ececec;"|'''Near Done'''<br />
!style="background: #ececec;"|'''Done'''<br />
!style="background: #ececec;"|'''High'''<br />
!style="background: #ececec;"|'''Medium'''<br />
!style="background: #ececec;"|'''Low'''<br />
|-<br />
|current status<br />
|57<br />
|12<br />
|0<br />
|0<br />
|1<br />
|33<br />
|12<br />
|25<br />
|}<br />
<br />
==[[Matrix_robustness_section|Robustness Testing]]==<br />
<br />
Remains stable and recovers even in extreme situations, Stability, interoperability, error recovery, race conditions, etc<br />
<br />
{|border="1" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|<br />
!style="background: #ececec;"|'''New'''<br />
!style="background: #ececec;"|'''Open'''<br />
!style="background: #ececec;"|'''In progress'''<br />
!style="background: #ececec;"|'''Near Done'''<br />
!style="background: #ececec;"|'''Done'''<br />
!style="background: #ececec;"|'''High'''<br />
!style="background: #ececec;"|'''Medium'''<br />
!style="background: #ececec;"|'''Low'''<br />
|-<br />
|current status<br />
|29 <!-- It was 37 --><br />
|6<br />
|1 <br />
|2 <!-- add maximum files exported / mounted --><br />
|6 <!-- tests ffsb/fsstress and IOZone running long periods (1 week) + disk limits on server/client maximum file size (=local fs)--><br />
|32<br />
|8<br />
|2<br />
|}<br />
<br />
==[[Matrix_performance_section|Performance Testing]]==<br />
<br />
Able to perform well under real and theoretical workloads Load, stress, destruction, scalability, etc<br />
<br />
{|border="1" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|<br />
!style="background: #ececec;"|'''New'''<br />
!style="background: #ececec;"|'''Open'''<br />
!style="background: #ececec;"|'''In progress'''<br />
!style="background: #ececec;"|'''Near Done'''<br />
!style="background: #ececec;"|'''Done'''<br />
!style="background: #ececec;"|'''High'''<br />
!style="background: #ececec;"|'''Medium'''<br />
!style="background: #ececec;"|'''Low'''<br />
|-<br />
|current status<br />
|35<br />
|10<br />
|6<br />
|1<br />
|3<br />
|19<br />
|26<br />
|4<br />
|}<br />
<br />
==[[Matrix_security_section|Security Testing]]==<br />
<br />
Resistant to being compromised and difficult to attack<br />
<br />
{|border="1" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|<br />
!style="background: #ececec;"|'''New'''<br />
!style="background: #ececec;"|'''Open'''<br />
!style="background: #ececec;"|'''In progress'''<br />
!style="background: #ececec;"|'''Near Done'''<br />
!style="background: #ececec;"|'''Done'''<br />
!style="background: #ececec;"|'''High'''<br />
!style="background: #ececec;"|'''Medium'''<br />
!style="background: #ececec;"|'''Low'''<br />
|-<br />
|current status<br />
|28<br />
|4<br />
|0<br />
|0<br />
|1<br />
|14<br />
|9<br />
|9<br />
|}<br />
<br />
==Definitions==<br />
<br />
*'''New''' : An owner has not been identified for the item and work has not started on it<br />
*'''Open''': The task has been adopted, but either has not been started, or progress is not yet known<br />
*'''In Progress''' : Some work has been completed on the task<br />
*'''Near Done''': The principle essense of the task has been finished, but there are some loose ends left<br />
*'''Done''': The task has been fully completed</div>
65.172.181.6
https://wiki.linux-nfs.org/wiki/index.php/General_troubleshooting_recommendations
General troubleshooting recommendations
2005-08-22T16:58:51Z
<p>65.172.181.6: </p>
<hr />
<div>Depending on your configuration, there's a number of ways that NFS can fail to work. Sometimes it can be difficult to determine exactly why it is not working. This page describes some general techniques for diagnosing the issue.<br />
<br />
If you cannot resolve your problem and plan to report it to the developer, see [[Reporting bugs]].<br />
<br />
=General NFSv4 Issues=<br />
<br />
== Check server's exports ==<br />
<br />
An easy first thing to doublecheck is that your server is exporting what you think it is. On the server, run the command:<br />
<br />
exportfs -v<br />
<br />
If you need to make modifications, edit /etc/exports and re-export using the command <br />
<br />
exportfs -r<br />
<br />
Remember that pseudo-filesystems in NFSv4 work very differently than NFSv3. Review the [http://www.citi.umich.edu/projects/nfsv4/linux/using-nfsv4.html Using NFSv4] directions if you have questions.<br />
<br />
== Check server mount functionality ==<br />
<br />
Try mounting the nfs4 export on the server itself by mounting localhost:/. This will isolate whether the problem is with the server configuration.<br />
<br />
== Getting detailed debug output of the client/server interactions ==<br />
<br />
=== NFS and RPC Trace Debugging ===<br />
<br />
You can capture more information about exactly what the client or server thinks is going on by enabling trace debugging. Trace debugging puts messages on the console and in /var/log/messages as the client or server goes through its paces so you can track progress and have some idea what request is being processed.<br />
<br />
The debugging value is a bit mask that indicates which types of events you'd like to see traced. For information on the flag values, look in include/linux/nfs_fs.h, include/linux/lockd/debug.h, include/linux/sunrpc/debug.h, or include/linux/nfsd/debug.h.<br />
<br />
To set the debugging value, you use a sysctl like so:<br />
<br />
sudo sysctl -w sunrpc.nfs_debug=3<br />
<br />
and to turn off debugging, just do this:<br />
<br />
sudo sysctl -w sunrpc.nfs_debug=0<br />
<br />
See also sunrpc.nfsd_debug, sunrpc.rpc_debug, and sunrpc.nlm_debug.<br />
<br />
Sometimes this kind of tracing can produce voluminous output. To ensure that your system log daemon can handle the traffic, make these adjustments:<br />
<br />
# When you build your kernel, set the CONFIG_LOG_BUF_SHIFT option to a larger value than is recommended for your hardware. That will allow the kernel to buffer more log messages.<br />
# Edit /etc/syslog.conf and place a "-" in front of "/var/log/messages" -- so you get "-/var/log/messages". That will switch syslogd into async mode to allow it to keep up.<br />
<br />
You may also consider enabling serial console support. This will cause all printk()'s to be delayed by the time it takes to write the message on the serial port. While this means that kernel logging can now easily keep up with trace message logging, it will also introduce a significant change in timing that may cause your problem to become unreproducible!<br />
<br />
=== Capturing a Network Trace ===<br />
<br />
If you suspect the problem may involve some sort of miscommunication between the client and server, it can be useful for debugging purposes to dump the communication stream:<br />
<br />
Start `tcpdump -s 9000 -w /tmp/dump.out port 2049` on the client, then conduct the client/server interaction. Review the /tmp/dump.out file (or include it with your bug report).<br />
<br />
Useful tips:<br />
<br />
# If you build your own kernels, enable CONFIG_PACKET_MMAP (Under Device Drivers --> Networking Support --> Network Options) to help tcpdump to keep up with traffic.<br />
# Use a tmpfs file system for the tcpdump output file. tcpdump will keep up more easily, especially with gigabit speed transfer rates.<br />
# Capture a trace on both ends if you suspect a network problem. Comparing the traces will show what each side of the communication is seeing.<br />
# Leave off the "port 2049" to capture DNS, NIS, LDAP, or Kerberos traffic, if you suspect one of these auxiliary protocols is causing misbehavior.<br />
# Don't forget about tcpslice and tethereal's command line parsers if you have a really big trace and you need to split it into manageable chunks.<br />
<br />
== Kernel Stack Traceback ==<br />
<br />
If you have hung processes, capture a stack traceback to show where the processes are waiting in the kernel. You will need to build your kernel with the CONFIG_MAGIC_SYSRQ option (under Kernel Hacking) to enable stack traceback.<br />
<br />
First, look in /etc/sysctl.conf to see if kernel.sysrq is set to 1. If not, then run this command:<br />
<br />
echo 1 > /proc/sys/kernel/sysrq<br />
<br />
Next, trigger a stack traceback via this command:<br />
<br />
echo t > /proc/sysrq-trigger<br />
<br />
Look on your console or in /var/log/messages for the output.<br />
<br />
Another option, which doesn't require rebuilding your kernel, is to grab the contents of /proc/self/wchan for all the processes on your system. This doesn't give a full traceback, but it will show where each process is waiting, which is sometimes useful. A simple bash script to do this might look like this:<br />
<br />
for i in /proc/*/wchan<br />
do<br />
echo "Process" $i<br />
cat $i<br />
echo " "<br />
done<br />
<br />
== Making Sense of a Kernel Oops report ==<br />
<br />
Tip: to get a clean oops report, make sure you've enabled the CONFIG_FRAME_POINTER option under Kernel Hacking when you build your kernel. Then, when you install, copy the System.map file from your build to your boot directory and name it "System.map-`uname -r`" so that the kernel can find it to resolve symbols properly.<br />
<br />
=="Reboot" the NFSv4 server without shutting down the machine==<br />
<br />
Just shut down rpc.nfsd and start it again.<br />
<br />
==Comparing results when mounting via NFSv3 and NFSv4==<br />
<br />
Find a file that is differing between v3 and v4, and look at the output from the `stat` utility. <br />
<br />
Or use `ls -lid --type-style=full-iso` and `ls -lid --time=ctime --time-style=full-iso` if you don't have stat.<br />
<br />
=Kerberos issues=<br />
<br />
==Check hostnames==<br />
<br />
Kerberos requires the hostname/domainname used in the keytab is correct. Run `hostname` and look in /etc/hosts to doublecheck that it is set properly. Compare with what you've listed in your keytab file.<br />
<br />
==Check keytabs==<br />
<br />
Run the following command to check your keytab:<br />
<br />
klist -k<br />
<br />
==Check krb5 ccache file==<br />
<br />
If you see log messages regarding something like 'FILE:/tmp/krb5cc_machine_FOO.BAR.AD.ROOT', you can review the file after trying to do the mount via:<br />
<br />
klist -e -f -c /tmp/krb5cc_machine_FOO.BAR.AD.ROOT<br />
<br />
This will list info about your principals such as the valid/expire dates, encryption types, etc.</div>
65.172.181.6
https://wiki.linux-nfs.org/wiki/index.php/Matrix_performance_section
Matrix performance section
2005-08-03T00:56:50Z
<p>65.172.181.6: /* Performances over Internet */</p>
<hr />
<div>== Comparison of NFSv4 vs. NFSv3 for common use cases==<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.A.1<br />
|Time to perform sequence of unique read/write operations<br />
|Iozone<br />
|'''In progress'''<br />
|'''Bull'''<br />
|Done by Bull in 2004<br />
|-<br />
|IV.A.2<br />
|Time to perform sequence of cacheable read/write operations<br />
|Iozone<br />
|'''In progress'''<br />
|<br />
|<br />
|-<br />
|IV.A.3<br />
|Random reads/writes/opens from many clients to one server<br />
|Iozone<br />
|'''In progress'''<br />
|'''Bull'''<br />
|Done by Bull in 2004<br />
|-<br />
|IV.A.4<br />
|Industry standard loads<br />
|SpecSFS, Specweb99<br />
|'''New'''<br />
|<br />
|''Tools does not exist''.<br />
|-<br />
|IV.A.5<br />
|Time to read file from beginning to end and then rewrite it<br />
|IOzone<br />
|'''In progress'''<br />
|'''Bull'''<br />
|Part of IOZone standard tests<br />
|-<br />
|IV.A.6<br />
|Time for appending info to a log file sporadically over time<br />
|Iozone<br />
|'''New'''<br />
|'''Bull'''<br />
|<br />
|-<br />
|IV.A.7<br />
|Metadata - open/close intensive workload<br />
|Iozone<br />
|'''New'''<br />
|Bull<br />
|<br />
|-<br />
|IV.A.8<br />
|Metadata - directory scanning<br />
|Iozone<br />
|'''Done'''<br />
|Bull<br />
|Directory scanning over NFSv4 is analysed [http://nfsv4.bullopensource.org/tools/tests/page19.php here]. Time to stat a directory is O(n²) where n is the number of files in the directory.<br />
|-<br />
|IV.A.9<br />
|Metadata - create/delete<br />
|Iozone<br />
|'''New'''<br />
|Bull<br />
|<br />
|-<br />
|IV.A.10<br />
|Metadata - changing attributes (chown, chmod) while dir scanning<br />
|IOZone<br />
|'''New'''<br />
|Bull<br />
|<br />
|-<br />
|IV.A.11<br />
|How many locks can be made and released over time<br />
|FFsB<br />
|'''New'''<br />
|Bull<br />
|<br />
|-<br />
|IV.A.12<br />
|Comparison of speeds attainable for different NIC cards<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|}<br />
<br />
== NFSv4 on TCP vs. RDMA ==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.B <br />
|Compare latency, throughput, etc. of NFSv4 on TCP vs. RDMA<br />
|<br />
|'''New'''<br />
|<br />
|Only prototypes exist currently; possibly will be more fully implemented by end of 2005<br />
|}<br />
<br />
== Test performance on different local filesystems ==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.C.1<br />
|Analyze whether file system choice affects performance<br />
|Iozone<br />
|'''DONE'''<br />
|'''Bull'''<br />
|[http://nfsv4.bullopensource.org/tools/tests/page2.php NFSv4 performances] do not depend on the local file-system used<br />
|-<br />
|IV.C.2<br />
|Test performance with Ext2 on server with metadata /acls<br />
|IOZone/FFsB<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.C.3<br />
|Test performance with ext3 on server with metadata / acls<br />
|IOZone/FFsB<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.C.4<br />
|Test performance with Reiser3 on server with metadata / acls<br />
|IOZone/FFsB<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.C.5<br />
|Test performance with xfs on server with metadata / acls<br />
|IOZone/FFsB<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.C.6<br />
|Test performance with jfs on server with metadata / acls<br />
|IOZone/FFsB<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.C.7<br />
|Test performance with Reiser4 on server with metadata /acls<br />
|IOZone/FFsB<br />
|'''New'''<br />
|<br />
|<br />
|}<br />
<br />
== Test perfomance on different cluster filesystems ==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.D.1<br />
|Test performance when using GFS cluster file system<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.D.2<br />
|Test performance when using Luster cluster file system<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.D.3<br />
|Test performance when using GPFS cluster file system<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.D.4<br />
|Test performance when using Polyserve cluster file system<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|}<br />
<br />
== Evaluation in various load scenarios ==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.E.1<br />
|Test performance with large numbers of small (<4k) files<br />
|addhoc tool<br />
|'''In progress'''<br />
|Bull<br />
|While most NFS functionnalities are not affected by the number of files (2 000 000 of empty files).<br />
|-<br />
|*IV.E.1<br />
*Sub topic 1<br />
|Test performance with large numbers of small (<4k) files - stat function ; empty files -<br />
|addhoc tool<br />
|'''Done'''<br />
|Bull<br />
|Stat answer is O(n²). More details [http://nfsv4.bullopensource.org/tools/tests/page19.php here]<br />
|-<br />
|IV.E.1<br />
*Sub topic 2<br />
|Test performance with large numbers of small (<4k) files - Open function ; empty files -<br />
|addhoc tool<br />
|'''Near done'''<br />
|Bull<br />
|Open function is O(n). There is a bottle neck for n=1620000. More details [http://nfsv4.bullopensource.org/tools/tests/page20.php here]. Comparisons with [http://nfsv4.bullopensource.org/tools/tests/page21.php local file system] and [http://nfsv4.bullopensource.org/tools/tests/page22.php NFSv3].<br />
|-<br />
|IV.E.2<br />
|Test performance with a few very large (>1G) files<br />
|IOzone<br />
|'''Open'''<br />
|Bull<br />
|Goals need clarifications: are we manipulating files (acl/metadatas/moving...) or reading/writing files?<br />
|-<br />
|IV.E.3<br />
|4-16 clients generating high load on 1 server in lab environment<br />
|Mail/user dir<br />
|'''New'''<br />
|Bull<br />
|<br />
|-<br />
|IV.E.4<br />
|2000-5000 clients on 5-10 servers in production environment<br />
|Clusters<br />
|'''New'''<br />
|NetApps<br />
|<br />
|-<br />
|IV.E.5<br />
|NFS "Cluster" scenario with 1000+ clients and several servers<br />
|Film industry, HPC or visualization workload<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.E.6<br />
|NFS front end with cluster backend; 100+ clients<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.E.7<br />
|Pure cluster; 100+ clients<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|}<br />
<br />
== Evaluation in stress scenarios ==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.F.1<br />
|Measure performance of server when in limited resource situations :<br />
*Low memory / heavy swap space usage<br />
*High inode count situations<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.F.2<br />
|Measure performance of client when in limited resource situations :<br />
*Low memory / heavy swap space usage<br />
*Low/saturated network bandwidth<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.F.3<br />
|Graceful failure mode<br />
|<br />
|'''New'''<br />
|<br />
|See Chuck for more info<br />
|-<br />
|IV.F.4<br />
|Measure memory/network/CPU efficiency of client for fixed workload<br />
|IOzone - FFsB<br />
|'''In progress'''<br />
|Bull<br />
|<br />
|}<br />
<br />
== Scalability (performance) ==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.G.<br />
|Verify server scalability with clients generating various basic requests (ACCESS, GETATTR, et al)<br />
|Iozone<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.G.2<br />
|Verify server scalability with clients using compound requests<br />
|Iozone<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.G.3<br />
|Measure effects of scaling up number of connections<br />
|IOZone<br />
|'''Open'''<br />
|Bull<br />
|SMP - Measure number of mounts per second on client and server<br />
|-<br />
|IV.G.4<br />
|Measure effects of increasing number of files<br />
|Addhoc tool<br />
|'''Open'''<br />
|Bull<br />
|<br />
|-<br />
|IV.G.5<br />
|Measure effects of increasing file size (with/without cache)<br />
|IOzone<br />
|'''Open'''<br />
|Bull<br />
|<br />
|-<br />
|IV.G.6<br />
|Measure effects when increasing size of on-the-wire NFS read or write operations :<br />
*Mount options from the client side; find optimal settings<br />
*Measure for stable latency behavior<br />
|Iozone<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.G.7<br />
|Measure performance when scaling CPU count per node on SMP&NUMA<br />
|Iozone<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.G.8<br />
|Measure performance when scaling memory per node on SMP&NUMA<br />
|Iozone<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.G.9<br />
|Measure performance when scaling NIC count per node<br />
|Iozone<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.G.10<br />
|Measure performance when scaling disk count per node<br />
|Iozone<br />
|'''New'''<br />
|<br />
|<br />
|}<br />
<br />
== Identify best practices for performance tuning ==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.H<br />
|Identify best practices for performance tuning:<br />
*--- Auto-tuning for max performance during installation?<br />
*Tuning NFS transfer size<br />
*Details will need to be captured as we complete other testing<br />
|<br />
|'''Open'''<br />
|Bull<br />
|Not clear. There is few tunables points on NFSv4.<br />
|}<br />
<br />
== Performance effects of security features ==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.J.1<br />
|Measure performance when operating with IPSec integrity and privacy<br />
|IOzone<br />
|'''Open'''<br />
|<br />
|<br />
|-<br />
|IV.J.2<br />
|Measure performance when operating with Kerberos 5 integrity and privacy<br />
|IOzone<br />
|'''Open'''<br />
|<br />
|<br />
|-<br />
|IV.J.3<br />
|Measure performance when operating with SPKM integrity and privacy<br />
|IOzone<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.J.4<br />
|Measure performance when operating with Lipkey integrity and privacy<br />
|IOzone<br />
|'''New'''<br />
|<br />
|<br />
|}<br />
<br />
== Performance over Internet==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.K.1<br />
|Measure performances for various fixed workoads over WAN<br />
|Iozone - FFsB<br />
|'''Open'''<br />
|Bull - CITI<br />
|Tests between CITI and Bull<br />
|-<br />
|IV.K.2<br />
|Measure performances for various fixed workoads with Kerberos enabled over WAN<br />
|Iozone - FFsB<br />
|'''Open'''<br />
|Bull - CITI<br />
|Tests between CITI and Bull<br />
|-<br />
|IV.K.3<br />
|Measure performances for metadata manipulation over WAN (directory lookup, attributes manipulations ...)<br />
|FFsB<br />
|'''Open'''<br />
|Bull - CITI<br />
|Tests between CITI and Bull<br />
|}</div>
65.172.181.6
https://wiki.linux-nfs.org/wiki/index.php/Matrix_performance_section
Matrix performance section
2005-08-03T00:56:28Z
<p>65.172.181.6: /* Test performance on different local filesystems */</p>
<hr />
<div>== Comparison of NFSv4 vs. NFSv3 for common use cases==<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.A.1<br />
|Time to perform sequence of unique read/write operations<br />
|Iozone<br />
|'''In progress'''<br />
|'''Bull'''<br />
|Done by Bull in 2004<br />
|-<br />
|IV.A.2<br />
|Time to perform sequence of cacheable read/write operations<br />
|Iozone<br />
|'''In progress'''<br />
|<br />
|<br />
|-<br />
|IV.A.3<br />
|Random reads/writes/opens from many clients to one server<br />
|Iozone<br />
|'''In progress'''<br />
|'''Bull'''<br />
|Done by Bull in 2004<br />
|-<br />
|IV.A.4<br />
|Industry standard loads<br />
|SpecSFS, Specweb99<br />
|'''New'''<br />
|<br />
|''Tools does not exist''.<br />
|-<br />
|IV.A.5<br />
|Time to read file from beginning to end and then rewrite it<br />
|IOzone<br />
|'''In progress'''<br />
|'''Bull'''<br />
|Part of IOZone standard tests<br />
|-<br />
|IV.A.6<br />
|Time for appending info to a log file sporadically over time<br />
|Iozone<br />
|'''New'''<br />
|'''Bull'''<br />
|<br />
|-<br />
|IV.A.7<br />
|Metadata - open/close intensive workload<br />
|Iozone<br />
|'''New'''<br />
|Bull<br />
|<br />
|-<br />
|IV.A.8<br />
|Metadata - directory scanning<br />
|Iozone<br />
|'''Done'''<br />
|Bull<br />
|Directory scanning over NFSv4 is analysed [http://nfsv4.bullopensource.org/tools/tests/page19.php here]. Time to stat a directory is O(n²) where n is the number of files in the directory.<br />
|-<br />
|IV.A.9<br />
|Metadata - create/delete<br />
|Iozone<br />
|'''New'''<br />
|Bull<br />
|<br />
|-<br />
|IV.A.10<br />
|Metadata - changing attributes (chown, chmod) while dir scanning<br />
|IOZone<br />
|'''New'''<br />
|Bull<br />
|<br />
|-<br />
|IV.A.11<br />
|How many locks can be made and released over time<br />
|FFsB<br />
|'''New'''<br />
|Bull<br />
|<br />
|-<br />
|IV.A.12<br />
|Comparison of speeds attainable for different NIC cards<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|}<br />
<br />
== NFSv4 on TCP vs. RDMA ==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.B <br />
|Compare latency, throughput, etc. of NFSv4 on TCP vs. RDMA<br />
|<br />
|'''New'''<br />
|<br />
|Only prototypes exist currently; possibly will be more fully implemented by end of 2005<br />
|}<br />
<br />
== Test performance on different local filesystems ==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.C.1<br />
|Analyze whether file system choice affects performance<br />
|Iozone<br />
|'''DONE'''<br />
|'''Bull'''<br />
|[http://nfsv4.bullopensource.org/tools/tests/page2.php NFSv4 performances] do not depend on the local file-system used<br />
|-<br />
|IV.C.2<br />
|Test performance with Ext2 on server with metadata /acls<br />
|IOZone/FFsB<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.C.3<br />
|Test performance with ext3 on server with metadata / acls<br />
|IOZone/FFsB<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.C.4<br />
|Test performance with Reiser3 on server with metadata / acls<br />
|IOZone/FFsB<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.C.5<br />
|Test performance with xfs on server with metadata / acls<br />
|IOZone/FFsB<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.C.6<br />
|Test performance with jfs on server with metadata / acls<br />
|IOZone/FFsB<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.C.7<br />
|Test performance with Reiser4 on server with metadata /acls<br />
|IOZone/FFsB<br />
|'''New'''<br />
|<br />
|<br />
|}<br />
<br />
== Test perfomance on different cluster filesystems ==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.D.1<br />
|Test performance when using GFS cluster file system<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.D.2<br />
|Test performance when using Luster cluster file system<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.D.3<br />
|Test performance when using GPFS cluster file system<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.D.4<br />
|Test performance when using Polyserve cluster file system<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|}<br />
<br />
== Evaluation in various load scenarios ==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.E.1<br />
|Test performance with large numbers of small (<4k) files<br />
|addhoc tool<br />
|'''In progress'''<br />
|Bull<br />
|While most NFS functionnalities are not affected by the number of files (2 000 000 of empty files).<br />
|-<br />
|*IV.E.1<br />
*Sub topic 1<br />
|Test performance with large numbers of small (<4k) files - stat function ; empty files -<br />
|addhoc tool<br />
|'''Done'''<br />
|Bull<br />
|Stat answer is O(n²). More details [http://nfsv4.bullopensource.org/tools/tests/page19.php here]<br />
|-<br />
|IV.E.1<br />
*Sub topic 2<br />
|Test performance with large numbers of small (<4k) files - Open function ; empty files -<br />
|addhoc tool<br />
|'''Near done'''<br />
|Bull<br />
|Open function is O(n). There is a bottle neck for n=1620000. More details [http://nfsv4.bullopensource.org/tools/tests/page20.php here]. Comparisons with [http://nfsv4.bullopensource.org/tools/tests/page21.php local file system] and [http://nfsv4.bullopensource.org/tools/tests/page22.php NFSv3].<br />
|-<br />
|IV.E.2<br />
|Test performance with a few very large (>1G) files<br />
|IOzone<br />
|'''Open'''<br />
|Bull<br />
|Goals need clarifications: are we manipulating files (acl/metadatas/moving...) or reading/writing files?<br />
|-<br />
|IV.E.3<br />
|4-16 clients generating high load on 1 server in lab environment<br />
|Mail/user dir<br />
|'''New'''<br />
|Bull<br />
|<br />
|-<br />
|IV.E.4<br />
|2000-5000 clients on 5-10 servers in production environment<br />
|Clusters<br />
|'''New'''<br />
|NetApps<br />
|<br />
|-<br />
|IV.E.5<br />
|NFS "Cluster" scenario with 1000+ clients and several servers<br />
|Film industry, HPC or visualization workload<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.E.6<br />
|NFS front end with cluster backend; 100+ clients<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.E.7<br />
|Pure cluster; 100+ clients<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|}<br />
<br />
== Evaluation in stress scenarios ==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.F.1<br />
|Measure performance of server when in limited resource situations :<br />
*Low memory / heavy swap space usage<br />
*High inode count situations<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.F.2<br />
|Measure performance of client when in limited resource situations :<br />
*Low memory / heavy swap space usage<br />
*Low/saturated network bandwidth<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.F.3<br />
|Graceful failure mode<br />
|<br />
|'''New'''<br />
|<br />
|See Chuck for more info<br />
|-<br />
|IV.F.4<br />
|Measure memory/network/CPU efficiency of client for fixed workload<br />
|IOzone - FFsB<br />
|'''In progress'''<br />
|Bull<br />
|<br />
|}<br />
<br />
== Scalability (performance) ==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.G.<br />
|Verify server scalability with clients generating various basic requests (ACCESS, GETATTR, et al)<br />
|Iozone<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.G.2<br />
|Verify server scalability with clients using compound requests<br />
|Iozone<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.G.3<br />
|Measure effects of scaling up number of connections<br />
|IOZone<br />
|'''Open'''<br />
|Bull<br />
|SMP - Measure number of mounts per second on client and server<br />
|-<br />
|IV.G.4<br />
|Measure effects of increasing number of files<br />
|Addhoc tool<br />
|'''Open'''<br />
|Bull<br />
|<br />
|-<br />
|IV.G.5<br />
|Measure effects of increasing file size (with/without cache)<br />
|IOzone<br />
|'''Open'''<br />
|Bull<br />
|<br />
|-<br />
|IV.G.6<br />
|Measure effects when increasing size of on-the-wire NFS read or write operations :<br />
*Mount options from the client side; find optimal settings<br />
*Measure for stable latency behavior<br />
|Iozone<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.G.7<br />
|Measure performance when scaling CPU count per node on SMP&NUMA<br />
|Iozone<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.G.8<br />
|Measure performance when scaling memory per node on SMP&NUMA<br />
|Iozone<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.G.9<br />
|Measure performance when scaling NIC count per node<br />
|Iozone<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.G.10<br />
|Measure performance when scaling disk count per node<br />
|Iozone<br />
|'''New'''<br />
|<br />
|<br />
|}<br />
<br />
== Identify best practices for performance tuning ==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.H<br />
|Identify best practices for performance tuning:<br />
*--- Auto-tuning for max performance during installation?<br />
*Tuning NFS transfer size<br />
*Details will need to be captured as we complete other testing<br />
|<br />
|'''Open'''<br />
|Bull<br />
|Not clear. There is few tunables points on NFSv4.<br />
|}<br />
<br />
== Performance effects of security features ==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.J.1<br />
|Measure performance when operating with IPSec integrity and privacy<br />
|IOzone<br />
|'''Open'''<br />
|<br />
|<br />
|-<br />
|IV.J.2<br />
|Measure performance when operating with Kerberos 5 integrity and privacy<br />
|IOzone<br />
|'''Open'''<br />
|<br />
|<br />
|-<br />
|IV.J.3<br />
|Measure performance when operating with SPKM integrity and privacy<br />
|IOzone<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.J.4<br />
|Measure performance when operating with Lipkey integrity and privacy<br />
|IOzone<br />
|'''New'''<br />
|<br />
|<br />
|}<br />
<br />
== Performances over Internet==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.K.1<br />
|Measure performances for various fixed workoads over WAN<br />
|Iozone - FFsB<br />
|'''Open'''<br />
|Bull - CITI<br />
|Tests between CITI and Bull<br />
|-<br />
|IV.K.2<br />
|Measure performances for various fixed workoads with Kerberos enabled over WAN<br />
|Iozone - FFsB<br />
|'''Open'''<br />
|Bull - CITI<br />
|Tests between CITI and Bull<br />
|-<br />
|IV.K.3<br />
|Measure performances for metadata manipulation over WAN (directory lookup, attributes manipulations ...)<br />
|FFsB<br />
|'''Open'''<br />
|Bull - CITI<br />
|Tests between CITI and Bull<br />
|}</div>
65.172.181.6
https://wiki.linux-nfs.org/wiki/index.php/Matrix_performance_section
Matrix performance section
2005-08-03T00:56:08Z
<p>65.172.181.6: /* Comparison of NFSv4 vs. NFSv3 for common use cases */</p>
<hr />
<div>== Comparison of NFSv4 vs. NFSv3 for common use cases==<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.A.1<br />
|Time to perform sequence of unique read/write operations<br />
|Iozone<br />
|'''In progress'''<br />
|'''Bull'''<br />
|Done by Bull in 2004<br />
|-<br />
|IV.A.2<br />
|Time to perform sequence of cacheable read/write operations<br />
|Iozone<br />
|'''In progress'''<br />
|<br />
|<br />
|-<br />
|IV.A.3<br />
|Random reads/writes/opens from many clients to one server<br />
|Iozone<br />
|'''In progress'''<br />
|'''Bull'''<br />
|Done by Bull in 2004<br />
|-<br />
|IV.A.4<br />
|Industry standard loads<br />
|SpecSFS, Specweb99<br />
|'''New'''<br />
|<br />
|''Tools does not exist''.<br />
|-<br />
|IV.A.5<br />
|Time to read file from beginning to end and then rewrite it<br />
|IOzone<br />
|'''In progress'''<br />
|'''Bull'''<br />
|Part of IOZone standard tests<br />
|-<br />
|IV.A.6<br />
|Time for appending info to a log file sporadically over time<br />
|Iozone<br />
|'''New'''<br />
|'''Bull'''<br />
|<br />
|-<br />
|IV.A.7<br />
|Metadata - open/close intensive workload<br />
|Iozone<br />
|'''New'''<br />
|Bull<br />
|<br />
|-<br />
|IV.A.8<br />
|Metadata - directory scanning<br />
|Iozone<br />
|'''Done'''<br />
|Bull<br />
|Directory scanning over NFSv4 is analysed [http://nfsv4.bullopensource.org/tools/tests/page19.php here]. Time to stat a directory is O(n²) where n is the number of files in the directory.<br />
|-<br />
|IV.A.9<br />
|Metadata - create/delete<br />
|Iozone<br />
|'''New'''<br />
|Bull<br />
|<br />
|-<br />
|IV.A.10<br />
|Metadata - changing attributes (chown, chmod) while dir scanning<br />
|IOZone<br />
|'''New'''<br />
|Bull<br />
|<br />
|-<br />
|IV.A.11<br />
|How many locks can be made and released over time<br />
|FFsB<br />
|'''New'''<br />
|Bull<br />
|<br />
|-<br />
|IV.A.12<br />
|Comparison of speeds attainable for different NIC cards<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|}<br />
<br />
== NFSv4 on TCP vs. RDMA ==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.B <br />
|Compare latency, throughput, etc. of NFSv4 on TCP vs. RDMA<br />
|<br />
|'''New'''<br />
|<br />
|Only prototypes exist currently; possibly will be more fully implemented by end of 2005<br />
|}<br />
<br />
== Test performance on different local filesystems ==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.C.1<br />
|Analyze whether file system choice affects performance<br />
|Iozone<br />
|'''Done'''<br />
|'''Bull'''<br />
|[http://nfsv4.bullopensource.org/tools/tests/page2.php NFSv4 performances] do not depend on the local file-system used<br />
|-<br />
|IV.C.2<br />
|Test performance with Ext2 on server with metadata /acls<br />
|IOZone/FFsB<br />
|<br />
|<br />
|<br />
|-<br />
|IV.C.3<br />
|Test performance with ext3 on server with metadata / acls<br />
|IOZone/FFsB<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.C.4<br />
|Test performance with Reiser3 on server with metadata / acls<br />
|IOZone/FFsB<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.C.5<br />
|Test performance with xfs on server with metadata / acls<br />
|IOZone/FFsB<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.C.6<br />
|Test performance with jfs on server with metadata / acls<br />
|IOZone/FFsB<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.C.7<br />
|Test performance with Reiser4 on server with metadata /acls<br />
|IOZone/FFsB<br />
|'''New'''<br />
|<br />
|<br />
|}<br />
<br />
== Test perfomance on different cluster filesystems ==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.D.1<br />
|Test performance when using GFS cluster file system<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.D.2<br />
|Test performance when using Luster cluster file system<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.D.3<br />
|Test performance when using GPFS cluster file system<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.D.4<br />
|Test performance when using Polyserve cluster file system<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|}<br />
<br />
== Evaluation in various load scenarios ==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.E.1<br />
|Test performance with large numbers of small (<4k) files<br />
|addhoc tool<br />
|'''In progress'''<br />
|Bull<br />
|While most NFS functionnalities are not affected by the number of files (2 000 000 of empty files).<br />
|-<br />
|*IV.E.1<br />
*Sub topic 1<br />
|Test performance with large numbers of small (<4k) files - stat function ; empty files -<br />
|addhoc tool<br />
|'''Done'''<br />
|Bull<br />
|Stat answer is O(n²). More details [http://nfsv4.bullopensource.org/tools/tests/page19.php here]<br />
|-<br />
|IV.E.1<br />
*Sub topic 2<br />
|Test performance with large numbers of small (<4k) files - Open function ; empty files -<br />
|addhoc tool<br />
|'''Near done'''<br />
|Bull<br />
|Open function is O(n). There is a bottle neck for n=1620000. More details [http://nfsv4.bullopensource.org/tools/tests/page20.php here]. Comparisons with [http://nfsv4.bullopensource.org/tools/tests/page21.php local file system] and [http://nfsv4.bullopensource.org/tools/tests/page22.php NFSv3].<br />
|-<br />
|IV.E.2<br />
|Test performance with a few very large (>1G) files<br />
|IOzone<br />
|'''Open'''<br />
|Bull<br />
|Goals need clarifications: are we manipulating files (acl/metadatas/moving...) or reading/writing files?<br />
|-<br />
|IV.E.3<br />
|4-16 clients generating high load on 1 server in lab environment<br />
|Mail/user dir<br />
|'''New'''<br />
|Bull<br />
|<br />
|-<br />
|IV.E.4<br />
|2000-5000 clients on 5-10 servers in production environment<br />
|Clusters<br />
|'''New'''<br />
|NetApps<br />
|<br />
|-<br />
|IV.E.5<br />
|NFS "Cluster" scenario with 1000+ clients and several servers<br />
|Film industry, HPC or visualization workload<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.E.6<br />
|NFS front end with cluster backend; 100+ clients<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.E.7<br />
|Pure cluster; 100+ clients<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|}<br />
<br />
== Evaluation in stress scenarios ==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.F.1<br />
|Measure performance of server when in limited resource situations :<br />
*Low memory / heavy swap space usage<br />
*High inode count situations<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.F.2<br />
|Measure performance of client when in limited resource situations :<br />
*Low memory / heavy swap space usage<br />
*Low/saturated network bandwidth<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.F.3<br />
|Graceful failure mode<br />
|<br />
|'''New'''<br />
|<br />
|See Chuck for more info<br />
|-<br />
|IV.F.4<br />
|Measure memory/network/CPU efficiency of client for fixed workload<br />
|IOzone - FFsB<br />
|'''In progress'''<br />
|Bull<br />
|<br />
|}<br />
<br />
== Scalability (performance) ==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.G.<br />
|Verify server scalability with clients generating various basic requests (ACCESS, GETATTR, et al)<br />
|Iozone<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.G.2<br />
|Verify server scalability with clients using compound requests<br />
|Iozone<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.G.3<br />
|Measure effects of scaling up number of connections<br />
|IOZone<br />
|'''Open'''<br />
|Bull<br />
|SMP - Measure number of mounts per second on client and server<br />
|-<br />
|IV.G.4<br />
|Measure effects of increasing number of files<br />
|Addhoc tool<br />
|'''Open'''<br />
|Bull<br />
|<br />
|-<br />
|IV.G.5<br />
|Measure effects of increasing file size (with/without cache)<br />
|IOzone<br />
|'''Open'''<br />
|Bull<br />
|<br />
|-<br />
|IV.G.6<br />
|Measure effects when increasing size of on-the-wire NFS read or write operations :<br />
*Mount options from the client side; find optimal settings<br />
*Measure for stable latency behavior<br />
|Iozone<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.G.7<br />
|Measure performance when scaling CPU count per node on SMP&NUMA<br />
|Iozone<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.G.8<br />
|Measure performance when scaling memory per node on SMP&NUMA<br />
|Iozone<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.G.9<br />
|Measure performance when scaling NIC count per node<br />
|Iozone<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.G.10<br />
|Measure performance when scaling disk count per node<br />
|Iozone<br />
|'''New'''<br />
|<br />
|<br />
|}<br />
<br />
== Identify best practices for performance tuning ==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.H<br />
|Identify best practices for performance tuning:<br />
*--- Auto-tuning for max performance during installation?<br />
*Tuning NFS transfer size<br />
*Details will need to be captured as we complete other testing<br />
|<br />
|'''Open'''<br />
|Bull<br />
|Not clear. There is few tunables points on NFSv4.<br />
|}<br />
<br />
== Performance effects of security features ==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.J.1<br />
|Measure performance when operating with IPSec integrity and privacy<br />
|IOzone<br />
|'''Open'''<br />
|<br />
|<br />
|-<br />
|IV.J.2<br />
|Measure performance when operating with Kerberos 5 integrity and privacy<br />
|IOzone<br />
|'''Open'''<br />
|<br />
|<br />
|-<br />
|IV.J.3<br />
|Measure performance when operating with SPKM integrity and privacy<br />
|IOzone<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.J.4<br />
|Measure performance when operating with Lipkey integrity and privacy<br />
|IOzone<br />
|'''New'''<br />
|<br />
|<br />
|}<br />
<br />
== Performances over Internet==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.K.1<br />
|Measure performances for various fixed workoads over WAN<br />
|Iozone - FFsB<br />
|'''Open'''<br />
|Bull - CITI<br />
|Tests between CITI and Bull<br />
|-<br />
|IV.K.2<br />
|Measure performances for various fixed workoads with Kerberos enabled over WAN<br />
|Iozone - FFsB<br />
|'''Open'''<br />
|Bull - CITI<br />
|Tests between CITI and Bull<br />
|-<br />
|IV.K.3<br />
|Measure performances for metadata manipulation over WAN (directory lookup, attributes manipulations ...)<br />
|FFsB<br />
|'''Open'''<br />
|Bull - CITI<br />
|Tests between CITI and Bull<br />
|}</div>
65.172.181.6
https://wiki.linux-nfs.org/wiki/index.php/Matrix_performance_section
Matrix performance section
2005-08-03T00:54:58Z
<p>65.172.181.6: /* Performance effects of security features */</p>
<hr />
<div>== Comparison of NFSv4 vs. NFSv3 for common use cases==<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.A.1<br />
|Time to perform sequence of unique read/write operations<br />
|Iozone<br />
|'''In progress'''<br />
|'''Bull'''<br />
|Done by Bull in 2004<br />
|-<br />
|IV.A.2<br />
|Time to perform sequence of cacheable read/write operations<br />
|Iozone<br />
|'''In progress'''<br />
|<br />
|<br />
|-<br />
|IV.A.3<br />
|Random reads/writes/opens from many clients to one server<br />
|Iozone<br />
|'''In progress'''<br />
|'''Bull'''<br />
|Done by Bull in 2004<br />
|-<br />
|IV.A.4<br />
|Industry standard loads<br />
|SpecSFS, Specweb99<br />
|'''New'''<br />
|<br />
|''Tools does not exist''.<br />
|-<br />
|IV.A.5<br />
|Time to read file from beginning to end and then rewrite it<br />
|IOzone<br />
|'''In progress'''<br />
|'''Bull'''<br />
|Part of IOZone standard tests<br />
|-<br />
|IV.A.6<br />
|Time for appending info to a log file sporadically over time<br />
|Iozone<br />
|'''New'''<br />
|'''Bull'''<br />
|<br />
|-<br />
|IV.A.7<br />
|Metadata - open/close intensive workload<br />
|Iozone<br />
|'''New'''<br />
|Bull<br />
|<br />
|-<br />
|IV.A.8<br />
|Metadata - directory scanning<br />
|Iozone<br />
|'''Done'''<br />
|Bull<br />
|Directory scanning over NFSv4 is analysed [http://nfsv4.bullopensource.org/tools/tests/page19.php here]. Time to stat a directory is O(n²) where n is the number of files in the directory.<br />
|-<br />
|IV.A.9<br />
|Metadata - create/delete<br />
|Iozone<br />
|'''New'''<br />
|Bull<br />
|<br />
|-<br />
|IV.A.10<br />
|Metadata - changing attributes (chown, chmod) while dir scanning<br />
|IOZone<br />
|'''New'''<br />
|Bull<br />
|<br />
|-<br />
|IV.A.11<br />
|How many locks can be made and released over time<br />
|FFsB<br />
|'''New'''<br />
|Bull<br />
|<br />
|-<br />
|IV.A.12<br />
|Comparison of speeds attainable for different NIC cards<br />
|<br />
|<br />
|<br />
|<br />
|}<br />
<br />
== NFSv4 on TCP vs. RDMA ==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.B <br />
|Compare latency, throughput, etc. of NFSv4 on TCP vs. RDMA<br />
|<br />
|'''New'''<br />
|<br />
|Only prototypes exist currently; possibly will be more fully implemented by end of 2005<br />
|}<br />
<br />
== Test performance on different local filesystems ==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.C.1<br />
|Analyze whether file system choice affects performance<br />
|Iozone<br />
|'''Done'''<br />
|'''Bull'''<br />
|[http://nfsv4.bullopensource.org/tools/tests/page2.php NFSv4 performances] do not depend on the local file-system used<br />
|-<br />
|IV.C.2<br />
|Test performance with Ext2 on server with metadata /acls<br />
|IOZone/FFsB<br />
|<br />
|<br />
|<br />
|-<br />
|IV.C.3<br />
|Test performance with ext3 on server with metadata / acls<br />
|IOZone/FFsB<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.C.4<br />
|Test performance with Reiser3 on server with metadata / acls<br />
|IOZone/FFsB<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.C.5<br />
|Test performance with xfs on server with metadata / acls<br />
|IOZone/FFsB<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.C.6<br />
|Test performance with jfs on server with metadata / acls<br />
|IOZone/FFsB<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.C.7<br />
|Test performance with Reiser4 on server with metadata /acls<br />
|IOZone/FFsB<br />
|'''New'''<br />
|<br />
|<br />
|}<br />
<br />
== Test perfomance on different cluster filesystems ==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.D.1<br />
|Test performance when using GFS cluster file system<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.D.2<br />
|Test performance when using Luster cluster file system<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.D.3<br />
|Test performance when using GPFS cluster file system<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.D.4<br />
|Test performance when using Polyserve cluster file system<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|}<br />
<br />
== Evaluation in various load scenarios ==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.E.1<br />
|Test performance with large numbers of small (<4k) files<br />
|addhoc tool<br />
|'''In progress'''<br />
|Bull<br />
|While most NFS functionnalities are not affected by the number of files (2 000 000 of empty files).<br />
|-<br />
|*IV.E.1<br />
*Sub topic 1<br />
|Test performance with large numbers of small (<4k) files - stat function ; empty files -<br />
|addhoc tool<br />
|'''Done'''<br />
|Bull<br />
|Stat answer is O(n²). More details [http://nfsv4.bullopensource.org/tools/tests/page19.php here]<br />
|-<br />
|IV.E.1<br />
*Sub topic 2<br />
|Test performance with large numbers of small (<4k) files - Open function ; empty files -<br />
|addhoc tool<br />
|'''Near done'''<br />
|Bull<br />
|Open function is O(n). There is a bottle neck for n=1620000. More details [http://nfsv4.bullopensource.org/tools/tests/page20.php here]. Comparisons with [http://nfsv4.bullopensource.org/tools/tests/page21.php local file system] and [http://nfsv4.bullopensource.org/tools/tests/page22.php NFSv3].<br />
|-<br />
|IV.E.2<br />
|Test performance with a few very large (>1G) files<br />
|IOzone<br />
|'''Open'''<br />
|Bull<br />
|Goals need clarifications: are we manipulating files (acl/metadatas/moving...) or reading/writing files?<br />
|-<br />
|IV.E.3<br />
|4-16 clients generating high load on 1 server in lab environment<br />
|Mail/user dir<br />
|'''New'''<br />
|Bull<br />
|<br />
|-<br />
|IV.E.4<br />
|2000-5000 clients on 5-10 servers in production environment<br />
|Clusters<br />
|'''New'''<br />
|NetApps<br />
|<br />
|-<br />
|IV.E.5<br />
|NFS "Cluster" scenario with 1000+ clients and several servers<br />
|Film industry, HPC or visualization workload<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.E.6<br />
|NFS front end with cluster backend; 100+ clients<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.E.7<br />
|Pure cluster; 100+ clients<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|}<br />
<br />
== Evaluation in stress scenarios ==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.F.1<br />
|Measure performance of server when in limited resource situations :<br />
*Low memory / heavy swap space usage<br />
*High inode count situations<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.F.2<br />
|Measure performance of client when in limited resource situations :<br />
*Low memory / heavy swap space usage<br />
*Low/saturated network bandwidth<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.F.3<br />
|Graceful failure mode<br />
|<br />
|'''New'''<br />
|<br />
|See Chuck for more info<br />
|-<br />
|IV.F.4<br />
|Measure memory/network/CPU efficiency of client for fixed workload<br />
|IOzone - FFsB<br />
|'''In progress'''<br />
|Bull<br />
|<br />
|}<br />
<br />
== Scalability (performance) ==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.G.<br />
|Verify server scalability with clients generating various basic requests (ACCESS, GETATTR, et al)<br />
|Iozone<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.G.2<br />
|Verify server scalability with clients using compound requests<br />
|Iozone<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.G.3<br />
|Measure effects of scaling up number of connections<br />
|IOZone<br />
|'''Open'''<br />
|Bull<br />
|SMP - Measure number of mounts per second on client and server<br />
|-<br />
|IV.G.4<br />
|Measure effects of increasing number of files<br />
|Addhoc tool<br />
|'''Open'''<br />
|Bull<br />
|<br />
|-<br />
|IV.G.5<br />
|Measure effects of increasing file size (with/without cache)<br />
|IOzone<br />
|'''Open'''<br />
|Bull<br />
|<br />
|-<br />
|IV.G.6<br />
|Measure effects when increasing size of on-the-wire NFS read or write operations :<br />
*Mount options from the client side; find optimal settings<br />
*Measure for stable latency behavior<br />
|Iozone<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.G.7<br />
|Measure performance when scaling CPU count per node on SMP&NUMA<br />
|Iozone<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.G.8<br />
|Measure performance when scaling memory per node on SMP&NUMA<br />
|Iozone<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.G.9<br />
|Measure performance when scaling NIC count per node<br />
|Iozone<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.G.10<br />
|Measure performance when scaling disk count per node<br />
|Iozone<br />
|'''New'''<br />
|<br />
|<br />
|}<br />
<br />
== Identify best practices for performance tuning ==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.H<br />
|Identify best practices for performance tuning:<br />
*--- Auto-tuning for max performance during installation?<br />
*Tuning NFS transfer size<br />
*Details will need to be captured as we complete other testing<br />
|<br />
|'''Open'''<br />
|Bull<br />
|Not clear. There is few tunables points on NFSv4.<br />
|}<br />
<br />
== Performance effects of security features ==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.J.1<br />
|Measure performance when operating with IPSec integrity and privacy<br />
|IOzone<br />
|'''Open'''<br />
|<br />
|<br />
|-<br />
|IV.J.2<br />
|Measure performance when operating with Kerberos 5 integrity and privacy<br />
|IOzone<br />
|'''Open'''<br />
|<br />
|<br />
|-<br />
|IV.J.3<br />
|Measure performance when operating with SPKM integrity and privacy<br />
|IOzone<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.J.4<br />
|Measure performance when operating with Lipkey integrity and privacy<br />
|IOzone<br />
|'''New'''<br />
|<br />
|<br />
|}<br />
<br />
== Performances over Internet==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.K.1<br />
|Measure performances for various fixed workoads over WAN<br />
|Iozone - FFsB<br />
|'''Open'''<br />
|Bull - CITI<br />
|Tests between CITI and Bull<br />
|-<br />
|IV.K.2<br />
|Measure performances for various fixed workoads with Kerberos enabled over WAN<br />
|Iozone - FFsB<br />
|'''Open'''<br />
|Bull - CITI<br />
|Tests between CITI and Bull<br />
|-<br />
|IV.K.3<br />
|Measure performances for metadata manipulation over WAN (directory lookup, attributes manipulations ...)<br />
|FFsB<br />
|'''Open'''<br />
|Bull - CITI<br />
|Tests between CITI and Bull<br />
|}</div>
65.172.181.6
https://wiki.linux-nfs.org/wiki/index.php/Matrix_performance_section
Matrix performance section
2005-08-03T00:54:19Z
<p>65.172.181.6: /* Identify best practices for performance tuning */</p>
<hr />
<div>== Comparison of NFSv4 vs. NFSv3 for common use cases==<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.A.1<br />
|Time to perform sequence of unique read/write operations<br />
|Iozone<br />
|'''In progress'''<br />
|'''Bull'''<br />
|Done by Bull in 2004<br />
|-<br />
|IV.A.2<br />
|Time to perform sequence of cacheable read/write operations<br />
|Iozone<br />
|'''In progress'''<br />
|<br />
|<br />
|-<br />
|IV.A.3<br />
|Random reads/writes/opens from many clients to one server<br />
|Iozone<br />
|'''In progress'''<br />
|'''Bull'''<br />
|Done by Bull in 2004<br />
|-<br />
|IV.A.4<br />
|Industry standard loads<br />
|SpecSFS, Specweb99<br />
|'''New'''<br />
|<br />
|''Tools does not exist''.<br />
|-<br />
|IV.A.5<br />
|Time to read file from beginning to end and then rewrite it<br />
|IOzone<br />
|'''In progress'''<br />
|'''Bull'''<br />
|Part of IOZone standard tests<br />
|-<br />
|IV.A.6<br />
|Time for appending info to a log file sporadically over time<br />
|Iozone<br />
|'''New'''<br />
|'''Bull'''<br />
|<br />
|-<br />
|IV.A.7<br />
|Metadata - open/close intensive workload<br />
|Iozone<br />
|'''New'''<br />
|Bull<br />
|<br />
|-<br />
|IV.A.8<br />
|Metadata - directory scanning<br />
|Iozone<br />
|'''Done'''<br />
|Bull<br />
|Directory scanning over NFSv4 is analysed [http://nfsv4.bullopensource.org/tools/tests/page19.php here]. Time to stat a directory is O(n²) where n is the number of files in the directory.<br />
|-<br />
|IV.A.9<br />
|Metadata - create/delete<br />
|Iozone<br />
|'''New'''<br />
|Bull<br />
|<br />
|-<br />
|IV.A.10<br />
|Metadata - changing attributes (chown, chmod) while dir scanning<br />
|IOZone<br />
|'''New'''<br />
|Bull<br />
|<br />
|-<br />
|IV.A.11<br />
|How many locks can be made and released over time<br />
|FFsB<br />
|'''New'''<br />
|Bull<br />
|<br />
|-<br />
|IV.A.12<br />
|Comparison of speeds attainable for different NIC cards<br />
|<br />
|<br />
|<br />
|<br />
|}<br />
<br />
== NFSv4 on TCP vs. RDMA ==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.B <br />
|Compare latency, throughput, etc. of NFSv4 on TCP vs. RDMA<br />
|<br />
|'''New'''<br />
|<br />
|Only prototypes exist currently; possibly will be more fully implemented by end of 2005<br />
|}<br />
<br />
== Test performance on different local filesystems ==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.C.1<br />
|Analyze whether file system choice affects performance<br />
|Iozone<br />
|'''Done'''<br />
|'''Bull'''<br />
|[http://nfsv4.bullopensource.org/tools/tests/page2.php NFSv4 performances] do not depend on the local file-system used<br />
|-<br />
|IV.C.2<br />
|Test performance with Ext2 on server with metadata /acls<br />
|IOZone/FFsB<br />
|<br />
|<br />
|<br />
|-<br />
|IV.C.3<br />
|Test performance with ext3 on server with metadata / acls<br />
|IOZone/FFsB<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.C.4<br />
|Test performance with Reiser3 on server with metadata / acls<br />
|IOZone/FFsB<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.C.5<br />
|Test performance with xfs on server with metadata / acls<br />
|IOZone/FFsB<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.C.6<br />
|Test performance with jfs on server with metadata / acls<br />
|IOZone/FFsB<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.C.7<br />
|Test performance with Reiser4 on server with metadata /acls<br />
|IOZone/FFsB<br />
|'''New'''<br />
|<br />
|<br />
|}<br />
<br />
== Test perfomance on different cluster filesystems ==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.D.1<br />
|Test performance when using GFS cluster file system<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.D.2<br />
|Test performance when using Luster cluster file system<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.D.3<br />
|Test performance when using GPFS cluster file system<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.D.4<br />
|Test performance when using Polyserve cluster file system<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|}<br />
<br />
== Evaluation in various load scenarios ==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.E.1<br />
|Test performance with large numbers of small (<4k) files<br />
|addhoc tool<br />
|'''In progress'''<br />
|Bull<br />
|While most NFS functionnalities are not affected by the number of files (2 000 000 of empty files).<br />
|-<br />
|*IV.E.1<br />
*Sub topic 1<br />
|Test performance with large numbers of small (<4k) files - stat function ; empty files -<br />
|addhoc tool<br />
|'''Done'''<br />
|Bull<br />
|Stat answer is O(n²). More details [http://nfsv4.bullopensource.org/tools/tests/page19.php here]<br />
|-<br />
|IV.E.1<br />
*Sub topic 2<br />
|Test performance with large numbers of small (<4k) files - Open function ; empty files -<br />
|addhoc tool<br />
|'''Near done'''<br />
|Bull<br />
|Open function is O(n). There is a bottle neck for n=1620000. More details [http://nfsv4.bullopensource.org/tools/tests/page20.php here]. Comparisons with [http://nfsv4.bullopensource.org/tools/tests/page21.php local file system] and [http://nfsv4.bullopensource.org/tools/tests/page22.php NFSv3].<br />
|-<br />
|IV.E.2<br />
|Test performance with a few very large (>1G) files<br />
|IOzone<br />
|'''Open'''<br />
|Bull<br />
|Goals need clarifications: are we manipulating files (acl/metadatas/moving...) or reading/writing files?<br />
|-<br />
|IV.E.3<br />
|4-16 clients generating high load on 1 server in lab environment<br />
|Mail/user dir<br />
|'''New'''<br />
|Bull<br />
|<br />
|-<br />
|IV.E.4<br />
|2000-5000 clients on 5-10 servers in production environment<br />
|Clusters<br />
|'''New'''<br />
|NetApps<br />
|<br />
|-<br />
|IV.E.5<br />
|NFS "Cluster" scenario with 1000+ clients and several servers<br />
|Film industry, HPC or visualization workload<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.E.6<br />
|NFS front end with cluster backend; 100+ clients<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.E.7<br />
|Pure cluster; 100+ clients<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|}<br />
<br />
== Evaluation in stress scenarios ==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.F.1<br />
|Measure performance of server when in limited resource situations :<br />
*Low memory / heavy swap space usage<br />
*High inode count situations<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.F.2<br />
|Measure performance of client when in limited resource situations :<br />
*Low memory / heavy swap space usage<br />
*Low/saturated network bandwidth<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.F.3<br />
|Graceful failure mode<br />
|<br />
|'''New'''<br />
|<br />
|See Chuck for more info<br />
|-<br />
|IV.F.4<br />
|Measure memory/network/CPU efficiency of client for fixed workload<br />
|IOzone - FFsB<br />
|'''In progress'''<br />
|Bull<br />
|<br />
|}<br />
<br />
== Scalability (performance) ==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.G.<br />
|Verify server scalability with clients generating various basic requests (ACCESS, GETATTR, et al)<br />
|Iozone<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.G.2<br />
|Verify server scalability with clients using compound requests<br />
|Iozone<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.G.3<br />
|Measure effects of scaling up number of connections<br />
|IOZone<br />
|'''Open'''<br />
|Bull<br />
|SMP - Measure number of mounts per second on client and server<br />
|-<br />
|IV.G.4<br />
|Measure effects of increasing number of files<br />
|Addhoc tool<br />
|'''Open'''<br />
|Bull<br />
|<br />
|-<br />
|IV.G.5<br />
|Measure effects of increasing file size (with/without cache)<br />
|IOzone<br />
|'''Open'''<br />
|Bull<br />
|<br />
|-<br />
|IV.G.6<br />
|Measure effects when increasing size of on-the-wire NFS read or write operations :<br />
*Mount options from the client side; find optimal settings<br />
*Measure for stable latency behavior<br />
|Iozone<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.G.7<br />
|Measure performance when scaling CPU count per node on SMP&NUMA<br />
|Iozone<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.G.8<br />
|Measure performance when scaling memory per node on SMP&NUMA<br />
|Iozone<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.G.9<br />
|Measure performance when scaling NIC count per node<br />
|Iozone<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.G.10<br />
|Measure performance when scaling disk count per node<br />
|Iozone<br />
|'''New'''<br />
|<br />
|<br />
|}<br />
<br />
== Identify best practices for performance tuning ==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.H<br />
|Identify best practices for performance tuning:<br />
*--- Auto-tuning for max performance during installation?<br />
*Tuning NFS transfer size<br />
*Details will need to be captured as we complete other testing<br />
|<br />
|'''Open'''<br />
|Bull<br />
|Not clear. There is few tunables points on NFSv4.<br />
|}<br />
<br />
== Performance effects of security features ==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.J.1<br />
|Measure performance when operating with IPSec integrity and privacy<br />
|IOzone<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.J.2<br />
|Measure performance when operating with Kerberos 5 integrity and privacy<br />
|IOzone<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.J.3<br />
|Measure performance when operating with SPKM integrity and privacy<br />
|IOzone<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.J.4<br />
|Measure performance when operating with Lipkey integrity and privacy<br />
|IOzone<br />
|'''New'''<br />
|<br />
|<br />
|}<br />
<br />
== Performances over Internet==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.K.1<br />
|Measure performances for various fixed workoads over WAN<br />
|Iozone - FFsB<br />
|'''Open'''<br />
|Bull - CITI<br />
|Tests between CITI and Bull<br />
|-<br />
|IV.K.2<br />
|Measure performances for various fixed workoads with Kerberos enabled over WAN<br />
|Iozone - FFsB<br />
|'''Open'''<br />
|Bull - CITI<br />
|Tests between CITI and Bull<br />
|-<br />
|IV.K.3<br />
|Measure performances for metadata manipulation over WAN (directory lookup, attributes manipulations ...)<br />
|FFsB<br />
|'''Open'''<br />
|Bull - CITI<br />
|Tests between CITI and Bull<br />
|}</div>
65.172.181.6
https://wiki.linux-nfs.org/wiki/index.php/Matrix_performance_section
Matrix performance section
2005-08-03T00:53:56Z
<p>65.172.181.6: /* Scalability (performance) */</p>
<hr />
<div>== Comparison of NFSv4 vs. NFSv3 for common use cases==<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.A.1<br />
|Time to perform sequence of unique read/write operations<br />
|Iozone<br />
|'''In progress'''<br />
|'''Bull'''<br />
|Done by Bull in 2004<br />
|-<br />
|IV.A.2<br />
|Time to perform sequence of cacheable read/write operations<br />
|Iozone<br />
|'''In progress'''<br />
|<br />
|<br />
|-<br />
|IV.A.3<br />
|Random reads/writes/opens from many clients to one server<br />
|Iozone<br />
|'''In progress'''<br />
|'''Bull'''<br />
|Done by Bull in 2004<br />
|-<br />
|IV.A.4<br />
|Industry standard loads<br />
|SpecSFS, Specweb99<br />
|'''New'''<br />
|<br />
|''Tools does not exist''.<br />
|-<br />
|IV.A.5<br />
|Time to read file from beginning to end and then rewrite it<br />
|IOzone<br />
|'''In progress'''<br />
|'''Bull'''<br />
|Part of IOZone standard tests<br />
|-<br />
|IV.A.6<br />
|Time for appending info to a log file sporadically over time<br />
|Iozone<br />
|'''New'''<br />
|'''Bull'''<br />
|<br />
|-<br />
|IV.A.7<br />
|Metadata - open/close intensive workload<br />
|Iozone<br />
|'''New'''<br />
|Bull<br />
|<br />
|-<br />
|IV.A.8<br />
|Metadata - directory scanning<br />
|Iozone<br />
|'''Done'''<br />
|Bull<br />
|Directory scanning over NFSv4 is analysed [http://nfsv4.bullopensource.org/tools/tests/page19.php here]. Time to stat a directory is O(n²) where n is the number of files in the directory.<br />
|-<br />
|IV.A.9<br />
|Metadata - create/delete<br />
|Iozone<br />
|'''New'''<br />
|Bull<br />
|<br />
|-<br />
|IV.A.10<br />
|Metadata - changing attributes (chown, chmod) while dir scanning<br />
|IOZone<br />
|'''New'''<br />
|Bull<br />
|<br />
|-<br />
|IV.A.11<br />
|How many locks can be made and released over time<br />
|FFsB<br />
|'''New'''<br />
|Bull<br />
|<br />
|-<br />
|IV.A.12<br />
|Comparison of speeds attainable for different NIC cards<br />
|<br />
|<br />
|<br />
|<br />
|}<br />
<br />
== NFSv4 on TCP vs. RDMA ==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.B <br />
|Compare latency, throughput, etc. of NFSv4 on TCP vs. RDMA<br />
|<br />
|'''New'''<br />
|<br />
|Only prototypes exist currently; possibly will be more fully implemented by end of 2005<br />
|}<br />
<br />
== Test performance on different local filesystems ==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.C.1<br />
|Analyze whether file system choice affects performance<br />
|Iozone<br />
|'''Done'''<br />
|'''Bull'''<br />
|[http://nfsv4.bullopensource.org/tools/tests/page2.php NFSv4 performances] do not depend on the local file-system used<br />
|-<br />
|IV.C.2<br />
|Test performance with Ext2 on server with metadata /acls<br />
|IOZone/FFsB<br />
|<br />
|<br />
|<br />
|-<br />
|IV.C.3<br />
|Test performance with ext3 on server with metadata / acls<br />
|IOZone/FFsB<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.C.4<br />
|Test performance with Reiser3 on server with metadata / acls<br />
|IOZone/FFsB<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.C.5<br />
|Test performance with xfs on server with metadata / acls<br />
|IOZone/FFsB<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.C.6<br />
|Test performance with jfs on server with metadata / acls<br />
|IOZone/FFsB<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.C.7<br />
|Test performance with Reiser4 on server with metadata /acls<br />
|IOZone/FFsB<br />
|'''New'''<br />
|<br />
|<br />
|}<br />
<br />
== Test perfomance on different cluster filesystems ==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.D.1<br />
|Test performance when using GFS cluster file system<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.D.2<br />
|Test performance when using Luster cluster file system<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.D.3<br />
|Test performance when using GPFS cluster file system<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.D.4<br />
|Test performance when using Polyserve cluster file system<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|}<br />
<br />
== Evaluation in various load scenarios ==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.E.1<br />
|Test performance with large numbers of small (<4k) files<br />
|addhoc tool<br />
|'''In progress'''<br />
|Bull<br />
|While most NFS functionnalities are not affected by the number of files (2 000 000 of empty files).<br />
|-<br />
|*IV.E.1<br />
*Sub topic 1<br />
|Test performance with large numbers of small (<4k) files - stat function ; empty files -<br />
|addhoc tool<br />
|'''Done'''<br />
|Bull<br />
|Stat answer is O(n²). More details [http://nfsv4.bullopensource.org/tools/tests/page19.php here]<br />
|-<br />
|IV.E.1<br />
*Sub topic 2<br />
|Test performance with large numbers of small (<4k) files - Open function ; empty files -<br />
|addhoc tool<br />
|'''Near done'''<br />
|Bull<br />
|Open function is O(n). There is a bottle neck for n=1620000. More details [http://nfsv4.bullopensource.org/tools/tests/page20.php here]. Comparisons with [http://nfsv4.bullopensource.org/tools/tests/page21.php local file system] and [http://nfsv4.bullopensource.org/tools/tests/page22.php NFSv3].<br />
|-<br />
|IV.E.2<br />
|Test performance with a few very large (>1G) files<br />
|IOzone<br />
|'''Open'''<br />
|Bull<br />
|Goals need clarifications: are we manipulating files (acl/metadatas/moving...) or reading/writing files?<br />
|-<br />
|IV.E.3<br />
|4-16 clients generating high load on 1 server in lab environment<br />
|Mail/user dir<br />
|'''New'''<br />
|Bull<br />
|<br />
|-<br />
|IV.E.4<br />
|2000-5000 clients on 5-10 servers in production environment<br />
|Clusters<br />
|'''New'''<br />
|NetApps<br />
|<br />
|-<br />
|IV.E.5<br />
|NFS "Cluster" scenario with 1000+ clients and several servers<br />
|Film industry, HPC or visualization workload<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.E.6<br />
|NFS front end with cluster backend; 100+ clients<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.E.7<br />
|Pure cluster; 100+ clients<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|}<br />
<br />
== Evaluation in stress scenarios ==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.F.1<br />
|Measure performance of server when in limited resource situations :<br />
*Low memory / heavy swap space usage<br />
*High inode count situations<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.F.2<br />
|Measure performance of client when in limited resource situations :<br />
*Low memory / heavy swap space usage<br />
*Low/saturated network bandwidth<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.F.3<br />
|Graceful failure mode<br />
|<br />
|'''New'''<br />
|<br />
|See Chuck for more info<br />
|-<br />
|IV.F.4<br />
|Measure memory/network/CPU efficiency of client for fixed workload<br />
|IOzone - FFsB<br />
|'''In progress'''<br />
|Bull<br />
|<br />
|}<br />
<br />
== Scalability (performance) ==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.G.<br />
|Verify server scalability with clients generating various basic requests (ACCESS, GETATTR, et al)<br />
|Iozone<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.G.2<br />
|Verify server scalability with clients using compound requests<br />
|Iozone<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.G.3<br />
|Measure effects of scaling up number of connections<br />
|IOZone<br />
|'''Open'''<br />
|Bull<br />
|SMP - Measure number of mounts per second on client and server<br />
|-<br />
|IV.G.4<br />
|Measure effects of increasing number of files<br />
|Addhoc tool<br />
|'''Open'''<br />
|Bull<br />
|<br />
|-<br />
|IV.G.5<br />
|Measure effects of increasing file size (with/without cache)<br />
|IOzone<br />
|'''Open'''<br />
|Bull<br />
|<br />
|-<br />
|IV.G.6<br />
|Measure effects when increasing size of on-the-wire NFS read or write operations :<br />
*Mount options from the client side; find optimal settings<br />
*Measure for stable latency behavior<br />
|Iozone<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.G.7<br />
|Measure performance when scaling CPU count per node on SMP&NUMA<br />
|Iozone<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.G.8<br />
|Measure performance when scaling memory per node on SMP&NUMA<br />
|Iozone<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.G.9<br />
|Measure performance when scaling NIC count per node<br />
|Iozone<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.G.10<br />
|Measure performance when scaling disk count per node<br />
|Iozone<br />
|'''New'''<br />
|<br />
|<br />
|}<br />
<br />
== Identify best practices for performance tuning ==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.H<br />
|Identify best practices for performance tuning:<br />
*--- Auto-tuning for max performance during installation?<br />
*Tuning NFS transfer size<br />
*Details will need to be captured as we complete other testing<br />
|<br />
|'''New'''<br />
|Bull<br />
|Not clear. There is few tunables points on NFSv4.<br />
|}<br />
<br />
== Performance effects of security features ==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.J.1<br />
|Measure performance when operating with IPSec integrity and privacy<br />
|IOzone<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.J.2<br />
|Measure performance when operating with Kerberos 5 integrity and privacy<br />
|IOzone<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.J.3<br />
|Measure performance when operating with SPKM integrity and privacy<br />
|IOzone<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.J.4<br />
|Measure performance when operating with Lipkey integrity and privacy<br />
|IOzone<br />
|'''New'''<br />
|<br />
|<br />
|}<br />
<br />
== Performances over Internet==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.K.1<br />
|Measure performances for various fixed workoads over WAN<br />
|Iozone - FFsB<br />
|'''Open'''<br />
|Bull - CITI<br />
|Tests between CITI and Bull<br />
|-<br />
|IV.K.2<br />
|Measure performances for various fixed workoads with Kerberos enabled over WAN<br />
|Iozone - FFsB<br />
|'''Open'''<br />
|Bull - CITI<br />
|Tests between CITI and Bull<br />
|-<br />
|IV.K.3<br />
|Measure performances for metadata manipulation over WAN (directory lookup, attributes manipulations ...)<br />
|FFsB<br />
|'''Open'''<br />
|Bull - CITI<br />
|Tests between CITI and Bull<br />
|}</div>
65.172.181.6
https://wiki.linux-nfs.org/wiki/index.php/Matrix_performance_section
Matrix performance section
2005-08-03T00:52:52Z
<p>65.172.181.6: </p>
<hr />
<div>== Comparison of NFSv4 vs. NFSv3 for common use cases==<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.A.1<br />
|Time to perform sequence of unique read/write operations<br />
|Iozone<br />
|'''In progress'''<br />
|'''Bull'''<br />
|Done by Bull in 2004<br />
|-<br />
|IV.A.2<br />
|Time to perform sequence of cacheable read/write operations<br />
|Iozone<br />
|'''In progress'''<br />
|<br />
|<br />
|-<br />
|IV.A.3<br />
|Random reads/writes/opens from many clients to one server<br />
|Iozone<br />
|'''In progress'''<br />
|'''Bull'''<br />
|Done by Bull in 2004<br />
|-<br />
|IV.A.4<br />
|Industry standard loads<br />
|SpecSFS, Specweb99<br />
|'''New'''<br />
|<br />
|''Tools does not exist''.<br />
|-<br />
|IV.A.5<br />
|Time to read file from beginning to end and then rewrite it<br />
|IOzone<br />
|'''In progress'''<br />
|'''Bull'''<br />
|Part of IOZone standard tests<br />
|-<br />
|IV.A.6<br />
|Time for appending info to a log file sporadically over time<br />
|Iozone<br />
|'''New'''<br />
|'''Bull'''<br />
|<br />
|-<br />
|IV.A.7<br />
|Metadata - open/close intensive workload<br />
|Iozone<br />
|'''New'''<br />
|Bull<br />
|<br />
|-<br />
|IV.A.8<br />
|Metadata - directory scanning<br />
|Iozone<br />
|'''Done'''<br />
|Bull<br />
|Directory scanning over NFSv4 is analysed [http://nfsv4.bullopensource.org/tools/tests/page19.php here]. Time to stat a directory is O(n²) where n is the number of files in the directory.<br />
|-<br />
|IV.A.9<br />
|Metadata - create/delete<br />
|Iozone<br />
|'''New'''<br />
|Bull<br />
|<br />
|-<br />
|IV.A.10<br />
|Metadata - changing attributes (chown, chmod) while dir scanning<br />
|IOZone<br />
|'''New'''<br />
|Bull<br />
|<br />
|-<br />
|IV.A.11<br />
|How many locks can be made and released over time<br />
|FFsB<br />
|'''New'''<br />
|Bull<br />
|<br />
|-<br />
|IV.A.12<br />
|Comparison of speeds attainable for different NIC cards<br />
|<br />
|<br />
|<br />
|<br />
|}<br />
<br />
== NFSv4 on TCP vs. RDMA ==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.B <br />
|Compare latency, throughput, etc. of NFSv4 on TCP vs. RDMA<br />
|<br />
|'''New'''<br />
|<br />
|Only prototypes exist currently; possibly will be more fully implemented by end of 2005<br />
|}<br />
<br />
== Test performance on different local filesystems ==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.C.1<br />
|Analyze whether file system choice affects performance<br />
|Iozone<br />
|'''Done'''<br />
|'''Bull'''<br />
|[http://nfsv4.bullopensource.org/tools/tests/page2.php NFSv4 performances] do not depend on the local file-system used<br />
|-<br />
|IV.C.2<br />
|Test performance with Ext2 on server with metadata /acls<br />
|IOZone/FFsB<br />
|<br />
|<br />
|<br />
|-<br />
|IV.C.3<br />
|Test performance with ext3 on server with metadata / acls<br />
|IOZone/FFsB<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.C.4<br />
|Test performance with Reiser3 on server with metadata / acls<br />
|IOZone/FFsB<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.C.5<br />
|Test performance with xfs on server with metadata / acls<br />
|IOZone/FFsB<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.C.6<br />
|Test performance with jfs on server with metadata / acls<br />
|IOZone/FFsB<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.C.7<br />
|Test performance with Reiser4 on server with metadata /acls<br />
|IOZone/FFsB<br />
|'''New'''<br />
|<br />
|<br />
|}<br />
<br />
== Test perfomance on different cluster filesystems ==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.D.1<br />
|Test performance when using GFS cluster file system<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.D.2<br />
|Test performance when using Luster cluster file system<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.D.3<br />
|Test performance when using GPFS cluster file system<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.D.4<br />
|Test performance when using Polyserve cluster file system<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|}<br />
<br />
== Evaluation in various load scenarios ==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.E.1<br />
|Test performance with large numbers of small (<4k) files<br />
|addhoc tool<br />
|'''In progress'''<br />
|Bull<br />
|While most NFS functionnalities are not affected by the number of files (2 000 000 of empty files).<br />
|-<br />
|*IV.E.1<br />
*Sub topic 1<br />
|Test performance with large numbers of small (<4k) files - stat function ; empty files -<br />
|addhoc tool<br />
|'''Done'''<br />
|Bull<br />
|Stat answer is O(n²). More details [http://nfsv4.bullopensource.org/tools/tests/page19.php here]<br />
|-<br />
|IV.E.1<br />
*Sub topic 2<br />
|Test performance with large numbers of small (<4k) files - Open function ; empty files -<br />
|addhoc tool<br />
|'''Near done'''<br />
|Bull<br />
|Open function is O(n). There is a bottle neck for n=1620000. More details [http://nfsv4.bullopensource.org/tools/tests/page20.php here]. Comparisons with [http://nfsv4.bullopensource.org/tools/tests/page21.php local file system] and [http://nfsv4.bullopensource.org/tools/tests/page22.php NFSv3].<br />
|-<br />
|IV.E.2<br />
|Test performance with a few very large (>1G) files<br />
|IOzone<br />
|'''Open'''<br />
|Bull<br />
|Goals need clarifications: are we manipulating files (acl/metadatas/moving...) or reading/writing files?<br />
|-<br />
|IV.E.3<br />
|4-16 clients generating high load on 1 server in lab environment<br />
|Mail/user dir<br />
|'''New'''<br />
|Bull<br />
|<br />
|-<br />
|IV.E.4<br />
|2000-5000 clients on 5-10 servers in production environment<br />
|Clusters<br />
|'''New'''<br />
|NetApps<br />
|<br />
|-<br />
|IV.E.5<br />
|NFS "Cluster" scenario with 1000+ clients and several servers<br />
|Film industry, HPC or visualization workload<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.E.6<br />
|NFS front end with cluster backend; 100+ clients<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.E.7<br />
|Pure cluster; 100+ clients<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|}<br />
<br />
== Evaluation in stress scenarios ==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.F.1<br />
|Measure performance of server when in limited resource situations :<br />
*Low memory / heavy swap space usage<br />
*High inode count situations<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.F.2<br />
|Measure performance of client when in limited resource situations :<br />
*Low memory / heavy swap space usage<br />
*Low/saturated network bandwidth<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.F.3<br />
|Graceful failure mode<br />
|<br />
|'''New'''<br />
|<br />
|See Chuck for more info<br />
|-<br />
|IV.F.4<br />
|Measure memory/network/CPU efficiency of client for fixed workload<br />
|IOzone - FFsB<br />
|'''In progress'''<br />
|Bull<br />
|<br />
|}<br />
<br />
== Scalability (performance) ==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.G.<br />
|Verify server scalability with clients generating various basic requests (ACCESS, GETATTR, et al)<br />
|Iozone<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.G.2<br />
|Verify server scalability with clients using compound requests<br />
|Iozone<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.G.3<br />
|Measure effects of scaling up number of connections<br />
|IOZone<br />
|'''New'''<br />
|Bull<br />
|SMP - Measure number of mounts per second on client and server<br />
|-<br />
|IV.G.4<br />
|Measure effects of increasing number of files<br />
|Addhoc tool<br />
|'''Open'''<br />
|Bull<br />
|<br />
|-<br />
|IV.G.5<br />
|Measure effects of increasing file size (with/without cache)<br />
|IOzone<br />
|'''Open'''<br />
|Bull<br />
|<br />
|-<br />
|IV.G.6<br />
|Measure effects when increasing size of on-the-wire NFS read or write operations :<br />
*Mount options from the client side; find optimal settings<br />
*Measure for stable latency behavior<br />
|Iozone<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.G.7<br />
|Measure performance when scaling CPU count per node on SMP&NUMA<br />
|Iozone<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.G.8<br />
|Measure performance when scaling memory per node on SMP&NUMA<br />
|Iozone<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.G.9<br />
|Measure performance when scaling NIC count per node<br />
|Iozone<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.G.10<br />
|Measure performance when scaling disk count per node<br />
|Iozone<br />
|'''New'''<br />
|<br />
|<br />
|}<br />
<br />
<br />
<br />
== Identify best practices for performance tuning ==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.H<br />
|Identify best practices for performance tuning:<br />
*--- Auto-tuning for max performance during installation?<br />
*Tuning NFS transfer size<br />
*Details will need to be captured as we complete other testing<br />
|<br />
|'''New'''<br />
|Bull<br />
|Not clear. There is few tunables points on NFSv4.<br />
|}<br />
<br />
== Performance effects of security features ==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.J.1<br />
|Measure performance when operating with IPSec integrity and privacy<br />
|IOzone<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.J.2<br />
|Measure performance when operating with Kerberos 5 integrity and privacy<br />
|IOzone<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.J.3<br />
|Measure performance when operating with SPKM integrity and privacy<br />
|IOzone<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|IV.J.4<br />
|Measure performance when operating with Lipkey integrity and privacy<br />
|IOzone<br />
|'''New'''<br />
|<br />
|<br />
|}<br />
<br />
== Performances over Internet==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|IV.K.1<br />
|Measure performances for various fixed workoads over WAN<br />
|Iozone - FFsB<br />
|'''Open'''<br />
|Bull - CITI<br />
|Tests between CITI and Bull<br />
|-<br />
|IV.K.2<br />
|Measure performances for various fixed workoads with Kerberos enabled over WAN<br />
|Iozone - FFsB<br />
|'''Open'''<br />
|Bull - CITI<br />
|Tests between CITI and Bull<br />
|-<br />
|IV.K.3<br />
|Measure performances for metadata manipulation over WAN (directory lookup, attributes manipulations ...)<br />
|FFsB<br />
|'''Open'''<br />
|Bull - CITI<br />
|Tests between CITI and Bull<br />
|}</div>
65.172.181.6
https://wiki.linux-nfs.org/wiki/index.php/Matrix_interop_section
Matrix interop section
2005-08-02T21:30:27Z
<p>65.172.181.6: /* Specific architectural/platform interoperability issues */</p>
<hr />
<div>==Interoperability with other protocols==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|II.A.1<br />
|Kerberos – verify basic functionality. Mount w/ krb5, etc.<br><br />
MIT implementation Open Bull Bull plans to do in 2005<br><br />
Heimdal implementation Open Bull Bull plans to do in 2005<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.A.2<br />
|Active Directory<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.A.3<br />
|IpSec – basic functionality w/ various VPNs, establishment, policies, best practices Unknown <br><br />
IpSec v4 Open Bull Bull plans to do in 2005 <br><br />
IpSec v6 New Not clear who will be using it<br><br />
CCM – very new, low priority New Very new, low priority<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.A.4<br />
|SPKM – Interoperability with key management New<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.A.5<br />
|Interoperability of RPCSEC_GSS in general DONE CITI Trond and Bruce have tested this at Connectathon and NFSv4 Bakeathon<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|}<br />
<br />
== Specific architectural/platform interoperability issues ==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|II.B.1<br />
|Interoperability between 32-bit and 64-bit for client and server Testing on two platforms will be sufficient<br><br />
Linux IA-32 client – AIX PPC server Open Bull<br><br />
Linux IA-32 client – Linux PPC server Open Bull<br><br />
Linux IA-32 client – Linux AMD server Optional<br><br />
Linux IA-32 client – Linux IA-64 server Optional<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.B.2<br />
|Interoperability between little endian and big endian Open Bull Bull plans to do Linux/AIX 5.3 in 2005<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|}<br />
<br />
== Client Interoperability with target architectures/platforms ==<br />
<br />
Need to define how to do interoperability testing – need more than just connectathon<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|II.C.1<br />
|Interoperability for Linux IA-32 client – Solaris 10 server Open Bull<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.C.2<br />
|Interoperability for Linux IA-32 client – NetApp Filer server New<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.C.3<br />
|Interoperability for Linux IA-32 client – EMC Filer server New<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.C.4<br />
|Interoperability for Linux IA-32 client – AIX 5.3 server Open Bull<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.C.5<br />
|Interoperability for Linux IA-32 client – AMD server New<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.C.6<br />
|Interoperability for Linux IA-32 client – PolyServe clustered products New<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.C.7<br />
|Interoperability for Linux IA-32 client – Hummingbird server New<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.C.9<br />
|Interoperability for Linux IA-32 client – HP server New<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.C.10<br />
|Interoperability for Linux IA-32 client – SGI server New<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.C.11<br />
|Interoperability for Linux IA-32 client – Spinniker server New<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|}<br />
<br />
== Server Interoperability with target architectures/platforms ==<br />
<br />
Need to define how to do interoperability testing – need more than just connectathon<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|II.D.1<br />
|Interoperability for Solaris 10 client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.D.2<br />
|Interoperability for NetApp client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.D.3<br />
|Interoperability for EMC client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.D.4<br />
|Interoperability for AIX 5.3 client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.D.5<br />
|Interoperability for AMD client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.D.6<br />
|Interoperability for Polyserve client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.D.7<br />
|Interoperability for Hummingbird client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.D.8<br />
|Interoperability for HP client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.D.9<br />
|Interoperability for SGI client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.D.10<br />
|Interoperability for Spinniker client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|}<br />
<br />
== File systems ==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|II.E.1<br />
|Verify features of cachefs for NFSv4<br />
|<br />
|'''New'''<br />
|<br />
|Not currently NFSv4 ready; needs additional development<br />
|-<br />
|II.E.2<br />
|Verify features of the Ext3 file system work under NFSv4<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.E.3<br />
|Verify features of the XFS file system work under NFSv4<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.E.4<br />
|Verify features of the Reiser file system work under NFSv4<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.E.5<br />
|Verify features of the GFS file system work under NFSv4<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.E.6<br />
|Verify features of cluster file systems (e.g. GFS) work under NFSv4<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.E.7<br />
|Verify features of the Luster file system work under NFSv4<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.E.8<br />
|Verify features of the GPFS file system work under NFSv4<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.E.9<br />
|Verify features of the Sanfs file system work under NFSv4<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.E.10<br />
|Verify features of the Polyserve file system work under NFSv4<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.E.11<br />
|Verify features of the Netcache file system work under NFSv4<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.E.12<br />
|Verify features of the Rainfinity file system work under NFSv4<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.E.13<br />
|Analyze file system configuration issues, such as:<br><br />
Logical volume manager behind server<br><br />
RAID-5 problem with small write workloads (may be performance issue?)<br><br />
Compiling POSIX ACL's in and out<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|}<br />
<br />
== Test ACL interoperability of Linux client for non-Linux servers ==<br />
See I.R.3; need test<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|II.F.1<br />
|ACL compatibility for Linux IA-32 client - Solaris 10 client<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.F.2<br />
|ACL compatibility for Linux IA-32 client - NetApp server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.F.3<br />
|ACL compatibility for Linux IA-32 client - EMC server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.F.4<br />
|ACL compatibility for Linux IA-32 client - AIX 5.3 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.F.5<br />
|ACL compatibility for Linux IA-32 client – AMD server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.F.6<br />
|ACL compatibility for Linux IA-32 client - Polyserve server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.F.7<br />
|ACL compatibility for Linux IA-32 client – Hummingbird server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.F.8<br />
|ACL compatibility for Linux IA-32 client – HP server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.F.9<br />
|ACL compatibility for Linux IA-32 client – SGI server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.F.10<br />
|ACL compatibility for Linux IA-32 client – Spinniker server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|}<br />
<br />
== Test ACL interoperability of Linux server with non-Linux clients ==<br />
See I.R.3; need test<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|II.G.1<br />
|ACL compatibility for Solaris 10 client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.G.2<br />
|ACL compatibility for NetApp client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.G.3<br />
|ACL compatibility for EMC client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.G.4<br />
|ACL compatibility for AIX 5.3 client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.G.5<br />
|ACL compatibility for AMD client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.G.6<br />
|ACL compatibility for Polyserve client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.G.7<br />
|ACL compatibility for Hummingbird client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.G.8<br />
|ACL compatibility for HP client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.G.9<br />
|ACL compatibility for SGI client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.G.10<br />
|ACL compatibility for Spinniker client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|}<br />
<br />
== Automounter interoperability ==<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|II.H.1<br />
|Verify amd will work as a drop-in automounter service with nfsv4<br />
|<br />
|'''Open'''<br />
|IBM<br />
|<br />
|-<br />
|II.H.2<br />
|Verify autong will work as a drop-in automounter service with nfsv4<br />
|<br />
|'''Open'''<br />
|IBM<br />
|<br />
|-<br />
|II.H.3<br />
|Verify autofs4 will work as a drop-in automounter service with nfsv4<br />
|<br />
|'''Open'''<br />
|IBM<br />
|<br />
|-<br />
|II.H.4<br />
|Verify interoperability of nfsv4 and automounter with various map sources:<br><br />
- Flat file Connectathon<br><br />
- Program file Connectathon<br><br />
- NIS Connectathon<br><br />
- NIS+<br><br />
- LDAP using NIS style maps (RFC2307)<br><br />
- LDAP using Linux style automounter maps<br><br />
- LDAP using Yet-Another schema (RFC2307bis, deleted, but used by solaris 9 last I checked)<br />
|<br />
|'''Open'''<br />
|IBM<br />
|<br />
|-<br />
|}</div>
65.172.181.6
https://wiki.linux-nfs.org/wiki/index.php/Matrix_interop_section
Matrix interop section
2005-08-02T21:29:03Z
<p>65.172.181.6: /* Interoperability with other protocols */</p>
<hr />
<div>==Interoperability with other protocols==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|II.A.1<br />
|Kerberos – verify basic functionality. Mount w/ krb5, etc.<br><br />
MIT implementation Open Bull Bull plans to do in 2005<br><br />
Heimdal implementation Open Bull Bull plans to do in 2005<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.A.2<br />
|Active Directory<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.A.3<br />
|IpSec – basic functionality w/ various VPNs, establishment, policies, best practices Unknown <br><br />
IpSec v4 Open Bull Bull plans to do in 2005 <br><br />
IpSec v6 New Not clear who will be using it<br><br />
CCM – very new, low priority New Very new, low priority<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.A.4<br />
|SPKM – Interoperability with key management New<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.A.5<br />
|Interoperability of RPCSEC_GSS in general DONE CITI Trond and Bruce have tested this at Connectathon and NFSv4 Bakeathon<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|}<br />
<br />
== Specific architectural/platform interoperability issues ==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|II.B.1<br />
|Interoperability between 32-bit and 64-bit for client and server Testing on two platforms will be sufficient<br><br />
Linux IA-32 client – AIX PPC server Open Bull<br><br />
Linux IA-32 client – Linux PPC server Open Bull<br><br />
Linux IA-32 client – Linux AMD server Optional<br><br />
Linux IA-32 client – Linux IA-64 server Optional<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.B.2<br />
|Interoperability between little endian and big endian Open Bull Bull plans to do Linux/AIX 5.3 in 2005<br />
|r><br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|}<br />
<br />
== Client Interoperability with target architectures/platforms ==<br />
<br />
Need to define how to do interoperability testing – need more than just connectathon<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|II.C.1<br />
|Interoperability for Linux IA-32 client – Solaris 10 server Open Bull<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.C.2<br />
|Interoperability for Linux IA-32 client – NetApp Filer server New<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.C.3<br />
|Interoperability for Linux IA-32 client – EMC Filer server New<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.C.4<br />
|Interoperability for Linux IA-32 client – AIX 5.3 server Open Bull<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.C.5<br />
|Interoperability for Linux IA-32 client – AMD server New<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.C.6<br />
|Interoperability for Linux IA-32 client – PolyServe clustered products New<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.C.7<br />
|Interoperability for Linux IA-32 client – Hummingbird server New<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.C.9<br />
|Interoperability for Linux IA-32 client – HP server New<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.C.10<br />
|Interoperability for Linux IA-32 client – SGI server New<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.C.11<br />
|Interoperability for Linux IA-32 client – Spinniker server New<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|}<br />
<br />
== Server Interoperability with target architectures/platforms ==<br />
<br />
Need to define how to do interoperability testing – need more than just connectathon<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|II.D.1<br />
|Interoperability for Solaris 10 client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.D.2<br />
|Interoperability for NetApp client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.D.3<br />
|Interoperability for EMC client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.D.4<br />
|Interoperability for AIX 5.3 client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.D.5<br />
|Interoperability for AMD client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.D.6<br />
|Interoperability for Polyserve client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.D.7<br />
|Interoperability for Hummingbird client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.D.8<br />
|Interoperability for HP client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.D.9<br />
|Interoperability for SGI client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.D.10<br />
|Interoperability for Spinniker client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|}<br />
<br />
== File systems ==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|II.E.1<br />
|Verify features of cachefs for NFSv4<br />
|<br />
|'''New'''<br />
|<br />
|Not currently NFSv4 ready; needs additional development<br />
|-<br />
|II.E.2<br />
|Verify features of the Ext3 file system work under NFSv4<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.E.3<br />
|Verify features of the XFS file system work under NFSv4<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.E.4<br />
|Verify features of the Reiser file system work under NFSv4<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.E.5<br />
|Verify features of the GFS file system work under NFSv4<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.E.6<br />
|Verify features of cluster file systems (e.g. GFS) work under NFSv4<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.E.7<br />
|Verify features of the Luster file system work under NFSv4<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.E.8<br />
|Verify features of the GPFS file system work under NFSv4<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.E.9<br />
|Verify features of the Sanfs file system work under NFSv4<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.E.10<br />
|Verify features of the Polyserve file system work under NFSv4<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.E.11<br />
|Verify features of the Netcache file system work under NFSv4<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.E.12<br />
|Verify features of the Rainfinity file system work under NFSv4<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.E.13<br />
|Analyze file system configuration issues, such as:<br><br />
Logical volume manager behind server<br><br />
RAID-5 problem with small write workloads (may be performance issue?)<br><br />
Compiling POSIX ACL's in and out<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|}<br />
<br />
== Test ACL interoperability of Linux client for non-Linux servers ==<br />
See I.R.3; need test<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|II.F.1<br />
|ACL compatibility for Linux IA-32 client - Solaris 10 client<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.F.2<br />
|ACL compatibility for Linux IA-32 client - NetApp server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.F.3<br />
|ACL compatibility for Linux IA-32 client - EMC server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.F.4<br />
|ACL compatibility for Linux IA-32 client - AIX 5.3 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.F.5<br />
|ACL compatibility for Linux IA-32 client – AMD server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.F.6<br />
|ACL compatibility for Linux IA-32 client - Polyserve server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.F.7<br />
|ACL compatibility for Linux IA-32 client – Hummingbird server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.F.8<br />
|ACL compatibility for Linux IA-32 client – HP server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.F.9<br />
|ACL compatibility for Linux IA-32 client – SGI server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.F.10<br />
|ACL compatibility for Linux IA-32 client – Spinniker server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|}<br />
<br />
== Test ACL interoperability of Linux server with non-Linux clients ==<br />
See I.R.3; need test<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|II.G.1<br />
|ACL compatibility for Solaris 10 client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.G.2<br />
|ACL compatibility for NetApp client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.G.3<br />
|ACL compatibility for EMC client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.G.4<br />
|ACL compatibility for AIX 5.3 client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.G.5<br />
|ACL compatibility for AMD client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.G.6<br />
|ACL compatibility for Polyserve client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.G.7<br />
|ACL compatibility for Hummingbird client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.G.8<br />
|ACL compatibility for HP client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.G.9<br />
|ACL compatibility for SGI client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|II.G.10<br />
|ACL compatibility for Spinniker client – Linux IA-32 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|}<br />
<br />
== Automounter interoperability ==<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|II.H.1<br />
|Verify amd will work as a drop-in automounter service with nfsv4<br />
|<br />
|'''Open'''<br />
|IBM<br />
|<br />
|-<br />
|II.H.2<br />
|Verify autong will work as a drop-in automounter service with nfsv4<br />
|<br />
|'''Open'''<br />
|IBM<br />
|<br />
|-<br />
|II.H.3<br />
|Verify autofs4 will work as a drop-in automounter service with nfsv4<br />
|<br />
|'''Open'''<br />
|IBM<br />
|<br />
|-<br />
|II.H.4<br />
|Verify interoperability of nfsv4 and automounter with various map sources:<br><br />
- Flat file Connectathon<br><br />
- Program file Connectathon<br><br />
- NIS Connectathon<br><br />
- NIS+<br><br />
- LDAP using NIS style maps (RFC2307)<br><br />
- LDAP using Linux style automounter maps<br><br />
- LDAP using Yet-Another schema (RFC2307bis, deleted, but used by solaris 9 last I checked)<br />
|<br />
|'''Open'''<br />
|IBM<br />
|<br />
|-<br />
|}</div>
65.172.181.6
https://wiki.linux-nfs.org/wiki/index.php/Comparison_of_NFS_vs._others
Comparison of NFS vs. others
2005-07-29T20:55:59Z
<p>65.172.181.6: </p>
<hr />
<div>Here is a description comparing NFS and other similar technologies, found at this page:<br />
[http://forums.designtechnica.com/archive/index.php/t-5132.html]<br />
<br />
<pre><br />
CIFS:<br />
Strengths:<br />
a) Huge installed client base (not just Windows),<br />
b) good, open source server implementation available (Samba!),<br />
c) token management (oplock) and referral ("dfs") semantics are a good<br />
compromise between usefulness and simplicity<br />
d) the key part of the filesystem protocol (mostly) documented,<br />
rich file open semantics map well to Windows and related OSs,<br />
e) kerberos security integration and RPC integration<br />
f) broader in scope (print, ACL, browsing etc.) than other filesystem<br />
protocols<br />
g) optional PDU signing above the RPC allowing maximal flexibility<br />
h) Unicode<br />
i) high performance<br />
j) huge amount of loosely related management/administrative function<br />
available via various DCE RPC calls<br />
k) efficient PDUs (small frame headers, less wasted bandwidth)<br />
<br />
Weaknesses:<br />
a) the extended protocol poorly documented,<br />
b) not an IETF standard<br />
c) elements of older protocol dialects still needed adding to<br />
complexity of implementations<br />
d) protocol needs addition of lock migration/recovery and support for<br />
new transport mechanisms (e.g. RDMA)<br />
e) ACL support - although useful is hard to understand<br />
f) (item j above) management/admistrative calls are proprietary<br />
<br />
NFSv3:<br />
Strengths:<br />
a) relatively simple to implement<br />
b) maps well to Unix VFS semantics (except for caching)<br />
c) protocol easy to understand by stripping file protocol to its<br />
minimum<br />
d) Unicode<br />
<br />
Weaknesses:<br />
a) statelessness of core protocol causes caching problems<br />
b) few Windows NFS clients installed<br />
c) maps poorly to Windows operating system API<br />
d) poor security (forcing it into lower layers if at all)<br />
e) not a standard (informational description published by Sun as<br />
informational RFC)<br />
f) relatively weak open source server implementation (at least<br />
compared to Samba and AFS) has scalability problems<br />
g) implementing many protocols needed to get CIFS equivalent e.g. lock<br />
manager, mount and port mapping protocol, SunRPC, NIS, ONC extensions (some<br />
proprietary)<br />
h) WebNFS enhancements partially implemented adding to some confusion<br />
<br />
<br />
NFSv4:<br />
Strengths:<br />
a) on track to be an IETF standard<br />
b) improved recovery (lock migration)<br />
c) supports Windows file sharing semantics better than NFS v3 did<br />
d) safe file caching<br />
<br />
Weaknesses:<br />
a) few clients<br />
b) perceived lack of Microsoft interest<br />
c) the existing prototype open source implementation is tricky to<br />
integrate into current Linux kernels<br />
d) protocol is moving target (it is not quite done yet)<br />
e) too late?<br />
f) complex<br />
<br />
DAFS:<br />
Strengths:<br />
a) Addition of RDMA to NFS style protocol, (probable) high performance<br />
in clusters and server farms.<br />
b) (see NFS v4)<br />
<br />
Weaknesses:<br />
a) unproven, lack of client support, perceived competition with NFS v4<br />
b) (see NFS v4)<br />
<br />
HTTP/WebDAV<br />
Strengths:<br />
a) official standard<br />
b) broadly implemented<br />
c) well suited to internet<br />
d) active standardization work - protocol will improve<br />
<br />
Weaknesses:<br />
a) frame headers are large (high % of frame size is wasted)<br />
b) security integration not optimal<br />
c) slow<br />
d) not a complete match to either Linux VFS or Win2K IFS API<br />
requirements<br />
<br />
NCP(Netware):<br />
Strengths:<br />
a) NDS integration<br />
b) good match for Windows<br />
c) good installed base on older systems<br />
<br />
Weaknesses:<br />
a) Proprietary<br />
b) poorly documented<br />
c) not a standard<br />
d) complex, with lots of dialects<br />
e) future clients questionable<br />
<br />
<br />
AFS/DFS:<br />
Strengths:<br />
a) sophisticated distributed caching (token management)<br />
b) DCE integration (including Kerberos and RPC)<br />
c) standardized by OpenGroup<br />
<br />
Weakness:<br />
a) lack of clients<br />
b) bulky, slow Windows clients<br />
c) server integration with Unix operating systems and server<br />
filesystem is complicated<br />
d) most implementations were expensive<br />
e) complex to implement<br />
<br />
<br />
Coda:<br />
Strengths:<br />
a) disconnected support<br />
<br />
Weaknesses:<br />
a) Lack of commercial implementations<br />
b) lack of Windows clients<br />
c) not well understood<br />
<br />
</pre></div>
65.172.181.6
https://wiki.linux-nfs.org/wiki/index.php/Main_Page
Main Page
2005-07-29T20:55:05Z
<p>65.172.181.6: </p>
<hr />
<div>NFS is a critical service in many organizations, and even a simple<br />
error can lead to major problems. NFSv4 promises to bring several key<br />
new features, but clearly it will be imperative to users that the new<br />
version of NFS be robust, that it perform well, and that it interoperate<br />
easily with other technologies.<br />
<br />
{|{|cellpadding="5" cellspacing="3" class="mainpagetable" width="100%"<br />
|-<br />
|valign="top" style="padding: .5em 1em 1em; color: #000000; background-color: #d7e4f4; width: 33%"|<br />
'''General'''<br />
* [[NFSv4_Introduction|End user documentation]]<br />
* [[Comparison of NFS vs. others]]<br />
* [[Design|Design documentation]]<br />
* Active Directory<br />
** [[http://nfsworld.blogspot.com/2005/06/using-active-directory-as-your-kdc-for.html Linux, AD, and NetApp filers]]<br />
* [[How to get involved]]<br />
|valign="top"|<br />
'''Troubleshooting'''<br />
* [[General troubleshooting recommendations]]<br />
* Common error messages<br />
* Tools for troubleshooting<br />
* Problems exporting<br />
* Problems mounting<br />
* Problems automounting<br />
* Problems with Kerberos Authentication<br />
* [[Reporting bugs]]<br />
|valign="top" style="padding: .5em 1em 1em; color: #000000; background-color: #d7e4f4; width:33%"|<br />
'''Testing'''<br />
* [[Testing tools]]<br />
* [[Functional testing]]<br />
* [[Interoperability testing]]<br />
* [[Performance testing]]<br />
* [[Robustness testing]]<br />
* [[Security testing]]<br />
* [[Tests needed]]<br />
* [[Testing methodologies]]<br />
* [[Test_matrix|test matrix]]<br />
* [[Testing forecast roadmap]]<br />
|}<br />
<br />
<br />
==Testing ==<br />
<br />
The Linux NFSv4 Testing effort seeks to ensure that the Linux<br />
implementation of NFSv4 succeeds on all these counts. The purpose of<br />
the testing is threefold:<br />
<br />
* To prove that the features are implemented correctly according to spec.<br />
* To locate and identify bugs, and verify the fixes. <br />
* To give confidence to users that upgrading to NFSv4 on Linux is of benefit.</div>
65.172.181.6
https://wiki.linux-nfs.org/wiki/index.php/Main_Page
Main Page
2005-07-29T20:54:50Z
<p>65.172.181.6: </p>
<hr />
<div>NFS is a critical service in many organizations, and even a simple<br />
error can lead to major problems. NFSv4 promises to bring several key<br />
new features, but clearly it will be imperative to users that the new<br />
version of NFS be robust, that it perform well, and that it interoperate<br />
easily with other technologies.<br />
<br />
{|{|cellpadding="5" cellspacing="3" class="mainpagetable" width="100%"<br />
|-<br />
|valign="top" style="padding: .5em 1em 1em; color: #000000; background-color: #d7e4f4; width: 33%"|<br />
'''General'''<br />
* [[NFSv4_Introduction|End user documentation]]<br />
* [[Comparison of NFS vs. other file sharing systems]]<br />
* [[Design|Design documentation]]<br />
* Active Directory<br />
** [[http://nfsworld.blogspot.com/2005/06/using-active-directory-as-your-kdc-for.html Linux, AD, and NetApp filers]]<br />
* [[How to get involved]]<br />
|valign="top"|<br />
'''Troubleshooting'''<br />
* [[General troubleshooting recommendations]]<br />
* Common error messages<br />
* Tools for troubleshooting<br />
* Problems exporting<br />
* Problems mounting<br />
* Problems automounting<br />
* Problems with Kerberos Authentication<br />
* [[Reporting bugs]]<br />
|valign="top" style="padding: .5em 1em 1em; color: #000000; background-color: #d7e4f4; width:33%"|<br />
'''Testing'''<br />
* [[Testing tools]]<br />
* [[Functional testing]]<br />
* [[Interoperability testing]]<br />
* [[Performance testing]]<br />
* [[Robustness testing]]<br />
* [[Security testing]]<br />
* [[Tests needed]]<br />
* [[Testing methodologies]]<br />
* [[Test_matrix|test matrix]]<br />
* [[Testing forecast roadmap]]<br />
|}<br />
<br />
<br />
==Testing ==<br />
<br />
The Linux NFSv4 Testing effort seeks to ensure that the Linux<br />
implementation of NFSv4 succeeds on all these counts. The purpose of<br />
the testing is threefold:<br />
<br />
* To prove that the features are implemented correctly according to spec.<br />
* To locate and identify bugs, and verify the fixes. <br />
* To give confidence to users that upgrading to NFSv4 on Linux is of benefit.</div>
65.172.181.6
https://wiki.linux-nfs.org/wiki/index.php/Testing_forecast_roadmap
Testing forecast roadmap
2005-07-29T00:17:38Z
<p>65.172.181.6: /* Milestone 0: Developer Testing Support */</p>
<hr />
<div>Linux NFSv4 Testing Roadmap<br />
---------------------------<br />
<br />
As of May 2005, we've completed a detailed itemization of testing work<br />
necessary for NFSv4, in a spreadsheet "Test Matrix", identifying items<br />
as High, Medium, and Low.<br />
<br />
This document seeks to divide the high priority work into achievable<br />
chunks that we as a community can strive to attain.<br />
<br />
I tried to prioritize for things that look reasonably easy to complete<br />
in the near term, that have owners, and/or are most likely to reveal<br />
issues that developers want to know about.<br />
<br />
<br />
==Milestone 0: Developer Testing Support==<br />
<br />
These testing tasks seek to put into place tools and practices that will<br />
help support development activities (including testing) on an ongoing<br />
basis.<br />
<br />
Functionality:<br />
I.B.1 [X] [OSDL] Automate running applicable existing functionality<br />
tests on codebase periodically: cthon, pynfs,<br />
iozone<br />
I.B.3 [X] [OSDL] Automate cross-compile testing for major platforms<br />
on each NFSv4 patchset<br />
I.C.2 [ ] [ ] Test install on Fedora Core of NFSv4 server &<br />
client, krb5, ldap, et al<br />
I.E.9 [ ] [ ] Verify ability to force operations (close files,<br />
change states, unmount)<br />
I.G.5 [ ] [Bull] Test compilation and functionality on IA-64<br />
I.G.7 [ ] [Bull] Test compilation and functionality on PPC-64<br />
I.K.2 [ ] [ ] Check that NFS HOWTO is updated with sufficient<br />
nfsv4 info<br />
<br />
Interop:<br />
II.A.1 [ ] [Bull] Kerberos (MIT) - verify basic functionality. Mount<br />
w/ krb5, etc.<br />
<br />
Robustness:<br />
III.A.3 [ ] [OSDL] Run NFS server for 2 wks with random configuration<br />
changes<br />
III.C.1 [ ] [Bull] Run LTP NFS fstress in a std config on each release<br />
<br />
Performance:<br />
IV.A.1 [ ] [Bull] Time to perform sequence of unique read/write<br />
operations<br />
IV.A.2 [ ] [Bull] Time to perform sequence of cacheable read/write<br />
operations<br />
IV.F.4 [ ] [ ] Measure memory/network/CPU efficiency of client for<br />
fixed workload<br />
IV.G.3 [ ] [Bull] Measure effects of scaling up number of<br />
connections. Measure number of mounts per second<br />
on client and server.<br />
IV.J.2 [ ] [Bull] Measure performance when operating with Kerberos 5<br />
integrity and privacy<br />
<br />
Security:<br />
V.A.6 [ ] [ ] Audit the mountd code<br />
V.B.4 [ ] [OSDL] Run sparse as regression test periodically<br />
V.L.1 [ ] [ ] Ensure there is high level design documentation of<br />
NFSv4 security<br />
V.L.2 [ ] [ ] Ensure there is inline documentation for security<br />
related code in kernel<br />
V.L.3 [ ] [ ] Ensure there is inline documentation for GSS API<br />
(libgssapi, librpcsecgss)<br />
<br />
Misc:<br />
* [X] [OSDL] Establish bug tracking process for NFSv4<br />
<br />
==Milestone 1: Distro Quality Assurance==<br />
<br />
This milestone strives to attain a "Top Ten" list of testing that is<br />
felt will emphasize that NFSv4 is stable enough to be included in all<br />
enterprise distros. The focus is robustness, and items that would cause<br />
distros the most headaches if they're busted.<br />
<br />
I.A.5 [ ] [ ] Protocol implementation interoperability between<br />
Linux server and client<br />
I.C.5 [ ] [ ] Test install on SLES of NFSv4 server & client,<br />
krb5, ldap, et al<br />
I.C.6 [ ] [ ] Test install on RHEL of NFSv4 server & client,<br />
krb5, ldap, et al<br />
I.H.1 [ ] [ ] Verify compatibility with glibc<br />
I.H.9 [ ] [ IBM] Verify compatibility with automounter<br />
I.H.11 [ ] [ ] Verify compatibility with basic system tools<br />
(file utils, core utils, util-linux, mount, sar,<br />
iostat, etc.)<br />
I.K.4 [ ] [ ] Check that Network Admin Guide at tldp.org is<br />
updated for nfsv4<br />
II.E.2 [ ] [ ] Verify features of the Ext3 file system work under<br />
NFSv4<br />
III.A.1 [ ] [ ] Run iozone for 2 wks on basic client/server<br />
operations<br />
III.A.2 [ ] [ ] Run automounter use case for 2 wks on amd, autofs,<br />
and autong<br />
III.A.4 [ ] [ ] Run connectathon locking tests against NFS server<br />
for 2 weeks<br />
III.E.1 [ ] [OSDL] Test short & long term local network failure<br />
(unplugged cable, ifdown eth0, etc.)<br />
III.E.2 [ ] [OSDL] Test short & long duration remote network partition<br />
III.E.3 [ ] [OSDL] Test behavior during crash/reboot of server with<br />
clients holding various states<br />
V.D.1 [ ] [ ] Review Authentication/ACL feature design<br />
V.E.1 [ ] [ ] Ensure a functionality test sufficiently tests<br />
Authentication/ACL<br />
<br />
<br />
==Milestone 2: Drill Down for One Use Case==<br />
<br />
This milestone strives to push NFSv4 through one complete use case, to<br />
give it some thorough exercise and scaling, and to establish a "case<br />
study" we can use as an example of NFSv4's value.<br />
<br />
I.E.5 [ ] [ ] Verify sufficient monitoring functionality within<br />
Ethereal<br />
I.F.1 [ ] [ ] Client notification to server of locking, write,<br />
read, etc.<br />
I.P.1 [ ] [OSDL] Database functionality on NFS<br />
I.L.1 [ ] [ ] Test compatibility with TCP protocol<br />
IV.A.7 [ ] [ ] NFSv3 vs. v4: Metadata - open/close intensive<br />
workload<br />
IV.A.8 [ ] [ ] NFSv3 vs. v4: Metadata - directory scanning<br />
IV.A.9 [ ] [ ] NFSv3 vs. v4: Metadata - create/delete<br />
IV.A.10 [ ] [ ] NFSv3 vs. v4: Metadata - changing attributes<br />
(chown, chmod) while dir scanning<br />
IV.E.1 [ ] [Bull] Test performance with large numbers of small (<4k)<br />
files<br />
IV.E.2 [ ] [ ] Test performance with a few very large (>1G) files<br />
IV.F.4 [ ] [Bull] Measure memory/network/CPU efficiency of client<br />
for fixed workload<br />
IV.G.1 [ ] [ ] Verify server scalability with clients generating<br />
various basic requests (ACCESS, GETATTR, et al)<br />
IV.G.2 [ ] [ ] Verify server scalability with clients using<br />
compound requests<br />
V.D.6 [ ] [ ] Penetration testing for client callback<br />
implementation<br />
V.E.6 [ ] [ ] Ensure a functionality test sufficiently covers<br />
penetration testing for client callback<br />
implementation<br />
<br />
==Milestone 3: Enterprise Usability==<br />
<br />
This milestone focuses on testing that verifies "basic" usability of<br />
NFSv4 in data centers. It strives to establish that NFSv4 is able to<br />
perform basic functions in enterprise-class deployments.<br />
<br />
I.F.2 [ ] [ ] Reboot recovery<br />
I.F.4 [ ] [ ] Open with shares / deny<br />
I.F.5 [ ] [ ] Bumping a sequence ID<br />
I.F.6 [ ] [ ] Network partition recovery<br />
I.F.8 [ ] [ ] Locking (Non-blocking locks)<br />
I.H.3 [ ] [ ] Verify compatibility with Kerberos<br />
I.H.4 [ ] [ ] Verify compatibility with Ipsec<br />
I.H.5 [ ] [ ] Verify compatibility with POSIX ACLs<br />
I.H.6 [ ] [ ] Verify compatibility with NFS ACLs<br />
II.B.1 [ ] [Bull] Interoperability between 32-bit and 64-bit for<br />
client and server: IA32/AIX-PPC, IA32/Linux-PPC<br />
II.B.2 [ ] [Bull] Interoperability between little endian and big<br />
endian<br />
II.C.1 [ ] [Bull] Interoperability for Linux IA-32 client ? Solaris<br />
10 server<br />
II.C.4 [ ] [Bull] Interoperability for Linux IA-32 client ? AIX 5.3<br />
server<br />
III.D.7 [ ] [ ] Test correctness of NFS client when backed by a<br />
large (>100GB) cachefs<br />
IV.E.5 [ ] [ ] NFS "Cluster" scenario with 1000+ clients and<br />
several servers<br />
V.A.7 [ ] [ ] Audit the RPC authentication code (gssd, authsys,<br />
etc.)<br />
V.D.2 [ ] [ ] Review each security flavor feature design:<br />
Krb5, Spkm<br />
V.E.2 [ ] [ ] Ensure a functionality test sufficiently covers<br />
each security flavor<br />
<br />
<br />
==Milestone 4: Enterprise Readiness==<br />
<br />
This milestone builds on the previous one by ensuring that NFSv4 will<br />
behave well and perform robustly under typical enterprise-class loads.<br />
<br />
III.B.2 [ ] [ ] Test stability of client in out of memory<br />
situation<br />
III.B.3 [ ] [ ] Test stability of client in out of disk space on<br />
server situation<br />
III.B.4 [ ] [ ] Test stability of client in out of inode situation<br />
III.B.5 [ ] [ ] Test stability of client in out of swap space<br />
situation<br />
III.B.6 [ ] [ ] Test stability of server in out of pid situation<br />
III.B.7 [ ] [ ] Test stability of server in out of memory<br />
situation<br />
III.B.8 [ ] [ ] Test stability of server in out of disk space<br />
situation<br />
III.B.9 [ ] [ ] Test stability of server in out of inode situation<br />
III.B.10 [ ] [ ] Test stability of server in out of swap space<br />
situation<br />
III.D.1 [ ] [ ] Find maximum number of connections to Linux IA-32<br />
server<br />
III.D.4 [ ] [ ] Find maximum number of mounted file systems on<br />
client<br />
III.E.4 [ ] [ ] Test multiple clients using, locking, etc. same<br />
files<br />
III.E.5 [ ] [ ] Test behavior of server with failed storage device<br />
III.E.6 [ ] [ ] Test behavior during crash of client with open<br />
delegations and locks<br />
III.E.7 [ ] [ ] Test recovery from denied permission<br />
III.E.8 [ ] [ ] Test recovery from JUKEBOX/DELAY<br />
III.E.9 [ ] [ ] Test recovery from ESTALE<br />
III.E.10 [ ] [ ] Test server callback mechanism (c.f. III.E.1,<br />
III.E.2)<br />
III.G.2 [ ] [ ] Test concurrent access tests for races in<br />
automounter<br />
IV.G.4 [ ] [ ] Measure effects of increasing number of files<br />
IV.G.5 [ ] [ ] Measure effects of increasing file size<br />
(with/without cache)<br />
IV.G.6 [ ] [ ] Measure effects when increasing size of<br />
on-the-wire NFS read or write operations<br />
V.J.1 [ ] [ ] Identify security issues assuming attack from<br />
client-side</div>
65.172.181.6
https://wiki.linux-nfs.org/wiki/index.php/Tests_needed
Tests needed
2005-07-16T00:00:20Z
<p>65.172.181.6: </p>
<hr />
<div>== NFS Parameter Tuning ==<br />
<br />
Create a test script that iterate through various NFS parameters and run test suites on them.<br />
<br />
In /etc/fstab, try various values for each of the following parameters, for both NFSv3 and NFSv4:<br />
<br />
default advanced test<br />
rsize=n 1024 performance at 512, 1024, 2048, 4091, 8192, 16384, 32768<br />
wsize=n 1024 performance at 512, 1024, 2048, 4091, 8192, 16384, 32768<br />
timeo=n 7 in busy network, performance at 3, 7, 15, 30, 60<br />
retrans=n 3 in faulty network, robustness at 1, 2, 3, 6, 12, 24<br />
acregmin=n 3 on highly loaded server, overall performance at 1, 2, 3, 6, 12, 24<br />
acregmax=n 60 on highly loaded server, robustness and overall performance at 15, 30, 60, 120, 240<br />
acdirmin=n 30 on highly loaded server, overall performance at 5, 10, 15, 30, 60, 120, 240<br />
acdirmax=n 60 on highly loaded server, robustness and overall performance at 15, 30, 60, 120, 240<br />
actimeo=n - ??<br />
retry=n 10000 try with value of 1 to verify it still works correctly<br />
namlen=n 255 ?? not sure if this is worth testing<br />
port=n 2049 set server to use port 10000, and verify this options works<br />
mountport=n set mountd to use port 10001, and verify this option works<br />
mounthost=name ??<br />
mountprog=n 100005 ??<br />
mountvers=n 1 ??<br />
nfsprog=n 100003 ??<br />
nfsvers=n 2 try with 3 and 4, and verify the right version gets used<br />
nolock off ??<br />
bg off switch this on, and verify mounts occur properly in background<br />
fg on <br />
soft off switch this on, and verify an I/O error is generated when mounting a nonexistant server<br />
hard on <br />
intr off test how this affects operation when major timeouts occur with hard mounts<br />
posix off turn on and test with filenames > 255 chars<br />
nocto off test how this works when <br />
noac off test performance with 1-N clients writing to the same filesystem on the server<br />
tcp off verify this option is ignored in nfsv4<br />
udp on verify this option is ignored in nfsv4<br />
<br />
<br />
== Mount Parameter Testing ==<br />
<br />
* Measure total time when using mount -F vs mount for a lot of mount points<br />
<br />
* Verify that mount -vf does not actually mount the filesystem but just pretends to<br />
<br />
* Make /etc read only, and verify that mount -n allows mounting without writing in /etc/mtab<br />
<br />
* Verify that the -s option allows invalid -o options to be specified to mount, and be ignored properly<br />
<br />
* Verify that mount -r mounts read only<br />
<br />
* Verify that mount -a -O no_nfs4 mounts everything but the nfs4 mounts<br />
<br />
* Verify that mount --bind works to remount a subtree somewhere else<br />
<br />
* Verify that mount --move works to move a subtree someplace else<br />
<br />
* Verify that mount exits with the proper codes on error:<br />
<br />
0 success<br />
1 incorrect invocation or permissions<br />
2 system error (out of memory, cannot fork, no more loop devices)<br />
4 internal mount bug or missing nfs support in mount<br />
8 user interrupt<br />
16 problems writing or locking /etc/mtab<br />
32 mount failure<br />
64 some mount succeeded<br />
<br />
== Umount Parameter Testing ==<br />
<br />
* Verify umount -n does not write to /etc/mtab<br />
<br />
* Verify umount -r remounts read-only when unmounting fails<br />
<br />
* Verify the umount command notifies the server when an NFS filesystem is unmounted. (Bug in NFSv3)<br />
<br />
* Verify that umount -t nfs4 unmounts a mountpoint only if it is an nfs4 mountpoint<br />
<br />
* Verify that umount -t no_nfs4 does not unmount a mountpoint if it is an nfs4 mountpoint<br />
<br />
* Verify that umount -a -t nfs4 unmounts all nfs4 mounts<br />
<br />
* Verify that umount -a -t no_nfs4 unmounts everything except nfs4 mounts<br />
<br />
* Verify that umount -O works to only allow mount points with the given options are unmounted<br />
<br />
* Verify that umount -f works to force unmount of unreachable NFS systems<br />
<br />
* Verify that umount -l detaches the filesystem from the filesystem hierarchy immediately, and cleans up references to the filesystem as the processes using them complete</div>
65.172.181.6
https://wiki.linux-nfs.org/wiki/index.php/Main_Page
Main Page
2005-07-15T22:05:37Z
<p>65.172.181.6: </p>
<hr />
<div>NFS is a critical service in many organizations, and even a simple<br />
error can lead to major problems. NFSv4 promises to bring several key<br />
new features, but clearly it will be imperative to users that the new<br />
version of NFS be robust, that it perform well, and that it interoperate<br />
easily with other technologies.<br />
<br />
{|{|cellpadding="5" cellspacing="3" class="mainpagetable" width="100%"<br />
|-<br />
|valign="top" style="padding: .5em 1em 1em; color: #000000; background-color: #d7e4f4; width: 33%"|<br />
'''General'''<br />
* [[NFSv4_Introduction|End user documentation]]<br />
* [[Design|Design documentation]]<br />
* Active Directory<br />
** [[http://nfsworld.blogspot.com/2005/06/using-active-directory-as-your-kdc-for.html Linux, AD, and NetApp filers]]<br />
* [[How to get involved]]<br />
|valign="top"|<br />
'''Troubleshooting'''<br />
* [[General troubleshooting recommendations]]<br />
* Common error messages<br />
* Tools for troubleshooting<br />
* Problems exporting<br />
* Problems mounting<br />
* Problems automounting<br />
* Problems with Kerberos Authentication<br />
* [[Reporting bugs]]<br />
|valign="top" style="padding: .5em 1em 1em; color: #000000; background-color: #d7e4f4; width:33%"|<br />
'''Testing'''<br />
* [[Testing tools]]<br />
* [[Functional testing]]<br />
* [[Interoperability testing]]<br />
* [[Performance testing]]<br />
* [[Robustness testing]]<br />
* [[Security testing]]<br />
* [[Tests needed]]<br />
* [[Testing methodologies]]<br />
* [[Test_matrix|test matrix]]<br />
* [[Testing forecast roadmap]]<br />
|}<br />
<br />
<br />
==Testing ==<br />
<br />
The Linux NFSv4 Testing effort seeks to ensure that the Linux<br />
implementation of NFSv4 succeeds on all these counts. The purpose of<br />
the testing is threefold:<br />
<br />
* To prove that the features are implemented correctly according to spec.<br />
* To locate and identify bugs, and verify the fixes. <br />
* To give confidence to users that upgrading to NFSv4 on Linux is of benefit.</div>
65.172.181.6
https://wiki.linux-nfs.org/wiki/index.php/Test_matrix
Test matrix
2005-07-09T00:25:17Z
<p>65.172.181.6: /* Functional Testing */</p>
<hr />
<div>This pages summarizes testing efforts for NFSv4, and identify testing gaps. Email nfsv4@linux-nfs.org with feedback or to take ownership of a task. If you are doing NFSv4 testing, please let us know!<br />
<br />
==[[Matrix_functional_section|Functional Testing]]==<br />
Ability to do what it's supposed to do. Standards compliance, regression, compatibility, static code analysis, etc.<br />
{|border="1" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|<br />
!style="background: #ececec;"|'''New'''<br />
!style="background: #ececec;"|'''Open'''<br />
!style="background: #ececec;"|'''In progress'''<br />
!style="background: #ececec;"|'''Near Done'''<br />
!style="background: #ececec;"|'''Done'''<br />
!style="background: #ececec;"|'''High'''<br />
!style="background: #ececec;"|'''Medium'''<br />
!style="background: #ececec;"|'''Low'''<br />
|-<br />
|current status<br />
|99<br />
|31<br />
|1<br />
|1<br />
|4<br />
|43<br />
|72<br />
|22<br />
|}<br />
<br />
==[[Matrix_interop_section|Interoperability Testing]]==<br />
<br />
Ability to work with other versions of NFS, other operating systems and other software/filesystems/etc. generally associated with NFS<br />
<br />
{|border="1" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|<br />
!style="background: #ececec;"|'''New'''<br />
!style="background: #ececec;"|'''Open'''<br />
!style="background: #ececec;"|'''In progress'''<br />
!style="background: #ececec;"|'''Near Done'''<br />
!style="background: #ececec;"|'''Done'''<br />
!style="background: #ececec;"|'''High'''<br />
!style="background: #ececec;"|'''Medium'''<br />
!style="background: #ececec;"|'''Low'''<br />
|-<br />
|current status<br />
|55<br />
|12<br />
|0<br />
|0<br />
|1<br />
|33<br />
|12<br />
|25<br />
|}<br />
<br />
<br />
==[[Matrix_robustness_section|Robustness Testing]]==<br />
<br />
Remains stable and recovers even in extreme situations, Stability, interoperability, error recovery, race conditions, etc<br />
<br />
{|border="1" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|<br />
!style="background: #ececec;"|'''New'''<br />
!style="background: #ececec;"|'''Open'''<br />
!style="background: #ececec;"|'''In progress'''<br />
!style="background: #ececec;"|'''Near Done'''<br />
!style="background: #ececec;"|'''Done'''<br />
!style="background: #ececec;"|'''High'''<br />
!style="background: #ececec;"|'''Medium'''<br />
!style="background: #ececec;"|'''Low'''<br />
|-<br />
|current status<br />
|29 <!-- It was 37 --><br />
|6<br />
|1 <br />
|2 <!-- add maximum files exported / mounted --><br />
|6 <!-- tests ffsb/fsstress and IOZone running long periods (1 week) + disk limits on server/client maximum file size (=local fs)--><br />
|32<br />
|8<br />
|2<br />
|}<br />
<br />
==[[Matrix_performance_section|Performance Testing]]==<br />
<br />
Able to perform well under real and theoretical workloads Load, stress, destruction, scalability, etc<br />
<br />
{|border="1" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|<br />
!style="background: #ececec;"|'''New'''<br />
!style="background: #ececec;"|'''Open'''<br />
!style="background: #ececec;"|'''In progress'''<br />
!style="background: #ececec;"|'''Near Done'''<br />
!style="background: #ececec;"|'''Done'''<br />
!style="background: #ececec;"|'''High'''<br />
!style="background: #ececec;"|'''Medium'''<br />
!style="background: #ececec;"|'''Low'''<br />
|-<br />
|current status<br />
|33<br />
|10<br />
|3<br />
|0<br />
|1<br />
|19<br />
|26<br />
|4<br />
|}<br />
<br />
==[[Matrix_security_section|Security Testing]]==<br />
<br />
Resistant to being compromised and difficult to attack<br />
<br />
{|border="1" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|<br />
!style="background: #ececec;"|'''New'''<br />
!style="background: #ececec;"|'''Open'''<br />
!style="background: #ececec;"|'''In progress'''<br />
!style="background: #ececec;"|'''Near Done'''<br />
!style="background: #ececec;"|'''Done'''<br />
!style="background: #ececec;"|'''High'''<br />
!style="background: #ececec;"|'''Medium'''<br />
!style="background: #ececec;"|'''Low'''<br />
|-<br />
|current status<br />
|28<br />
|4<br />
|0<br />
|0<br />
|1<br />
|14<br />
|9<br />
|9<br />
|}<br />
<br />
==Definitions==<br />
<br />
*'''New''' : An owner has not been identified for the item and work has not started on it<br />
*'''Open''': The task has been adopted, but either has not been started, or progress is not yet known<br />
*'''In Progress''' : Some work has been completed on the task<br />
*'''Near Done''': The principle essense of the task has been finished, but there are some loose ends left<br />
*'''Done''': The task has been fully completed</div>
65.172.181.6
https://wiki.linux-nfs.org/wiki/index.php/Matrix_functional_section
Matrix functional section
2005-07-09T00:24:44Z
<p>65.172.181.6: /* Installability */</p>
<hr />
<div>==Standards compliance/conformance verification (server)==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|I.A.1<br />
|Test POSIX conformance<br />
|POSIX testsuite<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.A.2<br />
|Test protocol compliance/conformance against NFSv2 spec<br />
|Connectathon<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.A.3<br />
|Test protocol compliance/conformance against NFSv3 spec<br />
|Connectathon<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.A.4<br />
|Test protocol compliance/conformance against NFSv4 spec (RFC 3530)<br />
|Pynfs, POSIX conformance suite, connectathon<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.A.5<br />
|Protocol implementation interoperability between Linux server and client<br />
|Connectathon<br />
|'''New'''<br />
|<br />
|<br />
|}<br />
<br />
<br />
==Regression testing==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|I.B.1<br />
|Run applicable existing functionality tests on codebase periodically<br />
|Connectathon, fsx, fsx-direct, OraSim, pynfs<br />
|'''Open'''<br />
|OSDL<br />
|<br />
|-<br />
|I.B.2<br />
|Review common faults reported with NFSv3 and check if they still exist<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.B.3<br />
|Cross-compile testing for variety of platforms on each NFSv4 patchset<br />
|<br />
|'''DONE'''<br />
|OSDL<br />
|<br />
|}<br />
<br />
==Installability==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|I.C.1<br />
|Test install on Debian unstable of NFSv4 server & client, krb5, ldap, et al<br />
|test<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.C.2<br />
|Test install on Fedora Core of NFSv4 server & client, krb5, ldap, et al<br />
|test<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.C.3<br />
|Test install on SuSE of NFSv4 server & client, krb5, ldap, et al<br />
|test<br />
|'''Open'''<br />
|Novell<br />
|alolla is coordinating testing with us<br />
|-<br />
|I.C.4<br />
|Test install on Gentoo of NFSv4 server & client, krb5, ldap, et al<br />
|test<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.C.5<br />
|Test install on SLES of NFSv4 server & client, krb5, ldap, et al<br />
|test<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.C.6<br />
|Test install on RHEL of NFSv4 server & client, krb5, ldap, et al<br />
|test<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.C.7<br />
|Test install on Ubuntu of NFSv4 server & client, krb5, ldap, et al<br />
|test<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.C.8<br />
|Test install on Mandrake of NFSv4 server & client, krb5, ldap, et al<br />
|test<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.C.9<br />
|Test install on Turbolinux of NFSv4 server & client, krb5, ldap, et al<br />
|test<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.C.10<br />
|Test installation of heimdal vs. MIT krb5 implementations<br />
|test<br />
|'''New'''<br />
|<br />
|<br />
|}<br />
<br />
==Integration testing==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|I.D.1<br />
|Verify functional requirements met for NFSv4 server / RPC<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.D.2<br />
|Verify functional requirements met for NFSv4 server / Transport Switch<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.D.3<br />
|Verify functional requirements met for NFSv4 server / GSS<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.D.4<br />
|Verify functional requirements met for NFSv4 server / GSS / Kerberos<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.D.5<br />
|Verify functional requirements met for NFSv4 server / GSS / SPKM<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.D.6<br />
|Verify functional requirements met for NFSv4 server / ACLs<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.D.7<br />
|Verify functional requirements met for NFSv4 client / NFSv4 server<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.D.8<br />
|Verify functional requirements met for NFSv4 client / GSS<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.D.9<br />
|Verify functional requirements met for NFSv4 client / GSS / Kerberos<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.D.10<br />
|Verify functional requirements met for NFSv4 client / GSS / SPKM<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.D.11<br />
|Verify functional requirements met for NFSv4 client / ACLs<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.D.12<br />
|Verify functional requirements met for NFSv4 client / mount<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.D.13<br />
|Verify functional requirements met for NFSv4 client / IDMAP<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|}<br />
<br />
==Serviceability==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|I.E.1<br />
|Verify NFSv4 administrative functionality within Webmin <br />
|<br />
|'''In Progress'''<br />
|Bull<br />
|Verification has been done by Bull in 2004. Code has been done and delivered. ACL to be studied. <br />
|-<br />
|I.E.2<br />
|Verify NFSv4 debugging functionality within nfsdebug, et al <br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.E.3<br />
|Verify NFSv4 monitoring functionality within nagios <br />
|<br />
|'''Open'''<br />
|Bull<br />
|Verification (and code) will be done by Bull in 2005<br />
|-<br />
|I.E.4<br />
|Verify informativeness of error/trace messages <br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.E.5<br />
|Verify sufficient monitoring functionality within Ethereal <br />
* Parse delegation callbacks (CB_NULL, CB_RECALL, CB_GETATTR)<br />
* Parse OPEN repy's with a granted READ or WRITE delegation<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.E.6<br />
|Verify ability to get detailed state info from service <br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.E.7<br />
|Verify ability to list who has open/locked files (ala lsof) <br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.E.8<br />
|Verify ability to list active mount points and who has them open <br />
|<br />
|'''New'''<br />
|<br />
|Showmount?<br />
|-<br />
|I.E.9<br />
|Verify ability to force operations (close files, change states, unmount) <br />
|<br />
|'''New'''<br />
|<br />
|e.g. Umount -f<br />
|-<br />
|I.E.10<br />
|Verify ability for global visualization of mounts/locks/traffic (like top/ntop) <br />
|<br />
|'''New'''<br />
|<br />
|An SNMP interface?<br />
|-<br />
|I.E.11<br />
|Verify ability to trace NFS activity (like strace) <br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.E.12<br />
|Verify ability to trace security rules (e.g., why did user X get auth'd) <br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.E.13<br />
|Verify admin access to session encryption key (so can e.g. decode protocol in Ethereal) <br />
|<br />
|'''New'''<br />
|<br />
|<br />
|}<br />
<br />
<br />
==State transitions==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|I.F.1<br />
|Client notification to server of locking, write, read, etc. <br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.F.2<br />
|Reboot recovery <br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.F.3<br />
|Delegation / delegation callbacks <br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.F.4<br />
|Open with shares / deny <br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.F.5<br />
|Bumping a sequence ID <br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.F.6<br />
|Network partition recovery <br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.F.7<br />
|Sharing file local accessors and remote accessors <br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.F.8<br />
|Locking <br />
* Blocking locks - fair queing<br />
* Non-blocking locks<br />
* Mandatory locks<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|}<br />
<br />
<br />
==Portability to target architectures/platforms==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|I.G.1<br />
|Test compilation and functionality on UP systems<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.G.2<br />
|Test compilation and functionality on SMP (2, 4, 8, 16, +) systems<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.G.3<br />
|Test compilation and functionality on cluster system(s)<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.G.4<br />
|Test compilation and functionality on IA-32 (2, 4, 8-way systems)<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.G.5<br />
|Test compilation and functionality on IA-64<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.G.6<br />
|Test compilation and functionality on PPC-64 with Linux in 32-bit mode<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.G.7<br />
|Test compilation and functionality on PPC-64<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.G.8<br />
|Test compilation and functionality on IA-32e, and if there are differences from IA-32<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.G.9<br />
|Test compilation and functionality on Sparc<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|}<br />
<br />
<br />
==Ecosystem compatibility==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|I.H.1<br />
|Verify compatibility with glibc<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.H.2<br />
|Verify compatibility with NLM/NSM and NFSv3 locking<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.H.3<br />
|Verify compatibility with Kerberos<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.H.4<br />
|Verify compatibility with Ipsec<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.H.5<br />
|Verify compatibility with POSIX ACLs<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.H.6<br />
|Verify compatibility with NFS ACLs<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.H.7<br />
|Verify compatibility with LDAP<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.H.8<br />
|Verify compatibility with NIS<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.H.9<br />
|Verify compatibility with automounter<br />
|<br />
|'''Open'''<br />
|IBM<br />
|<br />
|-<br />
|I.H.10<br />
|Verify compatibility with pNFS<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.H.11<br />
|Verify compatibility with basic system tools (file utils, core utils, util-linux, mount, sar, iostat, etc.)<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.H.12<br />
|Verify compatibility with Active Directory<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.H.13<br />
|Verify compatibility with Samba (CIFS Server)<br />
<br />
<br />
|}<br />
<br />
==Static code analysis==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|I.I.1<br />
|Syntax <br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.I.2<br />
|Unreachable code, unconditional branches into loops<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.I.3<br />
|Undeclared or uninitialized variables <br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.I.4<br />
|Parameter type mismatches <br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.I.5<br />
|Uncalled functions and procedures <br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.I.6<br />
|Non-usage of function results <br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.I.7<br />
|Possible array bound errors <br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.I.8<br />
|Misuse of pointers <br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.I.9<br />
|Sparse testing – random writes to a file as large as local file system<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|}<br />
<br />
==Localization/Internationalization testing==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|I.J.1<br />
|Verify multi-character filenames are supported<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|}<br />
<br />
==Documentation update verification==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|I.K.1<br />
|Check that web content at nfs.sf.net has updated nfsv4 info<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.K.2<br />
|Check that NFS HOWTO is updated with sufficient nfsv4 info<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.K.3<br />
|Check that all NFS man pages are updated with nfsv4 info<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.K.4<br />
|Check that Network Admin Guide at tldp.org is updated for nfsv4<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.K.5<br />
|Check that NFS docs for main distros are updated for nfsv4<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.K.6<br />
|Check that an NFSv4 Security Best Practices document available<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.K.7<br />
|Check the nfs performance section in howto<br />
|<br />
|'''Open'''<br />
|Chuck<br />
|<br />
|-<br />
|I.K.8<br />
|Make sure section RPCGSS, set up kerberos explanations, etc. exist<br />
|<br />
|'''New'''<br />
|<br />
|Is in FAQ but not HOWTO<br />
|-<br />
|I.K.9<br />
|List to check system for kerberos config's to make sure it's set up correctly<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.K.10<br />
|Interoperability considerations - known issues, things to test<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.K.11<br />
|Ensure there is inline documentation for all nfsv4 client code in kernel<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|-<br />
|I.K.12<br />
|Ensure there is inline documentation for all nfsv4 sever code in kernel<br />
|<br />
|'''New'''<br />
|<br />
|<br />
|}<br />
<br />
<br />
==Network transport protocols compatibility==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|I.L.1<br />
|title<br />
|test<br />
|'''New'''<br />
|<br />
|<br />
|}<br />
<br />
<br />
==Automounter functionality - amd==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|I.M.1<br />
|title<br />
|test<br />
|'''New'''<br />
|<br />
|<br />
|}<br />
<br />
<br />
==Automounter functionality - autofs4==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|I.N.1<br />
|title<br />
|test<br />
|'''New'''<br />
|<br />
|<br />
|}<br />
<br />
<br />
==Automounter functionality - autong==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|I.O.1<br />
|title<br />
|test<br />
|'''New'''<br />
|<br />
|<br />
|}<br />
<br />
<br />
==Use Case Scenarios==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|I.P.1<br />
|title<br />
|test<br />
|'''New'''<br />
|<br />
|<br />
|}<br />
<br />
<br />
==ID mapping==<br />
<br />
{|border="1" width="100%" cellpadding="1" cellspacing="0" style="font-size: 85%; border: gray solid 1px; border-collapse: collapse; text-align: center; width: 100%<br />
!style="background: #ececec;"|'''ID<br />
!style="background: #ececec;"|'''test'''<br />
!style="background: #ececec;"|'''tool test'''<br />
!style="background: #ececec;"|'''status'''<br />
!style="background: #ececec;"|'''owner'''<br />
!style="background: #ececec;"|'''notes'''<br />
|-<br />
|I.Q.1<br />
|title<br />
|test<br />
|'''New'''<br />
|<br />
|<br />
|}</div>
65.172.181.6
https://wiki.linux-nfs.org/wiki/index.php/Functional_testing
Functional testing
2005-06-27T23:58:09Z
<p>65.172.181.6: </p>
<hr />
<div>= NFSv4 Functionality testing =<br />
<br />
== Functionality testing of Automounter == <br />
Test clarifications: <br />
*Verify compatibility with automounter: <br />
How well the automounter works with NFSv4 in general.<br />
<br />
Functionality needs to be tested for the following versions supported by the distros. <br />
<br />
*Automounter functionality – amd<br />
RHEL2.1 – am-utils-6.0.6-3<br />
RHEL3 – am-utils-6.0.9-2.4<br />
RHEL4 – am-utils-6.0.9-10<br />
<br />
* Automounter functionality – autofs<br />
RHEL 2.1 – autofs-3.1.7 <br />
RHEL3 – autofs-4.1.3 <br />
RHEL4 – autofs-4.1.3<br />
SLES8/SLES9 – autofs-3.1.7<br />
(Note: RHEL 2.1 supports autofs-3.1.7 with the autofs 3 kernel module. <br />
RHEL 3 and RHEL 4 now only support the autofs 4 kernel modules. <br />
Both RHEL 3 and RHEL4 user space are based off of autofs-4.1.3, though <br />
they more resemble 4.1.4)<br />
<br />
* Automounter functionality – autong<br />
autofsng-0.4.1<br />
(Note: Autofsng is highly in development phase and so there is no support <br />
for the previous versions. As of now 0.4.1 is the latest release that <br />
will be supported and there is no distribution currently ships it.)<br />
<br />
== Serviceability Testing ==<br />
<br />
For any given service function (showmount, umount -f, etc. etc.) use the following checklist for verifying the functionality:<br />
<br />
<pre><br />
1. The feature reports accurate information<br />
a) reports correctly during exception case situations<br />
2. The feature does not cause misbehavior (ie an oops) when used<br />
3. The feature is consistent with other standard reporting facilities<br />
a) it uses recognized (POSIX) error codes<br />
b) it is internationalized appropriately<br />
c) it matches existing network and disk reporting tools<br />
d) it has a man page<br />
4. The feature does not cause undue performance impact<br />
a) it does not cause memory leaks<br />
5. The feature produces error messages that are useful<br />
(self-explanatory, not too much noise, not unnecessarily alarming)<br />
</pre></div>
65.172.181.6
https://wiki.linux-nfs.org/wiki/index.php/Functional_testing
Functional testing
2005-06-27T23:56:57Z
<p>65.172.181.6: </p>
<hr />
<div>=NFSv4 Functionality testing=<br />
<br />
==Functionality testing of Automounter== <br />
Test clarifications: <br />
*Verify compatibility with automounter: <br />
How well the automounter works with NFSv4 in general.<br />
<br />
Functionality needs to be tested for the following versions supported by the distros. <br />
<br />
*Automounter functionality – amd<br />
RHEL2.1 – am-utils-6.0.6-3<br />
RHEL3 – am-utils-6.0.9-2.4<br />
RHEL4 – am-utils-6.0.9-10<br />
<br />
* Automounter functionality – autofs<br />
RHEL 2.1 – autofs-3.1.7 <br />
RHEL3 – autofs-4.1.3 <br />
RHEL4 – autofs-4.1.3<br />
SLES8/SLES9 – autofs-3.1.7<br />
(Note: RHEL 2.1 supports autofs-3.1.7 with the autofs 3 kernel module. <br />
RHEL 3 and RHEL 4 now only support the autofs 4 kernel modules. <br />
Both RHEL 3 and RHEL4 user space are based off of autofs-4.1.3, though <br />
they more resemble 4.1.4)<br />
<br />
* Automounter functionality – autong<br />
autofsng-0.4.1<br />
(Note: Autofsng is highly in development phase and so there is no support <br />
for the previous versions. As of now 0.4.1 is the latest release that <br />
will be supported and there is no distribution currently ships it.)<br />
<br />
==Serviceability Testing==<br />
<br />
For any given service function (showmount, umount -f, etc. etc.) use the following checklist for verifying the functionality:<br />
<br />
<pre><br />
1. The feature reports accurate information<br />
a) reports correctly during exception case situations<br />
2. The feature does not cause misbehavior (ie an oops) when used<br />
3. The feature is consistent with other standard reporting facilities<br />
a) it uses recognized (POSIX) error codes<br />
b) it is internationalized appropriately<br />
c) it matches existing network and disk reporting tools<br />
d) it has a man page<br />
4. The feature does not cause undue performance impact<br />
a) it does not cause memory leaks<br />
5. The feature produces error messages that are useful<br />
(self-explanatory, not too much noise, not unnecessarily alarming)<br />
</pre></div>
65.172.181.6
https://wiki.linux-nfs.org/wiki/index.php/Main_Page
Main Page
2005-06-27T23:56:09Z
<p>65.172.181.6: </p>
<hr />
<div>NFS is a critical service in many organizations, and even a simple<br />
errors can lead to major problems. NFSv4 promises to bring several key<br />
new features, but clearly it will be imperitive to users that the new<br />
version of NFS be robust, that it perform well, and that it interoperate<br />
easily with other technologies.<br />
<br />
{|{|cellpadding="5" cellspacing="3" class="mainpagetable" width="100%"<br />
|-<br />
|valign="top" style="padding: .5em 1em 1em; color: #000000; background-color: #d7e4f4; width: 33%"|<br />
'''General'''<br />
* [[NFSv4_Introduction|End user documentation]]<br />
* [[Design|Design documentation]]<br />
* Active Directory<br />
** [[http://nfsworld.blogspot.com/2005/06/using-active-directory-as-your-kdc-for.html Linux, AD, and NetApp filers]]<br />
|valign="top"|<br />
'''Troubleshooting'''<br />
* [[General troubleshooting recommendations]]<br />
* Common error messages<br />
* Tools for troubleshooting<br />
* Problems exporting<br />
* Problems mounting<br />
* Problems automounting<br />
* Problems with Kerberos Authentication<br />
|valign="top" style="padding: .5em 1em 1em; color: #000000; background-color: #d7e4f4; width:33%"|<br />
'''Testing'''<br />
* [[Testing tools]]<br />
* [[Functional testing]]<br />
* [[Interoperability testing]]<br />
* [[Performance testing]]<br />
* [[Robustness testing]]<br />
* [[Security testing]]<br />
* Tests needed<br />
* [[Testing methodologies]]<br />
* [[Test_matrix|test matrix]]<br />
* [[Testing forecast roadmap]]<br />
|}<br />
<br />
<br />
==Testing ==<br />
<br />
The Linux NFSv4 Testing effort seeks to ensure that the Linux<br />
implementation of NFSv4 succeeds on all these counts. The purpose of<br />
the testing is threefold:<br />
<br />
* To prove that the features are implemented correctly according to spec.<br />
* To locate and identify bugs, and verify the fixes. <br />
* To give confidence to users that upgrading to NFSv4 on Linux is of benefit.</div>
65.172.181.6
https://wiki.linux-nfs.org/wiki/index.php/Functional_testing
Functional testing
2005-06-27T23:55:45Z
<p>65.172.181.6: /* NFSv4 Functionality testing */</p>
<hr />
<div>= NFSv4 Functionality testing =<br />
<br />
== 1. Functionality testing of Automounter == <br />
Test clarifications: <br />
*Verify compatibility with automounter: <br />
How well the automounter works with NFSv4 in general.<br />
<br />
Functionality needs to be tested for the following versions supported by the distros. <br />
<br />
*Automounter functionality – amd<br />
RHEL2.1 – am-utils-6.0.6-3<br />
RHEL3 – am-utils-6.0.9-2.4<br />
RHEL4 – am-utils-6.0.9-10<br />
<br />
* Automounter functionality – autofs<br />
RHEL 2.1 – autofs-3.1.7 <br />
RHEL3 – autofs-4.1.3 <br />
RHEL4 – autofs-4.1.3<br />
SLES8/SLES9 – autofs-3.1.7<br />
(Note: RHEL 2.1 supports autofs-3.1.7 with the autofs 3 kernel module. <br />
RHEL 3 and RHEL 4 now only support the autofs 4 kernel modules. <br />
Both RHEL 3 and RHEL4 user space are based off of autofs-4.1.3, though <br />
they more resemble 4.1.4)<br />
<br />
* Automounter functionality – autong<br />
autofsng-0.4.1<br />
(Note: Autofsng is highly in development phase and so there is no support <br />
for the previous versions. As of now 0.4.1 is the latest release that <br />
will be supported and there is no distribution currently ships it.)<br />
<br />
== Serviceability Testing ==<br />
<br />
For any given service function (showmount, umount -f, etc. etc.) use the following checklist for verifying the functionality:<br />
<br />
<pre><br />
1. The feature reports accurate information<br />
a) reports correctly during exception case situations<br />
2. The feature does not cause misbehavior (ie an oops) when used<br />
3. The feature is consistent with other standard reporting facilities<br />
a) it uses recognized (POSIX) error codes<br />
b) it is internationalized appropriately<br />
c) it matches existing network and disk reporting tools<br />
d) it has a man page<br />
4. The feature does not cause undue performance impact<br />
a) it does not cause memory leaks<br />
5. The feature produces error messages that are useful<br />
(self-explanatory, not too much noise, not unnecessarily alarming)<br />
</pre></div>
65.172.181.6
https://wiki.linux-nfs.org/wiki/index.php/Testing_methodologies
Testing methodologies
2005-06-03T00:32:04Z
<p>65.172.181.6: </p>
<hr />
<div><br />
The NFSv4 Test Matrix itemizes a number of tasks for testing the client,<br />
server, and related technologies in a variety of different ways. In<br />
many cases it should be evident how to conduct the testing, but in other<br />
cases the tester may benefit from some additional detail or guidance for<br />
what exactly to look for or how to properly conduct the testing.<br />
<br />
Normally, in formal testing you'd create a 'test plan', detailing<br />
everything the tester must do, the tools to use, the format of reports<br />
to be written, the specs for the hardware to use, etc. etc. But such<br />
documents are time consuming to write and make for dry reading.<br />
Fortunately, you probably can get 80% of the benefit for 20% of the work<br />
by just giving a 'test checklist' that gives the tester some general<br />
hints as to what to do. If they need something more formal, they can<br />
extrapolate from there.<br />
<br />
Thus, the purpose of this HOWTO document is to explain how to make a<br />
test checklist for NFSv4.<br />
<br />
==Example Test Methodology==<br />
<br />
For the impatient, here's an example. If this gives you a good enough<br />
idea what we're talking about, feel free to skip to the end where we say<br />
thank you and good luck. ;-)<br />
<br />
===Serviceability Testing===<br />
<br />
For any given service function (showmount, umount -f, etc. etc.) use the<br />
following checklist for verifying the functionality:<br />
<br />
1. The feature reports accurate information<br />
a) reports correctly during exception case situations<br />
2. The feature does not cause misbehavior (ie an oops) when used<br />
3. The feature is consistent with other standard reporting facilities<br />
a) it uses recognized (POSIX) error codes<br />
b) it is internationalized appropriately<br />
c) it matches existing network and disk reporting tools<br />
d) it has a man page<br />
4. The feature does not cause undue performance impact<br />
a) it does not cause memory leaks<br />
5. The feature produces error messages that are useful<br />
(self-explanatory, not too much noise, not unnecessarily alarming)<br />
<br />
==Philosophy==<br />
<br />
The basic purpose of these test checklists is to help guide a tester<br />
towards being able to do a good job. This helps all of us by ensuring a<br />
high level of quality. We'll have a better idea of how the tester did<br />
the work, and a better chance of recreating any issues they run across.<br />
<br />
We assume the tester has a relatively good understanding of NFSv4; if<br />
they don't, we can expect that they can tap into other documentation to<br />
gain that knowledge.<br />
<br />
==Test Matrix Scope==<br />
<br />
The test matrix covers a broad range of testing activities. Some<br />
require sysadmin skills, some need development skills, and some need<br />
analytical skills. Obviously, different types of people are needed for<br />
these different roles. Thus, make sure your test checklist identifies<br />
the types of skills needed.<br />
<br />
<i>System testing activities</i> are ones that involve running an<br />
existing test or performing a canned set of actions against a variety of<br />
configurations. The tester might be varying hardware, invoking failure<br />
cases, or altering the software composition of the system under test.<br />
The deliverable for this type of testing is a report summarizing the<br />
findings.<br />
<br />
<i>Test development activities</i> augment existing test suites or<br />
create new tests for things that are not already covered. For instance,<br />
many existing tests do not yet include some of the newer NFSv4<br />
features. A developer augments an existing test to add this<br />
functionality. The deliverable is a patch or tarball that other testers<br />
can use or that the test maintainer can incorporate.<br />
<br />
<i>Analyst activities</i> require deep review and consideration of the<br />
item under test. For example, if there is a performance flaw, this<br />
would seek to identify and understand the cause. The analyst's<br />
deliverable is a set of recommendations to the developers to help<br />
characterize the problem and suggest how to fix it.<br />
<br />
1. export filesystem to client.<br />
2. let client allow to mount it.<br />
3. remove all entries from rmtab on server.<br />
4. restart all nfs daemons.<br />
5. Now if client access filesystem , it gets<br />
permission denied error.Client can access<br />
filesystem only after remounting it.<br />
6. This show that mountd still uses rmtab to<br />
check if client had mounted filesystem or not.<br />
No entry in rmtab for a client means it has not<br />
mounted filesystem.<br />
<br />
<br />
Differences between various test items<br />
<br />
* Assume the tester knows what the heck they're doing. Don't bother explaining basic stuff that the reader can figure out on their own with a little research. Do give elaboration to particular elements relevant to this task, that aren't well documented or that are highly important to understand.<br />
<br />
* Give a reference if you have one.<br />
<br />
==Good Luck!==<br />
<br />
Thank you for giving consideration to helping the NFSv4 testing effort.<br />
Your test checklist will help enable the community to test your chosen<br />
test item more completely and accurately.</div>
65.172.181.6
https://wiki.linux-nfs.org/wiki/index.php/Main_Page
Main Page
2005-06-03T00:29:08Z
<p>65.172.181.6: /* Tests */</p>
<hr />
<div>==Design of NFSv4==<br />
* [[Design|Design documentation]]<br />
<br />
==Troubleshooting==<br />
* [[General troubleshooting recommendations]]<br />
* Problems exporting<br />
* Problems mounting<br />
* Problems automounting<br />
* Common error messages<br />
* Tools for troubleshooting<br />
<br />
==Tests ==<br />
<br />
* [[Testing tools]]<br />
* [[Functional testing]]<br />
** [[Serviceability testing]]<br />
* [[Interoperability testing]]<br />
* [[Performance testing]]<br />
* [[Robustness testing]]<br />
* [[Security testing]]<br />
* Tests needed<br />
* [[Testing methodologies]]<br />
<br />
==Testing Plans==<br />
* [[Test_matrix|test matrix]]<br />
<br />
== End User documentation ==<br />
* [[NFSv4_Introduction|End user documentation]]</div>
65.172.181.6
https://wiki.linux-nfs.org/wiki/index.php/Main_Page
Main Page
2005-05-18T01:57:27Z
<p>65.172.181.6: </p>
<hr />
<div>Wiki software successfully installed.<br />
<br />
Please see [http://meta.wikipedia.org/wiki/MediaWiki_i18n documentation on customizing the interface]<br />
and the [http://meta.wikipedia.org/wiki/MediaWiki_User%27s_Guide User's Guide] for usage and configuration help.<br />
<br />
Things this wiki could be useful for:<br />
<br />
* [[Troubleshooting]] tips / tricks<br />
* Comments on tests - how to run them, etc.<br />
* Convert test matrix to wiki(?)<br />
* Testing methodologies / details<br />
* Design documentation for NFSv4?<br />
* End user documentation?<br />
* other ideas...?</div>
65.172.181.6
https://wiki.linux-nfs.org/wiki/index.php/Main_Page
Main Page
2005-05-18T01:56:51Z
<p>65.172.181.6: </p>
<hr />
<div>Wiki software successfully installed.<br />
<br />
Please see [http://meta.wikipedia.org/wiki/MediaWiki_i18n documentation on customizing the interface]<br />
and the [http://meta.wikipedia.org/wiki/MediaWiki_User%27s_Guide User's Guide] for usage and configuration help.<br />
<br />
Things this wiki could be useful for:<br />
<br />
* Troubleshooting tips / tricks<br />
* Comments on tests - how to run them, etc.<br />
* Convert test matrix to wiki(?)<br />
* Testing methodologies / details<br />
* Design documentation for NFSv4?<br />
* End user documentation?</div>
65.172.181.6
https://wiki.linux-nfs.org/wiki/index.php/Main_Page
Main Page
2005-05-18T01:36:01Z
<p>65.172.181.6: </p>
<hr />
<div>Wiki software successfully installed.<br />
<br />
Please see [http://meta.wikipedia.org/wiki/MediaWiki_i18n documentation on customizing the interface]<br />
and the [http://meta.wikipedia.org/wiki/MediaWiki_User%27s_Guide User's Guide] for usage and configuration help.<br />
<br />
Testing 1 2 3</div>
65.172.181.6