Matrix robustness section

From Linux NFS

(Difference between revisions)
Jump to: navigation, search
(Recovery from problems while under light/normal/heavy loads)
(Scalability (robustness))
Line 176: Line 176:
==Scalability (robustness)==
==Scalability (robustness)==
-
*Find maximum number of connections to Linux IA-32 server Fsstress, fsx New
+
 
-
*Find maximum number of files for Linux IA-32 exported file system Fsstress, fsx
+
 
-
*Find maximum file size on Linux IA-32 Fsstress, fsx New
+
 
-
*Find maximum number of mounted file systems on client Fsstress, fsx New
+
<table nosave="" border="1" width="85%">
-
*Test robustness on NUMA when scaling CPU, mem, NIC, or disk count New
+
<tr nosave="" align="center" valign="CENTER">
-
*Test robustness on SMP when scaling CPU, mem, NIC, or disk count New
+
<td nosave="" align="center" valign="CENTER"></td>
-
*Test correctness of NFS client when backed by a large (>100GB) cachefs New
+
 
-
*Find maximum number exported file systems on server New
+
<td>test</td>
-
*Find maximum size of exported file systems on server New
+
<td>tool test</td>
 +
<td>status</td>
 +
<td>Owner</td>
 +
<td>notes</td>
 +
</tr>
 +
<tr>
 +
<td>III.D.1</td>
 +
<td>
 +
Find maximum number of connections to Linux IA-32 server</td><td>Fsstress, fsx</td><td>'''New'''</td><td>Bull (partial)</td><td></td>
 +
</tr>
 +
<tr>
 +
<td>III.D.2</td>
 +
<td>
 +
Find maximum number of files for Linux IA-32 exported file system</td><td>Fsstress, fsx</td><td>'''New'''</td><td>Bull (partial)</td><td></td>
 +
</tr>
 +
<tr>
 +
<td>III.D.3</td>
 +
<td>
 +
Find maximum file size on Linux IA-32</td><td>Fsstress, fsx</td><td>'''New'''</td><td>Bull (partial)</td><td></td>
 +
</tr>
 +
<tr>
 +
<td>III.D.4</td>
 +
<td>
 +
Find maximum number of mounted file systems on client</td><td>Fsstress, fsx</td><td>'''New'''</td><td>Bull (partial)</td><td></td>
 +
</tr>
 +
<tr>
 +
<td>III.D.5</td>
 +
<td>
 +
Test robustness on NUMA when scaling CPU, mem, NIC, or disk count</td><td>Fsstress, fsx</td><td>'''New'''</td><td></td><td></td>
 +
</tr>
 +
<tr>
 +
<td>III.D.6</td>
 +
<td>
 +
Test robustness on SMP when scaling CPU, mem, NIC, or disk count</td><td>Fsstress, fsx</td><td>'''New'''</td><td>Bull (partial)</td><td></td>
 +
</tr>
 +
<tr>
 +
<td>III.D.7</td>
 +
<td>
 +
Test correctness of NFS client when backed by a large (>100GB) cachefs</td><td></td><td>'''New'''</td><td></td><td></td>
 +
</tr>
 +
<tr>
 +
<td>III.D.8</td>
 +
<td>
 +
Find maximum number exported file systems on server</td><td></td><td>'''New'''</td><td></td><td></td>
 +
</tr>
 +
<tr>
 +
<td>III.D.9</td>
 +
<td>
 +
Find maximum size of exported file systems on server</td><td></td><td>'''New'''</td><td></td><td></td>
 +
</tr>
 +
</table>
==Recovery from problems while under light/normal/heavy loads==
==Recovery from problems while under light/normal/heavy loads==

Revision as of 11:36, 19 May 2005

Section III

Contents

ROBUSTNESS TESTING

Basic stability assessments

test tool test status Owner notes
III.A.1

Run iozone for 2 weeks on basic client/server operations, using:

  • Both data and metadata options
  • Cached and direct I/O
  • Various mount options
IOzonedoneBULLNow testing with fsstress and FFSB
III.A.2

Run automounter use case for 2 weeks on amd, autofs, and autong, using:

  • Large number of maps
  • Randomly mount and run workloads on an automounted partition
  • use a variety of workloads, such as randomly chosen fs tests
e.g. Crashme moreNewnonenone
III.A.3

Run NFS server for 2 wks with random configuration changes, using:

  • Interrupt server in various ways (reboot, power cycle, lan fail)
  • Change/reexport export rules at random
  • Trigger a client workload at arbitrary times
  • Analyze client recovery behaviors
OPENOSDL
III.A.4

Run connectathon locking tests against NFS server for 2 weeks, using:

  • Multiple client machines
  • Reboot at random
  • Analyze client cache coherency behaviors
  • Analyze locking behaviors
NEW
III.A.5

Run fsstress 2 weeks on basic client/server operations, using:

  • Long list random operations (1000 operations)
  • hight number of process (100)
fsstressDoneBULL1 week
III.A.6

Run FFSB 1 day on basic client/server operations in stress configuration, using:

  • 1 200 000 files
  • 100 directories
ffsbDoneBULL1 day

Resource limit testing

test tool test status Owner notes
III.B.1 Test stability of client in out of pid situation
III.B.2 Test stability of client in out of memory situationvalgrindnewIA32
III.B.3 Test stability of client in out of disk space on server situationdd,fsstressdoneBULLSimple error message no space left on device
III.B.4 Test stability of client in out of inode situation
III.B.5 Test stability of client in out of swap space situation
III.B.6 Test stability of server in out of pid situation
III.B.7 Test stability of server in out of memory situationvalgrindnewIA32
III.B.8 Test stability of server in out of disk space situationdd,fsstressdoneBULL Simple error message no space left on device
III.B.9 Test stability of server in out of inode situation
III.B.10 Test stability of server in out of swap space situation

Stress load testing

test tool test status Owner notes
III.C.1 Run stress tools in a std config on each release fsx,fsstress,ffsbIn progressBULL Tests used:
  • fsx
  • fsstress (1h)
  • ffsb (1h)
III.C.2 Analyze load balancing, failure modes, etc. under different stress loads New
III.C.3 Destructive testing by measuring point of failure for various loads New

Scalability (robustness)

test tool test status Owner notes
III.D.1 Find maximum number of connections to Linux IA-32 serverFsstress, fsxNewBull (partial)
III.D.2 Find maximum number of files for Linux IA-32 exported file systemFsstress, fsxNewBull (partial)
III.D.3 Find maximum file size on Linux IA-32Fsstress, fsxNewBull (partial)
III.D.4 Find maximum number of mounted file systems on clientFsstress, fsxNewBull (partial)
III.D.5 Test robustness on NUMA when scaling CPU, mem, NIC, or disk countFsstress, fsxNew
III.D.6 Test robustness on SMP when scaling CPU, mem, NIC, or disk countFsstress, fsxNewBull (partial)
III.D.7 Test correctness of NFS client when backed by a large (>100GB) cachefsNew
III.D.8 Find maximum number exported file systems on serverNew
III.D.9 Find maximum size of exported file systems on serverNew

Recovery from problems while under light/normal/heavy loads

test tool test status Owner notes
III.E.1 Test short & long term local network failure (unplugged cable, ifdown eth0, etc.)OpenOSDL
III.E.2 Test short & long duration remote network partitionOpenOSDL
III.E.3 Test behavior during crash/reboot of server with clients holding various statesOpenOSDLmore
III.E.4 Test multiple clients using, locking, etc. same filesNew
III.E.5 Test behavior of server with failed storage deviceNew
III.E.6 Test behavior during crash of client with open delegations and locksNew
III.E.7 Test recovery from denied permissionNew
III.E.5 Test recovery from JUKEBOX/DELAYNew
III.E.5 Test recovery from ESTALENew
Personal tools