[LU-12168] obdfilter-survey SHORT msg Created: 08/Apr/19  Updated: 30/Apr/19  Resolved: 30/Apr/19

Status: Resolved
Project: Lustre
Component/s: None
Affects Version/s: Lustre 2.13.0
Fix Version/s: Lustre 2.13.0

Type: Bug Priority: Major
Reporter: Alexander Boyko Assignee: Alexander Boyko
Resolution: Fixed Votes: 0
Labels: patch
Environment:

singlenode setup


Severity: 3
Rank (Obsolete): 9223372036854775807

 Description   
sudo tests_str='write rewrite read' rszlo=2048 rszhi=2048 nobjlo=4 nobjhi=4 size=32768 thrlo=128 thrhi=512 targets=" lustre-OST0000" /bin/obdfilter-survey
Mon Apr 8 08:25:56 EDT 2019 Obdfilter-survey for case=disk from devvm-centos-1
ost 1 sz 33554432K rsz 2048K obj 4 thr 128 write 8629.21 [11376.89, 11484.35] rewrite 8828.82 [11509.80, 11624.36] read 5592.10 [6512.02, 6579. 40]
ost 1 sz 33554432K rsz 2048K obj 4 thr 256 write 8921.24 [11461.74, 11614.22] rewrite 8636.16 [11330.46, 11545.90] read 6187.21 SHORT
ost 1 sz 33554432K rsz 2048K obj 4 thr 512 write 8267.24 [11295.09, 11586.17] rewrite 7136.59 [6831.46, 11087.51] read 5072.56 SHORT
/bin/iokit-libecho: line 236: 14010 Killed remote_shell $host "vmstat 5 >> $host_vmstatf" &>/dev/null
done!
 

SHORT is printed when there is no min/max statistics, rewrite globals has zeroes

=============> rewrite localhost:snx11117-OST0003_ecc
Print status every 1 seconds
--threads: starting 2816 threads on device 5 running test_brw 23 wx q 1024 704t42 p1024
Total: total 64768 threads 2816 sec 79.770391 811.930331/second
=============> rewrite global
0 0.000000 0.000000

min,max speeds calculated base on Total lines,

 Print status every 1 seconds
--threads: starting 2816 threads on device 5 running test_brw 23 rx q 1024 704t42 p1024
1458/2816 Total: 1457.424317/second
1413/2816 Total: 1412.337614/second

Total lines are printed when all threads are started.
We do have the whole statistic at the end, but no statistic for every seconds, so result is SHORT.
This could happen when two signals for a parent process comes during a verbose time. The counters are updated and start_time is dropped. By default timeperiod is 1 second.



 Comments   
Comment by Gerrit Updater [ 08/Apr/19 ]

Alexandr Boyko (c17825@cray.com) uploaded a new patch: https://review.whamcloud.com/34610
Subject: LU-12168 utils: obdfilter fix for SHORT msgs
Project: fs/lustre-release
Branch: master
Current Patch Set: 1
Commit: 065a225081f99ff9a369a0715473856f0c253c7c

Comment by Gerrit Updater [ 30/Apr/19 ]

Oleg Drokin (green@whamcloud.com) merged in patch https://review.whamcloud.com/34610/
Subject: LU-12168 utils: obdfilter fix for SHORT msgs
Project: fs/lustre-release
Branch: master
Current Patch Set:
Commit: 63f310a5c9f799e7ce99badf410853d3275380d2

Comment by Peter Jones [ 30/Apr/19 ]

Landed for 2.13

Generated at Sat Feb 10 02:50:14 UTC 2024 using Jira 9.4.14#940014-sha1:734e6822bbf0d45eff9af51f82432957f73aa32c.