[LU-697] sanity-benchmark timed out during iozone Created: 21/Sep/11  Updated: 28/May/17  Resolved: 28/May/17

Status: Resolved
Project: Lustre
Component/s: None
Affects Version/s: Lustre 2.1.0, Lustre 1.8.7
Fix Version/s: None

Type: Bug Priority: Minor
Reporter: Minh Diep Assignee: WC Triage
Resolution: Cannot Reproduce Votes: 0
Labels: None
Environment:

Lustre Clients:
Tag: 1.8.6-wc1
Distro/Arch: RHEL6/x86_64 (kernel version: 2.6.32_131.2.1.el6)
Build: http://newbuild.whamcloud.com/job/lustre-b1_8/100/arch=x86_64,build_type=client,distro=el6,ib_stack=inkernel/
Network: TCP
ENABLE_QUOTA=yes

Lustre Servers:
Tag: v2_1_0_0_RC2
Distro/Arch: RHEL6/x86_64 (kernel version: 2.6.32-131.6.1.el6_lustre.g65156ed.x86_64)
Build: http://newbuild.whamcloud.com/job/lustre-master/228/arch=x86_64,build_type=server,distro=el6,ib_stack=inkernel/
Network: TCP


Severity: 3
Rank (Obsolete): 5474

 Description   

2.1.0 RC2 testing, iozone test did not complete. No further info. Perhaps we should check if 3600s is enough

report: https://maloo.whamcloud.com/test_sets/ed0da0a4-e43f-11e0-9909-52540025f9af

== sanity-benchmark test iozone: iozone == 02:03:15 (1316509395)
min OST has 10366400kB available, using 4111400kB file size
lnet.debug=0
running as UID 500, GID 500
[touch] [/mnt/lustre/d0_runas_test/f17237]
running as UID 500, GID 500
[iozone] [-i] [0] [-i] [1] [-i] [2] [-e] [-+d] [-r] [512] [-s] [4111400] [-f] [/mnt/lustre/d0.iozone/iozone]
Iozone: Performance Test of File I/O
Version $Revision: 3.373 $
Compiled for 64 bit mode.
Build: linux-AMD64

Contributors:William Norcott, Don Capps, Isom Crawford, Kirby Collins
Al Slater, Scott Rhine, Mike Wisner, Ken Goss
Steve Landherr, Brad Smith, Mark Kelly, Dr. Alain CYR,
Randy Dunlap, Mark Montague, Dan Million, Gavin Brebner,
Jean-Marc Zucconi, Jeff Blomberg, Benny Halevy, Dave Boone,
Erik Habbinga, Kris Strecker, Walter Wong, Joshua Root,
Fabrice Bacchella, Zhenghua Xue, Qin Li, Darren Sawyer.

Run began: Tue Sep 20 02:03:17 2011

Include fsync in write timing
>>> I/O Diagnostic mode enabled. <<<
Performance measurements are invalid in this mode.
Record Size 512 KB
File size set to 4111400 KB
Command line used: iozone -i 0 -i 1 -i 2 -e -+d -r 512 -s 4111400 -f /mnt/lustre/d0.iozone/iozone
Output is in Kbytes/sec
Time Resolution = 0.000001 seconds.
Processor cache size set to 1024 Kbytes.
Processor cache line size set to 32 bytes.
File stride size set to 17 * record size.
random random bkwd record stride
KB reclen write rewrite read reread read write read rewrite read fwrite frewrite fread freread
4111400 512 27401 26851 29730 28806 12852 26617

iozone test complete.
lnet.debug=0x33f0484
directio on /mnt/lustre/f.iozone for 1x2097152 bytes
PASS
lnet.debug=0
running as UID 500, GID 500
[iozone] [-I] [-i] [0] [-i] [1] [-i] [2] [-e] [-+d] [-r] [512] [-s] [4111400] [-f] [/mnt/lustre/d0.iozone/iozone.odir]
Iozone: Performance Test of File I/O
Version $Revision: 3.373 $
Compiled for 64 bit mode.
Build: linux-AMD64

Contributors:William Norcott, Don Capps, Isom Crawford, Kirby Collins
Al Slater, Scott Rhine, Mike Wisner, Ken Goss
Steve Landherr, Brad Smith, Mark Kelly, Dr. Alain CYR,
Randy Dunlap, Mark Montague, Dan Million, Gavin Brebner,
Jean-Marc Zucconi, Jeff Blomberg, Benny Halevy, Dave Boone,
Erik Habbinga, Kris Strecker, Walter Wong, Joshua Root,
Fabrice Bacchella, Zhenghua Xue, Qin Li, Darren Sawyer.

Run began: Tue Sep 20 02:20:56 2011

O_DIRECT feature enabled
Include fsync in write timing
>>> I/O Diagnostic mode enabled. <<<
Performance measurements are invalid in this mode.
Record Size 512 KB
File size set to 4111400 KB
Command line used: iozone -I -i 0 -i 1 -i 2 -e -+d -r 512 -s 4111400 -f /mnt/lustre/d0.iozone/iozone.odir
Output is in Kbytes/sec
Time Resolution = 0.000001 seconds.
Processor cache size set to 1024 Kbytes.
Processor cache line size set to 32 bytes.
File stride size set to 17 * record size.
random random bkwd record stride
KB reclen write rewrite read reread read write read rewrite read fwrite frewrite fread freread



 Comments   
Comment by Jian Yu [ 23/Sep/11 ]

3600s is not enough for running sanity-benchmark with SLOW=yes. Chris, could you please increase the time limit value?

I found the following two passed sanity-benmark runs with SLOW=yes on Maloo:
https://maloo.whamcloud.com/test_sets/d677c9c4-db79-11e0-8d02-52540025f9af
https://maloo.whamcloud.com/test_sets/dcc173e0-dae1-11e0-8d02-52540025f9af
They took 7603s and 7729s separately.

Lustre Clients:
Tag: 1.8.6-wc1
Distro/Arch: RHEL6/x86_64 (kernel version: 2.6.32_131.2.1.el6)
Build: http://newbuild.whamcloud.com/job/lustre-b1_8/100/arch=x86_64,build_type=client,distro=el6,ib_stack=inkernel/
Network: TCP (1GigE)
ENABLE_QUOTA=yes

Lustre Servers:
Tag: v2_1_0_0_RC2
Distro/Arch: RHEL6/x86_64 (kernel version: 2.6.32-131.6.1.el6_lustre)
Build: http://newbuild.whamcloud.com/job/lustre-master/283/arch=x86_64,build_type=server,distro=el6,ib_stack=inkernel/

iozone and fsx tests passed in manual run: https://maloo.whamcloud.com/test_sets/38500ed4-e5d1-11e0-9909-52540025f9af

Comment by Andreas Dilger [ 28/May/17 ]

Close old issue.

Generated at Sat Feb 10 01:09:33 UTC 2024 using Jira 9.4.14#940014-sha1:734e6822bbf0d45eff9af51f82432957f73aa32c.