All of lore.kernel.org
 help / color / mirror / Atom feed
From: Tommi Virtanen <tommi.virtanen@dreamhost.com>
To: ceph-devel@vger.kernel.org
Subject: Autotest results from 2011-03-21
Date: Mon, 21 Mar 2011 13:41:21 -0700	[thread overview]
Message-ID: <20110321204121.GD17804@dreamer> (raw)

So, we have 10 filesystem tests plugged into Autotest. I scheduled
them for execution, with 6-node clusters (because that's easy for me
to do, and there's only one client creating load anyway), before I
left work last Friday. Summary of results is at the end of this email.

The DNS errors are probably related to the network outage we had on
that LAN.

Note for non-staff readers, sorry but you won't have access to
Autotest.

** ceph_blogbench (job 249) TRANSIENT FAILURE
DNS errors, rerunning test as job 264
** ceph_dbench (job 251) TRANSIENT FAILURE
DNS errors, rerunning test as job 262
** ceph_direct_io_test (job 252) TRANSIENT FAILURE
DNS errors, rerunning test as job 261
** ceph_ffsb (job 253) SUCCESS
captures performance info but does not analyze it
http://autotest.ceph.newdream.net/results/253-tv/group0/sepia23.ceph.dreamhost.com/ffsb/debug/ffsb.DEBUG
** ceph_fsstress (job 254) SUCCESS
** ceph_fsx (job 255) SUCCESS
** ceph_iozone (job 256) SUCCESS
captures & analyzes performance info
http://autotest.ceph.newdream.net/results/256-tv/group0/sepia82.ceph.dreamhost.com/iozone/results/keyval
** ceph_pjd_fstest (job 257) FAILURE
http://tracker.newdream.net/issues/906
** ceph_tiobench (job 258) FAILURE, TRANSIENT?
failure on client node
test software exited 255 after 488 seconds
http://autotest.ceph.newdream.net/results/258-tv/group0/sepia81.ceph.dreamhost.com/status
Run #1: ./tiotest -t 10 -f 102 -r 400 -b 4096 -d /usr/local/autotest/tmp/tmpno6nA__ceph_tiobench.cluster0/mnt.0 -T
Run #2: ./tiotest -t 10 -f 102 -r 400 -b 4096 -d /usr/local/autotest/tmp/tmpno6nA__ceph_tiobench.cluster0/mnt.0 -T
Illegal division by zero at ./tiobench.pl line 170.
*** debugging
sed -n '170,172p' < tiobench.pl
               $stat_data{$identifier}{$thread}{$size}{$block}{$field}{'cpueff'} =
                  ($stat_data{$identifier}{$thread}{$size}{$block}{$field}{'rate'} /
                  ($stat_data{$identifier}{$thread}{$size}{$block}{$field}{'cpu'}/100));
*** conclusion
tiobench internal bug? re-running test as job 260
** ceph_bonnie (job 259) TRANSIENT FAILURE
DNS errors, rerunning test as job 263

-- 
:(){ :|:&};:

                 reply	other threads:[~2011-03-21 20:41 UTC|newest]

Thread overview: [no followups] expand[flat|nested]  mbox.gz  Atom feed

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20110321204121.GD17804@dreamer \
    --to=tommi.virtanen@dreamhost.com \
    --cc=ceph-devel@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.