Activity
From 12/26/2012 to 01/24/2013
01/24/2013
- 11:21 PM Revision b150e8e3 (teuthology): workunit: pass java path as env variable
- The libcephfs-java test needs this.
- 08:50 PM Revision 6a859bcd (teuthology): ceph_manager: use 80/70 as pause_long, pause_check_after defaults
- OSD::op_tp suicides after 150.
Signed-off-by: Samuel Just <sam.just@inktank.com> - 06:08 PM Revision 0f24dca2 (teuthology): ceph_manager: use do_rados for rmpool
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 04:03 PM Feature #3932 (Closed): database: store performance data
- Following the implementation of #3931, track the data it outputs in the database, however we do that.
- 04:02 PM Feature #3931 (Resolved): create a timer task
- We discussed in the dev list how it would be nice to start gathering performance data out of our nightly runs. To fac...
- 10:06 AM Feature #3783 (In Progress): osdthrasher: power cycle osds
- 02:43 AM Revision 9b56f367 (teuthology): Merge remote-tracking branch 'gh/wip_heartbeat'
- 01:44 AM Revision ec5a1455 (teuthology): ceph_manager: default chance_down to 0.4
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 01:40 AM Revision 566ae533 (teuthology): ceph_manager: add filestore and heartbeat stalls
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 01:24 AM Revision ef1569e5 (teuthology): Use ceph git repo instead of github.
- This code change is so that instead of pulling the tarball of github
which can be unreliable at times it instead uses... - 01:22 AM Revision 0495764b (teuthology): Use ceph git repo instead of github.
- This code change is so that instead of pulling the tarball of github
which can be unreliable at times it instead uses... - 01:22 AM Revision 5d66c9ab (teuthology): Use ceph git repo instead of github.
- This code change is so that instead of pulling the tarball of github
which can be unreliable at times it instead uses...
01/23/2013
- 05:22 PM Bug #3876 (Resolved): workunit: use mirror instead of github
- Fixed to use our git repo instead of github:
https://github.com/ceph/teuthology/commit/399587c966e09de55e165db6181... - 09:24 AM Feature #3901 (Resolved): teuthology: make install a separate task from ceph
01/22/2013
- 11:48 PM Revision e714c778 (teuthology): osd: Testing of deep-scrub omap changes
- Fix scrub_test.py and add omap corruption test
Signed-off-by: David Zafman <david.zafman@inktank.com>
Reviewed-by: S... - 09:09 PM Revision b6e3edc6 (teuthology): test: create /tmp/cephtest/mnt.{id}
- The workunit task assumes that a mount exists
at /tmp/cephtest/mnt.{id}
This patch creates the path if it doesn't
exi... - 04:47 PM Feature #3782: cephmanager task: power cycle targets via ipmi
- I urge you to add status checking and loud error logging. ipmi is not reliable.
- 03:02 PM Feature #3782 (In Progress): cephmanager task: power cycle targets via ipmi
- 05:10 AM Revision 98cc1b83 (teuthology): task: mon_clock_skew_check: add option to run at least one timecheck
- at-least-once Runs at least once, even if we are told to stop.
(default: True)
at...
01/21/2013
- 04:25 PM Revision 2258f60e (teuthology): ceph.conf: separate replicas across osds
- ceph.git master now separates across crush hosts without this setting.
For teuthology clusters, we don't want that (u... - 04:24 PM Revision aeb83ac2 (teuthology): ceph: pass ceph.conf to osdmaptool
- This ensure it sees the chooseleaf option and generates the proper
CRUSH rules.
01/19/2013
- 07:56 PM Feature #3880 (Resolved): suite: the stable release suites are not currently run against upstream...
- argonaut/bobtail suites should be run against upstream stable kernels (specific versions still need to be specified)
01/18/2013
- 09:48 PM Revision 53f22d94 (teuthology): task/mds_thrasher: New task for thrashing the mds
- Signed-off-by: Sam Lang <sam.lang@inktank.com>
- 09:43 PM Bug #3876 (Resolved): workunit: use mirror instead of github
- github is now so unreliable here to be impractical. figure out how to yank the files we need from gitweb, or something.
- 06:47 PM Revision dbc38eff (teuthology): rbd.py: update scratch and test image sizes
- Test 167 was failing due to running out of space on the scratch
file system. The test reserves 21MB in a file, and r... - 01:59 PM Feature #1714: teuthology: use debs instead of /tmp/cephtest
- ...
- 01:49 PM Feature #1714: teuthology: use debs instead of /tmp/cephtest
- Sander Pool wrote:
> Update: apt-get gets the right packages (ceph.list is also updated) but fails due to the non-int... - 01:47 PM Feature #1714: teuthology: use debs instead of /tmp/cephtest
- Update: apt-get gets the right packages (ceph.list is also updated) but fails due to the non-interactive nature of th...
- 01:26 PM Feature #3868 (Rejected): Remote execution needs a way to get your hands on command output
- That is indeed easy, thanks.
- 01:24 PM Feature #3868: Remote execution needs a way to get your hands on command output
- With StringIO its just:
fooproc = remote.run(args=['echo', 'foo'], wait=False, stdout=StringIO())
output = foopro... - 11:44 AM Feature #3868: Remote execution needs a way to get your hands on command output
- Yeah, I tried to make that work. It expects a file object which isn't very friendly. I'm adding a string object handler.
- 11:42 AM Feature #3868: Remote execution needs a way to get your hands on command output
- You can use the stdin/stdout/stderr parameters to run. Its not
documented well (or at all), but there are examples ... - 11:30 AM Feature #3868 (Rejected): Remote execution needs a way to get your hands on command output
- It's hard to believe this isn't possible right now but the code in run.py makes it much too hard (or impossible) to g...
- 11:01 AM Bug #3864 (Resolved): rbd.py: xfstests 167 fails due to ENOSPC
- (Sage: I don't think so. 184 is the likely problem.)
I updated the sizes to 1200 MB and tested it once more and
... - 10:47 AM Bug #3864: rbd.py: xfstests 167 fails due to ENOSPC
- YAY! Does this mean we can reenable the various tests that follow that we've been disabling? :)
- 10:44 AM Bug #3864: rbd.py: xfstests 167 fails due to ENOSPC
- I did a test run of just test 167 and reproduced the problem.
I then had it use a 1200MB rbd image and that caused... - 10:42 AM Bug #3864 (Resolved): rbd.py: xfstests 167 fails due to ENOSPC
- I'm not sure why this started happening now, but after
updating the rbd client to be based on Linux 3.8-rc4
test 16... - 04:28 AM Revision cc049659 (teuthology): Merge branch 'wip-buck-localized-reads' of https://github.com/cep...
- 04:27 AM Revision 83c32540 (teuthology): Making suggested changes.
- Signed-off-by: Joe Buck <jbbuck@gmail.com>
- 03:52 AM Revision c08a57b4 (teuthology): Making suggested changes.
- Signed-off-by: Joe Buck <jbbuck@gmail.com>
01/17/2013
- 08:27 PM Revision cd09be6a (teuthology): ceph: pass ceph.conf to osdmaptool
- This ensure it sees the chooseleaf option and generates the proper
CRUSH rules. - 05:29 PM Revision 53e674bd (teuthology): task/mds_thrasher: New task for thrashing the mds
- Signed-off-by: Sam Lang <sam.lang@inktank.com>
- 05:14 AM Revision fbf6eae2 (teuthology): test: enable localized-reads flag for ceph-fuse
- Changes to the ceph-fuse task to allow the enabling
of --localized-reads.
Signed-off-by: Joe Buck <jbbuck@gmail.com> - 04:48 AM Revision 72db1a59 (teuthology): When running teuthology with targets provisionned on OpenStack an...
- Signed-off-by: Loic Dachary <loic@dachary.org>
01/16/2013
- 06:30 PM Feature #3823 (Duplicate): QA: Capture teuthology test run status in database
- same as #3792
- 02:54 PM Feature #3823 (Duplicate): QA: Capture teuthology test run status in database
- The status of teuthology test runs should be captured for metrics.
- 03:05 PM Feature #3825 (Need More Info): Create an s3 /swift load generator
- The load generator should have a configurable file size or range of sizes and configurable percentage of upload to do...
- 03:01 PM Feature #3824 (New): QA: Provision qa tools to test targets
- Need a consistent process for provisioning new test systems with testing tools. Xstudio agent, swatch, iogen, test sc...
- 02:52 PM Feature #3822 (Rejected): QA: Create "trouble maker" scripts for testing
- create scripts to fail specific OSD, MON and MDS for a duration of time and at some defined repetative frequency. Th...
- 09:18 AM Feature #3814: qa: test environment for a cluster/public networking setup
- The planas and burnupis actually do have the network for this... it's just a matter of adding hte public/cluster netw...
- 06:33 AM Feature #3814 (New): qa: test environment for a cluster/public networking setup
- We need tests that run on a ceph cluster where the osds/mons/mdss are configured on a separate cluster network, and t...
01/15/2013
- 11:40 PM Revision 5b79e921 (teuthology): test: create /tmp/cephtest/mnt.{id}
- The workunit task assumes that a mount exists
at /tmp/cephtest/mnt.{id}
This patch creates the path if it doesn't
exi... - 10:07 PM Revision c8a9a9a8 (teuthology): Add cram task
- This runs cram tests, which are an easy way to test output
stays consistent. We already use cram for basic cli tests ... - 04:52 PM Feature #2814 (Resolved): downburst: support creating vms for debian squeeze 6.0
- This is done. Created a 64-bit cloud-init image for debian squeeze (6.0) to be used with downburst (no 32-bit for now).
- 01:42 PM Feature #1714: teuthology: use debs instead of /tmp/cephtest
- Thanks for your comments. Good to know both are viable options. I'm now experimenting with overlayfs and chroot. Afte...
- 01:38 PM Feature #1714: teuthology: use debs instead of /tmp/cephtest
- I think either wget + dpkg -i on the debs, or apt-get would work. Either way, we need to remove --purge the packages...
- 10:36 AM Feature #1714: teuthology: use debs instead of /tmp/cephtest
- I think you can use the apt sources list stuff to do this. http://www.ceph.com/docs/master/install/debian/#developme...
- 10:09 AM Feature #1714: teuthology: use debs instead of /tmp/cephtest
- Proposed steps for installing a specific set of debian packages:
@- using existing logic to determine sha1 key use w... - 08:41 AM Feature #1714 (In Progress): teuthology: use debs instead of /tmp/cephtest
- Ok, I can now assign bugs. Or maybe I always could but I didn't know how.
- 08:39 AM Feature #1714: teuthology: use debs instead of /tmp/cephtest
- Yes, I'm also concerned about that. I already made notes to make sure the start-up works correctly after the install ...
- 07:03 AM Feature #1714: teuthology: use debs instead of /tmp/cephtest
- Just a heads up, I think there are quite a few tasks now that assume /tmp/cephtest exists. I've been assuming that i...
- 12:14 AM Revision 71097b7b (teuthology): Revert "task/kclient: chmod root to 1777."
- This reverts commit f17847e537802671c6f90bd1a0cdaa0e9d1e6f7a. It had
a typo and we hopefully don't need it.
Signed-o...
01/14/2013
- 10:05 PM Feature #1714: teuthology: use debs instead of /tmp/cephtest
- You're not sure you're allowed, or you tried and it doesn't work? The answer is "yes", and "if so we'll fix it"
- 01:56 PM Feature #2810 (Resolved): downburst: support creating i386 vms
- This has been completed. Currently only images exist for ubuntu (precise/quantal) as those ones are already made by u...
- 06:52 AM Revision 92a9d9c2 (teuthology): ceph.conf: separate replicas across osds
- ceph.git master now separates across crush hosts without this setting.
For teuthology clusters, we don't want that (u...
01/11/2013
- 01:42 PM Cleanup #3791: Go through teuthology readme and make it reflect reality
- keys in example.yaml should be /etc/ssh/ssh_host_rsa_key.pub
- 12:15 PM Cleanup #3791: Go through teuthology readme and make it reflect reality
- - add "check-locks: false" to example.yaml
- add section to create ~/.teuthology.yaml with nothing in it.
- explai... - 10:33 AM Cleanup #3791 (Resolved): Go through teuthology readme and make it reflect reality
- Been trying to run teuthology against my cluster using the provided documentation but it's inadequate. Not sure yet i...
- 10:45 AM Feature #3792: Insert teuthology tests and results into Xstudio
- Should have assigned this to myself, not allowed to do this now.
- 10:41 AM Feature #3792 (Closed): Insert teuthology tests and results into Xstudio
- It isn't clear that Xstudio actually supports this as-is. My current plan is to manipulate the SQL database directly.
- 10:39 AM Feature #3093: teuthology: support multiple pools of machines
- I think this is lower in priority than getting results from theuthology into Xstudio or otherwise tracked. Please ass...
- 10:37 AM Feature #1714: teuthology: use debs instead of /tmp/cephtest
- I tried to assign this to myself but I'm not sure I'm allowed.
- 02:04 AM Revision 9e4a3f03 (teuthology): Merge remote-tracking branch 'gh/wip-3633'
01/10/2013
- 04:02 PM Feature #3783 (Resolved): osdthrasher: power cycle osds
- 04:01 PM Feature #3782 (Resolved): cephmanager task: power cycle targets via ipmi
- 04:00 PM Feature #3781 (Resolved): teuthology: dynamically create targets via downburst
- This would presumably be based on some parameter specifying which "type" of target we want. Maybe that will be the s...
01/08/2013
- 06:11 PM Revision f17847e5 (teuthology): task/kclient: chmod root to 1777.
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 04:16 PM Bug #3767 (Resolved): teuthology: stale jobs detected
- In the nightly runs, we currently see "stale jobs detected" which means,the initial check by teuthology to find if th...
- 04:07 PM Revision f8958463 (teuthology): task/mpi: Allow working directory to be specified
- Signed-off-by: Sam Lang <sam.lang@inktank.com>
- 03:34 PM Revision 16248121 (teuthology): task: A task to setup mpi
- Signed-off-by: Sam Lang <sam.lang@inktank.com>
- 03:33 PM Revision e88c0fc8 (teuthology): task/ceph-fuse: chmod root to 1777
- Signed-off-by: Sam Lang <sam.lang@inktank.com>
- 03:32 PM Revision 4ed20ae8 (teuthology): task/pexec: Add barrier capability
- This patch adds the ability to barrier between
parallel exec tasks so that all tasks will perform
the following step ... - 03:31 PM Revision 35320083 (teuthology): task/pexec: More fixes for all case, exec on hosts
- We don't want to do an exec per role, but per-host. We
were already doing an exec per host, but the names were confu... - 03:29 PM Revision 081a80f8 (teuthology): task/pexec: Fix when 'all' is used
- Signed-off-by: Sam Lang <sam.lang@inktank.com>
- 03:25 PM Revision d44fb147 (teuthology): radosgw-admin.py: Increase test coverage to current admin feature...
- Signed-off-by: caleb miles <caleb.miles@inktank.com>
01/04/2013
- 06:16 PM Revision 620dd551 (teuthology): task: mon_clock_skew_check.py: Check for clock skews on the monitors
- Will run for as long as teuthology runs. By default, fails if any clock
skews higher than 0.05 seconds are detected, ... - 05:03 PM Revision e88b909a (teuthology): task: ceph_manager: add 'get_mon_health' function
- Signed-off-by: Joao Eduardo Luis <jecluis@gmail.com>
01/03/2013
- 11:04 PM Revision 5ce47c2a (teuthology): ssh_keys.py: pull the keys out of targets entry
- rather than the hosts known hosts file.
Signed-off-by: Joe Buck <jbbuck@gmail.com>
Reviewed-by: Sam Lang <sam.lang@i... - 04:44 AM Revision 9ca69e73 (teuthology): ceph: malloc check =3 means we hear on stderr too
01/02/2013
12/31/2012
- 04:11 PM Revision ed586c1b (teuthology): task: ceph: don't wait for 'healthy' if 'wait-for-healthy' is false.
- This new config option obviously defaults to 'true' in order to not only
maintain compatibility, but because it makes...
12/29/2012
Also available in: Atom