Commit Graph

685 Commits

Author SHA1 Message Date
Sage Weil
b97c3803c5 rados/thrash: rejection backfill reservations sometimes while thrashing 2014-04-03 18:11:01 -07:00
Sage Weil
946a9685f1 rados/singleton-nomsgr: add multi-backfill reservation rejection test
This triggers #7922.

Signed-off-by: Sage Weil <sage@inktank.com>
2014-04-03 18:08:19 -07:00
Sage Weil
0f6c92f076 Merge pull request #23 from ceph/wip-7771-wusui
FIxed dumpling - emperor upgrade suites
2014-04-03 15:11:05 -07:00
Sage Weil
39166b2d34 upgrade/dumpling-x: run dumpling version of s3tests
Signed-off-by: Sage Weil <sage@inktank.com>
2014-04-03 14:22:32 -07:00
Warren Usui
a60b50d61d FIxed dumpling - emperor upgrade suites
Reformatted many of the yaml files.
Fixed duplication of workunit definitions.
Do not do install.upgrade on clients.
Included branch: definition in final workload files.

Signed-off-by: Warren Usui <warren.usui@inktank.com>
2014-04-03 13:02:36 -07:00
Sage Weil
267307e601 upgrade/dumpling-emperor-x: do not warn about tunables
We do the same for dumpling-x.

Signed-off-by: Sage Weil <sage@inktank.com>
2014-04-03 11:42:52 -07:00
Sage Weil
a5a5ba3c84 upgrade/dumpling-emperor-x: ignore 'scrub mismatch' from mon
The encoded full osdmaps can differ due to a series of issues that were
fixed well after emperor.  We also whitelist this for dumpling-x.

Signed-off-by: Sage Weil <sage@inktank.com>
2014-04-03 11:42:36 -07:00
Sage Weil
552f9d8dee multimds: test ceph-fuse and kclient
Add client as a variable on the basic collection.  Move the other stuff
(libcephfs plus a weird restart test) to libcephfs collection.

Signed-off-by: Sage Weil <sage@inktank.com>
2014-04-02 17:13:39 -07:00
Sage Weil
48c36dc399 Merge pull request #21 from ceph/wip-thrash-affinity
krbd, kcephfs: trash osd primary-affinity
2014-03-31 20:47:24 -07:00
Sage Weil
06cab8b037 Merge pull request #22 from ceph/wip-fuse-permission
multimds: fuse_default_permissions = 0 for kernel build test
2014-03-31 20:46:12 -07:00
Yan, Zheng
2e283ce6d7 multimds: fuse_default_permissions = 0 for kernel build test
This can reduce the test time becuase it avoids sending getattr
request whenever the kernel checks inode permission.

Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
2014-04-01 09:30:27 +08:00
Ilya Dryomov
a536fd13d3 krbd, kcephfs: trash osd primary-affinity
libceph.ko support is in testing and should be in 3.15.  This commit
effectively reverts commit 66ffaa6565 ("kcephfs, krbd: do not thrash
primary-affinity").

Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
2014-03-31 20:34:18 +04:00
Sage Weil
cb699f6a1a rados/monthrash: shorten mon pings so that freezing triggers reconnects
This exercises (tho it doesn't necessarily verify) the mon ping reconnect
code when the thrasher freezes the mons.

See #7888.

Signed-off-by: Sage Weil <sage@inktank.com>
2014-03-28 16:17:00 -07:00
Josh Durgin
9f3a66440a rgw_pool_type: remove accidentally added empty file
Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
2014-03-28 10:28:14 -07:00
Sage Weil
5651ee8131 upgrade/dumpling-x/parallel: restart after cuttlefish->dumpling upgrade
Fixes: #7824
Signed-off-by: Sage Weil <sage@inktank.com>
2014-03-27 17:58:09 -07:00
Samuel Just
68343ee193 rados/thrash/workloads: make cache-agent-big use an ec base pool
Signed-off-by: Samuel Just <sam.just@inktank.com>
2014-03-27 11:51:44 -07:00
Josh Durgin
b454bd6cb5 rgw: add erasure coded data pool variant
Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
2014-03-26 20:01:40 -07:00
Josh Durgin
bf90414a9e rgw: set max-entries to 10 for data sync test
This way it tests the agent generating more than max-intries writes to
a bucket.

Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
2014-03-24 15:05:20 -07:00
Sage Weil
798daf5886 upgrade/dumpling-x/stress-split: set fastcgi idle timeout to 2 min
30 seconds isn't enough when combined with osd thrashing.

Fixes: #7702
Signed-off-by: Sage Weil <sage@inktank.com>
2014-03-20 16:51:03 -07:00
Sage Weil
6fd5ca9cff upgrade/dumpling-x/parallel: test cuttlefish->dumpling starting point
Maybe this will trigger #7519.  And anyway, it's good coverage.

Signed-off-by: Sage Weil <sage@inktank.com>
2014-03-18 21:34:25 -07:00
Sage Weil
0bfc365d2e distros: add rhel 6.4
Signed-off-by: Sage Weil <sage@inktank.com>
2014-03-18 15:19:06 -07:00
Sage Weil
6252d28dc2 distros: add wheezy
Signed-off-by: Sage Weil <sage@inktank.com>
2014-03-18 15:19:06 -07:00
wusui
cb194770e4 Merge pull request #20 from ceph/wip-distros
symlink all distros facets to a common set of 'supported' targets
2014-03-18 15:02:25 -07:00
Sage Weil
a27ead6724 distros: add 14.04 to supported list
Signed-off-by: Sage Weil <sage@inktank.com>
2014-03-18 14:03:37 -07:00
Sage Weil
8d4c4676cb distros: test rhel/centos 6.5 instead of 6.4 2014-03-18 13:55:13 -07:00
Sage Weil
99f4e9dda3 symlink all distros facets to a common set of 'supported' targets
This makes it easier to maintain the supported/tested targets.

Signed-off-by: Sage Weil <sage@inktank.com>
2014-03-18 13:39:13 -07:00
Sage Weil
d7f3eb34d9 knfs: make it a list
Signed-off-by: Sage Weil <sage@inktank.com>
2014-03-18 06:54:48 -07:00
Sage Weil
299766073e knfs: async export
Signed-off-by: Sage Weil <sage@inktank.com>
2014-03-17 18:26:56 -07:00
Sage Weil
a42e197f5d rados/monthrash: add pool create/delete tests
This is sufficient to trigger #7736 when combined with mon thrashing and
mon msg delay injection.

Signed-off-by: Sage Weil <sage@inktank.com>
2014-03-17 16:16:50 -07:00
Sage Weil
eb6cd3a6f4 nkfs: 6h timeout of kernel build
Yes, NFS reexport is slow.  But at the moment appears to be reliable.

Signed-off-by: Sage Weil <sage@inktank.com>
2014-03-17 06:56:36 -07:00
Sage Weil
2c875593c8 multimds: fix misc -> fs/misc paths
Signed-off-by: Sage Weil <sage@inktank.com>
2014-03-15 11:12:46 -07:00
Sage Weil
7597172695 upgrade/dumpling-x/stress-split: tolerate legacy crush tunables
Signed-off-by: Sage Weil <sage@inktank.com>
2014-03-15 09:18:33 -07:00
Josh Durgin
f476c9681b Merge pull request #19 from ceph/wip-print
added print task
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
2014-03-14 15:49:38 -07:00
Yuri Weinstein
752380dc96 added print task 2014-03-14 15:46:04 -07:00
Sage Weil
22c461b501 upgrade/dumpling-x: more mon scrub whitelist
There are two log messages; whitelist them both

Signed-off-by: Sage Weil <sage@inktank.com>
2014-03-14 08:31:59 -07:00
Sage Weil
2e487d8afc knfs: test v3 and v4
Signed-off-by: Sage Weil <sage@inktank.com>
2014-03-14 08:21:47 -07:00
Sage Weil
b125c95fc1 Merge pull request #18 from ceph/wip-knfs-fsstress
knfs: add fsstress and kernel build
2014-03-13 19:12:42 -07:00
Yan, Zheng
4773a27789 knfs: add fsstress and kernel build
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
2014-03-14 09:34:38 +08:00
Sage Weil
e1694b4c60 knfs: restructure a bit
Separate cluster buildup from tasks.

Signed-off-by: Sage Weil <sage@inktank.com>
2014-03-13 17:42:51 -07:00
Sage Weil
7b0eda03ee nfs -> knfs
Signed-off-by: Sage Weil <sage@inktank.com>
2014-03-13 17:39:32 -07:00
Sage Weil
adca646413 workunits/misc -> fs/misc
Signed-off-by: Sage Weil <sage@inktank.com>
2014-03-13 17:36:05 -07:00
Sage Weil
8b4c8cbf1a upgrade/dumpling-x: whitelist mon scrub mismatch
A mixed dumpling/firefly cluster will have each mon independently encode
the full map.  Firefly now puts feature bits in the Incremental so that
we encode the "right" way, but dumpling doesn't have that capability
yet, and we don't plan to backport it.

Fixes: #7704
Signed-off-by: Sage Weil <sage@inktank.com>
2014-03-13 16:27:56 -07:00
Sage Weil
efdee0d31c upgrade/dumpling-x: upgrade final client node for final test
This means the final workloads are running firefly code.

Signed-off-by: Sage Weil <sage@inktank.com>
2014-03-12 15:37:13 -07:00
Sage Weil
7fb5e14691 upgrade/dumpling-x: full librados tests after full upgrade
Signed-off-by: Sage Weil <sage@inktank.com>
2014-03-12 14:49:54 -07:00
Sage Weil
d5442a57b5 multimds: new (separate) suite for multi-mds tests
Eventually we can merge this into the fs suite, but for now it is useful
to segregate the test cases.

Start with a dup of basic and verify sections; add others later.

Signed-off-by: Sage Weil <sage@inktank.com>
2014-03-11 21:11:42 -07:00
Sage Weil
88efa65e6c Revert "fs/basic: multimds"
This reverts commit aea501beb7.

Let's put this in a separate subdir for now.  It won't pass on firefly because
the libcephfs changes aren't there.
2014-03-11 21:07:44 -07:00
Sage Weil
a18cd6ddba Merge remote-tracking branch 'gh/firefly' 2014-03-11 19:16:52 -07:00
Sage Weil
cfbbcf7c08 upgrade/dumpling-x/stress-split: use dumpling workunits
Signed-off-by: Sage Weil <sage@inktank.com>
2014-03-11 19:16:39 -07:00
Sage Weil
c0b1c1070f Merge pull request #16 from ceph/wip-hint-tests
rados/singleton-nomsgr: add allocation hint test

Reviewed-by: Sage Weil <sage@inktank.com>
2014-03-11 18:11:05 -07:00
wusui
1a9f6c32c8 Merge pull request #17 from ceph/wip-final_load_fix
fixed final_load problem
2014-03-11 16:00:28 -07:00