Activity
From 01/28/2013 to 02/26/2013
02/26/2013
- 06:57 PM Bug #4255: osdc/ObjectCacher.cc: 517: FAILED assert(i->empty())
- recent log: ubuntu@teuthology:/a/teuthology-2013-02-25_01:00:05-regression-master-testing-gcov/11554
2013-02-25T03... - 02:56 PM Bug #4272 (Resolved): rbd snap rollback broken on next
- commit:f58601d681d3aee6541119ab830ba5e2a9ec3a13
- 12:23 PM Bug #4272 (Resolved): rbd snap rollback broken on next
- ...
- 11:12 AM Cleanup #4262 (Fix Under Review): libceph: drop redundant page info assignments
- 05:12 AM Bug #4242: krbd: xfstest 259 failure (FS size near 4TB)
- Of course it's not going to be easy... The problem showed up
this time at offset 2199533527040 instead of 219953839...
02/25/2013
- 07:12 PM Bug #4237 (Resolved): krbd: ignore zero-length requests
- This has been committed.
commit 4dda41d3d76747414586a4bad5615b550e0986b1
Author: Alex Elder <elder@inktank.com>
... - 07:11 PM Bug #4238 (Resolved): krbd: still more barrier fixes
- This has been committed.
commit 632b88cadece050ca925d74bda250c4a320c5cc7
Author: Alex Elder <elder@inktank.com>
... - 07:11 PM Bug #4235 (Resolved): krbd: add some dout() trace calls
- This has been committed.
commit 37206ee5bede14d59306fea3af4c0105d4712342
Author: Alex Elder <elder@inktank.com>
... - 07:10 PM Cleanup #4234 (Resolved): libceph: encapsulate flag setting
- This has been committed.
commit c9ffc77adebf9dfe3026ede6c8b3c61586b485b7
Author: Alex Elder <elder@inktank.com>
... - 07:09 PM Bug #4184 (Resolved): krbd: fix some sparse problems
- Josh reviewed these patches, and I have updated, re-tested
and committed them.
cc344fa rbd: eliminate sparse warn... - 07:01 PM Feature #3190 (Resolved): qa: test fencing
- commit:ccdafa067afed74b209537ae45ff8b49bb5fab3b
- 05:49 PM Bug #4249 (Resolved): librbd: recursive lock of snap_lock during snap_rollback
- commit:9096d70642880946b0b477e33f7debabbefec9fa
- 12:26 PM Bug #4249 (Fix Under Review): librbd: recursive lock of snap_lock during snap_rollback
- wip-4249
- 05:41 PM Bug #4252 (Resolved): rbd python bindings: error removing image on list_children
- commit:21471c1ef4cf02e068a6e6c49cd41e95efec952a
- 04:46 PM Bug #4252 (Fix Under Review): rbd python bindings: error removing image on list_children
- wip-4252, test broke with the watch-notify changes
- 04:02 PM Bug #4252 (In Progress): rbd python bindings: error removing image on list_children
- 05:08 PM Bug #4242: krbd: xfstest 259 failure (FS size near 4TB)
- The output did not indicate that rbd thought it
did something wrong.
That is, the object request came back and in... - 04:08 PM Bug #4242: krbd: xfstest 259 failure (FS size near 4TB)
- Requests to write 4096 bytes came back from the osd with a
written count of 2048 bytes.
Now I'm afraid I have to ... - 01:23 PM Bug #4242: krbd: xfstest 259 failure (FS size near 4TB)
- > BTW fixed the rbd namer thing; pull latest teuthology.git.
Well, "fixed" is generous. It had a bug, which I've ... - 12:09 PM Bug #4242: krbd: xfstest 259 failure (FS size near 4TB)
- BTW fixed the rbd namer thing; pull latest teuthology.git.
- 11:12 AM Bug #4242: krbd: xfstest 259 failure (FS size near 4TB)
- I was reporting if an error code got returned from
the osd. However the loop device function that
reports the "Wri... - 11:04 AM Bug #4242: krbd: xfstest 259 failure (FS size near 4TB)
- The tests I started running this morning finally hit number 259.
It did have the problem, but I got no messages from... - 09:09 AM Bug #4242 (In Progress): krbd: xfstest 259 failure (FS size near 4TB)
- I tried to reproduce this with a smaller subset of tests
(just 258 and then 259 repeatedly) over the weekend but
th... - 04:58 PM Tasks #4210 (Rejected): get ceph and all libraries versions+patches in EPEL
- EPEL does not take packages already in RHEL.
- 03:43 PM Subtask #4263 (Fix Under Review): libceph: clearly abstract message data operations
- These patches have been posted for review.
[PATCH 0/4] libceph: abstract setting message data info
[PATCH 1/4] li... - 03:33 PM Subtask #4263 (Resolved): libceph: clearly abstract message data operations
- Currently the fields in a message structure related
what constitutes the data portion of a message are
manipulated ... - 03:15 PM Cleanup #4262: libceph: drop redundant page info assignments
- These patches have been posted for review (marking
this "Feedback").
[PATCH 0/3] libceph: focus calc_layout() on ... - 03:03 PM Cleanup #4262: libceph: drop redundant page info assignments
- Three patches implement this change. The net result is
that calc_layout() becomes focused only on filling in the
o... - 02:53 PM Cleanup #4262 (Resolved): libceph: drop redundant page info assignments
- In calc_layout(), there are some assignments to osd request
fields r_num_pages and r_page_alignment. These assignme... - 03:14 PM Bug #4240 (Fix Under Review): libceph: fix a osd request memory leak
- This has been posted for review.
[PATCH] libceph: fix a osd request memory leak - 12:27 PM Bug #4255 (Duplicate): osdc/ObjectCacher.cc: 517: FAILED assert(i->empty())
02/23/2013
- 08:43 PM Bug #4255 (Duplicate): osdc/ObjectCacher.cc: 517: FAILED assert(i->empty())
- ...
- 12:08 PM Bug #4252 (Resolved): rbd python bindings: error removing image on list_children
- ...
- 08:31 AM Bug #4249 (Resolved): librbd: recursive lock of snap_lock during snap_rollback
- ...
02/22/2013
- 06:44 PM Bug #4242: krbd: xfstest 259 failure (FS size near 4TB)
- I"m seeing this fairly consistently now.
- 01:03 PM Bug #4242: krbd: xfstest 259 failure (FS size near 4TB)
- Whoops, it was 4 TB (2^42) not 4 GB.
I'll update what I originally wrote shortly. - 01:00 PM Bug #4242 (Closed): krbd: xfstest 259 failure (FS size near 4TB)
- I have now seen this at least twice. I think it's inconsistent
but it might be important. Not marking it high yet,... - 03:33 PM Bug #3958 (Resolved): rbd fsx fails with EBUSY
- 03:14 PM Bug #1070 (Rejected): krbd: ^C doesn't work
- Yeah, marking rejected. thanks for digging in!
- 03:08 PM Bug #1070: krbd: ^C doesn't work
- I can't relate them but this is involved in at
least some of the code involved:
http://tracker.ceph.com/issues/38... - 02:24 PM Fix #3665 (Resolved): librbd: deadlock during flatten
- commit:e4fd70fcec3a9abb7f19517326e46f58031c4196
- 02:13 PM Bug #913 (Resolved): krbd: handle race between notify and rbd device shutdown
- This is very old. And--provided I understand it--it is resolved
in the current rbd code.
When a mapped rbd image... - 01:50 PM Bug #4244 (Resolved): rbd xfstests: re-enable xfstests 049 in nightly run
- Pushed to ceph-qa-suite/master....
- 01:38 PM Bug #4244 (Resolved): rbd xfstests: re-enable xfstests 049 in nightly run
- Running test 049 repeatedly is passing for me now. I'm not sure
when or how it got fixed but I'm going to re-enable... - 01:40 PM Bug #2572 (Resolved): krbd: writeback errors?
- I've run xfstests 49 a bunch of times consecutively
and I am no longer seeing this issue.
I'm about to run it 100... - 01:23 PM Bug #2700: blkdeviotune method at libvirt doesn`t work on RBD volumes
- Just checked, problem with blkdeviotune still exists in the 1.0.2.
- 11:53 AM Bug #2700: blkdeviotune method at libvirt doesn`t work on RBD volumes
- This is something that we should fix. Is it still an issue in current libvirt?
- 01:20 PM Bug #2654 (Resolved): Stale rbd volume cannot be unmaped
- Somewhere along the way, this got fixed....
- 01:15 PM Bug #4243 (Resolved): rbd cli: usage confusing for snapshot operations
- The correct usage for creating a snapshot seems to be:...
- 12:05 PM Bug #3939 (Duplicate): krbd: circular locking report in sysfs code
- Duplicate of 3925. I *did* write it up before.
- 12:02 PM Bug #3950 (Can't reproduce): krbd: new assertion failure running concurrent rbd test
- Not seeing this in current code.
- 11:59 AM Bug #3871 (In Progress): krbd: initial header read may be out of date
- 11:58 AM Bug #3743 (Won't Fix): krbd: errors on submitted requests are ignored
- This was found in old request code and therefore will not be fixed.
- 11:38 AM Bug #3936 (Rejected): rbd: Strange dd speed behaviour (server side issue?)
- Network issue.
- 11:37 AM Bug #3664: osdc/ObjectCacher.cc: 517: FAILED assert(!i->size())
- Need to reproduce with:...
- 11:35 AM Bug #3697 (Duplicate): rbd copy.sh test failing in nightly
- #3958
- 11:34 AM Bug #3980 (Won't Fix): rbd image created with size zero on a mixed cluster crashes rbd
- Problem not in Bobtail and future releases. Won't fix.
- 11:32 AM Bug #3524 (Duplicate): test_librbd_fsx: crash after flatten
- Same as #3665
- 11:26 AM Bug #3703 (Can't reproduce): osd: crash while encrypting
- 11:12 AM Bug #4240 (Resolved): libceph: fix a osd request memory leak
- If an invalid layout is provided to ceph_osdc_new_request(), its
call to calc_layout() might return an error. At th... - 09:39 AM Bug #4184: krbd: fix some sparse problems
- Forgot to set target version.
- 09:38 AM Bug #4184 (Fix Under Review): krbd: fix some sparse problems
- Re-posted for review. The patches have been re-based on
top of fixes for 4234, 4235, 4237, and 4238. - 09:37 AM Cleanup #4234: libceph: encapsulate flag setting
- Posted for review. (Marked this as "Feedback" because
I can't mark a cleanup issue "need review")... - 06:22 AM Cleanup #4234 (In Progress): libceph: encapsulate flag setting
- Forgot to indicate this was underway.
- 06:02 AM Cleanup #4234 (Resolved): libceph: encapsulate flag setting
- While working on http://tracker.ceph.com/issues/4079 I created
some helper routines to wrap around the code that tes... - 09:36 AM Bug #4235 (Fix Under Review): krbd: add some dout() trace calls
- Posted for review....
- 06:23 AM Bug #4235 (Resolved): krbd: add some dout() trace calls
- While working on http://tracker.ceph.com/issues/4079 I added
some calls to dout() to some of the new request code. ... - 09:36 AM Bug #4238 (Fix Under Review): krbd: still more barrier fixes
- Posted for review....
- 07:21 AM Bug #4238 (Resolved): krbd: still more barrier fixes
- While looking at http://tracker.ceph.com/issues/4079 I
concluded that the fix I put in for this might still
not be ... - 09:35 AM Bug #4237 (Fix Under Review): krbd: ignore zero-length requests
- Posted for review....
- 06:40 AM Bug #4237 (Resolved): krbd: ignore zero-length requests
- The old request code simply ignored zero-length requests
as soon as they were seen. The new request code currently
... - 06:41 AM Feature #4236: krbd: properly handle flush commands
- Note that http://tracker.ceph.com/issues/4237 describes
making the new request code ignore all zero-length commands.... - 06:38 AM Feature #4236 (Duplicate): krbd: properly handle flush commands
- REQ_FLUSH and REQ_FUA are intended to implement drive
cache flushes and barrier semantics. I don't know
precisely ... - 02:45 AM Feature #4231 (Closed): librbd: Java bindings
- As it seems right now the new CloudStack code will require more complex RBD operations which can not be accomplished ...
02/21/2013
- 06:16 PM Fix #3665 (Fix Under Review): librbd: deadlock during flatten
- wip-rbd-flatten-deadlock
- 03:50 PM Bug #4186: rbd: add another "udevadm settle" in the CLI
- awesome, I fixed this without even knowing it existed! :)
- 02:50 PM Bug #3737: Higher ping-latency observed in qemu with rbd_cache=true during disk-write
- I've looked at the logs, and I think #4091 should fix this. The high ping times tend to occur around when the cache f...
02/20/2013
- 11:20 PM Bug #3737: Higher ping-latency observed in qemu with rbd_cache=true during disk-write
- Sigh. The attachment might help...
- 11:18 PM Bug #3737: Higher ping-latency observed in qemu with rbd_cache=true during disk-write
- Confirmed here, with ceph-0.56.3 and qemu-1.3.1.
See attached test output.
A summary is, the average ping time,... - 09:15 PM Bug #3958 (In Progress): rbd fsx fails with EBUSY
- reproducing with logs, vapre f.yaml.out, to confirm this is just the osd's EBUSY. which we should fix.
- 12:50 PM Cleanup #4053 (Resolved): ceph: cleanup ceph page vector functions
- Committed to the testing branch.
9e0eb85 ceph: remove a few bogus declarations
b324814 libceph: use void pointers... - 12:49 PM Subtask #4007 (Resolved): libceph: support STAT osd operation
commit fbfab53966b279f9cdb36b96ffa1e22f042c96ff
Author: Alex Elder <elder@inktank.com>
Date: Fri Feb 8 09:55:48...- 12:42 PM Fix #3665 (In Progress): librbd: deadlock during flatten
- 11:26 AM Feature #4211 (Rejected): get good qemu, libvirt versions+patches in CentOS+
- 11:26 AM Tasks #4210 (Resolved): get ceph and all libraries versions+patches in EPEL
02/19/2013
- 02:34 PM Feature #2770 (In Progress): krbd: define tasks to add osd_client compound class op support
- 02:23 PM Feature #2770 (Resolved): krbd: define tasks to add osd_client compound class op support
- 02:22 PM Feature #4021 (Resolved): rbd: openstack: add ability to copy volume to image for rbd
- 02:20 PM Feature #4195 (Duplicate): rbd: migrate an active image between pools
- 11:40 AM Subtask #4007: libceph: support STAT osd operation
- Josh has reviewed this. Testing again before committing
to be included in the testing branch. - 11:39 AM Cleanup #4053: ceph: cleanup ceph page vector functions
- Josh has reviewed these, and I've rebased them onto
the top of the testing branch. I'm going to test some
before u... - 10:36 AM Bug #4184 (In Progress): krbd: fix some sparse problems
- I have resolved all of the reports that remain in the
code currently in the testing branch. There are a
few report... - 08:57 AM Bug #4183 (Resolved): rbd: EBUSY on unmap right after io
- commit:45a4fe09151bcdeaaa2c3b5dbd089a91deaa055f
- 08:45 AM Bug #4186 (Resolved): rbd: add another "udevadm settle" in the CLI
- commit:8ca2274cc09c6a9925cbe86ccaf68db7898956e8
- 05:06 AM Bug #4186: rbd: add another "udevadm settle" in the CLI
- The change looks good to me.
Reviewed-by: Alex Elder <elder@inktank.com>
02/18/2013
- 08:37 PM Bug #4186 (Fix Under Review): rbd: add another "udevadm settle" in the CLI
- see wip-4186
- 06:04 PM Bug #4186 (Resolved): rbd: add another "udevadm settle" in the CLI
- In http://tracker.ceph.com/issues/4183 it was reported that
unmapping an image was failing because it was busy.
F... - 06:10 PM Bug #4183 (In Progress): rbd: EBUSY on unmap right after io
- Reassigning to Sage.
Sage, I see you've been working on ceph qa/rbd/map-snapshot-io.sh
and I don't want to interf... - 06:05 PM Bug #4183: rbd: EBUSY on unmap right after io
- ...
- 06:04 PM Bug #4183: rbd: EBUSY on unmap right after io
- OK, I think I understand now.
It turns out that "blkid" is running again on the
device after its final close. Th... - 05:51 PM Bug #4183: rbd: EBUSY on unmap right after io
- We now are very careful about allowing an image to be unmapped
if it's still open, whereas previously we would allow... - 11:24 AM Bug #4183: rbd: EBUSY on unmap right after io
- NOTE: I adjusted the test to add the sleep 1 until this is fixed.
- 11:23 AM Bug #4183 (Resolved): rbd: EBUSY on unmap right after io
- the map-snapshot-io.sh does...
- 05:13 PM Bug #4184 (Resolved): krbd: fix some sparse problems
- The Linux kernel has a tool called "sparse" that scans
the source tree and reports various code problems that
the c... - 05:07 PM Cleanup #4164 (Resolved): libceph: update rados.h and related code
- commit 0315a7770983bbe69211efed1aaee08324acd54c
Author: Alex Elder <elder@inktank.com>
Date: Fri Feb 15 11:42:30 ... - 05:05 PM Subtask #4126 (Resolved): kernel osd client: kill off some dead code
- 87f979d ceph: kill ceph_osdc_writepages() "nofail" parameter
fbf8685 ceph: kill ceph_osdc_writepages() "dosync" para... - 05:01 PM Cleanup #4165 (Resolved): libceph: update ceph_fs.h and related code
- commit dd6f5e105d85e02bc41db0891eb07152b1746ad9
Author: Alex Elder <elder@inktank.com>
Date: Fri Feb 15 11:42:30 ...
02/16/2013
- 09:11 AM Cleanup #4165: libceph: update ceph_fs.h and related code
- The following have been posted for review to resolve
this issue.
[PATCH 0/2] libceph: update ceph_fs.h and relate... - 08:11 AM Cleanup #4165: libceph: update ceph_fs.h and related code
- (Another related commit)
libceph: update ceph_mds_state_name() and ceph_mds_op_name()
Update ceph_mds_state_nam... - 08:10 AM Cleanup #4165 (Resolved): libceph: update ceph_fs.h and related code
- (This work is done. I'm just documenting it because it's really
distinct from http://tracker.ceph.com/issues/4126.)... - 09:10 AM Subtask #4126 (Fix Under Review): kernel osd client: kill off some dead code
- (Oops, I forgot to mark this in progress yesterday.)
The following have been posted for review to resolve this
is... - 08:58 AM Cleanup #4164: libceph: update rados.h and related code
- The following have been posted for review to resolve this:
[PATCH 0/3] libceph: update rados.h and related code (4... - 08:07 AM Cleanup #4164: libceph: update rados.h and related code
- (Another commit related to this.)
libceph: update ceph_osd_op_name()
Update ceph_osd_op_name() to include the n... - 08:06 AM Cleanup #4164: libceph: update rados.h and related code
- (Another commit related to this.)
libceph: add ceph_osd_state_name()
Add the definition of ceph_osd_state_name(... - 08:05 AM Cleanup #4164 (Resolved): libceph: update rados.h and related code
- (This work is done, I'm just documenting it because it's really
something distinct from http://tracker.ceph.com/issu... - 08:29 AM Cleanup #4163: libceph: improve packing in struct ceph_osd_req_op
- This has been posted for review.
[PATCH] libceph: improve packing in struct ceph_osd_req_op - 08:00 AM Cleanup #4163 (Resolved): libceph: improve packing in struct ceph_osd_req_op
- (This is done, just documenting it because it's not directly
related to http://tracker.ceph.com/issues/4126)
The ...
02/15/2013
- 01:59 PM Cleanup #4156 (Resolved): qa: don't chown rbd stuff in rbd/* workunits
- Once we are doing proper installs, we can call sudo as needed and not worry about $PATH etc.
02/14/2013
- 05:03 PM Subtask #3272: send/receive rbd snapshots
- From Sage - "I think this breaks down into a few different pieces:
1) Decide what output format to use. We want t... - 05:02 PM Subtask #3387: librbd: expose changed objects since a given snapshot
- 8 points
- 04:25 PM Feature #4021 (Fix Under Review): rbd: openstack: add ability to copy volume to image for rbd
- 04:25 PM Subtask #4019 (In Progress): rbd: openstack: simplify volume booting with new api: add boot optio...
- 04:12 PM Subtask #4019: rbd: openstack: simplify volume booting with new api: add boot option to volumes
- 3 points
- 04:25 PM Subtask #4020 (In Progress): rbd: openstack: simplify volume booting with new api: make image boo...
- 04:12 PM Subtask #4020: rbd: openstack: simplify volume booting with new api: make image boot button add s...
- 2 points
- 04:24 PM Subtask #4018 (In Progress): rbd: openstack: simplify volume booting with new api: modify boot pa...
- 04:24 PM Feature #4017 (In Progress): rbd: openstack: simplify volume booting with new api
- 04:02 PM Bug #3947 (Resolved): krbd: read zeroing freed bio?
- This got resolved in version 2 of the "new request code,"
which is now present in the testing branch. - 03:12 PM Feature #4136 (Duplicate): rbd xfstests: update list of tests run
- The latest version of xfstests includes tests numbered
up to 296. The last test we run is 278. Some of the
update... - 07:06 AM Subtask #4125: kernel messenger: support multiple sources of data
- Here's a short list of smaller tasks I can identify right
now in order to implement this. I may create a new issue
... - 05:57 AM Subtask #4125 (Resolved): kernel messenger: support multiple sources of data
- We need to allow the osd client to have an array of osd ops
such that each can supply its own buffer for sending and... - 06:25 AM Subtask #4127 (Resolved): kernel osd client: clearly separate read and write data buffers
- The osd client (and messenger) have generally speaking one
field representing *either* the data to be sent *or* the
... - 06:14 AM Subtask #4126 (Resolved): kernel osd client: kill off some dead code
- While looking through how to implement multiple ops I have
noticed that there's some dead code in the osd client, or... - 05:40 AM Subtask #2854: krbd: write path
- This work actually did begin last week, after getting STAT
calls implemented (see http://tracker.ceph.com/issues/400... - 05:35 AM Tasks #2853: krbd: read path
- This work is close to complete, in that I have shown
that a lot of functionality seems to work correctly.
I was n... - 05:24 AM Feature #2770: krbd: define tasks to add osd_client compound class op support
- After the walk through described above, I spent a little more
time thinking about the messenger aspect of allowing m...
02/13/2013
- 06:10 AM Feature #3761: kernel messenger: need to support multiple ops per request
- Here's what I'm prototyping.
I'm going to try to expand the definition of the trail portion of
a message so inste... - 05:12 AM Feature #3761 (In Progress): kernel messenger: need to support multiple ops per request
- In order to support multiple ops for osd requests we're
going to have to do some work on the messenger as well.
I'm...
02/12/2013
- 05:34 PM Bug #4100 (Resolved): rbd: unprotecting a snapshot in the "UNPROTECTING" state fails with EINVAL
- commit:fe283813b44a7c45def6768ea0788a3a0635957e and commit:bfb4482c4596759b464caf45f8f30368898519d8 in bobtail.
- 09:37 AM Bug #4100: rbd: unprotecting a snapshot in the "UNPROTECTING" state fails with EINVAL
- Dan - please review the wip branch.
- 03:52 PM Bug #3958: rbd fsx fails with EBUSY
- ubuntu@teuthology:/a/teuthology-2013-02-11_20:00:06-regression-bobtail-master-basic/4941
- 02:11 PM Feature #2770: krbd: define tasks to add osd_client compound class op support
- The way the osd client handles an object class method right now
assumes that outbound data (headed from the client t... - 10:18 AM Feature #2770: krbd: define tasks to add osd_client compound class op support
- ...
- 10:16 AM Feature #2770: krbd: define tasks to add osd_client compound class op support
- ...
- 11:42 AM Feature #4104: osd_client: support passing page array as data for CALL op
- I guess this needs to be considered an rbd task if it is
to show up as a subtask for 2770. - 11:41 AM Feature #4104 (Resolved): osd_client: support passing page array as data for CALL op
- The rbd object "copyup" operation is defined as a class method
operation. Currently when a class method needs to su... - 12:49 AM Bug #3936: rbd: Strange dd speed behaviour (server side issue?)
- Journal is 1G in RAM. Since there are no writers at all yet, I don't think that journal is filled and causes device s...
- 12:47 AM Bug #3936: rbd: Strange dd speed behaviour (server side issue?)
- Tried on regular 1G ethernet (other client server). Works well. Speed is stable and no such effect.
I don't under...
02/11/2013
- 07:25 PM Bug #4100 (Fix Under Review): rbd: unprotecting a snapshot in the "UNPROTECTING" state fails with...
- wip-snap-unprotect
- 05:34 PM Bug #4100 (Resolved): rbd: unprotecting a snapshot in the "UNPROTECTING" state fails with EINVAL
- As reported on ceph-users, an unprotect earlier was taking too long (possibly due to inactive pgs) and was killed. Th...
- 03:35 PM Feature #4095 (Rejected): rbd: 2-phase commit for snapshot creation
- To ensure snapshots are created as close as possible to when the user intended, instead of just waiting for a notify,...
- 02:33 PM Subtask #4092: rbd: re-read header when watch is re-established
- Yes, I'll create corresponding tasks for krbd once I get the rest of the general ones in.
- 02:09 PM Subtask #4092: rbd: re-read header when watch is re-established
- This same issue would apply to the kernel rbd client also,
right? - 01:32 PM Subtask #4092 (Resolved): rbd: re-read header when watch is re-established
- This avoids races that would result in a snapshot not being created correctly, like:...
- 01:24 PM Subtask #4091 (Resolved): ObjectCacher: optionally make readx/writex calls never block
- The idea is to prevent any aio calls from blocking client (i.e. qemu) threads.
This was what Sage was thinking as ... - 12:41 PM Subtask #4090 (New): rbd: investigate sources of client-side latency
- Some possible sources:
* lock contention
* unnecessary data copying
* contention on queues
* throttling in messen... - 12:39 PM Feature #4089 (Closed): rbd: improve small I/O performance
- Root task for general improvement.
- 12:36 PM Feature #4088 (Resolved): rbd: optionally copy-on-read instead of copy-on-write
- This can be beneficial in some use cases (such as when there's high latency to the original pool, but not the new pool).
- 12:31 PM Feature #4087: rbd: bitmaps for tracking object existence
- Also, I wonder at what point it becomes worthwhile to
use something different from bitmaps (such as extents
that de... - 12:29 PM Feature #4087: rbd: bitmaps for tracking object existence
- I was thinking this weekend of creating this issue exactly.
Are you envisioning keeping these with the image heade... - 12:27 PM Feature #4087 (Resolved): rbd: bitmaps for tracking object existence
- This would improve layered image performance, and enable quick, conservative usage for an image. It should be possibl...
- 12:24 PM Feature #4086 (Resolved): rbd: rate-limiting
- Enforce policies like max-iops from a client point of view. The objecter throttling is too low-level, especially when...
- 12:15 PM Feature #4085 (New): qemu-rbd: allow storing snapshot of ram associated with snapshot of disk
- This way the entire state of a VM can be restored, instead of just the disks.
- 12:12 PM Feature #4084 (Resolved): rbd: incremental backups
- Root task for the feature in general
- 12:06 PM Feature #4083 (New): rbd-fuse: expose snapshots (and maybe other pools)
- Maybe only do so for an image when asked, but optionally always show all pool and snapshots? Need to think about the ...
- 12:03 PM Feature #4082 (Rejected): rbd-fuse: improve performance
- Use aio, different IoCtxs per image, and the C++ librbd api for fewer data copies.
- 12:02 PM Feature #4081 (New): rbd-fuse: improve usage, make consistent with other ceph tools
- Use the common command line/conf file/env var parsing. Re-write internals to c++ instead of C as needed.
- 11:51 AM Bug #3936: rbd: Strange dd speed behaviour (server side issue?)
- What size is the journal on your osds? You may just be seeing a slowdown when the journals fill up, and must be flush...
- 07:57 AM Bug #3936: rbd: Strange dd speed behaviour (server side issue?)
- It may be a network issue as well. Is it easy for you by chance to try with regular ethernet (say, gig instead of 10...
- 07:43 AM Bug #3936: rbd: Strange dd speed behaviour (server side issue?)
- > 3.7.2-ceph
That tells me a lot, and in fact makes me suspect it might
not be rbd that's the cause.
What can ... - 07:41 AM Bug #3936: rbd: Strange dd speed behaviour (server side issue?)
- During slow periods iostat shows no operations on OSDs. First of all I've thought about sceduler and iowait problems,...
- 07:38 AM Bug #3936: rbd: Strange dd speed behaviour (server side issue?)
- Linux hosting-cloud1-s1.zzzing.ru 3.7.2-ceph #1 SMP Wed Jan 16 23:25:11 NOVT 2013 x86_64 GNU/Linux
Kernel config: ... - 04:29 AM Bug #3936: rbd: Strange dd speed behaviour (server side issue?)
- I'm sorry if I missed it, but can you tell me the version
of the kernel you are working with? Running "uname -a"
m... - 11:51 AM Bug #3664: osdc/ObjectCacher.cc: 517: FAILED assert(!i->size())
- recent log: ubuntu@teuthology:/a/teuthology-2013-02-09_20:00:03-regression-bobtail-master-basic/3977...
- 11:30 AM Feature #2770 (In Progress): krbd: define tasks to add osd_client compound class op support
- At our sprint planning meeting we discussed this. The task
was too large and unknown to provide a meaningful estima... - 11:08 AM Bug #4033 (Resolved): krbd: add barriers near done flag operations
- I just committed this to the ceph-client/testing branch:
commit 4ad2b189c1a52ce8ae1d6d2528c512021a2f1654
Author: ... - 11:08 AM Bug #4010 (Resolved): krbd: turn off interrupts for open/remove locking
- I just committed this to the ceph-client/testing branch.
commit 4cfc31e59fc6521ee0950782a028eccb3f5c9096
Author: ...
02/10/2013
- 11:56 PM Bug #3936: rbd: Strange dd speed behaviour (server side issue?)
- eth1 and ib0 connected to ceph cloud.
- 11:53 PM Bug #3936: rbd: Strange dd speed behaviour (server side issue?)
- Ifstat output looks like:...
02/08/2013
- 08:36 AM Cleanup #4053: ceph: cleanup ceph page vector functions
- Apparently for cleanup there is no "need review" so I'm
marking this "Feedback". I've posted a series of patches
t... - 08:30 AM Cleanup #4053 (Resolved): ceph: cleanup ceph page vector functions
- This is just documenting some cleanup activity I've done
that I'm about to post for review.
- delete bogus (re)decl... - 08:21 AM Subtask #4007 (Fix Under Review): libceph: support STAT osd operation
- A patch implementing this has been posted to the
ceph-devel mailing list for review.
[PATCH] libceph: allow STAT ...
02/07/2013
- 05:08 PM Bug #4047 (Resolved): removing a non-existing rbd image logs error in osd logs
- when removing a non-existing rbd image floods osd logs even when the debug is turned off. This can be avoided.
ubu... - 04:22 PM Bug #4045 (Resolved): snap unprotect on a snapshot that is already unprotected throws inappropria...
- ceph version 0.56.2-7-gc3468f7 (c3468f76a5e68a6426f03e508d8ecf26950fca2a)
Trying to unprotect a snapshot, that is ... - 01:49 PM Bug #4003 (Resolved): rbd: EBUSY errors from rbd unmap
- closing this. phew!
02/06/2013
- 11:49 AM Subtask #4007: libceph: support STAT osd operation
- This has turned out to be simple change. It was needed in
rbd as well, and I'll just add support to both under this... - 09:19 AM Subtask #4007: libceph: support STAT osd operation
- It wasn't really possible to know this up front but
it looks like this is trivial. I've basically
completed it but... - 10:56 AM Bug #3697 (In Progress): rbd copy.sh test failing in nightly
- 08:56 AM Bug #3958: rbd fsx fails with EBUSY
- this is causing several failures on master runs.. something has changed.
latest:
ubuntu@teuthology:/a/sage-2013-... - 08:31 AM Bug #4003: rbd: EBUSY errors from rbd unmap
- The testing I've been doing now has shown no problems
now that teuthology has been updated.
The two other issues ... - 06:16 AM Bug #4003: rbd: EBUSY errors from rbd unmap
- Seems to have done the trick! The kernel_untar_build.sh
task just finished for me without error, and it failed
rel... - 05:06 AM Bug #4003: rbd: EBUSY errors from rbd unmap
- That sounds promising, I hope it works!
This was actually the last thing I was looking at last
night while waitin... - 07:20 AM Bug #4033 (Fix Under Review): krbd: add barriers near done flag operations
- A fix for this has been posted for review.
[PATCH] rbd: add barriers near done flag operations
- 06:15 AM Bug #4033 (Resolved): krbd: add barriers near done flag operations
- I fixed this problem while investigating the rbd hangs
in http://tracker.ceph.com/issues/4003.
Somehow, I missed ...
02/05/2013
- 11:43 PM Bug #4003: rbd: EBUSY errors from rbd unmap
- This was backing up qa stuff because the rbd.py qa task wasn't unmounting during cleanup. That bit is now fixed. I ...
- 10:54 PM Bug #4003: rbd: EBUSY errors from rbd unmap
- new theory:
the reason umount hangs is because nuke is killing the client and osds at the same time. the umount i... - 10:41 PM Bug #4003: rbd: EBUSY errors from rbd unmap
- I found that unmount was hanging too. I think somehow the
completion of the I/O is not getting propagated up when
... - 10:33 PM Bug #4003: rbd: EBUSY errors from rbd unmap
- aha:...
- 10:15 PM Bug #4003: rbd: EBUSY errors from rbd unmap
- btw i am able to reproduce the EBUSY with just...
- 08:28 PM Bug #4003: rbd: EBUSY errors from rbd unmap
- I've added some instrumentation and find that the rbd
client is not dropping its watch at the end of the
kernel_unt... - 12:51 PM Bug #4003: rbd: EBUSY errors from rbd unmap
- The interrupt issue has been fixed, but the other issue
(rbd device can't be unmapped because EBUSY) remains.
I h... - 11:35 AM Bug #4003: rbd: EBUSY errors from rbd unmap
- I ran the kernel_untar_build.sh workunit using the
ceph "master" branch and the ceph-client "testing"
branch and go... - 11:13 AM Bug #4003: rbd: EBUSY errors from rbd unmap
- I think I found *a* problem, possibly not *the* problem.
This commit:
bc7a62ee5 rbd: prevent open for image ... - 11:04 AM Bug #4003: rbd: EBUSY errors from rbd unmap
- I am able to reproduce this problem by running
the kernel_untar_build.sh workunit.
I ran the test using the ceph ... - 08:53 AM Bug #4003: rbd: EBUSY errors from rbd unmap
- > Alex, unless there is another high priority regression, can you
> look at this first?
Yes I will. - 08:52 AM Bug #4003: rbd: EBUSY errors from rbd unmap
- Sam Lang wrote:
> I was able to verify that this happens with an older version of teuthology, one without the change... - 08:41 AM Bug #4003: rbd: EBUSY errors from rbd unmap
- I was able to verify that this happens with an older version of teuthology, one without the changes I've made recentl...
- 05:18 AM Bug #4003: rbd: EBUSY errors from rbd unmap
- I had the impression this might be a problem that
is holding up completion of the nightly test suite.
But I'm not... - 01:47 PM Feature #4021 (Resolved): rbd: openstack: add ability to copy volume to image for rbd
- 01:46 PM Subtask #4020 (Resolved): rbd: openstack: simplify volume booting with new api: make image boot b...
- 01:44 PM Subtask #4019 (Resolved): rbd: openstack: simplify volume booting with new api: add boot option t...
- 01:44 PM Subtask #4018 (Resolved): rbd: openstack: simplify volume booting with new api: modify boot panel...
- 01:42 PM Feature #4017 (Resolved): rbd: openstack: simplify volume booting with new api
- 01:42 PM Feature #4013 (In Progress): rbd: openstack: extend nova boot api to support going from image to ...
- 01:24 PM Feature #4013 (Resolved): rbd: openstack: extend nova boot api to support going from image to volume
- 01:41 PM Subtask #4016 (Resolved): rbd: openstack: extend nova boot api: modify libvirt driver to support ...
- 01:40 PM Subtask #4015 (Resolved): rbd: openstack: extend nova boot api: add block_dev_mapping_v2 to nova-...
- 01:40 PM Subtask #4014 (Resolved): rbd: openstack: extend nova boot api: add block_dev_mapping_v2 to nova-api
- 01:13 PM Bug #4012 (Won't Fix): rbd: image creation behaviour has to be uniform across bobtail and argonau...
- rbd allows images to be created with size 0 in bobtail, but it fails in argonaut.
similarly,while in bobtail it do... - 12:52 PM Bug #4010 (Fix Under Review): krbd: turn off interrupts for open/remove locking
- Posted for review.
[PATCH] rbd: turn off interrupts for open/remove locking
- 12:49 PM Bug #4010 (Resolved): krbd: turn off interrupts for open/remove locking
- This fix is done. The problem was discovered while
investigating http://tracker.ceph.com/issues/4003.
This commi... - 10:12 AM Bug #3697: rbd copy.sh test failing in nightly
- recent log : ubuntu@teuthology:/a/teuthology-2013-02-04_20:00:03-regression-bobtail-master-basic/15773
- 07:42 AM Subtask #4007 (Resolved): libceph: support STAT osd operation
- In order to do layered writes we need to check whether
an object to be written exists before issuing the write.
Thi...
02/04/2013
- 05:53 PM Bug #4003: rbd: EBUSY errors from rbd unmap
- I really can't tell who's got a watch on the header
object. It should be getting removed when the object
gets unma... - 05:02 PM Bug #4003: rbd: EBUSY errors from rbd unmap
- There is clearly something that is keeping the rbd image
from getting removed. I reproduced this with just running
... - 04:12 PM Bug #4003 (In Progress): rbd: EBUSY errors from rbd unmap
- This sounds familiar, but I'm going to look a little
more closely to see if I can learn why it's happening.
- 04:03 PM Bug #4003 (Resolved): rbd: EBUSY errors from rbd unmap
- From the teuthology kernel untar task on rbd, we get EBUSY trying to unmap. I'm investigating that this isn't someho...
02/01/2013
- 02:18 PM Subtask #3741 (Resolved): krbd: rework request tracking code
- commit 9ac90ea3d8dd6ab82f3665a132ca29e6ada56ad8
Author: Alex Elder <elder@inktank.com>
Date: Thu Nov 22 00:00:08 ... - 02:17 PM Feature #3754 (Closed): krbd: use new request tracking code for notify ack
- commit 1c8c3c5c571607a188203142020d80aa58e5e280
Author: Alex Elder <elder@inktank.com>
Date: Fri Nov 30 17:53:04 ... - 02:16 PM Tasks #3755: krbd: use new request tracking code for sync object operations
- commit 5d08568324f53368f927cc10927b1b105533c044
Author: Alex Elder <elder@inktank.com>
Date: Thu Jan 17 12:25:27 ... - 01:44 PM Tasks #3755 (Resolved): krbd: use new request tracking code for sync object operations
- commit 304819b1a49937753ee01aa7ccf8d66547a0be36
Author: Alex Elder <elder@inktank.com>
Date: Sat Jan 19 00:30:28 ... - 02:11 PM Feature #3877 (Closed): krbd: don't wait for notify ack to complete
- commit a8a34efcac7a33e7631fe8bf25530bd4be0417f8
Author: Alex Elder <elder@inktank.com>
Date: Thu Jan 17 12:18:46 ... - 01:38 PM Bug #3940 (Resolved): krbd: decrement obj request count when deleting
- commit 150fde1984ec8454c163e4f89a50416cd68edbc4
Author: Alex Elder <elder@inktank.com>
Date: Fri Jan 25 17:08:55 ... - 01:38 PM Bug #3937 (Resolved): krbd: crash in rbd_assert(osd_req == obj_request->osd_req)
- commit 8d93192992301f8c3a288c8cf4dc8598ac4b8427
Author: Alex Elder <elder@inktank.com>
Date: Fri Jan 25 17:08:55 ... - 01:37 PM Bug #3427 (Resolved): krbd: unmap does not remove block device properly
- commit bc7a62ee52cffc735cb8383b6d26648883f1a01e
Author: Alex Elder <elder@inktank.com>
Date: Mon Jan 14 12:43:31 ... - 12:48 PM Bug #1740 (Resolved): krbd: don't return head data when reading from a non-existent snapshot
- This was fixed a while ago.
- 11:58 AM Bug #3980 (Won't Fix): rbd image created with size zero on a mixed cluster crashes rbd
- creating a rbd image with size 0 is allowed in bobtail but not on argonaut.
on a mixed cluster running argonaut[bu...
01/31/2013
- 08:51 PM Bug #3978 (Resolved): krbd qa: concurrent.sh test leaves something read-only
- I don't know what exactly is happening here, but it appears
that after running the "rbd/concurrent.sh" workunit, if
... - 02:21 PM Bug #3975 (Rejected): librbd: xfstests 008 failed inside qemu
- This one's not a problem. This test pokes random holes in a
file (or maybe fills random spots). And when done it s... - 02:05 PM Bug #3975 (Rejected): librbd: xfstests 008 failed inside qemu
- From xfstests output in ubuntu@teuthology:/a/teuthology-2013-01-29_20:00:04-regression-bobtail-master-basic/7794/remo...
01/30/2013
- 02:10 PM Bug #3937: krbd: crash in rbd_assert(osd_req == obj_request->osd_req)
- The patch is reviewed and ready to push to the testing
branch, and I will do that in a day or so.
I'm going to le... - 02:08 PM Bug #3940: krbd: decrement obj request count when deleting
- Reviewed and ready to push to master. Will do that in a day or so.
- 02:07 PM Bug #3427: krbd: unmap does not remove block device properly
- Reviewed and ready to push to the ceph-client "testing" branch.
I'm going to wait a day or two before pushing this... - 11:31 AM Bug #3964: krbd: 32-bit, kernel 3.2.0 system can't do O_DIRECT writes to mapped rbd image with sn...
- ...and to answer your other question Alex, there's now a workunit test Sage just added
in c782d2ac531cbb7650968e62f0... - 11:00 AM Bug #3964: krbd: 32-bit, kernel 3.2.0 system can't do O_DIRECT writes to mapped rbd image with sn...
- Josh thinks 32-bitness probably doesn't matter, and remembers problems with snapshots that were fixed long ago; I gue...
- 10:55 AM Bug #3964: krbd: 32-bit, kernel 3.2.0 system can't do O_DIRECT writes to mapped rbd image with sn...
- I don't know if Sage tested 32-bit, or if it matters, and no, that script was just a reproduction scenario; as far as...
- 06:25 AM Bug #3964: krbd: 32-bit, kernel 3.2.0 system can't do O_DIRECT writes to mapped rbd image with sn...
- So is this then a request to port whatever it was that
fixed the problem back to 3.2?
If so, how do we prioritize... - 01:10 AM Bug #3964: krbd: 32-bit, kernel 3.2.0 system can't do O_DIRECT writes to mapped rbd image with sn...
- added test to suite, commit:c782d2ac531cbb7650968e62f0b24e6136a64359
- 12:15 AM Bug #3964: krbd: 32-bit, kernel 3.2.0 system can't do O_DIRECT writes to mapped rbd image with sn...
- This works fine on current testing 3.6.0-00210-g8cc17ca
- 11:16 AM Bug #3961 (Resolved): 32-bit cls_rbd tries cls_log with %d for 64-bit int, segfaults
- commit:e253830abac76af03c63239302691f7fac1af381 on next
- 09:37 AM Subtask #3741: krbd: rework request tracking code
- My testing on this code is nearly complete. However, I'm going
to hold off on pushing this (along with the changes ... - 06:34 AM Subtask #3741: krbd: rework request tracking code
- 06:47 AM Bug #3927 (Closed): krbd: I/O errors (ENXIO) during rbd/kernel.sh workunit
- It turns out this new behavior is a good thing, we're just
reporting errors now where we apparently did not previous... - 06:47 AM Bug #3745 (Rejected): krbd: individual response errors are ignored
- I no longer believe this is a problem. Although there is no
aggregate result value for a collection of osd requests... - 06:35 AM Feature #3877: krbd: don't wait for notify ack to complete
- 06:35 AM Tasks #3755: krbd: use new request tracking code for sync object operations
- 06:35 AM Feature #3754: krbd: use new request tracking code for notify ack
01/29/2013
- 11:40 PM Bug #3964: krbd: 32-bit, kernel 3.2.0 system can't do O_DIRECT writes to mapped rbd image with sn...
- ...
- 11:28 PM Bug #3964 (Won't Fix): krbd: 32-bit, kernel 3.2.0 system can't do O_DIRECT writes to mapped rbd i...
- fghaas reported, I reproduced on a precise 32-bit system:
create an image, map, writes work fine, even with dd ofl... - 10:46 PM Bug #3961 (Resolved): 32-bit cls_rbd tries cls_log with %d for 64-bit int, segfaults
- 32-bit system: rbd create i -s 1; rbd rm i causes death of osd in cls_log();
presumably this is because of cls_log(%... - 08:33 PM Bug #3566 (Resolved): log max new = 1 can cause hang on process exit
- fixed a few weeks ago, commit:813787af3dbb99e42f481af670c4bb0e254e4432 and a few prior commits
- 08:26 PM Bug #3958 (Resolved): rbd fsx fails with EBUSY
- ...
- 03:11 PM Bug #3952 (Resolved): krbd: no need for object header version
- The header object watch operation had a sort of half implemented
use of the version of the object. It apparently is... - 03:08 PM Bug #3946 (Resolved): rbd fsx failing in nightly
- Just an extra delete in a code path in flush_set that wasn't exercised before. Fixed by commit:3bc21143552b35698c9916...
- 02:44 PM Bug #3946: rbd fsx failing in nightly
- Reproducing locally seems to confirm this, since there was a recent change to replace commit_set() with flush_set():
... - 12:06 PM Bug #3946: rbd fsx failing in nightly
- I'm guessing these are related to recent objectcacher changes, since they didn't affect runs without caching. The cor...
- 02:48 PM Feature #3949 (Resolved): krbd: create test script that exercises concurrent operations
- I just committed the test script to the ceph master branch.
The script is located here: qa/workunits/rbd/concurrent... - 09:16 AM Feature #3949: krbd: create test script that exercises concurrent operations
- Well the script is really nice. And I just got a new
crash while running it on a real machine (rather than
my UML ... - 08:22 AM Feature #3949 (Resolved): krbd: create test script that exercises concurrent operations
- I suggested doing this in http://tracker.ceph.com/issues/3427.
That issue is about a bug where an image unmapping ca... - 11:10 AM Bug #3950: krbd: new assertion failure running concurrent rbd test
- OK, I do have the osd request pointer now. It was available
in register R14. And with a little work I can determin... - 10:35 AM Bug #3950: krbd: new assertion failure running concurrent rbd test
- The object being operated on is the rbd header image, in
this case named "image.5X5ZNB.rbd". The object request typ... - 10:06 AM Bug #3950: krbd: new assertion failure running concurrent rbd test
- Weird. It looks to me like the object request that's
just completing is already done, meaning we got
a callback fr... - 09:19 AM Bug #3950 (Can't reproduce): krbd: new assertion failure running concurrent rbd test
- (I think this is a new issue, I haven't investigated it yet.)
I hit an assertion failure while running my new test... - 10:34 AM Bug #3937: krbd: crash in rbd_assert(osd_req == obj_request->osd_req)
- I've opened a new issue that has symptoms similar to this
but not identical:
http://tracker.ceph.com/issues/395... - 09:15 AM Bug #3427: krbd: unmap does not remove block device properly
- I have opened this to cover developing that test script
http://tracker.ceph.com/issues/3949
01/28/2013
- 09:18 PM Bug #3947 (Resolved): krbd: read zeroing freed bio?
- This happened to me once before but I wasn't sure what
I did. Now I think I do know. This is with the new
request... - 05:02 PM Bug #3946 (Resolved): rbd fsx failing in nightly
- ...
- 02:11 PM Bug #3427 (Fix Under Review): krbd: unmap does not remove block device properly
- I have posted two patches for review, the second of which
should fix this problem. I have not actually reproduced
...
Also available in: Atom