Project

General

Profile

Activity

From 03/31/2013 to 04/29/2013

04/29/2013

05:45 PM Bug #4661: xfstest 139 hung
and again!
ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2013-04-29_01:01:03-kernel-next-testing-basic...
Sage Weil
05:44 PM Bug #4661: xfstest 139 hung
happened again,
ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2013-04-28_21:32:47-kernel-next-testing-...
Sage Weil
05:01 PM Bug #4827 (In Progress): librbd: use after free of ceph context or something in it
Failed on the 8th try, in a similar way, although without logs.
The ObjectCacher looks like it's been destroyed al...
Josh Durgin
04:44 PM Bug #4827: librbd: use after free of ceph context or something in it
Sage Weil
03:29 PM Bug #4827: librbd: use after free of ceph context or something in it
The wip-rbd-close-image branch contains a potential fix. Running the test in a loop to see if it'll happen again. Josh Durgin
10:18 AM Bug #4827: librbd: use after free of ceph context or something in it
It didn't reproduce with log_max_recent = 1, but without that setting it happened after just 3 tries.
Unfortunatel...
Josh Durgin
12:38 PM Bug #4857 (Resolved): libceph: define snap context creation function
I created a function to encapsulate the creation of a snapshot
context, for use in rbd. In review, Josh said he tho...
Alex Elder
12:17 PM Feature #4550: Create Qemu+RBD rpm package for RHEL+CentOS 6.3 on ceph.com
For CentOS, I am less concerned about package version but for RHEL6.3, we should use the same version of qemu that sh... Neil Levine
11:02 AM Bug #4774: krbd: don't create /dev entries for backing devices
OK, finally getting to the point of this bug...
I just posted the following patches for review. The
last one act...
Alex Elder

04/27/2013

12:42 PM Bug #3871 (Fix Under Review): krbd: initial header read may be out of date
The following have been posted for review. They are available
in the "review/wip-rbd-cleanup-4" in the ceph-client ...
Alex Elder
08:09 AM Bug #4774 (Fix Under Review): krbd: don't create /dev entries for backing devices
I'm making headway on this now. It mostly is taking the form of
cleaning up code as I walk through how things get s...
Alex Elder
08:04 AM Bug #4833 (Fix Under Review): krbd: fix a bug in resizing a mapping
The following has been posted for review:
[PATCH] rbd: fix a bug in resizing a mapping
It was posted together w...
Alex Elder

04/26/2013

04:33 PM Bug #4446: librbd: crash from opensolaris vm
I tried booting in several configurations, and couldn't get it to fail. I used ceph 0.56.4, and qemu 1.0 for ubuntu 1... Josh Durgin
01:55 PM Bug #4446: librbd: crash from opensolaris vm
As an ex-Sun employee, I can point out that this is an *ancient* version of S10; there've been many many updates sinc... Dan Mick
03:44 PM Bug #4827: librbd: use after free of ceph context or something in it
Segfaults with different backtraces occurred with and without caching enabled. Unfortunately the first core file is c... Josh Durgin
09:21 AM Bug #4827 (Resolved): librbd: use after free of ceph context or something in it
From teuthology:/a/teuthology-2013-04-26_02:29:00-rbd-next-testing-basic/1393/teuthology.log:... Josh Durgin
02:06 PM Feature #4838 (New): rbd-fuse: use the low level fuse interface
The low level interface will let us parse custom options (i.e. standard ceph ones). Josh Durgin
12:03 PM Feature #4231: librbd: Java bindings
So I already started work on 'rados-java': https://github.com/wido/rados-java
I'm thinking about combining this to...
Wido den Hollander
11:49 AM Feature #4231: librbd: Java bindings
Possible good task for Joe and/or Noah? Ian Colle
11:52 AM Feature #4834: Recompile/package qemu with new version of librbd to enable asynchronous flushing ...
Gary and Josh to work together on this. Ian Colle
11:51 AM Feature #4834 (Resolved): Recompile/package qemu with new version of librbd to enable asynchronou...
Ian Colle
11:39 AM Bug #4833 (Resolved): krbd: fix a bug in resizing a mapping
When a snapshot context update occurs, rbd_update_mapping_size() is
called to set the capacity of the disk to record...
Alex Elder
11:38 AM Feature #2557: QEMU support for image locking
Need a blueprint to assist in architectural planning before we can estimate or plan this effort. Ian Colle
11:36 AM Feature #4454: openstack: support volume migration in Cinder
Initially copy from one back end to the other. Instead of using volume migrations blueprint, just use backup? Getting... Ian Colle
08:07 AM Feature #4013: rbd: openstack: extend nova boot api to support going from image to volume
Ian Colle
08:06 AM Feature #4017: rbd: openstack: simplify volume booting with new api
Ian Colle
07:59 AM Bug #4803: krbd: memory leaks while testing layered images
The following additional set of patches has been posted for
review. They're available in the "review/wip-rbd-cleanu...
Alex Elder
05:15 AM Bug #4803 (Fix Under Review): krbd: memory leaks while testing layered images
OK, I have some patches ready for review but I think this will
be an ongoing process so I'll probably be bouncing th...
Alex Elder
07:58 AM Bug #4800 (Fix Under Review): krbd: avoid dropping extra reference in rbd_free_disk()
The following has been posted for review:
rbd: avoid dropping extra reference in rbd_free_disk()
Alex Elder
05:10 AM Bug #4800 (In Progress): krbd: avoid dropping extra reference in rbd_free_disk()
Alex Elder
05:09 AM Bug #4800 (Fix Under Review): krbd: avoid dropping extra reference in rbd_free_disk()
(Nevermind. Will be ready for review shortly.) Alex Elder
05:22 AM Bug #4802: krbd: walk through error paths and fix them
I think it may be hard to describe exactly what the problems
of this type are. I do a fairly good job of it in the ...
Alex Elder
05:11 AM Bug #4796 (Fix Under Review): krbd: don't create sysfs entries for snapshots of mapped images

The following has been posted for review:
[PATCH] rbd: don't create sysfs entries for non-mapped snapshots
It...
Alex Elder

04/25/2013

01:19 PM Bug #4446: librbd: crash from opensolaris vm
Even without NIS or NFS, I'm guessing it'll get far enough to hit the error. I'll email you a place to upload the image. Josh Durgin
04:44 AM Bug #4446: librbd: crash from opensolaris vm
Thanks for continuing to pursue this.
I can send you the image (about 20GB), but it may have issues booting (depen...
Jeff Moskow
01:13 PM Bug #4803: krbd: memory leaks while testing layered images
I've been reviewing the rbd code with an eye toward finding
leaks. I have two small ones that I'll fix, but I have ...
Alex Elder
06:24 AM Bug #2654: Stale rbd volume cannot be unmaped
Hi, thanks for replying. Here's the info:... Leon Keijser
01:02 AM Bug #2700 (Resolved): blkdeviotune method at libvirt doesn`t work on RBD volumes
The patch got accepted into libvirt: http://www.libvirt.org/git/?p=libvirt.git;a=commit;h=e3e866aee0f8b0b125da74e1afc... Wido den Hollander

04/24/2013

05:10 PM Bug #4446: librbd: crash from opensolaris vm
Sorry for the delay. I've learned that Solaris sector counts could start at 1 instead of 0, so rbd did at least see t... Josh Durgin
04:22 PM Bug #3664 (Resolved): osdc/ObjectCacher.cc: 517: FAILED assert(!i->size())
commit:82d5cd601e0fb7cb24dda4ea1f0e9f12e5d18708 Josh Durgin
04:02 PM Bug #3664 (Fix Under Review): osdc/ObjectCacher.cc: 517: FAILED assert(!i->size())
Josh Durgin
08:13 AM Bug #3664: osdc/ObjectCacher.cc: 517: FAILED assert(!i->size())
ubuntu@teuthology:/a/teuthology-2013-04-23_19:55:59-rbd-next-testing-basic$ less 155/teuthology.log
Sage Weil
08:13 AM Bug #3664: osdc/ObjectCacher.cc: 517: FAILED assert(!i->size())
ubuntu@teuthology:/a/teuthology-2013-04-23_19:55:59-rbd-next-testing-basic$ less 148/teuthology.log
Sage Weil
03:14 PM Bug #4526 (Can't reproduce): rbd-fsx: ENOTEMPTY
Sage Weil
10:52 AM Bug #2654 (Need More Info): Stale rbd volume cannot be unmaped
Sage Weil
10:52 AM Bug #2654 (In Progress): Stale rbd volume cannot be unmaped
Can you post results from find /sys/bus/rbd/devices -ls and ls -al /dev/rbd* ? Sage Weil
12:06 AM Bug #2654: Stale rbd volume cannot be unmaped
Please consider re-opening this ticket. I am experiencing the same issue, even with the latest kernel version:
<pr...
Leon Keijser
10:47 AM Feature #4804 (Rejected): tgt: switch to aio
Use aio interface for tgt to avoid a workqueue + sync items. Sage Weil
10:09 AM Bug #4522 (Need More Info): RBD utility "showmapped" bug
Sage Weil
10:09 AM Bug #4522: RBD utility "showmapped" bug
Do you still see this?
What 'showmapped' is looking at is /sys/bus/rbd/devices/*... an ls -al of that directory wo...
Sage Weil
09:22 AM Bug #4803 (Resolved): krbd: memory leaks while testing layered images
I have a series of small tests I run to test rbd functionality.
I occasionally run them in a loop in my UML environm...
Alex Elder
09:03 AM Bug #4802: krbd: walk through error paths and fix them
Fixed project. Alex Elder
09:02 AM Bug #4802 (Resolved): krbd: walk through error paths and fix them
I have encountered a few places where the kernel rbd
code does not handle error conditions exactly right.
There app...
Alex Elder
08:57 AM Bug #4800: krbd: avoid dropping extra reference in rbd_free_disk()
This is basically done.
As I look through the code though I see there are other places
where error handling does ...
Alex Elder

04/23/2013

07:15 PM Bug #4800 (Resolved): krbd: avoid dropping extra reference in rbd_free_disk()
I found during some failure injection testing that the call to
rbd_free_disk() in the error path of rbd_dev_probe_fi...
Alex Elder
04:12 PM Bug #4665 (Resolved): librbd: read_iterate() can overflow its return value
commit:857c88e017f082b6ef2a81a1890baa7d20672a31 Josh Durgin
12:18 PM Bug #4665 (In Progress): librbd: read_iterate() can overflow its return value
Sage Weil
12:07 PM Bug #3737 (Resolved): Higher ping-latency observed in qemu with rbd_cache=true during disk-write
Thanks for testing it out everyone. It's now in the bobtail branch too. Josh Durgin
07:09 AM Bug #3737: Higher ping-latency observed in qemu with rbd_cache=true during disk-write
I just tested the Qemu patch with a cherry-pick to Qemu 1.2 and with the wip-bobtail-rbd-backports-req-order branch a... Wido den Hollander
12:06 PM Bug #4551 (Resolved): librbd: rollback broken for clones
Josh Durgin
12:06 PM Bug #4525 (Resolved): hang during librbd python tests
Josh Durgin
12:05 PM Bug #4364 (Resolved): ObjectCacher: inconsistency after flatten
Josh Durgin
12:05 PM Bug #4531 (Resolved): ObjectCacher: read waiters for parent data during copyup get reordered, cau...
Josh Durgin
11:38 AM Bug #4796 (Resolved): krbd: don't create sysfs entries for snapshots of mapped images
When an rbd image gets mapped a device entry gets created
for it under /sys/bus/rbd/devices/<id>/. Inside that
dir...
Alex Elder
08:06 AM Bug #4774: krbd: don't create /dev entries for backing devices
I'm unfortunately finding what I fought with last year when
working with the initialization and teardown of rbd devi...
Alex Elder

04/22/2013

05:53 PM Bug #3664: osdc/ObjectCacher.cc: 517: FAILED assert(!i->size())
Nevermind, the logs were saved after all. Hooray! Josh Durgin
05:52 PM Bug #3664: osdc/ObjectCacher.cc: 517: FAILED assert(!i->size())
Unfortunately the logs aren't there anymore (they weren't saved when a power failure restarted the machine running te... Josh Durgin
05:16 PM Bug #3664 (In Progress): osdc/ObjectCacher.cc: 517: FAILED assert(!i->size())
Looking at this again, hopefully will get it fixed tomorrow. Josh Durgin
05:11 PM Bug #4774 (In Progress): krbd: don't create /dev entries for backing devices
This is what I am now working on; just marking it so. Alex Elder
05:09 PM Bug #3847 (Resolved): rbd: figure out correct byte order for watch version
The following has been committed to the "testing" branch
of the ceph-client git repository:
42c6070 libceph: fix ...
Alex Elder
05:06 PM Feature #4709 (Resolved): krbd: support stripingv2 images that don't require I/O path changes
The following has been committed to the "testing" branch
of the ceph-client git repository:
09186dd rbd: get and ...
Alex Elder
05:04 PM Bug #4773 (Resolved): rbd: have rbd_obj_method_sync() return transfer count
The following have been committed to the "testing" branch of
the ceph-client git repository.
3ad6cbd9 libceph: ad...
Alex Elder
04:53 PM Feature #4724 (Resolved): krbd: handle layered I/O correctly when the child has been resized
The following has been committed to the "testing" branch
of the ceph-client git repository:
64548e0 rbd: enforce ...
Alex Elder
03:16 PM Bug #4242: krbd: xfstest 259 failure (FS size near 4TB)
I just hit this again with the current testing branch.
testing e7fce31 rbd: issue a copyup for layered writes
Alex Elder
02:59 PM Feature #4550 (In Progress): Create Qemu+RBD rpm package for RHEL+CentOS 6.3 on ceph.com
oops, didn't mean to change the status Josh Durgin
02:55 PM Feature #4550: Create Qemu+RBD rpm package for RHEL+CentOS 6.3 on ceph.com
I'd suggest starting with the latest version of qemu-kvm for centos 6 (the c6 branch of https://nazar.karan.org/summa... Josh Durgin
12:24 PM Feature #4550 (In Progress): Create Qemu+RBD rpm package for RHEL+CentOS 6.3 on ceph.com

It looks like I want to grab the source for the qemu-kvm-0.12.1.2-2.295 package that ships with centos 6.3, rebuild...
Anonymous
01:40 PM Bug #4710 (Resolved): rbd: STRIPINGV2 feature specified by default for format 2 images
Sage Weil
12:46 PM Bug #4710 (Fix Under Review): rbd: STRIPINGV2 feature specified by default for format 2 images
Sage Weil
11:42 AM Bug #4710 (In Progress): rbd: STRIPINGV2 feature specified by default for format 2 images
Sage Weil
11:29 AM Bug #4710: rbd: STRIPINGV2 feature specified by default for format 2 images
Per Josh, this is easy fix, let's get it into Cuttlefish. Ian Colle
12:46 PM Feature #3419 (Resolved): krbd: copy-up on write to clone
The following have been committed to the ceph-client
"testing" branch.
b15a1df rbd: implement full object parent ...
Alex Elder
10:08 AM Feature #3419: krbd: copy-up on write to clone
The following have been committed to the ceph-client
"testing" branch. Still waiting on reviews for the
last two.
...
Alex Elder
11:41 AM Bug #4707 (Resolved): rbd CLI: bad error code masked by udevadm_settle
commit:568101fa72e29ee960fcf3d704f04edfd50bd072 Sage Weil
11:39 AM Bug #4707 (In Progress): rbd CLI: bad error code masked by udevadm_settle
Sage Weil
11:27 AM Bug #4707: rbd CLI: bad error code masked by udevadm_settle
Let's try to get this into Cuttlefish. Ian Colle
11:31 AM Bug #4665: librbd: read_iterate() can overflow its return value
Per Josh, this is another easy fix, let's get it into Cuttlefish. Ian Colle
10:04 AM Bug #4762 (Resolved): libceph: fix two messenger bugs
The following has been committed to the ceph-client "testing"
branch:
68423cc libceph: fix two messenger bugs
Alex Elder
05:34 AM Bug #4777 (Resolved): krbd: verify a few things in the zeroing routines
The kernel rbd driver has a function zero_bio_chain() that's
used to zero out the data in a bio list starting at a g...
Alex Elder
03:02 AM Bug #3737: Higher ping-latency observed in qemu with rbd_cache=true during disk-write
Ooops, sorry...,
was a bit misleaded, cause "cache=writeback" was still in the config file.
Oliver.
Oliver Francke

04/21/2013

02:56 PM Bug #3847 (Fix Under Review): rbd: figure out correct byte order for watch version
The following has been posted for review:
[PATCH] libceph: fix byte order mismatch
It is available in the "revi...
Alex Elder
02:39 PM Bug #3847 (In Progress): rbd: figure out correct byte order for watch version
libceph: fix byte order mismatch
A WATCH op includes an object version. The version that's supplied
is incorrect...
Alex Elder
02:24 PM Bug #4774 (Resolved): krbd: don't create /dev entries for backing devices
Currently when a layered rbd device gets mapped, the
snapshot device that is its parent gets probed in the
same way...
Alex Elder
02:21 PM Feature #4709 (Fix Under Review): krbd: support stripingv2 images that don't require I/O path cha...
The following has been posted for review and is available
in the "review/wip-stripe-v2" branch of the ceph-client
g...
Alex Elder
06:50 AM Feature #4709 (In Progress): krbd: support stripingv2 images that don't require I/O path changes
Starting work on this. Alex Elder
02:20 PM Bug #4773 (Fix Under Review): rbd: have rbd_obj_method_sync() return transfer count
The following have been posted for review, and are
available in the "review/wip-stripe-v2" branch of
the ceph-clien...
Alex Elder
10:28 AM Bug #4773: rbd: have rbd_obj_method_sync() return transfer count
I've implemented these fixes and will post them for
review after I've done some better testing.
I also made a few...
Alex Elder
07:59 AM Bug #4773 (Resolved): rbd: have rbd_obj_method_sync() return transfer count
Callers of rbd_obj_method_sync() don't know how many bytes of data
got returned by the class method call. As a resu...
Alex Elder

04/20/2013

10:36 PM Feature #4724 (Fix Under Review): krbd: handle layered I/O correctly when the child has been resized
The following has been posted for review:
[PATCH] rbd: enforce parent overlap
Alex Elder
10:32 AM Feature #3418 (Resolved): krbd: write path (layering)
The following have been committed to the "testing" branch
of the ceph-client git repository:
a065a13 libceph: kil...
Alex Elder

04/19/2013

07:20 PM Feature #3419 (Fix Under Review): krbd: copy-up on write to clone
The following has been posted for review.
This set of patches culminates in providing layered
write functionality...
Alex Elder
07:19 PM Bug #4762 (Fix Under Review): libceph: fix two messenger bugs
The following has been posted for review:
[PATCH] libceph: fix two messenger bugs
Alex Elder
01:10 PM Bug #4762 (Resolved): libceph: fix two messenger bugs
While getting copyup functionality working I found two
bugs in the messenger that previously were not triggered.
...
Alex Elder
02:38 PM Bug #4763 (Resolved): rbd test scripts should use --allow-shrink flag when resizing rbd img
Sage Weil
01:58 PM Bug #4763 (In Progress): rbd test scripts should use --allow-shrink flag when resizing rbd img
Sage Weil
01:28 PM Bug #4763 (Resolved): rbd test scripts should use --allow-shrink flag when resizing rbd img
The existing rbd test script rbd/copy.sh fails with the recent inclusion of --allow-shrink flag for the resize comman... Tamilarasi muthamizhan
08:53 AM Bug #3664: osdc/ObjectCacher.cc: 517: FAILED assert(!i->size())
Josh - any update? Are we still going to get this in Cuttlefish? Ian Colle

04/18/2013

12:42 PM Documentation #4751 (Closed): Document Live Migration with RBD
For people migrating to Ceph, some information on migration would be helpful.
Wido "You can do Live Migration with...
John Wilkins

04/17/2013

03:53 PM Bug #4739 (Duplicate): Failed assert in librbd with rbd cache enabled
see #4531 Sage Weil
03:51 PM Bug #4739: Failed assert in librbd with rbd cache enabled
Mike Kelly wrote:
> Josh Durgin wrote:
> > The latest cause of this was #4531, whose fix was just merged yesterday....
Mike Kelly
10:25 AM Bug #4739: Failed assert in librbd with rbd cache enabled
Josh Durgin wrote:
> The latest cause of this was #4531, whose fix was just merged yesterday. If this is reproducibl...
Mike Kelly
09:53 AM Bug #4739: Failed assert in librbd with rbd cache enabled
The latest cause of this was #4531, whose fix was just merged yesterday. If this is reproducible, could you try using... Josh Durgin
09:36 AM Bug #4739: Failed assert in librbd with rbd cache enabled
How easy is this to reproduce? We have fixed several causes of this behavior, but I cant' remember offhand if they w... Sage Weil
07:44 AM Bug #4739 (Duplicate): Failed assert in librbd with rbd cache enabled
With librbd, as used by qemu (via libvirt), while using rsync to sync data to a fresh image:
osdc/ObjectCacher.cc:...
Mike Kelly
01:00 AM Bug #3737: Higher ping-latency observed in qemu with rbd_cache=true during disk-write
Well,
could it be, that the fix already made it into "ceph version 0.60 (f26f7a39021dbf440c28d6375222e21c94fe8e5c)...
Oliver Francke

04/16/2013

04:35 PM Bug #4683 (Resolved): librbd: diff_iterate test failures
Sage Weil
02:43 PM Bug #4683 (Fix Under Review): librbd: diff_iterate test failures
see wip.. we need to flush the cache. Sage Weil
03:49 PM Bug #4531 (Pending Backport): ObjectCacher: read waiters for parent data during copyup get reorde...
Sage Weil
03:48 PM Bug #4531 (Resolved): ObjectCacher: read waiters for parent data during copyup get reordered, cau...
Sage Weil
12:34 PM Bug #4661 (Need More Info): xfstest 139 hung
Ian Colle
11:49 AM Bug #4661: xfstest 139 hung
Test 139 does a forceful shutdown of the file system (without syncing)
to check on how well XFS handles it.
In th...
Alex Elder
10:46 AM Bug #3737: Higher ping-latency observed in qemu with rbd_cache=true during disk-write
Yeah, the backports should definitely be merged by next week. On your lab cluster, you could try librbd from the 'nex... Josh Durgin
05:50 AM Bug #3737: Higher ping-latency observed in qemu with rbd_cache=true during disk-write
Hi Josh,
sounds promising, unfortunately I'm currently on 0.60... in our lab. We are going to move forward to late...
Oliver Francke

04/15/2013

08:46 PM Feature #3418 (Fix Under Review): krbd: write path (layering)
I have posted the following for review:
I've broken these patches into three groups.
The first two are so...
Alex Elder
10:43 AM Feature #3418: krbd: write path (layering)
In order to distinguish this issue from
http://tracker.ceph.com/issues/3419 I'll
call this one complete when I have...
Alex Elder
05:30 AM Tasks #2853 (Resolved): krbd: read path
The following have been committed to the ceph-client
"testing" branch:
745c34c rbd: implement layered reads
3c38...
Alex Elder
12:16 AM Bug #3737: Higher ping-latency observed in qemu with rbd_cache=true during disk-write
The branch wip-bobtail-rbd-backports-req-order has the fix for this plus several other bugs backported on top of the ... Josh Durgin

04/14/2013

10:32 AM Feature #4724 (Resolved): krbd: handle layered I/O correctly when the child has been resized
When a child image is shrunk or expanded, the logical section of the child that may inherit the parent's data is no l... Josh Durgin

04/12/2013

07:16 PM Feature #2630 (Resolved): teuthology: add task to run qemu-iotests against rbd
commit:98de67d424fd4ea972130ac737062aa8c093cbff Josh Durgin
07:00 PM Bug #4581 (Resolved): qemu: use asychronous flush
http://patchwork.ozlabs.org/patch/232489/ Josh Durgin
05:49 PM Bug #4551 (Pending Backport): librbd: rollback broken for clones
This bisected to 860493e7ff0d87d02069b243fc1c8326ce0721f9. Fortunately, this is going to be backported anyway. Josh Durgin
12:53 PM Bug #4551 (In Progress): librbd: rollback broken for clones
I added some tests for various cases of this. They all pass on v0.60 and the next branch consistently in several conf... Josh Durgin
01:49 PM Bug #4531: ObjectCacher: read waiters for parent data during copyup get reordered, causing the wr...
I tried, but I just don't know enough about the cacher or the completion framework to understand this, I'm afraid. Dan Mick

04/11/2013

07:20 PM Tasks #2853 (Fix Under Review): krbd: read path
The following series has been posted for review.
This series puts in place code that is able to handle
read r...
Alex Elder
10:18 AM Tasks #2853: krbd: read path
Double fuckin' A. (Fuckin' double-A?)
I just updated my test to validate snapshot-of-clone and
clone-of-snapshot...
Alex Elder
09:36 AM Tasks #2853: krbd: read path
Fuckin' A. My test passed with the clone too.
(It should, but I wasn't sure until I ran it.)
Alex Elder
09:29 AM Tasks #2853: krbd: read path
Sweet, clone of snap of clone of snap of image produced the
same result as the original image. Finally back to wher...
Alex Elder
09:27 AM Tasks #2853: krbd: read path
OK, that feature bit was my problem. I am now able to
successfully map a version 2 image.
Having done that I cre...
Alex Elder
07:34 AM Tasks #2853: krbd: read path
I have identified two problems that I was hitting.
First, it was not possible for me to map a format 2 rbd image,
...
Alex Elder
12:33 PM Bug #4531 (Fix Under Review): ObjectCacher: read waiters for parent data during copyup get reorde...
Dan, can you look this over? https://github.com/ceph/ceph/pull/214 Josh Durgin
12:27 PM Bug #4710 (Resolved): rbd: STRIPINGV2 feature specified by default for format 2 images
There's a check for whether it's really needed, but the defaults are 0 and 0, which are turned into regular striping ... Josh Durgin
12:03 PM Feature #4709 (Resolved): krbd: support stripingv2 images that don't require I/O path changes
Currently when the rbd command creates format 2 images, due to a bug it always includes the STRIPINGV2 feature bit un... Josh Durgin
07:16 AM Bug #4707: rbd CLI: bad error code masked by udevadm_settle
It looks like the other places udevadm settle is called
do not suffer from this problem.
Alex Elder
07:14 AM Bug #4707 (Resolved): rbd CLI: bad error code masked by udevadm_settle
I found that despite my attempt to map a v2 image the rbd
CLI gave me an exit status of 0.
Looking at the code, I...
Alex Elder

04/10/2013

06:29 PM Bug #4531: ObjectCacher: read waiters for parent data during copyup get reordered, causing the wr...
wip-objectcacher-handler-ordered Josh Durgin
11:15 AM Bug #4684 (Resolved): qa: test_formatted_output needs updating for progress going to stderr
commit:3888a12385aa6fcf35c9cdce9ad82a2cdd3377b7 Josh Durgin

04/09/2013

06:53 PM Tasks #2853: krbd: read path
I have the read path code mostly working now. The problem was
that an object request that gets redirected to a pare...
Alex Elder
08:42 AM Feature #4692: rbd qa: create an rbd lib shell script
Based on our discussion...
A user's ~/.teuthology.yaml specifies the root of the
test directory by defining the v...
Alex Elder
08:13 AM Feature #4692 (Rejected): rbd qa: create an rbd lib shell script
I have been repeating big blogs of script code and I'd
like to create a library file that can be incorporated
into ...
Alex Elder

04/08/2013

08:25 PM Feature #3761 (Resolved): kernel messenger: need to support multiple ops per request
The following have been committed to the "testing" branch
of the ceph-client git repository:
b0ae840 libceph: com...
Alex Elder
08:25 PM Feature #2770 (Resolved): krbd: define tasks to add osd_client compound class op support
The following has been committed to the "testing" branch
of the ceph-client git repository:
436b0c0 libceph: add,...
Alex Elder
08:24 PM Feature #4104 (Resolved): osd_client: support passing page array as data for CALL op
The following has been committed to the "testing" branch
of the ceph-client git repository:
51122dd libceph: make...
Alex Elder
08:20 PM Bug #4674 (Rejected): messenger: crash in read_partial_message()
Rejecting this. It was a bug in a patch that had not
yet been committed. I fixed that patch, and it has
now been ...
Alex Elder
08:17 PM Subtask #4658 (Resolved): rbd: don't assume one op per request
The following have been committed to the "testing" branch
of the ceph-client git repository:
78c8c1a rbd: don't s...
Alex Elder
08:16 PM Subtask #4657 (Resolved): libceph: have each op describe its own data
The following have been committed to the "testing" branch
of the ceph-client git repository:
73b4c46 libceph: add...
Alex Elder
08:15 PM Subtask #4656 (Resolved): libceph: maintain source rather than wire ops array
The following have been committed to the "testing" branch
of the ceph-client git repository:
e642226 rbd: define ...
Alex Elder
08:13 PM Bug #4659 (Resolved): rbd: define inbound data size for method ops
The following has been committed to the "testing" branch
of the ceph-client git repository:
7b67a62 rbd: define i...
Alex Elder
08:13 PM Subtask #4589 (Resolved): libceph: consolidate maintenance of message data length
The following has been committed to the "testing" branch
of the ceph-client git repository:
0af231f libceph: prov...
Alex Elder
01:23 PM Bug #4684 (Resolved): qa: test_formatted_output needs updating for progress going to stderr
... Josh Durgin
01:20 PM Bug #4683 (Resolved): librbd: diff_iterate test failures
These are probably the same underlying issue.
From ubuntu@teuthology:/a/teuthology-2013-04-08_02:44:59-rbd-next-te...
Josh Durgin

04/06/2013

12:55 PM Bug #4674: messenger: crash in read_partial_message()
And now that I've looked at it, I see the cause...
It's this commit:
commit 0b809454cd5cd5cf3129a5beb6ba06970fd...
Alex Elder
12:44 PM Bug #4674 (Rejected): messenger: crash in read_partial_message()
Testing with 3.8.0-ceph-00293-ga39ffbd (which is a test
version of some code I've posted for review) I hit a
crash ...
Alex Elder

04/05/2013

10:29 PM Bug #4670 (Resolved): librbd: DiffIterateStress test failing
commit:79b71441f8c2a1b282fa0e85badcb7d410c8005d Sage Weil
09:32 PM Bug #4670 (Resolved): librbd: DiffIterateStress test failing
it only happens when you do the full test set and not when you run just that test because the random seed is differen... Sage Weil
04:40 PM Feature #4104 (Fix Under Review): osd_client: support passing page array as data for CALL op
Found one small problem in this patch and another
one (probably the real cause) in one of the messenger
patches I p...
Alex Elder
03:34 PM Feature #4104: osd_client: support passing page array as data for CALL op
I have a patch that resolves this, based on the code just
posted for review for http://tracker.ceph.com/issues/3761....
Alex Elder
07:29 AM Feature #4104 (In Progress): osd_client: support passing page array as data for CALL op
Now that I've got the per-op data out for review I can
start looking at this one.
It is going to be my test case ...
Alex Elder
04:36 PM Feature #3761: kernel messenger: need to support multiple ops per request
I updated one of the patches posted:
[PATCH 5/6, v2] libceph: implement multiple data items in a message
Here's...
Alex Elder
03:31 PM Feature #3761: kernel messenger: need to support multiple ops per request
Hopefully this will be it.
I have one more patch, which adds a second outgoing data item
for a osd class method C...
Alex Elder
03:28 PM Feature #3761 (Fix Under Review): kernel messenger: need to support multiple ops per request
The following patches have been posted for review:
[PATCH 1/6] libceph: record bio length
[PATCH 2/6] libceph: mo...
Alex Elder
07:30 AM Feature #3761: kernel messenger: need to support multiple ops per request
Just to be clear, there is another handful of patches that
I have yet to post for review in order to complete this
...
Alex Elder
07:22 AM Feature #3761: kernel messenger: need to support multiple ops per request
Here are some patches that I just posted for review which
were part of implementing this, but were more along the
l...
Alex Elder
03:27 PM Feature #2770 (Fix Under Review): krbd: define tasks to add osd_client compound class op support
The following patch has been posted for review:
[PATCH 6/6] libceph: add, don't set data for a message
Alex Elder
02:50 PM Bug #4665 (Resolved): librbd: read_iterate() can overflow its return value
If the length requested is longer than int64_t, it will wrap around. This happened to someone on irc when doing an rb... Josh Durgin
09:13 AM Bug #2700: blkdeviotune method at libvirt doesn`t work on RBD volumes
Andrey Korolyov wrote:
> > One thing I noted, which doesn't seem related to RBD is that a Virtual Machine becomes ve...
Wido den Hollander
08:56 AM Bug #2700: blkdeviotune method at libvirt doesn`t work on RBD volumes
> One thing I noted, which doesn't seem related to RBD is that a Virtual Machine becomes very slow and unresponsive w... Andrey Korolyov
08:39 AM Bug #2700: blkdeviotune method at libvirt doesn`t work on RBD volumes
I've just submitted a patch for this to libvirt (also attached).
I tested it locally with libvirt 1.0.4 and it wor...
Wido den Hollander
08:24 AM Bug #4661 (Can't reproduce): xfstest 139 hung
i thought there was a bug open for this (saw it last week) but i guess not... Sage Weil
07:23 AM Subtask #4657 (Fix Under Review): libceph: have each op describe its own data
Out for review. Alex Elder
07:22 AM Subtask #4657: libceph: have each op describe its own data
The following patches have been posted for review:
[PATCH 10/20] libceph: add data pointers in osd op structures
...
Alex Elder
05:56 AM Subtask #4657 (Resolved): libceph: have each op describe its own data
Each osd request has an array of osd operations (ops). Each
op can have a data item associated with it.
Currentl...
Alex Elder
07:21 AM Subtask #4658 (Fix Under Review): rbd: don't assume one op per request
The following patches have been posted for review:
[PATCH 12/20] rbd: don't set data in rbd_osd_req_format_op()
[...
Alex Elder
06:17 AM Subtask #4658 (Resolved): rbd: don't assume one op per request
I found it became necessary to rework a little of the rbd code
while working through having the osd support multiple...
Alex Elder
07:12 AM Subtask #4656 (Fix Under Review): libceph: maintain source rather than wire ops array
The following patches have been posted for review:
[PATCH 07/20] rbd: define rbd_osd_req_format_op()
[PATCH 08/20...
Alex Elder
05:49 AM Subtask #4656 (Resolved): libceph: maintain source rather than wire ops array
The osd client currently maintains the ops array for an osd
request directly in its request message. It formats int...
Alex Elder
07:10 AM Bug #4659 (Fix Under Review): rbd: define inbound data size for method ops
The following patch has been posted for review:
[PATCH 01/20] rbd: define inbound data size for method ops
Alex Elder
06:25 AM Bug #4659 (Resolved): rbd: define inbound data size for method ops
When rbd creates an object request containing an object method call
operation it is passing 0 for the size. I origi...
Alex Elder
06:36 AM Subtask #4589 (Fix Under Review): libceph: consolidate maintenance of message data length
One more patch that probably should have been included has
now been posted for review:
[PATCH] libceph: provide d...
Alex Elder
05:23 AM Subtask #4589 (Resolved): libceph: consolidate maintenance of message data length
The following have been committed to the ceph-client
"testing" repository:
fb3f962 libceph: record length of bio ...
Alex Elder

04/04/2013

09:52 AM Feature #3893: krbd: document the new request code
It's no longer fresh, and perhaps it's no more (or less)
worthy of documenting than any other piece of code we
have...
Alex Elder
09:49 AM Bug #4559: krbd: kernel BUG when mapping unexisting rbd device
I'm updating this because the bug I identified in the
new code while trying to reproduce this has been
committed. ...
Alex Elder
09:30 AM Subtask #4589 (Fix Under Review): libceph: consolidate maintenance of message data length
The following patches have been posted for review:
[PATCH 3/9] libceph: record length of bio list with bio
[PATCH...
Alex Elder
09:01 AM Subtask #4589: libceph: consolidate maintenance of message data length
One more thing. I will be recording the message data length
(in CPU byte order) in a separate field in the message,...
Alex Elder
08:55 AM Subtask #4589: libceph: consolidate maintenance of message data length
Just a comment on the work that leads up to getting
this to happen.
My aim is to have ceph_osdc_build_request() b...
Alex Elder
08:09 AM Subtask #4125 (Resolved): kernel messenger: support multiple sources of data
As mentioned, I fixed a simple problem (which was
more a problem for the reader than the computer),
and am therefor...
Alex Elder
08:07 AM Feature #3861 (Resolved): rbd: consider splitting rbd_osd_req_op_create()
The following have been committed to the ceph-client
"testing" branch:
76aa2dc ceph: move max constant definition...
Alex Elder

04/02/2013

03:11 PM Feature #4211: get good qemu, libvirt versions+patches in CentOS+
Ian Colle

04/01/2013

11:56 AM Bug #4531 (In Progress): ObjectCacher: read waiters for parent data during copyup get reordered, ...
Josh Durgin
11:55 AM Bug #2608: rbd: hung xfstest 270
Test 270 now doesn't run because:
270 [not run] fsgqa user not defined.
There are a few tests that require a...
Alex Elder
11:34 AM Bug #2608: rbd: hung xfstest 270
Trying to run 270 right now.
Alex Elder
11:30 AM Bug #2608: rbd: hung xfstest 270
TODO: Try xfstests #270 on recent kernel (current testing
should be fine).
Alex Elder
11:54 AM Feature #4605 (Duplicate): rbd xfstests: define qa user, group, etc.
Some xfstests require a designated user (and as I recall
a group too) in order to run. I think one example of this
...
Alex Elder
11:48 AM Bug #3701 (Can't reproduce): qemu xfstest hung BUG: unable to handle kernel NULL pointer derefere...
Sage Weil
11:47 AM Fix #3588: rbd.py's clone should take stripe parms, call rbd_clone2
Josh Durgin
11:47 AM Bug #3871: krbd: initial header read may be out of date
Ian Colle
11:26 AM Feature #4444 (Resolved): send/receive rbd snapshots
Sage Weil
11:26 AM Feature #4084 (Resolved): rbd: incremental backups
Sage Weil
11:26 AM Feature #4445 (Resolved): librbd: expose changed objects since a given snapshot
Sage Weil
09:26 AM Bug #4540 (Resolved): libceph: problem in ceph_osdc_msg_data_set
Sage Weil

03/31/2013

01:10 PM Bug #3737: Higher ping-latency observed in qemu with rbd_cache=true during disk-write
Thanks for your great work! Is there already a way / branch to test this with bobtail? Stefan Priebe
 

Also available in: Atom