Project

General

Profile

Activity

From 11/08/2010 to 12/07/2010

12/07/2010

09:40 PM Bug #15 (Resolved): mds rejoin: invented dirfrags (MDCache.cc:3469)
commit:b5fd2e4d4ee4bf02a993e75b756a3775b2d566e5 Sage Weil
03:25 PM Feature #91: mds: up:shadow mode
Okay, this seems to be working now. Had to adjust how the Journaler treated read_pos and to fix a few of my new re-re... Greg Farnum

12/06/2010

12:42 PM Feature #600 (Resolved): mds: store full trace on directories
Done in commit:d69f3dd327730a61b614c9f41f6155626bc07686. Just loops through the parents and encodes them sequentially... Greg Farnum
11:03 AM Bug #451 (Closed): mds: replay error
It look like the cluster is running pretty old code (0.22~rc). This particular problem was fixed by 1c934ebd (0.23). Sage Weil
10:22 AM Bug #451 (In Progress): mds: replay error
Sage Weil
03:59 AM Bug #451: mds: replay error
<removed sensitive info> Henry Chang

12/05/2010

08:32 PM Feature #601: mds: order directory commits after rename
What if another file is renamed in the other direction? Do a partial commit first? Tricky. Sage Weil

12/04/2010

08:38 PM Feature #630 (Resolved): release caps on inodes unlinked by other clients
If client A writes a file, and client B unlinks it, client A needs to drop the inode sooner rather than later.
O...
Sage Weil

12/03/2010

09:36 AM Bug #623 (Resolved): MDS: MDSTable::load_2
Sage Weil
12:32 AM Bug #623: MDS: MDSTable::load_2
Yes, tried with the latest rc, works!
MDS starts and recovers, als mounting and using the FS goes fine.
Wido den Hollander

12/02/2010

06:16 PM Feature #91: mds: up:shadow mode
I have yet to implement trimming, but the basic restarting-replay bits are now in place along with hooks to make it s... Greg Farnum
04:52 PM Bug #623: MDS: MDSTable::load_2
I think that commit:da5ab7c9a49f8996b41783175683d4b8b13ece4d should fix this issue.
wido, can you re-run with the ...
Colin McCabe
04:44 PM Bug #623: MDS: MDSTable::load_2
root@noisy:/var/log/ceph# grep mark_all_unfound_as_lost *
[ no results ]
So we're not marking things as lost in...
Colin McCabe
11:52 AM Bug #623: MDS: MDSTable::load_2
actually -23 is NFILE, which is I think coming from the LOST code...but that should never trigger unless the admin ha... Sage Weil
05:12 AM Bug #623 (Resolved): MDS: MDSTable::load_2
On a small test machine I have a Ceph RC cluster running (Which was running a old unstable before), after my upgrade ... Wido den Hollander
11:25 AM Feature #626 (Closed): qa: add IOR, rompio, or other parallel workloads suite
We've had reports that rompio is just terrifically unstable, and shows serious scaling issues.
IOR is a more commo...
Greg Farnum

12/01/2010

09:14 AM Bug #344 (Resolved): cfuse should pass all qa tests
Sage asked me to mark this resolved. I ran the bonnie test yesterday and it eventually crashed when the disk ran out ... Greg Farnum

11/30/2010

04:20 PM Bug #594: mds: frag split/merge vs replay
disabled in v0.24 Sage Weil

11/29/2010

10:15 AM Subtask #547 (Resolved): mds: define fsck strategy, required metadata
Sage Weil
10:13 AM Bug #594: mds: frag split/merge vs replay
needs to be fixed in 0.24, or g_conf.mds_frag needs to be disabled. Sage Weil

11/23/2010

11:46 AM Feature #593 (Rejected): mds: fsck: anchor table repair
dup Sage Weil
09:39 AM Bug #608 (Resolved): mds: MDCache::create_system_inode()
this should be fixed by commit:fc212548aea1d7f001b56ba096a79ba54b8a92c3
Thanks!
Sage Weil
07:09 AM Bug #608 (Resolved): mds: MDCache::create_system_inode()
On a small test cluster I saw that my MDS was not coming up after a fresh mkcephfs, this is what the log showed:
<...
Wido den Hollander

11/22/2010

04:29 PM Feature #91: mds: up:shadow mode
Updated Journaler to make new interface options asynchronous.
Presently working on how to disambiguate between a one...
Greg Farnum
01:24 PM Feature #88 (Resolved): mds: change stray commit strategy to avoid rolling stray dir commits
commit:ac6b018acbeaf8670f8c268db164cfb8a12c171d Sage Weil
12:47 PM Feature #606 (Duplicate): mds: optionally store parent attr on file objects
The goal is to be able to find files contained in rebuilt directories (#603). We can store the same attrs we do for ... Sage Weil
12:45 PM Feature #605 (Rejected): mds: verify/repair anchor table
- Make sure every item we encounter while traversing the that is anchored correctly appears in the anchor table.
- M...
Sage Weil
12:43 PM Feature #603 (Resolved): mds: repair directory hierarchy
The goals are
- rebuild missing/corrupt directories
- repair multiple primary links to directories
We'll do so...
Sage Weil
12:40 PM Feature #602 (Resolved): mds: handle corrupt/missing journals
This probably means
- shutting down current instances, resetting cluster membership
- throwing out journals (or m...
Sage Weil
12:37 PM Feature #601 (New): mds: order directory commits after rename
When we rename something between directories, we should try to commit the target directory _before_ the source direct... Sage Weil
12:34 PM Feature #600 (Resolved): mds: store full trace on directories
Currently we only store the immediate parent; store a full trace up to the root. This is CInode::encode_parent_mutat... Sage Weil
09:14 AM Bug #596 (Resolved): crash during mds reconnect
Well, that seems to fix it. I added a releases vector to the MetaReqest so it will only encode the releases once, and... Greg Farnum

11/19/2010

08:21 PM Bug #596: crash during mds reconnect
The encode_cap_releases can only be called _once_, the very first time we send the request. So at some level this is... Sage Weil
04:22 PM Bug #596 (Resolved): crash during mds reconnect
While testing my Journaler changes, I got a cfuse segfault. My steps:
vstart with 1 of each daemon
mount cfuse
cop...
Greg Farnum
04:26 PM Feature #91 (In Progress): mds: up:shadow mode
I've been getting some proper time in on this on and off over the last few days. Pushed the Journaler changes to the ... Greg Farnum
02:29 PM Bug #594 (Resolved): mds: frag split/merge vs replay
Need to reconcile refragmenting with resolve stage. Currently handle_resolve assumes frags match, when in reality th... Sage Weil
10:14 AM Feature #545 (Resolved): mds: use bloom filter to supplement dirfrag COMPLETE flag
merged commit:4303820b43721a8b46ef36d0e9ef4e1167857c80 Sage Weil
09:38 AM Feature #593 (Rejected): mds: fsck: anchor table repair
We need to be able to fix up the anchor table when there are problems, to avoid e.g.... Sage Weil

11/17/2010

09:59 AM Bug #344: cfuse should pass all qa tests
At this point the only test it's failing is bonnie. This one tends to fail on a SEGV that just keeps going through th... Greg Farnum
09:57 AM Bug #583 (Resolved): cfuse fails snaptest-upchildrealms
Okay, a proper fix for this is going to require a bit of work, since right now Inodes can only have one parent dentry... Greg Farnum
09:52 AM Cleanup #588 (Resolved): Allow Inodes to have multiple parent Dentries
Right now, cached Inodes can only have one parent Dentry. This is unfortunate when there are multiple hard links to a... Greg Farnum

11/16/2010

06:21 PM Bug #583: cfuse fails snaptest-upchildrealms
Looks like the problem is caused by linking b/bar to b/foo. The server response to goes through insert_dentry_inode v... Greg Farnum
06:17 PM Bug #583 (Resolved): cfuse fails snaptest-upchildrealms
Fails to rm a/b, ENOTEMPTY. Greg Farnum
12:06 PM Feature #483 (Resolved): mds: add timestamp to LogEvent
commit:8f24919d39734cf518f2bf6e50faf6f5266d6eff Sage Weil
11:52 AM Feature #560 (Resolved): mds: alternate directory hashing
kernel part is done and in unstable branch, currently commit:9f62e3eaafd52875e1f2e4344e11e51ddb726f48 Sage Weil
09:59 AM Feature #560: mds: alternate directory hashing
commit:05bd6b078d743d6c235c0fcedda7ee4f64ab2ad5 has it working for the user client. Sage Weil

11/15/2010

04:54 PM Feature #560: mds: alternate directory hashing
almost there. need to fix/test uclient hashing.
then implement for kclient...
Sage Weil
01:39 PM Feature #545: mds: use bloom filter to supplement dirfrag COMPLETE flag
Pushed it to branch "mds" (which I apparently created, but thought existed...weird!). Testing it now on a secondary i... Greg Farnum

11/12/2010

02:16 PM Feature #545: mds: use bloom filter to supplement dirfrag COMPLETE flag
Trying to find a bloom filter library. Unfortunately there don't seem to be any available under a GPL-compatible lice... Greg Farnum
01:15 PM Cleanup #514 (Rejected): Optimize MIX/MIX_STALE reconnects, etc
mix_stale is no more Sage Weil
07:56 AM Bug #561 (Resolved): snaptest-2 doesn't execute properly
Figured this out. LSSNAPs was adding the snap dentries to the cache under the parent dir instead of the hidden .snap... Sage Weil

11/11/2010

03:09 PM Tasks #366 (New): test snaptests against clustered mds failures
Sage Weil
03:08 PM Tasks #366 (Rejected): test snaptests against clustered mds failures
Sage Weil
03:08 PM Bug #362 (Rejected): mds: rejoin crashes on snaptest-2 workload
Sage Weil

11/10/2010

09:46 PM Bug #561: snaptest-2 doesn't execute properly
I ran the test again and didn't get an mds crash. There was one issue remaining:... Greg Farnum
06:14 PM Bug #561 (In Progress): snaptest-2 doesn't execute properly
I think I may have finally nailed this problem, or at least found a band-aid by more aggressively removing the I_COMP... Greg Farnum
09:18 PM Bug #570 (Resolved): Locker::_do_null_snapflush assert failure
Sage Weil
09:18 PM Bug #570: Locker::_do_null_snapflush assert failure
Nice catch. Fixed by commit:3d10b340748e5bbff86b49ac7386da9efa27a070. Added a unit test too! Sage Weil
02:58 PM Bug #570 (Resolved): Locker::_do_null_snapflush assert failure
Seen this a lot while working on the snaptest-2 issue, when shutting down cfuse.... Greg Farnum
08:18 AM Feature #548 (Resolved): mds: shadowreplay one-shot mode
commit:ca3693d8ffcdffc3ae95eaba506a72889829bcb5 makes minimal changes to the MDS and MDSMonitor code to enable the ne... Greg Farnum

11/09/2010

12:59 PM Bug #556 (Resolved): clustered mds: rename
this wasn't too bad.. the locking auth_pin scheme changed a while ago and the auth_pin allowance didn't get adjusted ... Sage Weil

11/08/2010

09:32 AM Bug #561: snaptest-2 doesn't execute properly
Okay, looks like this may be an issue with the test rather than Ceph. I just copied it into the root of the ceph moun... Greg Farnum
09:07 AM Bug #561 (Resolved): snaptest-2 doesn't execute properly
Checked it on cfuse and kclient:... Greg Farnum
09:20 AM Cleanup #427 (Rejected): mds: tie scatter pins directly to freeze machinery
no more scatterpins, yay! Sage Weil
07:39 AM Feature #560 (Resolved): mds: alternate directory hashing
Currently dentries are hashed among dirfrags using the linux dcache's hash function, which is pretty trivial. The pr... Sage Weil
 

Also available in: Atom