]>
git.apps.os.sepia.ceph.com Git - ceph.git/log
Sage Weil [Wed, 3 Dec 2008 23:06:25 +0000 (15:06 -0800)]
Merge branch 'diskformat' into unstable
Sage Weil [Wed, 3 Dec 2008 22:57:23 +0000 (14:57 -0800)]
mon: include last_scrub info in pg dump
Sage Weil [Wed, 3 Dec 2008 22:57:09 +0000 (14:57 -0800)]
osd: remove pg from recovery_wq with clear_primary_state
Sage Weil [Wed, 3 Dec 2008 22:51:26 +0000 (14:51 -0800)]
osd: make pg refcounting vs work queues constent
Either refcount items in queue, or don't.
Sage Weil [Wed, 3 Dec 2008 22:37:10 +0000 (14:37 -0800)]
osd: do clone scrub based on our generated scrub map
Sage Weil [Wed, 3 Dec 2008 22:17:54 +0000 (14:17 -0800)]
osd: scrub info in pg_stat_t. scrub states.
Sage Weil [Wed, 3 Dec 2008 21:55:48 +0000 (13:55 -0800)]
osd: fix small quirk read_log missing generation
The missing entry .have field was probably wrong due to the use
of missing.add_event (which assumes missing is up to date wrt
the previous log entry). Use the prior version we just pulled off
disk instead.
Also, be a bit more verbose.
Sage Weil [Wed, 3 Dec 2008 21:41:12 +0000 (13:41 -0800)]
mon: always discard pending on election completion
Previously we tried to save the pending if we were still the
leader. The problem is that while we were not leader, we may have
missed out on some updates, in which case the pending may no longer
be based on the current state.
In the future, we could make the commit waiters smart about callback
return codes so that they try to reapply. For now, don't worry
about it.
Sage Weil [Wed, 3 Dec 2008 20:26:24 +0000 (12:26 -0800)]
mds: update segment on ETableServer replay
Otherwise we may forget to flush table changes to disk before
trimming.
Also, clean up code a bit to use update_segment() whenever
possible (instead of duplicating the specific LogSegment update).
Sage Weil [Wed, 3 Dec 2008 20:20:35 +0000 (12:20 -0800)]
mds: print table version loaded during log replay
Sage Weil [Wed, 3 Dec 2008 20:20:22 +0000 (12:20 -0800)]
osd: default 2x pg only for now
Sage Weil [Wed, 3 Dec 2008 20:19:59 +0000 (12:19 -0800)]
osd: distributed scrub compares primary vs replica contents
The checks are still pretty trivial at this point.
Sage Weil [Wed, 3 Dec 2008 18:35:10 +0000 (10:35 -0800)]
osd: do not clear ops vector to indicate noop (protocol change)
The reply needs to include the full ops vector. Use a separate
flag to indicate a noop.
Sage Weil [Wed, 3 Dec 2008 00:02:43 +0000 (16:02 -0800)]
osd: rewrite pg_stats queueing
Use an xlist instead of a separate map. Avoid inefficient
requeueing and external map overhead.
Sage Weil [Tue, 2 Dec 2008 22:38:12 +0000 (14:38 -0800)]
osd: remove useless raid4pg from build
Yehuda Sadeh [Wed, 3 Dec 2008 18:10:55 +0000 (10:10 -0800)]
kclient: fix oops in case written size doesn't match request
Yehuda Sadeh [Wed, 3 Dec 2008 00:16:41 +0000 (16:16 -0800)]
kclient: some logs revision
Sage Weil [Tue, 2 Dec 2008 22:27:30 +0000 (14:27 -0800)]
osd: don't forget about skipped clones during recover_primary
Only advance requested_to if we haven't skipped any items.
Sage Weil [Tue, 2 Dec 2008 22:26:06 +0000 (14:26 -0800)]
always print snapids in hex
Sage Weil [Tue, 2 Dec 2008 22:25:54 +0000 (14:25 -0800)]
osd: log scrub errors to system log
Sage Weil [Tue, 2 Dec 2008 22:28:30 +0000 (14:28 -0800)]
mon: system-wide log
Pretty rudimentary still.
Sage Weil [Tue, 2 Dec 2008 20:03:15 +0000 (12:03 -0800)]
mds: pick_inode_snap should consider follows==0 valid
I suspect a larger audit of 'follows' semantics may be necessary..
but this fixes the bug I was seeing with:
echo asdf > a
mkdir .snap/1
echo qwer > b
mkdir .snap/2
echo zxcv > a
mkdir .snap/3
sync
cat .snap/1/a # empty
ll .snap/* # hangs
Yehuda Sadeh [Tue, 2 Dec 2008 21:37:02 +0000 (13:37 -0800)]
kclient: initialize some protocol fields
Sage Weil [Tue, 2 Dec 2008 03:00:58 +0000 (19:00 -0800)]
osd: log stats for push and pull bytes
Sage Weil [Tue, 2 Dec 2008 19:45:37 +0000 (11:45 -0800)]
mds: avoid overlapping release attempts
If the first release attempt is waiting for the log to flush, we
should avoid sending any RELEASED ack until all releases have
flushed. That is, only the last release will ack. Keep a counter
in Capability to do this.
Otherwise, we may close out a capability from under a release
that is flushing, and our seq # will be meaningless later in
_finish_release_cap() when we're trying to decide what to do.
Sage Weil [Tue, 2 Dec 2008 19:09:16 +0000 (11:09 -0800)]
kclient: avoid queueing cap_snap when nothing is dirty or writing
Save ourselves the trouble when there is nothing to flush
Sage Weil [Tue, 2 Dec 2008 18:49:22 +0000 (10:49 -0800)]
osd: send old_version to replicas
Otherwise CLONE entries in the PG log on replicas have 0'0 for
prior_version, and everything goes to hell.
Sage Weil [Tue, 2 Dec 2008 18:43:36 +0000 (10:43 -0800)]
osd: always get old_version; include in debug output
Sage Weil [Tue, 2 Dec 2008 18:00:18 +0000 (10:00 -0800)]
osd: show prior_version in log dump, output recovery_primary debug output
Sage Weil [Tue, 2 Dec 2008 05:13:34 +0000 (21:13 -0800)]
mds: suspend instead of suicide on beacon timeout
If we don't hear from the monitor, suspend doing any useful work instead
of just committing suicide. If the monitor comes back and hasn't killed
us off, then we're fine. If we've been marked as failed, we will shut
down as before.
Sage Weil [Tue, 2 Dec 2008 00:55:40 +0000 (16:55 -0800)]
filestore: show return codes in debug output
Sage Weil [Tue, 2 Dec 2008 00:53:16 +0000 (16:53 -0800)]
object: print snapid in hex
Sage Weil [Wed, 26 Nov 2008 22:48:52 +0000 (14:48 -0800)]
osd: allow admin to mark osd lost to kickstart recovery (disk format change)
This is important when an osd (or osds) may contain modifications
but is offline. If the data is truly lost, we can kickstart
recovery.
Note that if the osd was storing metadata, this could be
especially dangerous!
Sage Weil [Tue, 2 Dec 2008 00:31:16 +0000 (16:31 -0800)]
osd: clean up pg_stat, osd_stat summation, fields a bit
Yehuda Sadeh [Tue, 2 Dec 2008 00:00:35 +0000 (16:00 -0800)]
kclient: no page cache for write without wrbuf cap
Yehuda Sadeh [Mon, 1 Dec 2008 23:51:58 +0000 (15:51 -0800)]
Merge branch 'unstable' of ssh://ceph.newdream.net/git/ceph into unstable
Yehuda Sadeh [Mon, 1 Dec 2008 23:50:36 +0000 (15:50 -0800)]
kclient: sync writes use page cache
Sage Weil [Mon, 1 Dec 2008 23:29:56 +0000 (15:29 -0800)]
kclient: clean out old BACKOFF bit flag, comments
Sage Weil [Mon, 1 Dec 2008 22:24:35 +0000 (14:24 -0800)]
osdmaptool: print new osd_info fields
down_at, last_clean interval, etc.
Sage Weil [Mon, 1 Dec 2008 23:16:24 +0000 (15:16 -0800)]
osd: make pg log dump obey debug levels
Sage Weil [Mon, 1 Dec 2008 23:13:25 +0000 (15:13 -0800)]
osd: rebuild past intervals when needed; tolerate partial info
Tolerate missing past_intervals attr.
Also, if only some past intervals are missing, rebuild them all; don't
assume that if any are there then all are there.
Sage Weil [Mon, 1 Dec 2008 19:03:52 +0000 (11:03 -0800)]
osd: send and process heartbeats in separate thread, channel
Use a separate dispatch thread to process heartbeats. Use a
separate thread to send them. This ensures something slow
(e.g. a map update) does not make an osd appear to be down.
This also means a spearate entity_addr for heartbeats, which puts
them over a separate TCP stream.
Sage Weil [Mon, 1 Dec 2008 22:01:45 +0000 (14:01 -0800)]
mds: do not purge until leases expire
Sage Weil [Mon, 1 Dec 2008 18:41:29 +0000 (10:41 -0800)]
lockdep: lockdep_dump_locks()
Handy for dumping held locks in gdb w/ 'p lockdep_dump_lock()'
Sage Weil [Mon, 1 Dec 2008 18:13:00 +0000 (10:13 -0800)]
rwlock: try_get_read, try_get_write
Sage Weil [Mon, 1 Dec 2008 15:13:30 +0000 (07:13 -0800)]
osd: optionally avoid zeroing trimmed log on disk
This is a half-hearted attempt to keep old PG log content around. It'll
still be lost if a PG moves to another node or the entire log is written
to disk for some other reason.
Yehuda Sadeh [Mon, 1 Dec 2008 20:36:37 +0000 (12:36 -0800)]
kclient: fix bad check
Yehuda Sadeh [Mon, 1 Dec 2008 19:39:00 +0000 (11:39 -0800)]
kclient: slient down some log message
Sage Weil [Mon, 1 Dec 2008 04:42:44 +0000 (20:42 -0800)]
osd: skip peer_info on down osds
We don't clean old/down OSDs out of peer_info map, since we may not
restart peering when strays go up/down. That's fine... just make sure
we ignore them later.
Sage Weil [Mon, 1 Dec 2008 04:41:50 +0000 (20:41 -0800)]
osd: remove bad PG::put() assertion
Sage Weil [Sun, 30 Nov 2008 21:06:37 +0000 (13:06 -0800)]
osd: fix lock inversion on workqueue shutdown
Simplify PG get/put vs lock/unlock. Since we are reference counting with
an atomic_t, we don't need to re-use PG::lock to protect the reference
count.
Sage Weil [Thu, 27 Nov 2008 16:34:52 +0000 (08:34 -0800)]
todo
Sage Weil [Thu, 27 Nov 2008 16:34:43 +0000 (08:34 -0800)]
workqueue: deliberately leak string with lock name
Lockdep assumes strings are statically allocated.
Ariela [Thu, 27 Nov 2008 01:17:05 +0000 (17:17 -0800)]
Merge branch 'unstable' of ssh://yehudasa@ceph.newdream.net/git/ceph into unstable
Ariela [Thu, 27 Nov 2008 01:16:43 +0000 (17:16 -0800)]
wireshark: update for win32
Sage Weil [Thu, 27 Nov 2008 00:20:48 +0000 (16:20 -0800)]
osd: fix bad sub_op_push assertion; only write data we need
We adjust the pushed buffer so that we only write the portions
of it that we can't clone.
Sage Weil [Thu, 27 Nov 2008 00:42:01 +0000 (16:42 -0800)]
objectcacher: only call flushed callback if there are also no dirty buffers
Otherwise we call the flushed_callback too soon.
Sage Weil [Thu, 27 Nov 2008 00:32:29 +0000 (16:32 -0800)]
mds: fix up loner_cap whenever we manually change filelock state
This is kind of a pain.
Sage Weil [Wed, 26 Nov 2008 22:35:56 +0000 (14:35 -0800)]
osd: clean up touch() calls to use exists bool
We only need to touch of the head object itself doesn't exist.
Do so far all ops. This works cleanly despite any op munging
above.
Sage Weil [Wed, 26 Nov 2008 22:35:02 +0000 (14:35 -0800)]
objectstore: fix touch()
Wrong opcode meant skewed args, and all kinds of badness.
Sage Weil [Wed, 26 Nov 2008 21:50:33 +0000 (13:50 -0800)]
mon: instruct individual pgs to scrub
Factor out pg parsing into pg_t.
Sage Weil [Wed, 26 Nov 2008 21:42:17 +0000 (13:42 -0800)]
osd: debug write_info a bit, clean up Transaction cruft
Sage Weil [Wed, 26 Nov 2008 21:41:14 +0000 (13:41 -0800)]
osd: initiate scrub via monitor message
Sage Weil [Wed, 26 Nov 2008 20:39:36 +0000 (12:39 -0800)]
objecter: scan_pgs even on original full map
We may have queued ops before getting _any_ map; those still need to
be kicked.
Sage Weil [Wed, 26 Nov 2008 20:18:10 +0000 (12:18 -0800)]
osd: ensure target osd is still up when sending MPGRemoves
Sage Weil [Wed, 26 Nov 2008 19:23:15 +0000 (11:23 -0800)]
osd: move stats into PG::Info (disk format change)
We want the pg stats to propagate along with last_update. Do so
in merge_log.
Also, stop doing delayed stats update on primary; we always update
the in-core copy of Info, and only delay applying the transaction
to disk. At least currently.
Sage Weil [Wed, 26 Nov 2008 18:55:54 +0000 (10:55 -0800)]
osd: (re)set degraded flag on activate
This ensures the bit is properly set on newly created PGs..
Sage Weil [Wed, 26 Nov 2008 18:55:14 +0000 (10:55 -0800)]
timer: discard unfired events on shutdown
Mostly this just cleans up valgrind leak check output.
Sage Weil [Wed, 26 Nov 2008 18:44:48 +0000 (10:44 -0800)]
client: fix use-after-free
put_node at the end.
Sage Weil [Wed, 26 Nov 2008 18:35:23 +0000 (10:35 -0800)]
msgr: discard queued messages when closing pipe
These were leaking whenever we, say, did mark_down().
Sage Weil [Wed, 26 Nov 2008 18:19:08 +0000 (10:19 -0800)]
objectcacher: do callbacks _last_ to avoid a use-after-free
The callback may call back into release_set, so do not assume any pointers
will remain valid after the callback.
Sage Weil [Wed, 26 Nov 2008 17:58:32 +0000 (09:58 -0800)]
mds: initialize CInode::loner_cap when twiddling filelock states after reconnect
loner_cap must either be defined or not defined to match the lock states.
Sage Weil [Wed, 26 Nov 2008 17:57:35 +0000 (09:57 -0800)]
objecter: use full osdmap to get started
Previously we requested and then decoded the full history of incrementals,
a big waste of time during startup.
Sage Weil [Wed, 26 Nov 2008 18:07:54 +0000 (10:07 -0800)]
osd: ensure 0-byte object created by push
Specifically, a zero-length HEAD object whose snapset we care
about.
Sage Weil [Wed, 26 Nov 2008 16:28:11 +0000 (08:28 -0800)]
osd: mark repops aborteds in on_shutdown
Otherwise the op_modify_ondisk() completion gets confused.
Sage Weil [Wed, 26 Nov 2008 01:31:34 +0000 (17:31 -0800)]
dstart: show filestore ops
Sage Weil [Wed, 26 Nov 2008 01:30:15 +0000 (17:30 -0800)]
osd: clear out workqueue queues on shutdown
Sage Weil [Wed, 26 Nov 2008 01:28:00 +0000 (17:28 -0800)]
mon: show both user data and actual disk space used
Sage Weil [Wed, 26 Nov 2008 01:26:56 +0000 (17:26 -0800)]
debug: rotate old courtesy symlinks to .0, .1, etc.
This will make it much easier to find the next-oldest instantiation of
osd foo.
Sage Weil [Tue, 25 Nov 2008 22:43:56 +0000 (14:43 -0800)]
osd: remove bad assertion in op_modify_ondisk
We may not be in waitfor_disk if we are marked failed and
on_osd_failure acked and removed us from the set.
Sage Weil [Tue, 25 Nov 2008 22:00:55 +0000 (14:00 -0800)]
osd: fix clone push when head is correct old version
If the replica's head is the clone source version, our push should instruct
the replica to clone its contents.
Sage Weil [Tue, 25 Nov 2008 21:19:16 +0000 (13:19 -0800)]
mds: remove anchors when destroy stray inodes
purge_stray() is now the sole caller of anchor_destroy, so we can still
avoid any locking considerations.
Sage Weil [Tue, 25 Nov 2008 20:50:00 +0000 (12:50 -0800)]
mds: clean up request write condition, can_forward logic a bit
Sage Weil [Tue, 25 Nov 2008 20:21:20 +0000 (12:21 -0800)]
osd: fix rare memory leak
Sage Weil [Tue, 25 Nov 2008 20:14:26 +0000 (12:14 -0800)]
cmonctl: print summary every 20 lines when in watch mode
Sage Weil [Tue, 25 Nov 2008 19:22:14 +0000 (11:22 -0800)]
osd: fix up recovery pointers a bit
Yehuda Sadeh [Tue, 25 Nov 2008 18:57:37 +0000 (10:57 -0800)]
wireshark: wireshark ceph plugin patch
Sage Weil [Tue, 25 Nov 2008 18:42:36 +0000 (10:42 -0800)]
osd: be a bit more verbose in push_to_replica
Sage Weil [Tue, 25 Nov 2008 18:02:48 +0000 (10:02 -0800)]
osd: lots of fixes
Sage Weil [Tue, 25 Nov 2008 00:41:54 +0000 (16:41 -0800)]
todos
Sage Weil [Tue, 25 Nov 2008 14:45:48 +0000 (06:45 -0800)]
osd: clean up repop code
Sage Weil [Tue, 25 Nov 2008 04:46:16 +0000 (20:46 -0800)]
osd: fix up repop_ack
Sage Weil [Tue, 25 Nov 2008 00:52:23 +0000 (16:52 -0800)]
osd: ack type in osd sub ops
Sage Weil [Tue, 25 Nov 2008 00:35:43 +0000 (16:35 -0800)]
osd: infrastructure for ack vs nvram vs disk osd_op ack types
NVRAM ack not generated, yet. The completion callbacks from the store
need some work first.
Sage Weil [Mon, 24 Nov 2008 22:56:46 +0000 (14:56 -0800)]
os: separate onjournal, ondisk callbacks for apply_transaction
Sage Weil [Mon, 24 Nov 2008 22:06:49 +0000 (14:06 -0800)]
context: all C_Gather to OR instead of AND subs.
That is, call completion when first sub completes.
Sage Weil [Mon, 24 Nov 2008 21:49:17 +0000 (13:49 -0800)]
osd: remove snap collection after it is trimmed
We can still end up with empty collections for existing snaps but no
local objects. However, they'll eventually go away when the snap is
deleted, so who cares.
Sage Weil [Mon, 24 Nov 2008 21:47:54 +0000 (13:47 -0800)]
os: add collection_empty method
Sage Weil [Mon, 24 Nov 2008 20:06:18 +0000 (12:06 -0800)]
todos
Sage Weil [Mon, 24 Nov 2008 20:06:08 +0000 (12:06 -0800)]
osd: reply with EBLACKLISTED if sender is blacklisted
Move reply_op_error helper into OSD.cc.