Commit Graph

5753 Commits

Author SHA1 Message Date
Sage Weil
59d6e18017 osd: keep peer_info.last_{update,complete} up to date in case we get later stray
We need to be able to call peer() again after going active and get
meaningful results.
2009-01-26 16:21:50 -08:00
Sage Weil
63f04bf189 osd: bit more verbose in oldest_update calculation 2009-01-26 16:21:49 -08:00
Sage Weil
f37d4b42c4 osd: adjust generate_backlog assertions
We should never generate a backlog while active.
2009-01-26 16:21:48 -08:00
Sage Weil
da981f57b0 mds: clean up EUpdate output 2009-01-26 16:21:47 -08:00
Sage Weil
c5f55f2ab7 mds: do not trim log during recovery 2009-01-26 16:21:46 -08:00
Sage Weil
898e90cbe7 osd: only check replicas in recover_replicas 2009-01-26 16:21:45 -08:00
Sage Weil
69d2fad7db osd: clean up activate, peer recovery debug output 2009-01-26 16:21:44 -08:00
Yehuda Sadeh
85b9900676 messenger: added a no-crc option 2009-01-26 12:47:48 -08:00
Sage Weil
814e9c719f osd: fix pg log trimming
Log entries rarely ever fall on block boundaries.  Behave
accordingly.

Also, decide whether to trim on primary only, at a high level in
op_modify.
2009-01-26 11:23:25 -08:00
Sage Weil
68d19a3dc1 paxos: tolerate commits for older states
We may have races if paxos recovery restarts.
2009-01-26 11:06:42 -08:00
Sage Weil
654e90704b osd: fix repop cleanup in on_change, _shutdown 2009-01-26 10:27:01 -08:00
Sage Weil
21367558ba ceph: warn when we get message with wrong fsid 2009-01-26 10:26:58 -08:00
Sage Weil
bdf405cd02 todos 2009-01-23 16:47:21 -08:00
Sage Weil
9a63cb13be paxos: ignore LAST message if pn is old
And old PN means that it's from a prior COLLECT attempt.
2009-01-23 16:47:21 -08:00
Sage Weil
6e2728eb9c mds: increase ino prealloc limit to 1000
Ideally this should self-tune, somehow...
2009-01-23 16:44:42 -08:00
Sage Weil
4df3be7ed1 osd: remove RepGather::put() debug print 2009-01-23 16:44:41 -08:00
Sage Weil
fd55dc6ad6 crush: remote list builder printf 2009-01-23 16:44:40 -08:00
Sage Weil
d3591be52b dstart: mount btrfs with new options 2009-01-23 16:44:40 -08:00
Sage Weil
cfdd83d741 kclient: statfs_request_tree alloc context is NOFS, not ATOMIC 2009-01-23 16:43:09 -08:00
Yehuda Sadeh
59369fb9c4 config: added include, misc stuff 2009-01-23 15:37:12 -08:00
Sage Weil
c4760afe68 kclient: do sync writepages if FILE_WRBUFFER is being revoked
This doesn't capture the case where we already started writeout
and _then_ the MDS tries to revoke, but that's probably not worth
the complexity.
2009-01-23 14:50:13 -08:00
Sage Weil
26cac11150 mds: fix max_size update
Force wrlock if client is issued WR cap; whether they are flushing
dirty data is irrelevant to whether we can safely force a wrlock.
2009-01-23 14:40:26 -08:00
Sage Weil
311d3a49ff kclient: initiate a sync when doing writepages for O_SYNC writers
Include 'startsync' osd op in write if there are any O_SYNC writers
pending on the inode.

We should eventually do the same if our WRBUFFER cap is being
revoked.
2009-01-23 14:18:16 -08:00
Sage Weil
63c2e9ea49 mds: set straydn.first properly for rename overwrite
Also reorder unlink_local a bit to match rename_prepare pattern.
2009-01-23 13:43:17 -08:00
Sage Weil
8239bedecc mds: only update cap wanted if seq matches 2009-01-23 13:23:22 -08:00
Sage Weil
37348a1a79 kclient: fix osd writes
Fixes commit 9664adfcb2.
2009-01-23 12:52:19 -08:00
Sage Weil
a4a1d5424f mds: take straydn.first form inode.first during unlink 2009-01-23 12:43:14 -08:00
Sage Weil
9664adfcb2 kclient: resend osd ops when pg membership changes
Previously we resent only when the primary OSD changed.  See
f49f78d03b.
2009-01-23 12:43:14 -08:00
Yehuda Sadeh
46696ade9c config: read configuration file before parsing command line
also does not write configuration unless specified
2009-01-23 12:40:16 -08:00
Yehuda Sadeh
a92400c82f mount.ceph: fix segfault when port is not specified 2009-01-23 12:38:29 -08:00
Yehuda Sadeh
b929f12baa confutils: complete config.cc configuration and adjustments 2009-01-23 09:31:42 -08:00
Yehuda Sadeh
331d1c4c38 confutils: cleanup, bug fixes 2009-01-23 09:31:42 -08:00
Yehuda Sadeh
44550ae7d3 confutils: can flush config, preliminary config.cc integration 2009-01-23 09:31:42 -08:00
Yehuda Sadeh
0ba80f81b4 confutils: some cleanup 2009-01-23 09:31:42 -08:00
Yehuda Sadeh
78d12c824c confutils: encoding/decoding using templates 2009-01-23 09:31:42 -08:00
Yehuda Sadeh
68a144514f confutils: going forward 2009-01-23 09:31:42 -08:00
Yehuda Sadeh
1acf016c51 confutils: adding missing file 2009-01-23 09:31:42 -08:00
Yehuda Sadeh
1481960516 confutils: some more
Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net>
2009-01-23 09:31:42 -08:00
Yehuda Sadeh
9a103e5b76 confutils: some more changes
Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net>
2009-01-23 09:31:42 -08:00
Yehuda Sadeh
dbc6141999 config: some more changes
Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net>
2009-01-23 09:31:42 -08:00
Yehuda Sadeh
18fdf6ea1c confutils: still not usable 2009-01-23 09:31:42 -08:00
Sage Weil
0af200da88 config: remove some old cruft 2009-01-22 16:17:04 -08:00
Sage Weil
f49f78d03b osd: reset peering, in-flight repops on every pg change
Instead of complicated (and flawed) logic for letting in-progress rep ops
complete while the PG changes (but primary remains the same), reset the
pg state entirely.  Apply any ops we have in hand, but drop everything
else, including PUSH/PULL ops.

This vastly simplifies the logic in the OSD and makes it easy to reason
about things.

Fix clients (Objecter, osd_client) to resubmit ops when PG membership
changes (not just on primary change).
2009-01-22 16:14:52 -08:00
Sage Weil
4b224b9b8d mds: eval_cap_gather in handle_client_caps even if no update
We may have recalled caps and journaled an update for some but
not all locks.  We should check for cap gathers even if something
(else) is journaled.
2009-01-22 11:22:04 -08:00
Sage Weil
2564622a32 script: find high latency requests in mds log 2009-01-22 11:04:54 -08:00
Sage Weil
4c75e0a8b7 mds: fix xattr projection 2009-01-21 16:44:21 -08:00
Sage Weil
1c2d62486f mds: drop rdlocks _after_ journaling; use new journal_and_reply helper
If we drop locks earlier we may run contexts that journal _other_
items out of order.  Badness.
2009-01-21 16:23:00 -08:00
Sage Weil
0c6ffaa905 mds: make cdentry debug print nicer 2009-01-21 15:34:47 -08:00
Sage Weil
004898a73e mds: unique (per mds) cap_id
A new cap_id is issued each time an MDS creates a new capability,
and is checked when releasing a capability to ensure it is the same
capability instance.  This specifically avoids a race like:

1- mds issues cap
2- mds sends cap message
3- mds and client time out cap
4- client receives cap message, sends release
5- mds reissues cap on same inode
6- mds receives release, doesn't realize the release is for the
   old capability

Checking seq numbers isn't enough because the MDS may reissue the
cap any number of times between 3 and 6.
2009-01-21 15:34:31 -08:00
Sage Weil
62e5b801bc mds: set straydn.first correctly during unlink
We need to do this in _unlink_local, not get_or_create_stray, just
as we set dn->first elsewhere in Server.cc.
2009-01-21 14:52:38 -08:00