Samuel Just [Mon, 13 Feb 2012 19:49:42 +0000 (11:49 -0800)]
ReplicatedPG: refactor push and pull
Now, push progress is represented by ObjectRecoveryProgress. In
particular, rather than tracking data_subset_*ing, we track the furthest
offset before which the data will be consistent once cloning is complete.
sub_op_push now separates the pull response implementation from the
replica push implementation.
Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
Sage Weil [Mon, 13 Feb 2012 19:27:11 +0000 (11:27 -0800)]
add CEPH_FEATURE_OSDENC
Require it for osd <-> osd and osd <-> mon communication.
This covers all the new encoding changes, except hobject_t, which is used
between the rados command line tool and the OSD for a object listing
position marker. We can't distinguish between specific types of clients,
though, and we don't want to introduce any incompatibility with other
clients, so we'll just have to make do here. :(
Samuel Just [Sun, 12 Feb 2012 01:53:47 +0000 (17:53 -0800)]
ReplicatedPG: is_degraded may return true for backfill
If is_degraded returns true for backfill, the object may not be
in any replica's missing set. Only call start_recovery_op if
we actually started an op. This bug could cause a stuck
in backfill error.
Signed-off-by: Samuel Just <samuel.just@dreamhost.com> Signed-off-by: Sage Weil <sage@newdream.net>
Samuel Just [Sun, 12 Feb 2012 01:53:47 +0000 (17:53 -0800)]
ReplicatedPG: is_degraded may return true for backfill
If is_degraded returns true for backfill, the object may not be
in any replica's missing set. Only call start_recovery_op if
we actually started an op. This bug could cause a stuck
in backfill error.
Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
Sage Weil [Mon, 13 Feb 2012 19:06:34 +0000 (11:06 -0800)]
osd: remove peer_stat from MOSDOp entirely
We haven't used this feature for years and years, and don't plan to. It
was there to facilitate "read shedding", where the primary OSD would
forward a read request to a replica. However, replicas can't reply back
to the client in that case because OSDs don't initiate connections (they
used to).
Rip this out for now, especially since osd_peer_stat_t just changed.
Sage Weil [Mon, 13 Feb 2012 02:08:34 +0000 (18:08 -0800)]
osd: protect per-pg heartbeat peers with inner lock
Currently we update the overall heartbeat peers by looking directly at
per-pg state. This is potentially problematic now (#2033), and definitely
so in the future when we push more peering operations into the work queues.
Create a per-pg set of peers, protected by an inner lock, and update it
using PG::update_heartbeat_peers() when appropriate under pg->lock. Then
aggregate it into the osd peer list in OSD::update_heatbeat_peers() under
osd_lock and the inner lock.
We could probably have re-used osd->heartbeat_lock instead of adding a
new pg->heartbeat_peer_lock, but the finer locking can't hurt.
Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
Sage Weil [Sun, 12 Feb 2012 05:47:42 +0000 (21:47 -0800)]
osd: flush pg on activate _after_ we queue our transaction
We recently added a flush on activate, but we are still building the
transaction (the caller queues it), so calling osr.flush() here is totally
useless.
Instead, set a flag 'need_flush', and do the flush the next time we receive
some work.
This has the added benefit of doing the flush in the worker thread, outside
of osd_lock.
Sage Weil [Sun, 12 Feb 2012 05:24:54 +0000 (21:24 -0800)]
filestore: make flush() block forever if blackholed
If we are blackholing the disk, we need to make flush() wait forever, or
else the flush() logic will return (the IO wasn't queued!) and higher
layers will continue and (eventually) misbehave.
Sage Weil [Sat, 11 Feb 2012 22:55:06 +0000 (14:55 -0800)]
osd: filter trimming|purged snaps out of op SnapContext
We can receive an op with an old SnapContext that includes snaps that we've
already trimmed or are in the process of trimming. Filter them out!
Otherwise we will recreate and add links into collections we've already
marked as removed, and we'll get things like ENOTEMPTY when we try to
remove them. Or just leave them laying around.
Fixes: #1949 Signed-off-by: Sage Weil <sage@newdream.net>
Sage Weil [Sat, 11 Feb 2012 17:28:14 +0000 (09:28 -0800)]
osd: queue pg removal under pg's epoch
The PG may be doing work relative to a different epoch than what the osd
has. Make sure the PG removal message is queued under that epoch to avoid
confusing/crashing the recipient like so:
2012-02-10 23:26:35.691793 7f387281f700 osd.3 514 queue_pg_for_deletion: 0.0
osd/OSD.cc: In function 'void OSD::handle_pg_remove(OpRequest*)' thread 7f387281f700 time 2012-02-10 23:26:35.691820
osd/OSD.cc: 4860: FAILED assert(pg->get_primary() == m->get_source().num())
Greg Farnum [Fri, 10 Feb 2012 23:07:10 +0000 (15:07 -0800)]
mon: remove the last_consumed setting in Paxos
This was only ever used while initializing the Paxos machine, and it
doesn't need to be. Its existence is just an invitation to have races
between updating the stashed data and the stashed version.
Greg Farnum [Fri, 10 Feb 2012 23:02:03 +0000 (15:02 -0800)]
mon: handle inconsistent disk states on startup.
This lets us recover from an interrupted slurp while still noticing
other corruption issues. Rather than running init() and then
update_from_paxos() on each instance, we run init() and check
consistency. If it is consistent, we update_from_paxos as before. If
it is not, we do nothing and detect the slurping state
in handle_probe_reply(). (This assumes the disk was in a slurping state. If not, the
daemon crashes because something else went horribly wrong.)
While we're at it, remove unnecessary sets of first_committed. These
are done in the call to pax->trim_to().
Sage Weil [Fri, 10 Feb 2012 22:38:13 +0000 (14:38 -0800)]
messages: populate header.version in constructor
Define a HEAD_VERSION and COMPAT_VERSION for any versioned message. Pass
to Message constructor so that it is always initialized, even from the
the default constructor. That's needed because we use that to check
decoding compatibility when receiving/decoding messages.
If we are conditionally encoding an old version, explicitly set
header.version in encode_payload().
We also set compat_version to demonstrate what will happen for future
revisions. In this case, it's moot, because no old code understands
compat_version yet: nobody with old decode code will see these values
anyway. But use this opportunity to demonstrate how it would be used in
the future.
Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
Greg Farnum [Fri, 10 Feb 2012 18:42:24 +0000 (10:42 -0800)]
mon: add a slurping flag to the Paxos state
Set it before we start slurping, and clear it when we end slurping.
This allows us to differentiate between deliberately inconsistent
disk states, and broken disk states. Run simple checks in a new
is_consistent() call.
Greg Farnum [Fri, 10 Feb 2012 17:16:58 +0000 (09:16 -0800)]
mon: initialize paxos state in constructor
These should all be initialized in init() anyway
(except accepted_pn_from, which is set in collect and handle_collect),
but initializing them to safe defaults in the constructor provides
a safety net.
Sage Weil [Fri, 10 Feb 2012 05:54:34 +0000 (21:54 -0800)]
osd: new encoding for pg_create_t
There was no version encoding previously, so this is an incompatible
change. Fortunately this type is only used in one place, MOSDPGCreate,
so we'll rev that encoding and compensate there. All is well!
Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
projects / ceph.git / log