ceph/doc/changelog/v0.48.1argonaut.txt
Sage Weil 5ab4939c36 doc: v0.48.1argonaut release notes, changelog
Signed-off-by: Sage Weil <sage@inktank.com>
2012-08-14 10:06:16 -07:00

1287 lines
46 KiB
Plaintext

commit a7ad701b9bd479f20429f19e6fea7373ca6bba7c
Author: Sage Weil <sage@inktank.com>
Date: Mon Aug 13 14:58:51 2012 -0700
v0.48.1argonaut
commit d4849f2f8a8c213c266658467bc5f22763010bc2
Author: Yehuda Sadeh <yehuda@inktank.com>
Date: Wed Aug 1 13:22:38 2012 -0700
rgw: fix usage trim call encoding
Fixes: #2841.
Usage trim operation was encoding the wrong op structure (usage read).
Since the structures somewhat overlapped it somewhat worked, but user
info wasn't encoded.
Backport: argonaut
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
commit 515952d07107d442889754ec3bd6a344fad25d58
Author: Yehuda Sadeh <yehuda@inktank.com>
Date: Wed Aug 8 15:21:53 2012 -0700
cls_rgw: fix rgw_cls_usage_log_trim_op encode/decode
It was not encoding user, adding that and reset version
compatibility.
This changes affects command interface, makes use of
radosgw-admin usage trim incompatible. Use of old
radosgw-admin usage trim should be avoided, as it may
remove more data than requested. In any case, upgraded
server code will not handle old client's trim requests.
backport: argonaut
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
commit 2e77130d5c80220be1612b5499d422de620d2d0b
Author: Yehuda Sadeh <yehuda@inktank.com>
Date: Tue Jul 31 16:17:22 2012 -0700
rgw: expand date format support
Relaxing the date format parsing function to allow UTC
instead of GMT.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
commit 14fa77d9277b5ef5d0c6683504b368773b39ccc4
Author: Yehuda Sadeh <yehuda@inktank.com>
Date: Thu Aug 2 11:13:05 2012 -0700
rgw: complete multipart upload can handle chunked encoding
Fixes: #2878
We now allow complete multipart upload to use chunked encoding
when sending request data. With chunked encoding the HTTP_LENGTH
header is not required.
Backport: argonaut
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
commit a06f7783fbcc02e775fc36f30e422fe0f9e0ec2d
Author: Yehuda Sadeh <yehuda@inktank.com>
Date: Wed Aug 1 11:19:32 2012 -0700
rgw_xml: xml_handle_data() appends data string
Fixes: #2879.
xml_handle_data() appends data to the object instead of just
replacing it. Parsed data can arrive in pieces, specifically
when data is escaped.
Backport: argonaut
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
commit a8b224b9c4877a559ce420a2e04f19f68c8c5680
Author: Yehuda Sadeh <yehuda@inktank.com>
Date: Wed Aug 1 13:09:41 2012 -0700
rgw: ETag is unquoted in multipart upload complete
Fixes #2877.
Removing quotes from ETag before comparing it to what we
have when completing a multipart upload.
Backport: argonaut
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
commit 22259c6efda9a5d55221fd036c757bf123796753
Author: Josh Durgin <josh.durgin@inktank.com>
Date: Wed Aug 8 15:24:57 2012 -0700
MonMap: return error on failure in build_initial
If mon_host fails to parse, return an error instead of success.
This avoids failing later on an assert monmap.size() > 0 in the
monmap in MonClient.
Fixes: #2913
Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
commit 49b2c7b5a79b8fb4a3941eca2cb0dbaf22f658b7
Author: Josh Durgin <josh.durgin@inktank.com>
Date: Wed Aug 8 15:10:27 2012 -0700
addr_parsing: report correct error message
getaddrinfo uses its return code to report failures.
Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
commit 7084f29544f431b7c6a3286356f2448ae0333eda
Author: Sage Weil <sage@inktank.com>
Date: Wed Aug 8 14:01:53 2012 -0700
mkcephfs: use default osd_data, _journal values
Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Greg Farnum <greg@inktank.com>
commit 96b1a496cdfda34a5efdb6686becf0d2e7e3a1c0
Author: Sage Weil <sage@inktank.com>
Date: Wed Aug 8 14:01:35 2012 -0700
mkcephfs: use new default keyring locations
The ceph-conf command only parses the conf; it does not apply default
config values. This breaks mkcephfs if values are not specified in the
config.
Let ceph-osd create its own key, fix copying, and fix creation/copying for
the mds.
Fixes: #2845
Reported-by: Florian Haas <florian@hastexo.com>
Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Greg Farnum <greg@inktank.com>
commit 4bd466d6ed49c7192df4a5bf0d63bda5d7d7dd9a
Author: Sage Weil <sage@inktank.com>
Date: Tue Jul 31 14:01:57 2012 -0700
osd: peering: detect when log source osd goes down
The Peering state has a generic check based on the prior set osds that
will restart peering if one of them goes down (or one of the interesting
down ones comes up). The GetLog state, however, can pull the log from
a peer that is not in the prior set if it got a notify from them (e.g., an
osd in an old interval that was down when the prior set was calculated).
If that osd goes down, we don't detect it and will block forward.
Fix by adding a simple check in GetLog for the newest_update_osd going
down.
(BTW GetMissing does not suffer from this problem because
peer_missing_requested is a subset of the prior set, so the Peering check
is sufficient.)
Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Samuel Just <sam.just@inktank.com>
commit 87defa88a0c6d6aafaa65437a6e4ddd92418f834
Author: Sylvain Munaut <tnt@246tNt.com>
Date: Tue Jul 31 11:55:56 2012 -0700
rbd: fix off-by-one error in key name
Fixes: #2846
Signed-off-by: Sylvain Munaut <tnt@246tNt.com>
commit 37d5b46269c8a4227e5df61a88579d94f7b56772
Author: Sylvain Munaut <tnt@246tNt.com>
Date: Tue Jul 31 11:54:29 2012 -0700
secret: return error on empty secret
Signed-off-by: Sylvain Munaut <tnt@246tNt.com>
commit 7b9d37c662313929b52011ddae47cc8abab99095
Author: Sage Weil <sage@inktank.com>
Date: Sat Jul 28 10:05:47 2012 -0700
osd: set STRAY on pg load when non-primary
The STRAY bit indicates that we should annouce ourselves to the primary,
but it is only set in start_peering_interval(). We also need to set it
initially, so that a PG that is loaded but whose role does not change
(e.g., the stray replica stays a stray) will notify the primary.
Observed:
- osd starts up
- mapping does not change, STRAY not set
- does not announce to primary
- primary does not re-check must_have_unfound, objects appear unfound
Fix this by initializing STRAY when pg is loaded or created whenever we
are not the primary.
Fixes: #2866
Signed-off-by: Sage Weil <sage@inktank.com>
commit 96feca450c5505a06868bc012fe998a03371b77f
Author: Sage Weil <sage@inktank.com>
Date: Fri Jul 27 16:03:26 2012 -0700
osd: peering: make Incomplete a Peering substate
This allows us to still catch changes in the prior set that would affect
our conclusions (that we are incomplete) and, when they happen, restart
peering.
Consider:
- calc prior set, osd A is down
- query everyone else, no good info
- set down, go to Incomplete (previously WaitActingChange) state.
- osd A comes back up (we do nothing)
- osd A sends notify message with good info (we ignore)
By making this a Peering substate, we catch the Peering AdvMap reaction,
which will notice a prior set down osd is now up and move to Reset.
Fixes: #2860
Signed-off-by: Sage Weil <sage@inktank.com>
commit a71e442fe620fa3a22ad9302413d8344a3a1a969
Author: Sage Weil <sage@inktank.com>
Date: Fri Jul 27 15:39:40 2012 -0700
osd: peering: move to Incomplete when.. incomplete
PG::choose_acting() may return false and *not* request an acting set change
if it can't find any suitable peers with enough info to recover. In that
case, we should move to Incomplete, not WaitActingChange, just like we do
a bit lower in GetLog() if we have non-contiguous logs. The state name is
more accurate, and this is also needed to fix bug #2860.
Signed-off-by: Sage Weil <sage@inktank.com>
commit 623026d9bc8ea4c845eb3b06d79e0ca9bef50deb
Merge: 87b6e80 9db7809
Author: Sage Weil <sage@inktank.com>
Date: Fri Jul 27 14:00:52 2012 -0700
Merge remote-tracking branch 'gh/stable' into stable-next
commit 9db78090451e609e3520ac3e57a5f53da03f9ee2
Author: Sage Weil <sage@inktank.com>
Date: Thu Jul 26 16:35:00 2012 -0700
osd: fixing sharing of past_intervals on backfill restart
We need to share past_intervals whenever we instantiate the PG on a peer.
In the PG activation case, this is based on whether our peer_info[] value
for that peer is dne(). However, the backfill code was updating the
peer info (history) in the block preceeding the dne() check, which meant
we never shared past_intervals in this case and the peer would have to
chew through a potentially large number of maps if the PG has not been
clean recently.
Fix by checking dne() prior to the backfill block. We still need to fill
in the message later because it isn't yet instantiated.
Fixes: #2849
Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Yehuda Sadeh <yehuda@inktank.com>
commit 87b6e8045a3a1ff6439d2684e960ad0dc8988b33
Merge: 81d72e5 7dfdf4f
Author: Sage Weil <sage@inktank.com>
Date: Thu Jul 26 15:04:12 2012 -0700
Merge remote-tracking branch 'gh/wip-rbd-bid' into stable-next
commit 81d72e5d7ba4713eb7c290878d901e21c0709028
Author: Sage Weil <sage@inktank.com>
Date: Mon Jul 23 10:47:10 2012 -0700
mon: make 'ceph osd rm ...' wipe out all state bits, not just EXISTS
This ensures that when a new osd reclaims that id it behaves as if it were
really new.
Backport: argonaut
Signed-off-by: Sage Weil <sage@inktank.com>
commit ad9c37f2c029f6eb372efb711b234014397057e9
Author: Sage Weil <sage@inktank.com>
Date: Mon Jul 9 20:54:19 2012 -0700
test_stress_watch: just one librados instance
This was creating a new cluster connection/session per iteration, and
along with it a few service threads and sockets and so forth.
Unfortunately, librados leaks like a sieve, starting with CephContext
and ceph::crypto::init(). See #845 and #2067.
Signed-off-by: Sage Weil <sage@inktank.com>
commit c60afe1842a48dd75944822c0872fce6a7229f5a
Merge: 8833050 35b1326
Author: Sage Weil <sage@inktank.com>
Date: Thu Jul 26 15:03:50 2012 -0700
Merge commit '35b13266923f8095650f45562d66372e618c8824' into stable-next
First batch of msgr fixes.
commit 88330505cc772a5528e9405d515aa2b945b0819e
Author: Samuel Just <sam.just@inktank.com>
Date: Mon Jul 9 15:53:31 2012 -0700
ReplicatedPG: fix replay op ordering
After a client reconnect, the client replays outstanding ops. The
OSD then immediately responds with success if the op has already
committed (version < ReplicatedPG::get_first_in_progress).
Otherwise, we stick it in waiting_for_ondisk to be replied to when
eval_repop concludes that waitfor_disk is empty.
Fixes #2508
Signed-off-by: Samuel Just <sam.just@inktank.com>
Conflicts:
src/osd/ReplicatedPG.cc
commit 682609a9343d0488788b1c6b03bc437b7905e4d6
Author: Sage Weil <sage@inktank.com>
Date: Wed Jul 18 12:55:35 2012 -0700
objecter: always resend linger registrations
If a linger op (watch) is sent to the OSD and updates the object, and then
the client loses the reply, it will resend the request. The OSD will see
that it is a dup, however, and not set up the in-memory session state for
the watch. This in turn will break the watch (i.e., notifies won't
get delivered).
Instead, always resend linger registration ops, so that we always have a
unique reqid and do the correct session registeration for each session.
* track the tid of the registation op for each LingerOp
* mark registrations ops as should_resend=false; cancel as needed
* when we send a new registration op, cancel the old one to ensure we
ignore the reply. This is needed becuase we resend linger ops on any
pg change, not just a primary change.
* drop the first_send arg to send_linger(), as we can now infer that
from register_tid == 0.
The bug was easily reproduced with ms inject socket failures = 500 and the
test_stress_watch utility.
Fixes: #2796
Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
commit 4d7d3e276967d555fed8a689976047f72c96c2db
Author: Sage Weil <sage@inktank.com>
Date: Mon Jul 9 13:22:42 2012 -0700
osd: guard class call decoding
Backport: argonaut
Signed-off-by: Sage Weil <sage@inktank.com>
commit 7fbbe4652ffb2826978aa1f1cacce4456d2ef1fc
Author: Sage Weil <sage@inktank.com>
Date: Thu Jul 5 18:08:58 2012 -0700
librados: take lock when signaling notify cond
When we are signaling the cond to indicate that a notify is complete,
take the appropriate lock. This removes the possibility of a race
that loses our signal. (That would be very difficult given that there
are network round trips involved, but this makes the lock/cond usage
"correct.")
Signed-off-by: Sage Weil <sage@inktank.com>
commit 6ed01df412b4f4745c8f427a94446987c88b6bef
Author: Sage Weil <sage@inktank.com>
Date: Sun Jul 22 07:46:11 2012 -0700
workqueue: kick -> wake or _wake, depending on locking
Break kick() into wake() and _wake() methods, depending on whether the
lock is already held. (The rename ensures that we audit/fix all
callers.)
Signed-off-by: Sage Weil <sage@inktank.com>
Conflicts:
src/common/WorkQueue.h
src/osd/OSD.cc
commit d2d40dc3059d91450925534f361f2c03eec9ef88
Author: Sage Weil <sage@inktank.com>
Date: Wed Jul 4 15:11:21 2012 -0700
client: fix locking for SafeCond users
Need to wait on flock, not client_lock.
Signed-off-by: Sage Weil <sage@inktank.com>
commit c963a21a8620779d97d6cbb51572551bdbb50d0b
Author: Sage Weil <sage@inktank.com>
Date: Thu Jul 26 15:01:05 2012 -0700
filestore: check for EIO in read path
Check for EIO in read methods and helpers. Try to do checks in low-level
methods (e.g., lfn_*()) to avoid duplication in higher-level methods.
The transaction apply function already checks for EIO on writes, and will
generate a nicer error message, so we can largely ignore the write path,
as long as errors get passed up correctly.
Signed-off-by: Sage Weil <sage@inktank.com>
commit 6bd89aeb1bf3b1cbb663107ae6bcda8a84dd8601
Author: Sage Weil <sage@inktank.com>
Date: Thu Jul 26 09:07:46 2012 -0700
filestore: add 'filestore fail eio' option, default true
By default we will assert/fail/crash on EIO from the underlying fs. We
already do this in the write path, but not the read path, or in various
internal infrastructure.
Signed-off-by: Sage Weil <sage@inktank.com>
commit e9b5a289838f17f75efbf9d1640b949e7485d530
Author: Sage Weil <sage@inktank.com>
Date: Tue Jul 24 13:53:03 2012 -0700
config: fix 'config set' admin socket command
Fixes: #2832
Backport: argonaut
Signed-off-by: Sage Weil <sage@inktank.com>
commit 1a6cd9659abcdad0169fe802ed47967467c448b3
Author: Sage Weil <sage@inktank.com>
Date: Wed Jul 25 16:35:09 2012 -0700
osd: break potentially large transaction into pieces
We do a similar trick elsewhere. Control this via a tunable. Eventually
we'll control the others (in a non-stable branch).
Signed-off-by: Sage Weil <sage@inktank.com>
commit 15e1622959f5a46f7a98502cdbaebfda2247a35b
Author: Sage Weil <sage@inktank.com>
Date: Wed Jul 25 14:53:34 2012 -0700
osd: only commit past intervals at end of parallel build
We don't check for gaps in the past intervals, so we should only commit
this when we are completely done. Otherwise a partial run and rsetart will
leave the gap in place, which may confuse the peering code that relies on
this information.
Signed-off-by: Sage Weil <sage@inktank.com>
commit 16302acefd8def98fc4597366d6ba2845e17fcb6
Author: Sage Weil <sage@inktank.com>
Date: Wed Jul 25 10:57:35 2012 -0700
osd: generate past intervals in parallel on boot
Even though we aggressively share past_intervals with notifies etc, it is
still possible for an osd to get buried behind a pile of old maps and need
to generate these if it has been out of the cluster for a while. This has
happened to us in the past but, sadly, we did not merge the work then.
On the bright side, this implementation is much much much cleaner than the
old one because of the pg_interval_t helper we've since switched to.
On bootup, we look at the intervals each pg needs and calclate the union,
and then iterate over that map range. The inner bit of the loop is
functionally identical to PG::build_past_intervals(), keeping the per-pg
state in the pistate struct.
Backport: argonaut
Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Yehuda Sadeh <yehuda@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
commit fca65ff52a5f7d49bcac83b3b2232963a879e446
Author: Sage Weil <sage@inktank.com>
Date: Wed Jul 25 10:58:07 2012 -0700
osd: move calculation of past_interval range into helper
PG::generate_past_intervals() first calculates the range over which it
needs to generate past intervals. Do this in a helper function.
Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Yehuda Sadeh <yehuda@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
commit 5979351ef3d3d03bced9286f79cbc22524c4a8de
Author: Sage Weil <sage@inktank.com>
Date: Wed Jul 25 10:58:28 2012 -0700
osd: fix map epoch boot condition
We only want to join the cluster if we can catch up to the latest
osdmap with a small number of maps, in this case a single map message.
Backport: argonaut
Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Yehuda Sadeh <yehuda@inktank.com>
commit 8c7186d02627f8255273009269d50955172efb52
Author: Sage Weil <sage@inktank.com>
Date: Tue Jul 24 20:18:01 2012 -0700
mon: ignore pgtemp messages from down osds
Signed-off-by: Sage Weil <sage@inktank.com>
commit b17f54671f350fd4247f895f7666d46860736728
Author: Sage Weil <sage@inktank.com>
Date: Tue Jul 24 20:16:04 2012 -0700
mon: ignore osd_alive messages from down osds
Signed-off-by: Sage Weil <sage@inktank.com>
commit 7dfdf4f8de16155edd434534e161e06ba7c79d7d
Author: Josh Durgin <josh.durgin@inktank.com>
Date: Mon Jul 23 14:05:53 2012 -0700
librbd: replace assign_bid with client id and random number
The assign_bid method has issues with replay because it is a write
that also returns data. This means that the replayed operation would
return success, but no data, and cause a create to fail. Instead, let
the client set the bid based on its global id and a random number.
This only affects the creation of new images, since the bid is put
into an opaque string as part of the object prefix.
Keep the server side assign_bid around in case there are old clients
still using it.
Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
commit dc2d67112163bee8b111f75ae3e3ca42884b09b4
Author: Dan Mick <dan.mick@inktank.com>
Date: Mon Jul 9 14:11:23 2012 -0700
librados: add new constructor to form a Rados object from IoCtx
This creates a separate reference to an existing connection, for
use when a client holding IoCtx needs to consult another (say,
for rbd cloning)
Signed-off-by: Dan Mick <dan.mick@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
commit c99671201de9d9cdf03bbf0f4e28e8afb70c280c
Author: Sage Weil <sage@inktank.com>
Date: Wed Jul 18 19:49:58 2012 -0700
add CRUSH_TUNABLES feature bit
Signed-off-by: Sage Weil <sage@inktank.com>
commit 0b579546cfddec35095b2aec753028d8e63f3533
Author: Josh Durgin <josh.durgin@inktank.com>
Date: Wed Jul 18 10:24:58 2012 -0700
ObjectCacher: fix cache_bytes_hit accounting
Misses are not hits!
Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
commit 2869039b79027e530c2863ebe990662685e4bbe6
Author: Pascal de Bruijn | Unilogic Networks B.V <pascal@unilogicnetworks.net>
Date: Wed Jul 11 15:23:16 2012 +0200
Robustify ceph-rbdnamer and adapt udev rules
Below is a patch which makes the ceph-rbdnamer script more robust and
fixes a problem with the rbd udev rules.
On our setup we encountered a symlink which was linked to the wrong rbd:
/dev/rbd/mypool/myrbd -> /dev/rbd1
While that link should have gone to /dev/rbd3 (on which a
partition /dev/rbd3p1 was present).
Now the old udev rule passes %n to the ceph-rbdnamer script, the problem
with %n is that %n results in a value of 3 (for rbd3), but in a value of
1 (for rbd3p1), so it seems it can't be depended upon for rbdnaming.
In the patch below the ceph-rbdnamer script is made more robust and it
now it can be called in various ways:
/usr/bin/ceph-rbdnamer /dev/rbd3
/usr/bin/ceph-rbdnamer /dev/rbd3p1
/usr/bin/ceph-rbdnamer rbd3
/usr/bin/ceph-rbdnamer rbd3p1
/usr/bin/ceph-rbdnamer 3
Even with all these different styles of calling the modified script, it
should now return the same rbdname. This change "has" to be combined
with calling it from udev with %k though.
With that fixed, we hit the second problem. We ended up with:
/dev/rbd/mypool/myrbd -> /dev/rbd3p1
So the rbdname was symlinked to the partition on the rbd instead of the
rbd itself. So what probably went wrong is udev discovering the disk and
running ceph-rbdnamer which resolved it to myrbd so the following
symlink was created:
/dev/rbd/mypool/myrbd -> /dev/rbd3
However partitions would be discovered next and ceph-rbdnamer would be
run with rbd3p1 (%k) as parameter, resulting in the name myrbd too, with
the previous correct symlink being overwritten with a faulty one:
/dev/rbd/mypool/myrbd -> /dev/rbd3p1
The solution to the problem is in differentiating between disks and
partitions in udev and handling them slightly differently. So with the
patch below partitions now get their own symlinks in the following style
(which is fairly consistent with other udev rules):
/dev/rbd/mypool/myrbd-part1 -> /dev/rbd3p1
Please let me know any feedback you have on this patch or the approach
used.
Regards,
Pascal de Bruijn
Unilogic B.V.
Signed-off-by: Pascal de Bruijn <pascal@unilogicnetworks.net>
Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
commit 426384f6beccabf9e9b9601efcb8147904ec97c2
Author: Sage Weil <sage@inktank.com>
Date: Mon Jul 16 16:02:14 2012 -0700
log: apply log_level to stderr/syslog logic
In non-crash situations, we want to make sure the message is both below the
syslog/stderr threshold and also below the normal log threshold. Otherwise
we get anything we gather on those channels, even when the log level is
low.
Signed-off-by: Sage Weil <sage@inktank.com>
commit 8dafcc5c1906095cb7d15d648a7c1d7524df3768
Author: Sage Weil <sage@inktank.com>
Date: Mon Jul 16 15:40:53 2012 -0700
log: fix event gather condition
We should gather an event if it is below the log or gather threshold.
Previously we were only gathering if we were going to print it, which makes
the dump no more useful than what was already logged.
Signed-off-by: Sage Weil <sage@inktank.com>
commit ec5cd6def9817039704b6cc010f2797a700d8500
Author: Samuel Just <sam.just@inktank.com>
Date: Mon Jul 16 13:11:24 2012 -0700
PG::RecoveryState::Stray::react(LogEvt&): reset last_pg_scrub
We need to reset the last_pg_scrub data in the osd since we
are replacing the info.
Probably fixes #2453
In cases like 2453, we hit the following backtrace:
0> 2012-05-19 17:24:09.113684 7fe66be3d700 -1 osd/OSD.h: In function 'void OSD::unreg_last_pg_scrub(pg_t, utime_t)' thread 7fe66be3d700 time 2012-05-19 17:24:09.095719
osd/OSD.h: 840: FAILED assert(last_scrub_pg.count(p))
ceph version 0.46-313-g4277d4d (commit:4277d4d3378dde4264e2b8d211371569219c6e4b)
1: (OSD::unreg_last_pg_scrub(pg_t, utime_t)+0x149) [0x641f49]
2: (PG::proc_primary_info(ObjectStore::Transaction&, pg_info_t const&)+0x5e) [0x63383e]
3: (PG::RecoveryState::ReplicaActive::react(PG::RecoveryState::MInfoRec const&)+0x4a) [0x633eda]
4: (boost::statechart::detail::reaction_result boost::statechart::simple_state<PG::RecoveryState::ReplicaActive, PG::RecoveryState::Started, boost::mpl::list<mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na>, (boost::statechart::history_mode)0>::local_react_impl_non_empty::local_react_impl<boost::mpl::list3<boost::statechart::custom_reaction<PG::RecoveryState::MQuery>, boost::statechart::custom_reaction<PG::RecoveryState::MInfoRec>, boost::statechart::custom_reaction<PG::RecoveryState::MLogRec> >, boost::statechart::simple_state<PG::RecoveryState::ReplicaActive, PG::RecoveryState::Started, boost::mpl::list<mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na>, (boost::statechart::history_mode)0> >(boost::statechart::simple_state<PG::RecoveryState::ReplicaActive, PG::RecoveryState::Started, boost::mpl::list<mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na>, (boost::statechart::history_mode)0>&, boost::statechart::event_base const&, void const*)+0x130) [0x6466a0]
5: (boost::statechart::simple_state<PG::RecoveryState::ReplicaActive, PG::RecoveryState::Started, boost::mpl::list<mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na>, (boost::statechart::history_mode)0>::react_impl(boost::statechart::event_base const&, void const*)+0x81) [0x646791]
6: (boost::statechart::state_machine<PG::RecoveryState::RecoveryMachine, PG::RecoveryState::Initial, std::allocator<void>, boost::statechart::null_exception_translator>::send_event(boost::statechart::event_base const&)+0x5b) [0x63dfcb]
7: (boost::statechart::state_machine<PG::RecoveryState::RecoveryMachine, PG::RecoveryState::Initial, std::allocator<void>, boost::statechart::null_exception_translator>::process_event(boost::statechart::event_base const&)+0x11) [0x63e0f1]
8: (PG::RecoveryState::handle_info(int, pg_info_t&, PG::RecoveryCtx*)+0x177) [0x616987]
9: (OSD::handle_pg_info(std::tr1::shared_ptr<OpRequest>)+0x665) [0x5d3d15]
10: (OSD::dispatch_op(std::tr1::shared_ptr<OpRequest>)+0x2a0) [0x5d7370]
11: (OSD::_dispatch(Message*)+0x191) [0x5dd4a1]
12: (OSD::ms_dispatch(Message*)+0x153) [0x5ddda3]
13: (SimpleMessenger::dispatch_entry()+0x863) [0x77fbc3]
14: (SimpleMessenger::DispatchThread::entry()+0xd) [0x746c5d]
15: (()+0x7efc) [0x7fe679b1fefc]
16: (clone()+0x6d) [0x7fe67815089d]
NOTE: a copy of the executable, or `objdump -rdS <executable>` is needed to interpret this.
Because we don't clear the scrub state before reseting info,
the last_scrub_stamp state in the info.history structure
changes without updating the osd state resulting in the
above assert failure.
Backport: stable
Signed-off-by: Samuel Just <sam.just@inktank.com>
commit 248cfaddd0403c7bae8e1533a3d2e27d1a335b9b
Author: Samuel Just <sam.just@inktank.com>
Date: Mon Jul 9 17:57:03 2012 -0700
ReplicatedPG: don't warn if backfill peer stats don't match
pinfo.stats might be wrong if we did log-based recovery on the
backfilled portion in addition to continuing backfill.
bug #2750
Signed-off-by: Samuel Just <sam.just@inktank.com>
commit bcb1073f9171253adc37b67ee8d302932ba1667b
Author: Sage Weil <sage@inktank.com>
Date: Sun Jul 15 20:30:34 2012 -0700
mon/MonitorStore: always O_TRUNC when writing states
It is possible for a .new file to already exist, potentially with a
larger size. This would happen if:
- we were proposing a different value
- we crashed (or were stopped) before it got renamed into place
- after restarting, a different value was proposed and accepted.
This isn't so unlikely for the log state machine, where we're
aggregating random messages. O_TRUNC ensure we avoid getting the tail
end of some previous junk.
I observed #2593 and found that a logm state value had a larger size on
one mon (after slurping) than the others, pointing to put_bl_sn_map().
While we are at it, O_TRUNC put_int() too; the same type of bug is
possible there, too.
Fixes: #2593
Signed-off-by: Sage Weil <sage@inktank.com>
commit 41a570778a51fe9a36a5b67a177d173889e58363
Author: Sage Weil <sage@inktank.com>
Date: Sat Jul 14 14:31:34 2012 -0700
osd: based misdirected op role calc on acting set
We want to look at the acting set here, nothing else. This was causing us
to erroneously queue ops for later (wasting memory) and to erroneously
print out a 'misdrected op' message in the cluster log (confusion and
incorrect [but ignored] -ENXIO reply).
Fixes: #2022
Signed-off-by: Sage Weil <sage@inktank.com>
commit b3d077c61e977e8ebb91288aa2294fb21c197fe7
Author: Josh Durgin <josh.durgin@inktank.com>
Date: Fri Jul 13 09:42:20 2012 -0700
qa: download tests from specified branch
These python tests aren't installed, so they need to be downloaded
Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
commit e855cb247b5a9eda6845637e2da5b6358f69c2ed
Author: Yehuda Sadeh <yehuda@inktank.com>
Date: Mon Jun 25 09:47:37 2012 -0700
rgw: don't override subuser perm mask if perm not specified
Bug #2650. We were overriding subuser perm mask whenever subuser
was modified, even if perm mask was not passed.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
commit d6c766ea425d87a2f2405c08dcec66f000a4e1a0
Author: James Page <james.page@ubuntu.com>
Date: Wed Jul 11 11:34:21 2012 -0700
debian: fix ceph-fs-common-dbg depends
Signed-off-by: James Page <james.page@ubuntu.com>
commit 95e8d87bc3fb12580e4058401674b93e19df6e02
Author: Yehuda Sadeh <yehuda@inktank.com>
Date: Wed Jul 11 11:52:24 2012 -0700
rados tool: remove -t param option for target pool
Bug #2772. This fixes an issue that was introduced when we
added the 'rados cp' command. The -t param was already used
for rados bench. With this change the only way to specify
a target pool is using --target-pool.
Though this problem is post argonaut, the 'rados cp' command
has been backported, so we need this fix there too.
Backport: argonaut
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
commit 5b10778399d5bee602e57035df7d40092a649c06
Author: Sage Weil <sage@inktank.com>
Date: Wed Jul 11 09:19:00 2012 -0700
Makefile: don't install crush headers
This is leftover from when we built a libcrush.so. We can re-add when we
start doing that again.
Reported-by: Laszlo Boszormenyi <gcs@debian.hu>
Signed-off-by: Sage Weil <sage@inktank.com>
commit 35b13266923f8095650f45562d66372e618c8824
Author: Sage Weil <sage@inktank.com>
Date: Tue Jul 10 13:18:27 2012 -0700
msgr: take over existing Connection on Pipe replacement
If a new pipe/socket is taking over an existing session, it should also
take over the Connection* associated with the existing session. Because
we cannot clear existing->connection_state, we just take another reference.
Clean up the comments a bit while we're here.
This affects MDS<->client sessions when reconnecting after a socket fault.
It probably also affects intra-cluster (osd/osd, mds/mds, mon/mon)
sessions as well, but I did not confirm that.
Backport: argonaut
Signed-off-by: Sage Weil <sage@inktank.com>
commit b387077b1d019ee52b28bc3bc5305bfb53dfd892
Author: Sage Weil <sage@inktank.com>
Date: Sun Jul 8 20:33:12 2012 -0700
debian: include librados-config in librados-dev
Reported-by: Laszlo Boszormenyi <gcs@debian.hu>
Signed-off-by: Sage Weil <sage@inktank.com>
commit 03c2dc244af11b711e2514fd5f32b9bfa34183f6
Author: Sage Weil <sage@inktank.com>
Date: Tue Jul 3 13:04:28 2012 -0700
lockdep: increase max locks
Hit this limit with the rados api tests.
Signed-off-by: Sage Weil <sage@inktank.com>
commit b554d112c107efe78ec64f85b5fe588f1e7137ce
Author: Sage Weil <sage@inktank.com>
Date: Tue Jul 3 12:07:28 2012 -0700
config: add unlocked version of get_my_sections; use it internally
Signed-off-by: Sage Weil <sage@inktank.com>
commit 01da287b8fdc07262be252f1a7c115734d3cc328
Author: Sage Weil <sage@inktank.com>
Date: Tue Jul 3 08:20:06 2012 -0700
config: fix lock recursion in get_val_from_conf_file()
Introduce a private, already-locked version.
Signed-off-by: Sage Weil <sage@inktank.com>
commit c73c64a0f722477a5b0db93da2e26e313a5f52ba
Author: Sage Weil <sage@inktank.com>
Date: Tue Jul 3 08:15:08 2012 -0700
config: fix recursive lock in parse_config_files()
The _impl() helper is only called from parse_config_files(); don't retake
the lock.
Signed-off-by: Sage Weil <sage@inktank.com>
commit 6646e891ff0bd31c935d1ce0870367b1e086ddfd
Author: Sage Weil <sage@inktank.com>
Date: Tue Jul 3 18:51:02 2012 -0700
rgw: initialize fields of RGWObjEnt
This fixes various valgrind warnings triggered by the s3test
test_object_create_unreadable.
Signed-off-by: Sage Weil <sage@inktank.com>
commit b33553aae63f70ccba8e3d377ad3068c6144c99a
Author: Yehuda Sadeh <yehuda@inktank.com>
Date: Fri Jul 6 13:14:53 2012 -0700
rgw: handle response-* params
Handle response-* params that set response header field values.
Fixes #2734, #2735.
Backport: argonaut
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
commit 74f687501a8a02ef248a76f061fbc4d862a9abc4
Author: Sage Weil <sage@inktank.com>
Date: Wed Jul 4 13:59:04 2012 -0700
osd: add missing formatter close_section() to scrub status
Also add braces to make the open/close matchups easier to see. Broken
by f36617392710f9b3538bfd59d45fd72265993d57.
Signed-off-by: Sage Weil <sage@inktank.com>
commit 020b29961303b12224524ddf78c0c6763a61242e
Author: Mike Ryan <mike.ryan@inktank.com>
Date: Wed Jun 27 14:14:30 2012 -0700
pg: report scrub status
Signed-off-by: Mike Ryan <mike.ryan@inktank.com>
commit db6d83b3ed51c07b361b27d2e5ce3227a51e2c60
Author: Mike Ryan <mike.ryan@inktank.com>
Date: Wed Jun 27 13:30:45 2012 -0700
pg: track who we are waiting for maps from
Signed-off-by: Mike Ryan <mike.ryan@inktank.com>
commit e1d4855fa18b1cda85923ad9debd95768260d4eb
Author: Mike Ryan <mike.ryan@inktank.com>
Date: Tue Jun 26 16:25:27 2012 -0700
pg: reduce scrub write lock window
Wait for all replicas to construct the base scrub map before finalizing
the scrub and locking out writes.
Signed-off-by: Mike Ryan <mike.ryan@inktank.com>
commit 27409aa1612c1512bf393de22b62bbfe79b104c1
Author: Yehuda Sadeh <yehuda@inktank.com>
Date: Thu Jul 5 15:52:51 2012 -0700
rgw: don't store bucket info indexed by bucket_id
Issue #2701. This info wasn't really used anywhere and we weren't
removing it. It was also sharing the same pool namespace as the
info indexed by bucket name, which is bad.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
commit 9814374a2b40e15c13eb03ce6b8e642b0f7f93e4
Author: Yehuda Sadeh <yehuda@inktank.com>
Date: Thu Jul 5 14:59:22 2012 -0700
test_rados_tool.sh: test copy pool
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
commit d75100667a539baf47c79d752b787ed5dcb51d7a
Author: Yehuda Sadeh <yehuda@inktank.com>
Date: Thu Jul 5 13:42:23 2012 -0700
rados tool: copy object in chunks
Instead of reading the entire object and then writing it,
we read it in chunks.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
commit 16ea64fbdebb7a74e69e80a18d98f35d68b8d9a1
Author: Yehuda Sadeh <yehuda@inktank.com>
Date: Fri Jun 29 14:43:00 2012 -0700
rados tool: copy entire pool
A new rados tool command that copies an entire pool
into another existing pool.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
commit 960c2124804520e81086df97905a299c8dd4e08c
Author: Yehuda Sadeh <yehuda@inktank.com>
Date: Fri Jun 29 14:09:08 2012 -0700
rados tool: copy object
New rados command: rados cp <src-obj> [dest-obj]
Requires specifying source pool. Target pool and locator can be specified.
The new command preserves object xattrs and omap data.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
commit 23d31d3e2aa7f2b474a7b8e9d40deb245d8be9de
Author: Sage Weil <sage@inktank.com>
Date: Fri Jul 6 08:47:44 2012 -0700
ceph.spec.in: add ceph-disk-{activate,prepare}
Reported-by: Jimmy Tang <jtang@tchpc.tcd.ie>
Signed-off-by: Sage Weil <sage@inktank.com>
commit ea11c7f9d8fd9795e127cfd7e8a1f28d4f5472e9
Author: Wido den Hollander <wido@widodh.nl>
Date: Thu Jul 5 15:29:54 2012 +0200
Allow URL-safe base64 cephx keys to be decoded.
In these cases + and / are replaced by - and _ to prevent problems when using
the base64 strings in URLs.
Signed-off-by: Wido den Hollander <wido@widodh.nl>
Signed-off-by: Sage Weil <sage@inktank.com>
commit f67fe4e368b5f250f0adfb183476f5f294e8a529
Author: Wido den Hollander <wido@widodh.nl>
Date: Wed Jul 4 15:46:04 2012 +0200
librados: Bump the version to 0.48
Signed-off-by: Wido den Hollander <wido@widodh.nl>
Signed-off-by: Sage Weil <sage@inktank.com>
commit 35b9ec881aecf84b3a49ec0395d7208de36dc67d
Author: Yehuda Sadeh <yehuda@inktank.com>
Date: Tue Jun 26 17:28:51 2012 -0700
rgw-admin: use correct modifier with strptime
Bug #2658: used %I (12h) instead of %H (24h)
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
commit da251fe88503d32b86113ee0618db7c446d34853
Author: Yehuda Sadeh <yehuda@inktank.com>
Date: Thu Jun 21 15:40:27 2012 -0700
rgw: send both swift x-storage-token and x-auth-token
older clients need x-storage-token, newer x-auth-token
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
commit 4c19ecb9a34e77e71d523a0a97e17f747bd5767d
Author: Yehuda Sadeh <yehuda@inktank.com>
Date: Thu Jun 21 15:17:19 2012 -0700
rgw: radosgw-admin date params now also accept time
The date format now is "YYYY-MM-DD[ hh:mm:ss]". Got rid of
the --time param for the old ops log stuff.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
Conflicts:
src/test/cli/radosgw-admin/help.t
commit 6958aeb898fc683159483bfbb798f069a9b5330a
Author: Yehuda Sadeh <yehuda@inktank.com>
Date: Thu Jun 21 13:14:47 2012 -0700
rgw-admin: fix usage help
s/show/trim
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
commit 83c043f803ab2ed74fa9a84ae9237dd7df2a0c57
Author: Sage Weil <sage@inktank.com>
Date: Tue Jul 3 14:07:16 2012 -0700
radosgw-admin: fix clit test
Signed-off-by: Sage Weil <sage@inktank.com>
commit 5674158163e9c1d50985796931240b237676b74d
Author: Sage Weil <sage@inktank.com>
Date: Tue Jul 3 11:32:57 2012 -0700
ceph: fix cli help test
Signed-off-by: Sage Weil <sage@inktank.com>
commit 151bf0eef59acae2d1fcf3f0feb8b6aa963dc2f6
Author: Samuel Just <sam.just@inktank.com>
Date: Tue Jul 3 11:23:16 2012 -0700
ReplicatedPG: remove faulty scrub assert in sub_op_modify_applied
This assert assumed that all ops submitted before MOSDRepScrub was
submitted were processed by the time that MOSDRepScrub was
processed. In fact, MOSDRepScrub's scrub_to may refer to a
last_update yet to be seen by the replica.
Bug #2693
Signed-off-by: Samuel Just <sam.just@inktank.com>
commit 32833e88a1ad793fa4be86101ce9c22b6f677c06
Author: Kyle Bader <kyle.bader@dreamhost.com>
Date: Tue Jul 3 11:20:38 2012 -0700
ceph: better usage
Signed-off-by: Kyle Bader <kyle.bader@dreamhost.com>
commit 67455c21879c9c117f6402259b5e2da84524e169
Author: Sage Weil <sage@inktank.com>
Date: Tue Jul 3 09:20:35 2012 -0700
debian: strip new ceph-mds package
Reported-by: Amon Ott <a.ott@m-privacy.de>
Signed-off-by: Sage Weil <sage@inktank.com>
commit b53cdb97d15f9276a9b26bec9f29034149f93358
Author: Sage Weil <sage@inktank.com>
Date: Tue Jul 3 06:46:10 2012 -0700
config: remove bad argparse_flag argument in parse_option()
This is wrong, and thankfully valgrind picks it up.
Signed-off-by: Sage Weil <sage@inktank.com>
commit f7d4e39740fd2afe82ac40c711bd3fe7a282e816
Author: Sage Weil <sage@inktank.com>
Date: Sun Jul 1 17:23:28 2012 -0700
msgr: restart_queue when replacing existing pipe and taking over the queue
The queue may have been previously stopped (by discard_queue()), and needs
to be restarted.
Fixes consistent failures from the mon_recovery.py integration tests.
Signed-off-by: Sage Weil <sage@inktank.com>
commit 5dfd2a512d309f7f641bcf7c43277f08cf650b01
Author: Sage Weil <sage@inktank.com>
Date: Sun Jul 1 15:37:31 2012 -0700
msgr: choose incoming connection if ours is STANDBY
If the connect_seq matches, but our existing connection is in STANDBY, take
the incoming one. Otherwise, the other end will wait indefinitely for us
to connect but we won't.
Alternatively, we could "win" the race and trigger a connection by sending
a keepalive (or similar), but that is more work; we may as well accept the
incoming connection we have now.
This removes STANDBY from the acceptable WAIT case states. It also keeps
responsibility squarely on the shoulders of the peer with something to
deliver.
Without this patch, a 3-osd vstart cluster with
'ms inject socket failures = 100' and rados bench write -b 4096 would start
generating slow request warnings after a few minutes due to the osds
failing to connect to each other. With the patch, I complete a 10 minute
run without problems.
Signed-off-by: Sage Weil <sage@inktank.com>
commit b7007a159f6d941fa8313a24af5810ce295b36ca
Author: Sage Weil <sage@inktank.com>
Date: Thu Jun 28 17:50:47 2012 -0700
msgr: preserve incoming message queue when replacing pipes
If we replace an existing pipe with a new one, move the incoming queue
of messages that have not yet been dispatched over to the new Pipe so that
they are not lost. This prevents messages from being lost.
Alternatively, we could set in_seq = existing->in_seq - existing->in_qlen,
but that would make the other end resend those messages, which is a waste
of bandwidth.
Very easy to reproduce the original bug with 'ms inject socket failures'.
Signed-off-by: Sage Weil <sage@inktank.com>
commit 1f3a722e150f9f27fe7919e9579b5a88dcd15639
Author: Sage Weil <sage@inktank.com>
Date: Thu Jun 28 17:45:24 2012 -0700
msgr: move dispatch_entry into DispatchQueue class
A bit cleaner.
Signed-off-by: Sage Weil <sage@inktank.com>
commit 03445290dad5b1213dd138cacf46e379400201c9
Author: Sage Weil <sage@inktank.com>
Date: Thu Jun 28 17:38:34 2012 -0700
msgr: move incoming queue to separate class
This extricates the incoming queue and its funky relationship with
DispatchQueue from Pipe and moves it into IncomingQueue. There is now a
single IncomingQueue attached to each Pipe. DispatchQueue is now no
longer tied to Pipe.
This modularizes the code a bit better (tho that is still a work in
progress) and (more importantly) will make it possible to move the
incoming messages from one pipe to another in accept().
Signed-off-by: Sage Weil <sage@inktank.com>
commit 0dbc54169512da776c16161ec3b8fa0b3f08e248
Author: Sage Weil <sage@inktank.com>
Date: Wed Jun 27 17:06:40 2012 -0700
msgr: make D_CONNECT constant non-zero, fix ms_handle_connect() callback
A while ago we inadvertantly broke ms_handle_connect() callbacks because
of a check for m being non-zero in the dispatch_entry() thread. Adjust the
enums so that they get delivered again.
This fixes hangs when, for example, the ceph tool sends a command, gets a
connection reset, and doesn't get the connect callback to resend after
reconnecting to a new monitor.
Signed-off-by: Sage Weil <sage@inktank.com>
commit 2429556a51e8f60b0d9bdee71ef7b34b367f2f38
Author: Sage Weil <sage@inktank.com>
Date: Tue Jun 26 17:10:40 2012 -0700
msgr: fix pipe replacement assert
We may replace an existing pipe in the STANDBY state if the previous
attempt failed during accept() (see previous patches).
This might fix #1378.
Signed-off-by: Sage Weil <sage@inktank.com>
commit 204bc594be1a6046d1b362693d086b49294c2a27
Author: Sage Weil <sage@inktank.com>
Date: Tue Jun 26 17:07:31 2012 -0700
msgr: do not try to reconnect con with CLOSED pipe
If we have a con with a closed pipe, drop the message. For lossless
sessions, the state will be STANDBY if we should reconnect. For lossy
sessions, we will end up with CLOSED and we *should* drop the message.
Signed-off-by: Sage Weil <sage@inktank.com>
commit e6ad6d25a58b8e34a220d090d01e26293c2437b4
Author: Sage Weil <sage@inktank.com>
Date: Tue Jun 26 17:06:41 2012 -0700
msgr: move to STANDBY if we replace during accept and then fail
If we replace an existing pipe during accept() and then fail, move to
STANDBY so that our connection state (connect_seq, etc.) is preserved.
Otherwise, we will throw out that information and falsely trigger a
RESETSESSION on the next connection attempt.
Signed-off-by: Sage Weil <sage@inktank.com>