Wip mgr nfs svcmap #54
Open
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Uniform class RGWObjectExpirer and class RGWGC's destructor Signed-off-by: jimifm <[email protected]>
Fixes: http://tracker.ceph.com/issues/19739 Signed-off-by: Yehuda Sadeh <[email protected]>
The recent Static Analysis for Ceph (linked 13 June 2017 on ceph-devel) shows that the link() method of RGWBucket assigns to a variable but doesn't use it later. The anomaly is caused by lack of proper error handling. This commit rectifies it. Fixes: http://tracker.ceph.com/issues/20279 Signed-off-by: Radoslaw Zarzynski <[email protected]>
* list_bucket_multiparts() * abort_bucket_multiparts() Fixes: http://tracker.ceph.com/issues/17164 Signed-off-by: Abhishek Varshney <[email protected]>
Fixes: http://tracker.ceph.com/issues/17164 Signed-off-by: Abhishek Varshney <[email protected]>
Fixes: http://tracker.ceph.com/issues/17164 Signed-off-by: Abhishek Varshney <[email protected]>
Fixes: http://tracker.ceph.com/issues/17164 Signed-off-by: Abhishek Varshney <[email protected]>
For luminous, let's drop unused peer_as_of_epoch and peer_stat fields from MOSDPing message. Signed-off-by: Piotr Dałek <[email protected]>
Fixes: http://tracker.ceph.com/issues/20394 Signed-off-by: Radoslaw Zarzynski <[email protected]>
…der['Date'] fix http://tracker.ceph.com/issues/20176 Signed-off-by: yuliyang <[email protected]>
Fixes: http://tracker.ceph.com/issues/20377 Signed-off-by: Pavan Rallabhandi <[email protected]>
(1) rename try_reuse_blob->can_reuse_blob to keep pace with can_split/can_split_at. (2) replace blob with get_blob(). Signed-off-by: xie xingguo <[email protected]>
Signed-off-by: xie xingguo <[email protected]>
Signed-off-by: xie xingguo <[email protected]>
Signed-off-by: Gui Hecheng <[email protected]>
We don't need to read read object policy for a ListBucket operation (RGWReaddir, RGWRMdirCheck, RGWStatLeaf). Also, there are "virtual" directories that do not have a corresponding object, read object policy on them results in ENOENT for RGWStatLeaf. Signed-off-by: Gui Hecheng <[email protected]>
Although under normal packaging circumstances this would probably not be done, in Ceph there is no reasonable deployment scenario where multiple major versions of libcephfs would need to be present at the same time. Signed-off-by: Nathan Cutler <[email protected]>
Signed-off-by: Nathan Cutler <[email protected]>
Signed-off-by: Nathan Cutler <[email protected]>
Signed-off-by: jimifm <[email protected]>
Signed-off-by: runsisi <[email protected]>
Signed-off-by: Nathan Cutler <[email protected]>
(1) The new PAXOS_MGRSTAT is excluded and may cause
problems
(2) This method has no consumer
Considering (2), it's better to be removed than to be fixed...
Signed-off-by: xie xingguo <[email protected]>
In bufferlist::prepend_zero do the same thing:
bufferlist z;
z.append_zero(head_pad);
z.claim_append(padded);
padded.claim(z);
Signed-off-by: Jianpeng Ma <[email protected]>
Signed-off-by: Jianpeng Ma <[email protected]>
Signed-off-by: Jianpeng Ma <[email protected]>
It seems that the intent of 45877d3 was to change all instances of "lease_stack = ..." to "lease_stack.reset(...)", but this one was missed. Signed-off-by: Nathan Cutler <[email protected]>
New command to create crush rule that specifies a class of device. Plus all of the fallout in other callers to the CrushWrapper helpers, the crushtool cli change, and cli test. Signed-off-by: Sage Weil <[email protected]>
1) ruleset is an obsolete term, and
2) crush-{rule,failure-domain,...} is more descriptive.
Note that we are changing the names of the erasure code profile keys
from ruleset-* to crush-*. We will update this on upgrade when the
luminous flag is set, but that means that during mon upgrade you cannot
create EC pools that use these fields.
When the upgrade completes (users sets require_osd_release = luminous)
existing ec profiles are updated automatically.
Signed-off-by: Sage Weil <[email protected]>
Signed-off-by: Sage Weil <[email protected]>
Signed-off-by: Sage Weil <[email protected]>
Signed-off-by: Sage Weil <[email protected]>
Signed-off-by: Sage Weil <[email protected]>
...so we can whitelist it. Signed-off-by: Sage Weil <[email protected]>
Signed-off-by: John Spray <[email protected]>
The .available flag is there to tell MgrClients whether to try and connect -- it isn't the right condition for a health complaint. Signed-off-by: John Spray <[email protected]>
Previously, the mgr would send MMonMgrReport indicating a very unhappy PGMap to the mon right after startup. This is a change to hold off on sending that report until all the OSDs have reported in, or until some time has passed. Signed-off-by: John Spray <[email protected]>
Add a "Cluster is now healthy" to give clarity after a series of "health check cleared" that they were the last ones. Convert certain health check messages into well formed sentences. Don't print severity in the log string (it's already expressed in the severity of the log entry. Signed-off-by: John Spray <[email protected]>
The PaxosService subclasses should be writing out informative log messages, and not relying on a stream of map summary prints to communicate changes. Signed-off-by: John Spray <[email protected]>
Signed-off-by: John Spray <[email protected]>
Instead of a distinct health check for each possible PG state, group the states into categories for availability, degraded, damage, and report on that. That way, while a PG/pool is suffering from one of those bad PG states, health conditions don't keep toggling on and off as we transition from one unavailable state to another unavailable state. Signed-off-by: John Spray <[email protected]>
This behaviour led to way too many messages going to the cluster log when an OSD is marked in. Retain the messages at debug level. Signed-off-by: John Spray <[email protected]>
Cleaner prose for the auto-out case, and add a cluster log message for OSDs that go out at the behest of the administrator. Signed-off-by: John Spray <[email protected]>
The last_beacon map is local to an election interval; if there is a new election completed we should reset it or else we may kill an apparently laggy mgr that hasn't been able to get a beacon processed due to the mon quorum changing, or had its beacon processed on a different leader. Signed-off-by: Sage Weil <[email protected]>
Signed-off-by: Sage Weil <[email protected]>
Signed-off-by: Sage Weil <[email protected]>
Signed-off-by: Sage Weil <[email protected]>
Signed-off-by: Sage Weil <[email protected]>
Signed-off-by: Sage Weil <[email protected]>
Signed-off-by: Sage Weil <[email protected]>
Avoid health warnings. Signed-off-by: Sage Weil <[email protected]>
OSDs may report fullness in any order. Signed-off-by: Sage Weil <[email protected]>
Avoid an overflow (and false warning) when scrub stamps are in the future. Signed-off-by: Sage Weil <[email protected]>
mon: revamp health check/warning system
test/fio: remove experimental option for bluestore & rocksdb. Reviewed-by: Casey Bodley <[email protected]>
Signed-off-by: Dan Mick <[email protected]>
mgr: increase debug level for ticks 0 -> 10
Add static service map registration for librgw/NFS. In this verision registration is unconditional (e.g., unit tests would register) and, in addition, since there is no API change, we don't know anything about the upper-layer client. Signed-off-by: Matt Benjamin <[email protected]>
mattbenjamin
force-pushed
the
wip-mgr-nfs-svcmap
branch
from
10b90af to
d78fffa
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Add NFS registration to Yehuda's frontend registrations.