0c551664a5
vendor github.com/ceph/go-ceph/rados
2019-05-16 18:38:39 -04:00
0241ef7863
collectors/pool: add pool info collector
2019-05-16 18:28:26 -04:00
53db874aa7
Merge pull request #112 from tbregolin/export-osdmap-flags
...
Export OSD cluster map flags
2019-02-25 16:20:09 -05:00
eb4e8483b8
health: export OSD cluster map flags
2019-02-17 03:06:34 +00:00
f91b1241dc
Merge pull request #110 from digitalocean/luminous_pg_down
...
health: add stats for down PGs
2018-11-22 11:25:46 -05:00
31bb74f8ea
health: add stats for down PGs
2018-11-22 11:22:11 -05:00
3efbebdb4f
Merge pull request #108 from digitalocean/add-recovery-backfill-stats
...
luminous: add recovery/backfill stats
2018-11-01 12:50:28 -04:00
6e7bdd9c3e
luminous: add recovery/backfill stats
2018-11-01 12:46:18 -04:00
d0ed675640
Merge pull request #107 from digitalocean/fix-degraded-misplaced-count
...
health: fix degraded/misplaced object count
2018-10-23 17:38:12 -04:00
595bd8c641
health: fix degraded/misplaced object count
2018-10-23 16:56:39 -04:00
b311e48b4e
Merge pull request #100 from ralfonso/patch-1
...
Update README.md to add additional flags
2018-10-18 13:19:28 -07:00
6aba5522bd
Merge pull request #103 from jan--f/reset-some-metric-labels
...
collectors: Reset metric vectors; pools and daemons can vanish
2018-09-19 11:16:27 -04:00
4fc19fbc03
collectors: Reset metric vectors; pools and daemons can vanish
...
Signed-off-by: Jan Fajerski <jfajerski@suse.com>
2018-09-13 14:19:35 +02:00
7814098640
Merge pull request #101 from benyanke/patch-1
...
Bump Copyright
2018-09-10 12:31:42 -04:00
f3a9fa3195
Update README.md
2018-09-10 11:24:25 -05:00
213d8453b5
Bump Copyright
2018-09-05 20:42:09 -05:00
0e8962eb82
Update README.md
...
Add additional flags.
2018-09-04 12:56:25 -07:00
415d296c31
Ssobolewski/run rgw stats in background ( #97 )
...
* RGW GC stat collection can take a long time if there is a very large backlog
* Use a const for background interval
* Minor change per code review
2018-08-10 13:43:02 -06:00
dc6ab9c636
Optionally collect RGW GC task stats ( #94 )
...
* Optionally collect RGW GC task stats
* Minor changes per code-review, add some additional tests to squeeze out extra coverage
2018-08-01 07:37:07 -06:00
ae0f874abb
Merge pull request #90 from jan--f/add-active-pgs-luminous
...
health: add active_pg metric
2018-07-09 09:48:59 -04:00
5df7451281
Merge pull request #89 from jan--f/backport-80-terminate-process
...
Terminate exporter process if maximum open files exceeded
2018-07-09 09:36:42 -04:00
a42a258a28
Add constant for tcp keepalive periode
...
Signed-off-by: Jan Fajerski <jfajerski@suse.com>
2018-07-09 11:08:14 +02:00
2436d00967
health: add active_pg metric
...
This metric allows to graph active PGs vs not active, i.e. the number of
PGs ceph is serving vs. currently unavailable PGs.
Signed-off-by: Jan Fajerski <jfajerski@suse.com>
2018-07-09 10:18:47 +02:00
cd84a7b9db
Merge pull request #93 from digitalocean/ceph_osd_down_destroyed
...
osd: add metrics for down and destroyed OSD
2018-06-25 10:47:19 -04:00
6aed4c4f74
Merge pull request #92 from digitalocean/luminous_latency_skew_support
...
monitors: add back clock skew and latency metric support
2018-06-25 10:46:34 -04:00
aa5abdc470
osd: add metrics for down and destroyed OSD
2018-06-24 13:20:58 -04:00
6f290751c9
monitors: add back clock skew and latency metric support
2018-06-23 19:09:07 -04:00
9a39cc64ed
Add tracking of scrub/deep scrub on a per osd basis ( #91 )
...
* Add tracking of scrub/deep scrub on a per osd basis
* Changes per code review comments/discussion
2018-06-14 12:40:46 -06:00
cd9aa031a8
Terminate exporter process if maximum open files exceeded
...
This is somewhat of a workaround for the exporter becoming
perpetually blocked when it runs out of file descriptors if
the cluster is down for too long, as mentioned in:
https://github.com/digitalocean/ceph_exporter/issues/60#issuecomment-319396108
The problem is that if the MONs are down for long enough,
each time prometheus scrapes the metrics, another socket is
opened, but these block forever. If the cluster comes back
up before we run out of FDs, the blocked requests recover.
If the clusetr *doesn't* come back up before we run out of
FDs, the blocked requests never recover.
This commit causes ceph exporter to terminate if it runs
out of file descriptors, which IMO is better than blocking
forever -- it'll be a noisier failure, and also if you're
running ceph_exporter via systemd, systemd will then
automatically trigger a service restart.
Signed-off-by: Tim Serong <tserong@suse.com>
(cherry picked from commit bb1ad364b5
2018-06-12 10:49:04 +02:00
ccd6b7135b
Merge pull request #88 from digitalocean/fix_stuck_requests
...
health: add visibility for stuck requests
2018-05-10 13:52:14 -04:00
c887505a42
health: add visibility for stuck requests
2018-05-10 13:04:52 -04:00
1b91b5bf2d
Merge pull request #87 from digitalocean/add_slow_request_osd
...
health: capture slow request per osd
2018-05-10 12:11:50 -04:00
219fb69bde
health: capture slow request per osd
2018-05-10 11:55:39 -04:00
afd5a2c4bf
update travis go to 1.9.2
2018-01-23 21:04:24 +05:30
5f702bc55f
Merge pull request #76 from digitalocean/luminous-switch-json
...
luminous: move health stats to be extracted from status json
2017-11-14 16:09:58 -05:00
9c40ffc620
luminous: pick correct value from health status after compat warning is removed
2017-11-13 15:27:20 -05:00
96785e82b1
luminous: move luminous stats to be extracted from json
2017-11-13 15:26:20 -05:00
c41f6ae85c
Merge pull request #59 from AcalephStorage/multi-stage-build
...
Dockerfile with multi-stage build
2017-11-10 16:47:08 -05:00
3828da2b24
Merge pull request #71 from tserong/wip-add-promhttp-to-vendor
...
Add promhttp to vendor directory
2017-11-10 16:34:04 -05:00
66a684fbce
Add promhttp to vendor directory
...
This adds promhttp (required by 4c70969
2017-09-23 17:16:34 +02:00
ac79cf743b
Merge pull request #69 from utkarshmani1997/feature_issue#68_exporter
...
update /metrics handler to promhttp.Handler()
2017-09-14 08:12:40 -04:00
4c70969940
update /metrics handler to promhttp.Handler()
2017-09-14 17:09:52 +05:30
f870fc3254
Merge pull request #67 from fitschn/fix-metrics-recovery-client-io-luminous
...
health: expose client io and recovery io for luminous
2017-09-02 11:43:51 -04:00
bb62aa1b76
Merge pull request #66 from fitschn/fix-metrics-slow-request-luminous
...
health: expose slow requests for luminous
2017-08-23 21:55:48 -04:00
b2f520b9aa
health: expose client io and recovery io for luminous
...
An update to ceph luminous breaks the metrics for recovery and client io, because of the new output format for ceph status.
The updates are still compatible to older versions of ceph.
2017-08-23 15:22:26 +02:00
8ba20e8cb3
osd: expose slow requests for luminous
...
Extract slow request information from health checks in ceph luminous. It's still compatible to older versions of ceph.
It's possible to add additional luminous metrics, i.e. stucked pgs, in the same way.
2017-08-23 11:39:48 +02:00
f2a4404e28
Merge pull request #64 from tserong/remove-no-pools-error
...
pool: remove error log when no pools present
2017-08-18 09:48:20 -04:00
ac1d8a93e2
pool: remove error log when no pools present
...
If there's no pools created yet (which can be true after a ceph
cluster is initially created, but before any pools are present),
there'll be a log every minute "[ERROR] failed collecting pool
usage metrics: no pools found in the cluster to report stats on".
IMO that's not actually an error, it's just the way things are,
so doesn't really need to be reported.
Signed-off-by: Tim Serong <tserong@suse.com>
2017-08-18 15:22:28 +10:00
5121d03b6f
Update Dockerfile with multistage build
...
- Gets the image size down to around 60MB
- Bumps up the base image to 16.04
2017-06-13 12:58:18 +08:00
80aa3ff0d0
Merge pull request #53 from skloeckner/master
...
Added docker-compose for quick test environment and brief description…
2017-05-02 12:03:24 -04:00
Vaibhav Bhembre
Vaibhav Bhembre
Thomás S. Bregolin
Ryan Roemmich
Jan Fajerski
Ben Yanke
ssobolewski
Tim Serong
utkarshmani1997
Mathias Nohr
Hunter Nield