RepoMirrors/ceph
1
0
Fork 0
mirror of https://github.com/ceph/ceph synced 2025-02-24 03:27:10 +00:00
Code Issues Packages Projects Releases Wiki Activity
100,874 Commits 216 Branches 395 Tags 1.4 GiB
a3039beaba
Commit Graph

100874 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Casey Bodley
a3039beaba
Merge pull request #29118 from cbodley/wip-rgw-metadata-servicification 
rgw: metadata refactoring

Reviewed-by: Daniel Gryniewicz <dang@redhat.com>
 2019-08-13 12:56:52 -04:00
Casey Bodley
75e1ec8a29 Merge branch 'wip-rgw-metadata-servicification' 
Conflicts:
	src/rgw/rgw_auth.cc
	src/rgw/rgw_auth_registry.h
	src/rgw/rgw_auth_s3.h
	src/rgw/rgw_bucket.cc
	src/rgw/rgw_bucket.h
	src/rgw/rgw_data_sync.h
	src/rgw/rgw_frontend.h
	src/rgw/rgw_log.h
	src/rgw/rgw_main.cc
	src/rgw/rgw_rados.cc
	src/rgw/rgw_rados.h
	src/rgw/rgw_rest_s3.h
	src/rgw/rgw_rest_sts.h
	src/rgw/rgw_swift_auth.h
	src/rgw/rgw_user.cc
	src/rgw/rgw_user.h
	src/rgw/services/svc_sys_obj_core.h
 2019-08-13 10:24:50 -04:00
Casey Bodley
ba9bcf024d
Merge pull request #29633 from hanfengzhe-hi/Fix-decompression-logprint 
rgw:Fix rgw decompression log-print

Reviewed-by: Casey Bodley <cbodley@redhat.com>
 2019-08-13 08:15:17 -04:00
Han Fengzhe
9d22ccc0c6
rgw:Fix rgw decompression log-print 
The zlib compression takes effect in RGW。
When getting objects failed because of decompress-failed。“ceph-client.rgw” log printed “Compression failed with exit code......”，it should be “deCompression failed with exit code......”。

Signed-off-by: Han Fengzhe  <hanfengzhe@hisilicon.com>
 2019-08-13 17:08:23 +08:00
Yuval Lifshitz
76b97cacff
Merge pull request #29587 from yuvalif/wip-yuvali-fix-issue-41169 
rgw: don't throw when accept errors are happening on frontend
 2019-08-13 17:11:34 +09:00
Kefu Chai
3a27c3c800
Merge pull request #29615 from tchaikov/wip-qa/tasks/mgr/dashboard/test_health 
qa/tasks/mgr/dashboard/test_health: add missing field for test_full_health

Reviewed-by: Kiefer Chang <kiefer.chang@suse.com>
 2019-08-13 13:59:28 +08:00
Kefu Chai
b1c05009f9 qa/tasks/mgr/dashboard/test_health: add missing field for test_full_health 
fix regressions introduced by a076260e and d6ff61ed

Signed-off-by: Kefu Chai <kchai@redhat.com>
 2019-08-13 11:30:09 +08:00
Kefu Chai
f13c7c83d9
Merge pull request #29342 from Jeegn-Chen/wip-scrub-extended-sleep 
osd: support osd_scrub_extended_sleep

Reviewed-by: David Zafman <dzafman@redhat.com>
 2019-08-13 09:09:52 +08:00
Kefu Chai
9666fabc67
Merge pull request #29522 from majianpeng/bluestore-optimization 
os/bluestore: deferred IO notify and locking optimization

Reviewed-by: Sage Weil <sage@redhat.com>
 2019-08-13 09:08:00 +08:00
Kefu Chai
308125d3f0
Merge pull request #29418 from junxfl/test1 
OSD: modify n.cookie to op.notify.cookie

Reviewed-by: Samuel Just <sjust@redhat.com>
Reviewed-by: Kefu Chai <kchai@redhat.com>
 2019-08-13 09:06:52 +08:00
Kefu Chai
1b8ee44dcb
Merge pull request #29571 from tchaikov/wip-41177 
ceph-objectstore-tool: update-mon-db: do not fail if incmap is missing

Reviewed-by: huangjun <huangjun@xsky.com>
Reviewed-by: Neha Ojha <nojha@redhat.com>
 2019-08-13 09:04:58 +08:00
Casey Bodley
2bf103100b rgw: RGWUserCtl::PutParams::attrs defaults to nullptr 
Signed-off-by: Casey Bodley <cbodley@redhat.com>
 2019-08-12 14:10:43 -04:00
Casey Bodley
1937f74c33
Merge pull request #29605 from yaozongyou/remove-unused-marco 
common: remove unused _STR and STRINGIFY macro

Reviewed-by: Casey Bodley <cbodley@redhat.com>
 2019-08-12 10:14:52 -04:00
Casey Bodley
456fd7c1c1
Merge pull request #29553 from cbodley/wip-rgw-http-unlock-suspend 
rgw: http client drops lock before suspending coroutine

Reviewed-by: Yuval Lifshitz <yuvalif@yahoo.com>
 2019-08-12 10:04:40 -04:00
Yao Zongyou
a140dba8c8 common: remove unused _STR and STRINGIFY macro 
Signed-off-by: Yao Zongyou <yaozongyou@vip.qq.com>
 2019-08-12 20:49:30 +08:00
Jan Fajerski
84498bfcb4
Merge pull request #29547 from jan--f/c-v-always-log-to-stdout 
ceph-volume: never log to stdout, use stderr instead
 2019-08-12 14:13:19 +02:00
Kefu Chai
aed743aee4
Merge pull request #29076 from tchaikov/wip-crimson-rep-op 
crimson/osd: implement replicated write

Reviewed-by: Radoslaw Zarzynski <rzarzyns@redhat.com>
 2019-08-12 18:51:46 +08:00
Kefu Chai
9759005452
Merge pull request #29378 from cyx1231st/rfc-seastar-msgr-lossless-master 
crimson/net: lossless policy for v2 protocol

Reviewed-by: Radoslaw Zarzynski <rzarzyns@redhat.com>
Reviewed-by: Kefu Chai <kchai@redhat.com>
 2019-08-12 18:50:40 +08:00
Kefu Chai
4f7d7769c0 crimson/osd: log if the dest of send_to_osd() is not valid 
Signed-off-by: Kefu Chai <kchai@redhat.com>
 2019-08-12 18:01:46 +08:00
Kefu Chai
f95c69d0df crimson/osd: do not return "void" 
to avoid potential confusions.

Signed-off-by: Kefu Chai <kchai@redhat.com>
 2019-08-12 18:01:46 +08:00
Kefu Chai
11ac2af314 crimson/osd: write pg info after done with peering 
Signed-off-by: Kefu Chai <kchai@redhat.com>
 2019-08-12 18:01:46 +08:00
Kefu Chai
a7a52efffd crimson/osd: handle MOSDRepOp 
* add a `RepRequest` operation which is blocked by `ConnectionPipeline`
  and `PGPipeline`. these two pipelines are modeled after their
  counterparts of `ClientRequest`.
* add these two blockers to `PG` and `OSDConnectionPriv` accordingly.

Signed-off-by: Kefu Chai <kchai@redhat.com>
 2019-08-12 18:01:46 +08:00
Kefu Chai
4add5fd47b crimson/osd: replicate transaction to peers 
* handle `MOSDRepOpReply` message in osd, and pass it all the way down
  to `PGBackend`.

Signed-off-by: Kefu Chai <kchai@redhat.com>
 2019-08-12 18:01:46 +08:00
Kefu Chai
e26ba3aeed crimson/osd: implement PeeringListener::on_activate() 
see also f7b55ec144

Signed-off-by: Kefu Chai <kchai@redhat.com>
 2019-08-12 18:01:46 +08:00
Yingxin Cheng
acca474339 crimson/net: minor logging cleanup 
Signed-off-by: Yingxin Cheng <yingxin.cheng@intel.com>
 2019-08-12 17:22:45 +08:00
Yingxin Cheng
5491bc48ae crimson/net: throw bad_peer_address when reconnect address doesn't match 
Signed-off-by: Yingxin Cheng <yingxin.cheng@intel.com>
 2019-08-12 17:22:45 +08:00
Yingxin Cheng
c41c44b2e9 crimson/net: REPLACING state to resolve racing and retain session 
Signed-off-by: Yingxin Cheng <yingxin.cheng@intel.com>
 2019-08-12 17:22:45 +08:00
Yingxin Cheng
d1cd196981 crimson/net: handle fault for READY, CONNECTING and ACCEPTING 
Signed-off-by: Yingxin Cheng <yingxin.cheng@intel.com>
 2019-08-12 17:22:45 +08:00
Yingxin Cheng
d75c9e884a crimson/net: WAIT state and backoff for client 
Client goes to WAIT state when it is delayed to reconnect, or wants to
be replaced by a newly established socket.

Signed-off-by: Yingxin Cheng <yingxin.cheng@intel.com>
 2019-08-12 17:22:45 +08:00
Yingxin Cheng
8ea10a6a75 crimson/net: SERVER_WAIT state for accepting server 
Server wait for peer client close the socket at SERVER_WAIT.

Signed-off-by: Yingxin Cheng <yingxin.cheng@intel.com>
 2019-08-12 17:22:45 +08:00
Yingxin Cheng
f8053d08ee crimson/net: STANDBY state for lossless server or peer 
Signed-off-by: Yingxin Cheng <yingxin.cheng@intel.com>
 2019-08-12 17:22:38 +08:00
Yingxin Cheng
dd59586ef0 crimson/net: allow REPLACING state wait for protocol exit 
Signed-off-by: Yingxin Cheng <yingxin.cheng@intel.com>
 2019-08-12 17:22:23 +08:00
Yingxin Cheng
49a08e8bc3 crimson/net: send AckFrame for lossless policy 
Signed-off-by: Yingxin Cheng <yingxin.cheng@intel.com>
 2019-08-12 17:18:15 +08:00
Yingxin Cheng
6cacf1f7b2 crimson/net: maintain the sent queue for lossless policy 
Signed-off-by: Yingxin Cheng <yingxin.cheng@intel.com>
 2019-08-12 17:17:43 +08:00
Yingxin Cheng
492263962c crimson/net: reset write state with reset_write() 
Signed-off-by: Yingxin Cheng <yingxin.cheng@intel.com>
 2019-08-12 17:02:52 +08:00
Yingxin Cheng
babc9c24fd crimson/net: allow connecting state reentrant 
Signed-off-by: Yingxin Cheng <yingxin.cheng@intel.com>
 2019-08-12 17:02:52 +08:00
Yingxin Cheng
675a50326c crimson/net: reset handshake status when connecting/accepting 
Signed-off-by: Yingxin Cheng <yingxin.cheng@intel.com>
 2019-08-12 17:02:52 +08:00
Yingxin Cheng
b7c7dc0b26 crimson/net: pending_q to store the pending(sending) messages 
We cannot left the pending messages in the out_q, because with lossless
policy, they can be partially sent and even acknowledged.

Signed-off-by: Yingxin Cheng <yingxin.cheng@intel.com>
 2019-08-12 17:02:52 +08:00
Yingxin Cheng
4fa1c4c07d crimson/net: wait_write_exit() to wait for writer stopped 
Signed-off-by: Yingxin Cheng <yingxin.cheng@intel.com>
 2019-08-12 17:02:51 +08:00
Yingxin Cheng
b3f1e56d6c crimson/net: is_queued() to check if there's any pending writes 
Signed-off-by: Yingxin Cheng <yingxin.cheng@intel.com>
 2019-08-12 17:02:51 +08:00
Yingxin Cheng
04f8a35d79 crimson/net: fix variables for stateful connection 
server_cookie, client_cookie, connect_seq and global_seq are identifiers
of a stateful connection.

We already have some related implementations, but they are stub code
when implement lossy policy and cannot work properly.

Signed-off-by: Yingxin Cheng <yingxin.cheng@intel.com>
 2019-08-12 17:02:42 +08:00
Jeegn Chen
3bfb5c2621 osd: support osd_scrub_extended_sleep 
1. always take osd_scrub_sleep for manually initiated
   scrubs
2. when scrub_time_permit() return true for scheduled
   ones, the existing osd_scrub_sleep is used
3. when scrub_time_permit() return false for scheduled
   ones, there may be 2 scenarios
   3.1 if osd_scrub_extended_sleep <= osd_scrub_sleep,
       let's take osd_scrub_sleep
   3.2 otherwise, let's take osd_scrub_extended_sleep

Fixes: http://tracker.ceph.com/issues/40955
Signed-off-by: Jeegn Chen <jeegnchen@tencent.com>
 2019-08-12 16:54:36 +08:00
Yingxin Cheng
469a9cda73 crimson/net: clean up, exsiting_conn and existing_proto 
Signed-off-by: Yingxin Cheng <yingxin.cheng@intel.com>
 2019-08-12 16:34:45 +08:00
Yingxin Cheng
014a662b20 crimson/net: next_step_t for explicit decision of next state 
Signed-off-by: Yingxin Cheng <yingxin.cheng@intel.com>
 2019-08-12 16:34:45 +08:00
Yingxin Cheng
b41af731b4 crimson/net: introduce 3 ways to abort the active protocol state 
* abort_in_fault(): a fault is happening and needs to be handled.
* abort_protocol(): abort the current protocol state due to preemptive
                    state change.
* abort_in_close(): close this connection and abort the current protocol
                    state due to some fatal error.

Signed-off-by: Yingxin Cheng <yingxin.cheng@intel.com>
 2019-08-12 16:34:38 +08:00
Kefu Chai
2e2414b3df ceph-objectstore-tool: update-mon-db: do not fail if incmap is missing 
there is chance that we could use an OSD which does not have incmap of a
certain epoch for rebuilding the monstore. and since OSD does not read
and store the incmap if the MOSDMap message already has the fullmap of
that fullmap, and if an OSD does not have previous fullmap, monitor
will just send it the fullmao. so it's not unusual that an OSD has
a fullmap of some epoch without corresponding incmap.

Fixes: https://tracker.ceph.com/issues/41177
Signed-off-by: Kefu Chai <kchai@redhat.com>
 2019-08-12 13:06:01 +08:00
Matt Benjamin
801d2f0449
Merge pull request #28157 from Kriechi/docs-rgw-ldap 
docs: improve rgw ldap auth options
 2019-08-11 20:45:29 -04:00
Yuval Lifshitz
929c062ae9 rgw: don't throw when accept errors are happening on frontend 
Signed-off-by: Yuval Lifshitz <yuvalif@yahoo.com>
 2019-08-11 10:06:05 +03:00
Josh Durgin
3f18ed55aa
Merge pull request #28227 from sseshasa/monCachePriority 
mon/OSDMonitor: Use generic priority cache tuner for mon caches

Reviewed-by: Josh Durgin <jdurgin@redhat.com>
 2019-08-09 14:23:39 -07:00
Casey Bodley
bc45261470
Merge pull request #29540 from cbodley/wip-rgw-user-rename 
rgw: followup for 'user rename'

Reviewed-by: Shilpa Jagannath <smanjara@redhat.com>
Reviewed-by: Matt Benjamin <mbenjamin@redhat.com>
 2019-08-09 16:57:25 -04:00