RepoMirrors/ceph
1
0
Fork 0
mirror of https://github.com/ceph/ceph synced 2025-01-19 17:41:39 +00:00
Code Issues Packages Projects Releases Wiki Activity
93,708 Commits 216 Branches 0 Tags 1.8 GiB
0cc78cfb63
Commit Graph

93708 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Sage Weil
2483b774f2 Merge PR #25823 into master 
* refs/pull/25823/head:
	msg/async/Protocol*: fix mark_down vs accept race

Reviewed-by: Ricardo Dias <rdias@suse.com>
Reviewed-by: Gregory Farnum <gfarnum@redhat.com>
Reviewed-by: Greg Farnum <gfarnum@redhat.com>
 2019-01-08 13:05:11 -06:00
Sage Weil
e1d147fa7a osd: support osd_numa_node, osd_numa_auto_affinity, osd_numa_prefer_iface 
- osd_numa_node manually specifies a numa node.
- osd_numa_prefer_iface makes us prefer IPs in public_network that are
  on the same numa node as the storage
- osd_numa_auto_affinity will set affinity to a numa node when both the
  store and network(s) are on the same numa node.

These options are all flagged as 'startup', although osd_numa_node and
osd_numa_auto_affinity takes effect when the OSD is marked up, so doing
'ceph osd down ...' is sufficient to induce an update.

Signed-off-by: Sage Weil <sage@redhat.com>
 2019-01-08 12:57:00 -06:00
Sage Weil
1d5ad4d653 mon/OSDMonitor: add 'osd numa-status' command 
Signed-off-by: Sage Weil <sage@redhat.com>
 2019-01-08 12:57:00 -06:00
Sage Weil
2328b6cd9c osd: report numa node for network interface(s) 
Signed-off-by: Sage Weil <sage@redhat.com>
 2019-01-08 12:57:00 -06:00
Sage Weil
a7c4419492 common/pick_address: get numa node info for a interface 
Signed-off-by: Sage Weil <sage@redhat.com>
 2019-01-08 12:57:00 -06:00
Casey Bodley
1b2b885518
Merge pull request #25381 from cbodley/wip-qa-rgw-cls 
qa/rgw: add cls_lock/log/refcount/version tests to verify suite

Reviewed-by: Abhishek Lekshmanan <abhishek@suse.com>
 2019-01-08 13:05:11 -05:00
Matt Benjamin
b2f9adf77b
Merge pull request #24027 from theanalyst/wip-civetweb-poll 
rgw: civetweb: use poll instead of select while waiting on sockets
 2019-01-08 12:50:49 -05:00
Sage Weil
b8e475af0c Merge PR #25835 into master 
* refs/pull/25835/head:
	mgr/ServiceMap: print daemon addr in legacy format

Reviewed-by: Ricardo Dias <rdias@suse.com>
Reviewed-by: Volker Theile <vtheile@suse.com>
 2019-01-08 11:19:21 -06:00
Patrick Donnelly
6873dfc06e
Merge PR #24172 into master 
* refs/pull/24172/head:
	client: fix fuse client hang because its pipe to mds is not ok

Reviewed-by: Patrick Donnelly <pdonnell@redhat.com>
 2019-01-08 08:20:59 -08:00
Nathan Weinberg
b8226793b8 mgr/dashboard: Added breadcrumb and tab tests to Pools menu 
Fixes: https://tracker.ceph.com/issues/37667
Signed-off-by: Nathan Weinberg <nweinber@redhat.com>
 2019-01-08 10:16:04 -06:00
Sage Weil
671641df5a mgr/ServiceMap: print daemon addr in legacy format 
The v1/v2 prefix isn't useful anyway since the client can connect via
any protocol.

Signed-off-by: Sage Weil <sage@redhat.com>
 2019-01-08 09:23:12 -06:00
Patrick Donnelly
112d754650
Merge PR #25741 into master 
* refs/pull/25741/head:
	mds: remove wrong assertion in Locker::snapflush_nudge

Reviewed-by: Patrick Donnelly <pdonnell@redhat.com>
 2019-01-08 07:03:40 -08:00
Sage Weil
759027daf2 test/cls_rgw: fix signed/unsigned warning 
Signed-off-by: Sage Weil <sage@redhat.com>
 2019-01-08 09:03:21 -06:00
Patrick Donnelly
5e073231f9
Merge PR #25479 into master 
* refs/pull/25479/head:
	client: fix fuse client can't read or write data due its caps is invalid
	Revert "client: fix fuse client can't read or write data due its caps is invalid"

Reviewed-by: Patrick Donnelly <pdonnell@redhat.com>
 2019-01-08 07:00:26 -08:00
Sage Weil
dcae55c6f3 test/msgr/test_msgr: fix signed/unsigned warning 
Signed-off-by: Sage Weil <sage@redhat.com>
 2019-01-08 08:46:38 -06:00
Sage Weil
f1c9bd1766 msg/Connection: protect peer_addrs with safe_item_history<> 
The peer_addrs can be updated during the initial connection handshake,
but we don't want users (e.g., dout()) to race with an update and
wander off into bad memory.

We use the same strategy for Messenger's my_addrs.

Fixes: http://tracker.ceph.com/issues/37807
Signed-off-by: Sage Weil <sage@redhat.com>
 2019-01-08 08:46:25 -06:00
Mykola Golub
24cc60335d test/pybind/test_rbd: filter out unknown list_children2 keys 
Fixes: http://tracker.ceph.com/issues/37729
Signed-off-by: Mykola Golub <mgolub@suse.com>
 2019-01-08 16:35:13 +02:00
Lenz Grimmer
e0c8284ec5
Merge pull request #25812 from Exotelis/toc 
mgr/dashboard: Add table of contents to HACKING.rst

Reviewed-by: Laura Paduano <lpaduano@suse.com>
 2019-01-08 15:34:53 +01:00
Lenz Grimmer
22947238f3
Merge pull request #25830 from rhcs-dashboard/grafana-500 
mgr/dashboard: Fixes Grafana 500 error

Reviewed-by: Laura Paduano <lpaduano@suse.com>
Reviewed-by: Ricardo Marques <rimarques@suse.com>
Reviewed-by: Tatjana Dehler <tdehler@suse.com>
 2019-01-08 15:33:41 +01:00
Sage Weil
587b548043 Merge PR #25801 into master 
* refs/pull/25801/head:
	qa/tasks/radosbench: default to 64k writes

Reviewed-by: Kefu Chai <kchai@redhat.com>
 2019-01-08 08:30:25 -06:00
Matt Benjamin
87a1baa8a6
Merge pull request #24714 from pritha-srivastava/wip-rgw-role-doc 
rgw: Adding documentation for Roles.
 2019-01-08 09:11:26 -05:00
Volker Theile
18b435a529 mgr/dashboard: Improve RgwUser controller 
Use the new 'user?list' RGW Admin OPS API endpoint.

Signed-off-by: Volker Theile <vtheile@suse.com>
 2019-01-08 14:44:47 +01:00
Sage Weil
d8207b916d Merge PR #25821 into master 
* refs/pull/25821/head:
	doc/dev/msgr2: checksum frame header (tag + length)

Reviewed-by: Ricardo Dias <rdias@suse.com>
Reviewed-by: Gregory Farnum <gfarnum@redhat.com>
Reviewed-by: Greg Farnum <gfarnum@redhat.com>
 2019-01-08 07:23:48 -06:00
Sage Weil
a1613e60a0 msg/async/Protocol*: fix mark_down vs accept race 
If we mark_down the connection while we have the lock dropped the state
maybe CLOSED when we retake it.  Bail out if that happens instead of
continuing to process the connection and eventually running into an
assertion on can_write.

Fixes: http://tracker.ceph.com/issues/36497
Signed-off-by: Sage Weil <sage@redhat.com>
 2019-01-08 07:13:23 -06:00
Alfredo Deza
4f345d4c9f
Merge pull request #25820 from alfredodeza/wip-rm37805 
ceph-volume tests/functional declare ceph-ansible roles instead of importing them

Reviewed-by: Andrew Schoen <aschoen@redhat.com>
 2019-01-08 07:49:21 -05:00
Volker Theile
8bf0721b3f mgr/dashboard: Fix navbar focused color 
The previous gray does not match the new branding color. Now use the green from https://ceph.com.

Signed-off-by: Volker Theile <vtheile@suse.com>
 2019-01-08 13:15:25 +01:00
Kanika Murarka
609fe223d4 mgr/dashboard: Fixes Grafana 500 error 
Fixes: http://tracker.ceph.com/issues/37809
Signed-off-by: Kanika Murarka <kmurarka@redhat.com>
 2019-01-08 12:15:05 +05:30
YunfeiGuan
77bc12e21e client: fix fuse client can't read or write data due its caps is invalid 
We can't do read or write if we don't have Fr or Fw. Similarly, if the
caps is invalid, we can't read or wirte either.

What's worse, the mds don't konw our cap gen is invalid and think client
inode's caps is right. Thus will lead client application hung all the time.

Fixes: http://tracker.ceph.com/issues/36189
Signed-off-by: Guan yunfei <yunfei.guan@xtaotech.com>
Signed-off-by: "Yan, Zheng" <zyan@redhat.com>
 2019-01-08 11:42:53 +08:00
Yan, Zheng
c7f324b0ce Revert "client: fix fuse client can't read or write data due its caps is invalid" 
This reverts commit 1d742aa51b.

Signed-off-by: "Yan, Zheng" <zyan@redhat.com>
 2019-01-08 11:42:43 +08:00
Neha Ojha
6abcc20dca mon/OSDMonitor.cc: make a note about reusing jewel feature bit 
For OSD_PGLOG_HARDLIMIT, we have reused a jewel feature bit that was retired
in luminous. Therefore, we need to check the release version for
>= CEPH_RELEASE_LUMINOUS, before using it.

Signed-off-by: Neha Ojha <nojha@redhat.com>
 2019-01-07 15:33:56 -08:00
Sage Weil
9badd953f4 doc/dev/msgr2: checksum frame header (tag + length) 
Ensure we catch transport errors early (before we, say, try to allocate
a missized payload buffer).

Signed-off-by: Sage Weil <sage@redhat.com>
 2019-01-07 15:01:21 -06:00
Alfredo Deza
ad6b924e2b ceph-volume tests/functional declare ceph-ansible roles instead of importing them 
Signed-off-by: Alfredo Deza <adeza@redhat.com>
 2019-01-07 15:15:21 -05:00
Neha Ojha
c0da26505f qa/suites/upgrade/*-x/stress-split: set pglog_hardlimit flag 
Signed-off-by: Neha Ojha <nojha@redhat.com>
 2019-01-07 09:42:54 -08:00
Neha Ojha
24c3e2d669 qa/suites/upgrade/luminous-x: add pg log settings 
Signed-off-by: Neha Ojha <nojha@redhat.com>
 2019-01-07 09:42:54 -08:00
Yuri Weinstein
45af678d3d qa/tests: added pg log settings to mimic-x 
Signed-off-by: Yuri Weinstein <yweinste@redhat.com>
Signed-off-by: Neha Ojha <nojha@redhat.com>
 2019-01-07 09:42:22 -08:00
Sage Weil
d49e2e9075 Merge PR #25795 into master 
* refs/pull/25795/head:
	ceph-objectstore-tool: fix split check on import

Reviewed-by: Neha Ojha <nojha@redhat.com>
 2019-01-07 10:54:22 -06:00
Sage Weil
78070b96bf qa/tasks/radosbench: default to 64k writes 
The default rados bench is 4MB writes, but this tends to fill up our
tiny test clusters.  Use 64KB instead.

Signed-off-by: Sage Weil <sage@redhat.com>
 2019-01-07 07:22:29 -06:00
alfonsomthd
dcf46cfe94 mgr/dashboard: updated health API test 
Updated test_full_health to reflect changes in
mgr_map / mon_status payloads.

Signed-off-by: Alfonso Martínez <almartin@redhat.com>
 2019-01-07 12:49:25 +01:00
Sebastian Krah
cb254e7fcd mgr/dashboard: Add table of contents 
Adds a table of contents to the HACKING.rst to make the navigation easier

Signed-off-by: Sebastian Krah <skrah@suse.com>
 2019-01-07 11:11:50 +01:00
Yan, Zheng
b593e5a881 tools/cephfs: make 'cephfs-data-scan scan_links' update snaptable 
Signed-off-by: "Yan, Zheng" <zyan@redhat.com>
 2019-01-07 16:50:04 +08:00
Yan, Zheng
01089652d3 tools/cephfs: make 'cephfs-data-scan scan_links' update inotable 
Signed-off-by: "Yan, Zheng" <zyan@redhat.com>
 2019-01-07 16:49:31 +08:00
Kefu Chai
fa24a0312f
Merge pull request #25646 from tone-zhang/nvme-hang 
bluestore/NVMEDevice.cc: fix NVMEManager thread hang

Reviewed-by: Kefu Chai <kchai@redhat.com>
Reviewed-by: Haomai Wang <haomai@xsky.com>
 2019-01-07 16:00:11 +08:00
Kefu Chai
33a72c1537
Merge pull request #25797 from falcon78921/wip-doc-37793 
doc: updated Ceph documentation links

Reviewed-by: Kefu Chai <kchai@redhat.com>
 2019-01-07 15:29:08 +08:00
tone.zhang
4c0fb6c263 bluestore/NVMEDevice.cc: fix NVMEManager thread halt 
When enable SPDK in Ceph and start up Ceph development cluster, met
NVMEManager thread halt.

On aarch64 platform, the log as below:

Starting SPDK v18.04.1 / DPDK 18.05.0 initialization...
[ DPDK EAL parameters: nvme-device-manager -c 0x1 -m 2048 --file-prefix=spdk_pid16987 ]
EAL: Detected 46 lcore(s)
EAL: Detected 1 NUMA nodes
EAL: Multi-process socket /var/run/dpdk/spdk_pid16987/mp_socket
EAL: Probing VFIO support...
EAL: VFIO support initialized
EAL: PCI device 0000:01:00.0 on NUMA socket 0
EAL:   probe driver: 8086:953 spdk_nvme
EAL:   using IOMMU type 1 (Type 1)
^C

The reason is that pthread_cond_destroy() cannot destroy the active
condition_variable parameter.

Also on x86 debug builds we get the following error messages due to
probe_queue_lock still being active during ~NVMEManager:

/home/ubuntu/ceph/src/common/mutex_debug.h: 114: FAILED ceph_assert(r == 0)
 ceph version 14.0.1-1862-g403622b (403622be72) nautilus (dev)

The change fixes the issue.

Fixes: http://tracker.ceph.com/issues/37720

Signed-off-by: tone.zhang <tone.zhang@arm.com>
Signed-off-by: Steve Capper <steve.capper@arm.com>
 2019-01-07 11:14:43 +08:00
Sage Weil
ab517a8b5c Merge PR #25799 into master 
* refs/pull/25799/head:
	msg: fix includes for ostringstream

Reviewed-by: Kefu Chai <kchai@redhat.com>
 2019-01-06 09:12:15 -06:00
Sage Weil
c7b45ca63b Merge PR #25802 into master 
* refs/pull/25802/head:
	qa/suites/rados/thrash-old-clients: no async-v2only

Reviewed-by: Kefu Chai <kchai@redhat.com>
 2019-01-06 08:41:05 -06:00
Sage Weil
1688d8fd92 qa/suites/rados/thrash-old-clients: no async-v2only 
Old clients don't support the v2 protocol.

Signed-off-by: Sage Weil <sage@redhat.com>
 2019-01-05 12:26:56 -06:00
Sage Weil
1e6f0a1250 Merge PR #25780 into master 
* refs/pull/25780/head:
	mon/OSDMonitor: do not populate void pg_temp into nextmap

Reviewed-by: Sage Weil <sage@redhat.com>
 2019-01-05 12:01:23 -06:00
Willem Jan Withagen
c68369d48c msg: fix includes for ostringstream 
Clang complains...

```
/home/jenkins/workspace/ceph-master/src/msg/msg_types.h:420:19: error: implicit instantiation of undefined template 'std::__1::basic_ostringstream<char, std::__1::char_traits<char>, std::__1::allocator<char> >'
    ostringstream ss;
                  ^
/usr/include/c++/v1/iosfwd:123:32: note: template is declared here
    class _LIBCPP_TEMPLATE_VIS basic_ostringstream;
                               ^
1 error generated.
```

Signed-off-by: Willem Jan Withagen <wjw@digiware.nl>
 2019-01-05 16:05:20 +01:00
Kefu Chai
43b6c32964
Merge pull request #25716 from cyx1231st/wip-crimson-msgr-errorleak 
crimson/net: fix crimson msgr error leaks to caller

Reviewed-by: Radoslaw Zarzynski <rzarzyns@redhat.com>
Reviewed-by: Kefu Chai <kchai@redhat.com>
 2019-01-05 18:45:50 +08:00