Commit Graph

33 Commits

Author SHA1 Message Date
Sage Weil
364d0b4091 ceph.conf: longer client_moutn_timeout (which also applies to librados)
Signed-off-by: Sage Weil <sage@inktank.com>
2014-04-10 13:24:41 -07:00
Yuri Weinstein
b3218eeb09 changed mon data avail warn to avoid monitor storage warnings 2014-04-08 18:21:56 -07:00
Sage Weil
a0c1952d58 ceph.conf: don't force lockdep on mds
Signed-off-by: Sage Weil <sage@inktank.com>
2014-04-07 16:02:33 -07:00
Sage Weil
5679ae2a1f Merge branch 'firefly' 2014-03-18 15:01:04 -07:00
Sage Weil
8e748c0c2e ceph.conf: tolerate 500ms of clock drift (up from 250)
Signed-off-by: Sage Weil <sage@inktank.com>
2014-03-18 15:00:55 -07:00
Loic Dachary
6acfa6d638 ceph_manager: update ec_pool creation parameters
As of https://github.com/ceph/ceph/pull/1477 the erasure code parameters
are controled via the osd erasure-code-profile set command instead of
being inlined and duplicated in the crush ruleset creation and the pool
creation. There is no need to create the crush ruleset, it is done
implicitly.

Signed-off-by: Loic Dachary <loic@dachary.org>
2014-03-18 00:48:53 +01:00
Samuel Just
9a8bf66d70 ceph.conf.template: add in sensible erasure coding defaults
Signed-off-by: Samuel Just <sam.just@inktank.com>
2014-03-05 12:39:10 -08:00
Sage Weil
dc95aef24b ceph.conf: mon osd allow primary affinity = true
Signed-off-by: Sage Weil <sage@inktank.com>
2014-02-15 20:01:48 -08:00
Sage Weil
2266eeb301 ceph.conf: put 2x command in [global]
so that osdmaptool sees it.

Signed-off-by: Sage Weil <sage@inktank.com>
2013-12-09 15:37:58 -08:00
Sage Weil
a276606312 ceph.conf: default to 2x
A bunch of our tests rely on this; they need to be fixed
before we can run at 3x.

Signed-off-by: Sage Weil <sage@inktank.com>
2013-12-07 13:20:58 -08:00
Sage Weil
759bbb4bdb Revert "ceph.conf: filestore sloppy crc = true"
This reverts commit 631476b979.

This fails on ext4 because of xattr size limits.
2013-10-02 13:22:10 -07:00
Sage Weil
631476b979 ceph.conf: filestore sloppy crc = true
Signed-off-by: Sage Weil <sage@inktank.com>
2013-09-30 16:22:45 -07:00
Sage Weil
f1aac6678e ceph.conf: fix typo
Signed-off-by: Sage Weil <sage@inktank.com>
2013-09-24 15:04:39 -05:00
Sage Weil
ed6c2c087e ceph.conf: reduce min pg per osd
Signed-off-by: Sage Weil <sage@inktank.com>
2013-09-24 08:49:32 -07:00
Samuel Just
c30310af5a ceph.conf.template: add osd_debug_pg_log_writeout = true
Signed-off-by: Samuel Just <sam.just@inktank.com>
2013-08-27 18:48:48 -07:00
Sage Weil
a739206666 ceph.conf: open osd classes on start
This is the default for master, but needs to be explicitly enabled for
cuttlefish.
2013-08-07 14:01:00 -07:00
Josh Durgin
65172a0938 rgw: pass socket path directly to radosgw
Only radosgw needs this option, and each one will be different, so
remove it from the ceph.conf template.

Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
2013-07-26 14:13:19 -07:00
Samuel Just
9e91395a2e ceph.conf.template: enable osd debug verify stray on activate
Signed-off-by: Samuel Just <sam.just@inktank.com>
2013-07-17 18:14:58 -07:00
Sage Weil
0ee700830d ceph.conf: enable old message assert
If this triggers, the RECONNECT_SEQ feature is broken (and
maybe we've caught #5517).
2013-07-12 15:18:50 -07:00
Sage Weil
7fbe467f2f ceph.conf: enable full debugging on the mon 2013-04-23 11:02:27 -07:00
Sage Weil
a3c48351a4 ceph.conf: lower mon disk avail warning threshold
Only wanr when we hit 90% instead of default 70%

Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit cf4bf09b2c)
2013-04-18 10:15:44 -07:00
Sage Weil
07e324ae65 ceph.conf: osd debug op order = true
Debug the osd op ordering by default.  Most of the runs have a small number
of clients, which makes the STL maps cheap.

Signed-off-by: Sage Weil <sage@inktank.com>
2013-03-26 12:21:13 -07:00
Sage Weil
67f0aa11fe ceph.conf: auth debug = true
Signed-off-by: Sage Weil <sage@inktank.com>
2013-03-13 13:39:54 -07:00
Sage Weil
36b877add3 Revert "ceph.conf: osd debug op order = true"
This reverts commit 4f68e3ee12.

Until we fix 4392... the kernel is sending ops out of order.
2013-03-08 09:33:51 -08:00
Sage Weil
4f68e3ee12 ceph.conf: osd debug op order = true
Debug the osd op ordering by default.  Most of the runs have a small number
of clients, which makes the STL maps cheap.

Signed-off-by: Sage Weil <sage@inktank.com>
2013-03-06 21:35:41 -08:00
Sage Weil
31ef4a1276 ceph.conf: debug ms = 1 for monitors
Signed-off-by: Sage Weil <sage@inktank.com>
2013-02-25 15:12:56 -06:00
Sage Weil
278be217b6 ceph.conf: log file, not log dir
Signed-off-by: Sage Weil <sage@inktank.com>
2013-02-21 16:21:33 -08:00
Sage Weil
e1573ea181 ceph.conf: use default locations for admin socket; fix client log file
Signed-off-by: Sage Weil <sage@inktank.com>
2013-02-21 11:35:36 -08:00
Sage Weil
2574d87562 make /var/log/ceph writeable by non-root; make clients log to it
Signed-off-by: Sage Weil <sage@inktank.com>
2013-02-21 11:05:30 -08:00
Sage Weil
88ebc27f16 ceph: store logs in normal location
We need to switch around how these are compressed and pulled, since they
aren't in the regular archive dir anymore.

Signed-off-by: Sage Weil <sage@inktank.com>
2013-02-18 13:39:05 -08:00
Sage Weil
d1d36241b7 ceph: use default data, keyring locations
This required reordering the cluster setup so that we do the ceph-osd
--mkfs --mkkey prior to gathering keys and initializing the monitors.

Also, run daemons as root.

Signed-off-by: Sage Weil <sage@inktank.com>
2013-02-18 13:39:05 -08:00
Sander Pool
c525e1061b Install ceph debs and use installed debs
The ceph task installs ceph using the debian
packages now, and all invocations of binaries installed
in {tmpdir}/binary/usr/local/bin/ are replace with
the use of the binaries installed in standard locations
by the debs.

Author:    Sander Pool <sander.pool@inktank.com>
Signed-off-by: Sam Lang <sam.lang@inktank.com>
2013-02-18 13:39:03 -08:00
Sam Lang
ace4cb07b2 Replace /tmp/cephtest/ with configurable path
Teuthology uses /tmp/cephtest/ as the scratch test directory for
a run.  This patch replaces /tmp/cephtest/ everywhere with a
per-run directory: {basedir}/{rundir} where {basedir} is a directory
configured in .teuthology.yaml (/tmp/cephtest if not specified),
and {rundir} is the name of the run, as given in --name.  If no name
is specified, {user}-{timestamp} is used.

To get the old behavior (/tmp/cephtest), set test_path: /tmp/cephtest
in .teuthology.yaml.

This change was modivated by #3782, which requires a test dir that
survives across reboots, but also resolves #3767.

Signed-off-by: Sam Lang <sam.lang@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
2013-01-31 08:23:31 -06:00