diff options
| author | Sage Weil <sage@inktank.com> | 2013-04-29 10:51:00 -0700 |
|---|---|---|
| committer | Sage Weil <sage@inktank.com> | 2013-04-29 15:45:39 -0700 |
| commit | 90b6b6df319d946b441ea296eaf321dd3ffcf498 (patch) | |
| tree | 430c33e7861f4979c6facb3742ded4ef0d7e8863 | |
| parent | ee3cdaa86c03536ef42d4c2f2af702bdf650be8a (diff) | |
| download | ceph-90b6b6df319d946b441ea296eaf321dd3ffcf498.tar.gz | |
mon: compact leveldb on bootstrap
This is an opportunistic time to optimize our local data since we are
out of quorum. It serves as a safety net for cases where leveldb's
automatic compaction doesn't work quite right and lets things get out
of hand.
Anecdotally we have seen stores in excess of 30GB compact down to a few
hundred KB. And a 9GB store compact down to 900MB in only 1 minute.
Signed-off-by: Sage Weil <sage@inktank.com>
| -rw-r--r-- | src/common/config_opts.h | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/src/common/config_opts.h b/src/common/config_opts.h index 348b1cd3fec..c8e634f46ac 100644 --- a/src/common/config_opts.h +++ b/src/common/config_opts.h @@ -125,7 +125,7 @@ OPTION(mon_data, OPT_STR, "/var/lib/ceph/mon/$cluster-$id") OPTION(mon_initial_members, OPT_STR, "") // list of initial cluster mon ids; if specified, need majority to form initial quorum and create new cluster OPTION(mon_sync_fs_threshold, OPT_INT, 5) // sync() when writing this many objects; 0 to disable. OPTION(mon_compact_on_start, OPT_BOOL, false) // compact leveldb on ceph-mon start -OPTION(mon_compact_on_bootstrap, OPT_BOOL, true) // trigger leveldb compaction on bootstrap +OPTION(mon_compact_on_bootstrap, OPT_BOOL, false) // trigger leveldb compaction on bootstrap OPTION(mon_tick_interval, OPT_INT, 5) OPTION(mon_subscribe_interval, OPT_DOUBLE, 300) OPTION(mon_osd_laggy_halflife, OPT_INT, 60*60) // (seconds) how quickly our laggy estimations decay |