diff options
| author | Sage Weil <sage@inktank.com> | 2013-10-01 09:28:29 -0700 |
|---|---|---|
| committer | Sage Weil <sage@inktank.com> | 2013-10-01 09:28:29 -0700 |
| commit | cce990efc8f2a58c8d0fa11c234ddf2242b1b856 (patch) | |
| tree | 47b986f94933e41032dbf9e7e03052ba9a0774f7 | |
| parent | 055e31359ac977943f014270cc56a1b7786abee3 (diff) | |
| download | ceph-cce990efc8f2a58c8d0fa11c234ddf2242b1b856.tar.gz | |
osdc/ObjectCacher: limit writeback IOs generated while holding lock
While analyzing a log from Mike Dawson I saw a long stall while librbd's
objectcacher was starting lots (many hundreds) of IOs. Limit the amount of
time we spend doing this at a time to allow IO replies to be processed so
that the cache remains responsive.
I'm not sure this warrants a tunable (which we would need to add for both
libcephfs and librbd).
Signed-off-by: Sage Weil <sage@inktank.com>
| -rw-r--r-- | src/osdc/ObjectCacher.cc | 6 |
1 files changed, 5 insertions, 1 deletions
diff --git a/src/osdc/ObjectCacher.cc b/src/osdc/ObjectCacher.cc index 590b5d473a8..81335b7957f 100644 --- a/src/osdc/ObjectCacher.cc +++ b/src/osdc/ObjectCacher.cc @@ -11,6 +11,8 @@ #include "include/assert.h" +#define MAX_FLUSH_UNDER_LOCK 20 ///< max bh's we start writeback on while holding the lock + /*** ObjectCacher::BufferHead ***/ @@ -1448,8 +1450,10 @@ void ObjectCacher::flusher_entry() utime_t cutoff = ceph_clock_now(cct); cutoff -= max_dirty_age; BufferHead *bh = 0; + int max = MAX_FLUSH_UNDER_LOCK; while ((bh = static_cast<BufferHead*>(bh_lru_dirty.lru_get_next_expire())) != 0 && - bh->last_write < cutoff) { + bh->last_write < cutoff && + --max > 0) { ldout(cct, 10) << "flusher flushing aged dirty bh " << *bh << dendl; bh_write(bh); } |