diff options
| author | Lars Ellenberg | 2013-12-20 11:22:13 +0100 |
|---|---|---|
| committer | Philipp Reisner | 2014-07-10 18:35:13 +0200 |
| commit | ad3fee790088d36ad862e31535b5b99c25adeef4 (patch) | |
| tree | 916a5c23cf57283f9f6a5abf8418364c52249ad9 /drivers/block/drbd/drbd_worker.c | |
| parent | drbd: add caching oldest request pointers for replication stages (diff) | |
| download | kernel-qcow2-linux-ad3fee790088d36ad862e31535b5b99c25adeef4.tar.gz kernel-qcow2-linux-ad3fee790088d36ad862e31535b5b99c25adeef4.tar.xz kernel-qcow2-linux-ad3fee790088d36ad862e31535b5b99c25adeef4.zip | |
drbd: improve throttling decisions of background resynchronisation
Background resynchronisation does some "side-stepping", or throttles
itself, if it detects application IO activity, and the current resync
rate estimate is above the configured "cmin-rate".
What was not detected: if there is no application IO,
because it blocks on activity log transactions.
Introduce a new atomic_t ap_actlog_cnt, tracking such blocked requests,
and count non-zero as application IO activity.
This counter is exposed at proc_details level 2 and above.
Also make sure to release the currently locked resync extent
if we side-step due to such voluntary throttling.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
Diffstat (limited to 'drivers/block/drbd/drbd_worker.c')
| -rw-r--r-- | drivers/block/drbd/drbd_worker.c | 9 |
1 files changed, 2 insertions, 7 deletions
diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c index 0ff8f4637741..48975a264985 100644 --- a/drivers/block/drbd/drbd_worker.c +++ b/drivers/block/drbd/drbd_worker.c @@ -395,9 +395,6 @@ static int read_for_csum(struct drbd_peer_device *peer_device, sector_t sector, if (!get_ldev(device)) return -EIO; - if (drbd_rs_should_slow_down(device, sector)) - goto defer; - /* GFP_TRY, because if there is no memory available right now, this may * be rescheduled for later. It is "only" background resync, after all. */ peer_req = drbd_alloc_peer_req(peer_device, ID_SYNCER /* unused */, sector, @@ -651,8 +648,7 @@ next_sector: sector = BM_BIT_TO_SECT(bit); - if (drbd_rs_should_slow_down(device, sector) || - drbd_try_rs_begin_io(device, sector)) { + if (drbd_try_rs_begin_io(device, sector)) { device->bm_resync_fo = bit; goto requeue; } @@ -783,8 +779,7 @@ static int make_ov_request(struct drbd_device *device, int cancel) size = BM_BLOCK_SIZE; - if (drbd_rs_should_slow_down(device, sector) || - drbd_try_rs_begin_io(device, sector)) { + if (drbd_try_rs_begin_io(device, sector)) { device->ov_position = sector; goto requeue; } |