md: improve usefulness and accuracy of sysfs file md/sync_completed.
The sync_completed file reports how much of a resync (or recovery or
reshape) has been completed.
However due to the possibility of out-of-order completion of writes,
it is not certain to be accurate.
We have an internal value - mddev->curr_resync_completed - which is an
accurate value (though it might not always be quite so uptodate).
So:
- make curr_resync_completed be uptodate a little more often,
particularly when raid5 reshape updates status in the metadata
- report curr_resync_completed in the sysfs file
- allow poll/select to report all updates to md/sync_completed.
This makes sync_completed completed usable by any external metadata
handler that wants to record this status information in its metadata.
Signed-off-by: NeilBrown <neilb@suse.de>
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 298731b..7af64f3 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -2017,6 +2017,8 @@
clear_bit(MD_CHANGE_PENDING, &mddev->flags);
spin_unlock_irq(&mddev->write_lock);
wake_up(&mddev->sb_wait);
+ if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
+ sysfs_notify(&mddev->kobj, NULL, "sync_completed");
}
@@ -3486,12 +3488,15 @@
{
unsigned long max_sectors, resync;
+ if (!test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
+ return sprintf(page, "none\n");
+
if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery))
max_sectors = mddev->resync_max_sectors;
else
max_sectors = mddev->dev_sectors;
- resync = (mddev->curr_resync - atomic_read(&mddev->recovery_active));
+ resync = mddev->curr_resync_completed;
return sprintf(page, "%lu / %lu\n", resync, max_sectors);
}
@@ -6338,18 +6343,12 @@
sector_t sectors;
skipped = 0;
- if (j >= mddev->resync_max) {
- sysfs_notify(&mddev->kobj, NULL, "sync_completed");
- wait_event(mddev->recovery_wait,
- mddev->resync_max > j
- || kthread_should_stop());
- }
- if (kthread_should_stop())
- goto interrupted;
- if (mddev->curr_resync > mddev->curr_resync_completed &&
- (mddev->curr_resync - mddev->curr_resync_completed)
- > (max_sectors >> 4)) {
+ if ((mddev->curr_resync > mddev->curr_resync_completed &&
+ (mddev->curr_resync - mddev->curr_resync_completed)
+ > (max_sectors >> 4)) ||
+ j >= mddev->resync_max
+ ) {
/* time to update curr_resync_completed */
blk_unplug(mddev->queue);
wait_event(mddev->recovery_wait,
@@ -6357,7 +6356,17 @@
mddev->curr_resync_completed =
mddev->curr_resync;
set_bit(MD_CHANGE_CLEAN, &mddev->flags);
+ sysfs_notify(&mddev->kobj, NULL, "sync_completed");
}
+
+ if (j >= mddev->resync_max)
+ wait_event(mddev->recovery_wait,
+ mddev->resync_max > j
+ || kthread_should_stop());
+
+ if (kthread_should_stop())
+ goto interrupted;
+
sectors = mddev->pers->sync_request(mddev, j, &skipped,
currspeed < speed_min(mddev));
if (sectors == 0) {
@@ -6465,6 +6474,7 @@
skip:
mddev->curr_resync = 0;
+ mddev->curr_resync_completed = 0;
mddev->resync_min = 0;
mddev->resync_max = MaxSector;
sysfs_notify(&mddev->kobj, NULL, "sync_completed");