md: Update md bitmap during resync.

Currently an md array with a write-intent bitmap does not updated that bitmap
to reflect successful partial resync.  Rather the entire bitmap is updated
when the resync completes.

This is because there is no guarentee that resync requests will complete in
order, and tracking each request individually is unnecessarily burdensome.

However there is value in regularly updating the bitmap, so add code to
periodically pause while all pending sync requests complete, then update the
bitmap.  Doing this only every few seconds (the same as the bitmap update
time) does not notciably affect resync performance.

[snitzer@gmail.com: export bitmap_cond_end_sync]
Signed-off-by: Neil Brown <neilb@suse.de>
Cc: "Mike Snitzer" <snitzer@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

5 files changed, 39 insertions, 5 deletions

diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index 1b1ef3130e6e..9231cd700fe8 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -1348,14 +1348,38 @@ void bitmap_close_sync(struct bitmap *bitmap)
          */
         sector_t sector = 0;
         int blocks;
-        if (!bitmap) return;
+        if (!bitmap)
+                return;
         while (sector < bitmap->mddev->resync_max_sectors) {
                 bitmap_end_sync(bitmap, sector, &blocks, 0);
-/*
-                if (sector < 500) printk("bitmap_close_sync: sec %llu blks %d\n",
-                                         (unsigned long long)sector, blocks);
-*/              sector += blocks;
+                sector += blocks;
+        }
+}
+
+void bitmap_cond_end_sync(struct bitmap *bitmap, sector_t sector)
+{
+        sector_t s = 0;
+        int blocks;
+
+        if (!bitmap)
+                return;
+        if (sector == 0) {
+                bitmap->last_end_sync = jiffies;
+                return;
+        }
+        if (time_before(jiffies, (bitmap->last_end_sync
+                                  + bitmap->daemon_sleep * HZ)))
+                return;
+        wait_event(bitmap->mddev->recovery_wait,
+                   atomic_read(&bitmap->mddev->recovery_active) == 0);
+
+        sector &= ~((1ULL << CHUNK_BLOCK_SHIFT(bitmap)) - 1);
+        s = 0;
+        while (s < sector && s < bitmap->mddev->resync_max_sectors) {
+                bitmap_end_sync(bitmap, s, &blocks, 0);
+                s += blocks;
         }
+        bitmap->last_end_sync = jiffies;
 }
 
 static void bitmap_set_memory_bits(struct bitmap *bitmap, sector_t offset, int needed)
@@ -1565,3 +1589,4 @@ EXPORT_SYMBOL(bitmap_start_sync);
 EXPORT_SYMBOL(bitmap_end_sync);
 EXPORT_SYMBOL(bitmap_unplug);
 EXPORT_SYMBOL(bitmap_close_sync);
+EXPORT_SYMBOL(bitmap_cond_end_sync);
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 4a69c416e045..e0b8d0dd7a87 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -1684,6 +1684,7 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i
         if (!go_faster && conf->nr_waiting)
                 msleep_interruptible(1000);
 
+        bitmap_cond_end_sync(mddev->bitmap, sector_nr);
         raise_barrier(conf);
 
         conf->next_resync = sector_nr;
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 5cdcc9386200..ba125277c6c4 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -1670,6 +1670,8 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i
         if (!go_faster && conf->nr_waiting)
                 msleep_interruptible(1000);
 
+        bitmap_cond_end_sync(mddev->bitmap, sector_nr);
+
         /* Again, very different code for resync and recovery.
          * Both must result in an r10bio with a list of bios that
          * have bi_end_io, bi_sector, bi_bdev set,
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index e8c8157b02fc..388a974d63ef 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -3753,6 +3753,9 @@ static inline sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *ski
                 return sync_blocks * STRIPE_SECTORS; /* keep things rounded to whole stripes */
         }
 
+
+        bitmap_cond_end_sync(mddev->bitmap, sector_nr);
+
         pd_idx = stripe_to_pdidx(sector_nr, conf, raid_disks);
         sh = get_active_stripe(conf, sector_nr, raid_disks, pd_idx, 1);
         if (sh == NULL) {
diff --git a/include/linux/raid/bitmap.h b/include/linux/raid/bitmap.h
index 306a1d1a5af0..e51b531cd0b2 100644
--- a/include/linux/raid/bitmap.h
+++ b/include/linux/raid/bitmap.h
@@ -244,6 +244,8 @@ struct bitmap {
          */
         unsigned long daemon_lastrun; /* jiffies of last run */
         unsigned long daemon_sleep; /* how many seconds between updates? */
+        unsigned long last_end_sync; /* when we lasted called end_sync to
+                                      * update bitmap with resync progress */
 
         atomic_t pending_writes; /* pending writes to the bitmap file */
         wait_queue_head_t write_wait;
@@ -275,6 +277,7 @@ void bitmap_endwrite(struct bitmap *bitmap, sector_t offset,
 int bitmap_start_sync(struct bitmap *bitmap, sector_t offset, int *blocks, int degraded);
 void bitmap_end_sync(struct bitmap *bitmap, sector_t offset, int *blocks, int aborted);
 void bitmap_close_sync(struct bitmap *bitmap);
+void bitmap_cond_end_sync(struct bitmap *bitmap, sector_t sector);
 
 void bitmap_unplug(struct bitmap *bitmap);
 void bitmap_daemon_work(struct bitmap *bitmap);