summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorNeil Brown <neilb@notabene.brown>2008-06-28 08:31:22 +1000
committerNeil Brown <neilb@notabene.brown>2008-06-28 08:31:22 +1000
commita0da84f35b25875870270d16b6eccda4884d61a7 (patch)
tree3c092bcef7a8c8704054b02197156e1c803306b2
parent0e13fe23a00ad88c737d91d94a050707c6139ce4 (diff)
Improve setting of "events_cleared" for write-intent bitmaps.
When an array is degraded, bits in the write-intent bitmap are not cleared, so that if the missing device is re-added, it can be synced by only updated those parts of the device that have changed since it was removed. The enable this a 'events_cleared' value is stored. It is the event counter for the array the last time that any bits were cleared. Sometimes - if a device disappears from an array while it is 'clean' - the events_cleared value gets updated incorrectly (there are subtle ordering issues between updateing events in the main metadata and the bitmap metadata) resulting in the missing device appearing to require a full resync when it is re-added. With this patch, we update events_cleared precisely when we are about to clear a bit in the bitmap. We record events_cleared when we clear the bit internally, and copy that to the superblock which is written out before the bit on storage. This makes it more "obviously correct". We also need to update events_cleared when the event_count is going backwards (as happens on a dirty->clean transition of a non-degraded array). Thanks to Mike Snitzer for identifying this problem and testing early "fixes". Cc: "Mike Snitzer" <snitzer@gmail.com> Signed-off-by: Neil Brown <neilb@suse.de>
-rw-r--r--drivers/md/bitmap.c29
-rw-r--r--include/linux/raid/bitmap.h1
2 files changed, 25 insertions, 5 deletions
diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index b26927ce889..dedba16d42f 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -454,8 +454,11 @@ void bitmap_update_sb(struct bitmap *bitmap)
spin_unlock_irqrestore(&bitmap->lock, flags);
sb = (bitmap_super_t *)kmap_atomic(bitmap->sb_page, KM_USER0);
sb->events = cpu_to_le64(bitmap->mddev->events);
- if (!bitmap->mddev->degraded)
- sb->events_cleared = cpu_to_le64(bitmap->mddev->events);
+ if (bitmap->mddev->events < bitmap->events_cleared) {
+ /* rocking back to read-only */
+ bitmap->events_cleared = bitmap->mddev->events;
+ sb->events_cleared = cpu_to_le64(bitmap->events_cleared);
+ }
kunmap_atomic(sb, KM_USER0);
write_page(bitmap, bitmap->sb_page, 1);
}
@@ -1085,9 +1088,19 @@ void bitmap_daemon_work(struct bitmap *bitmap)
} else
spin_unlock_irqrestore(&bitmap->lock, flags);
lastpage = page;
-/*
- printk("bitmap clean at page %lu\n", j);
-*/
+
+ /* We are possibly going to clear some bits, so make
+ * sure that events_cleared is up-to-date.
+ */
+ if (bitmap->need_sync) {
+ bitmap_super_t *sb;
+ bitmap->need_sync = 0;
+ sb = kmap_atomic(bitmap->sb_page, KM_USER0);
+ sb->events_cleared =
+ cpu_to_le64(bitmap->events_cleared);
+ kunmap_atomic(sb, KM_USER0);
+ write_page(bitmap, bitmap->sb_page, 1);
+ }
spin_lock_irqsave(&bitmap->lock, flags);
clear_page_attr(bitmap, page, BITMAP_PAGE_CLEAN);
}
@@ -1257,6 +1270,12 @@ void bitmap_endwrite(struct bitmap *bitmap, sector_t offset, unsigned long secto
return;
}
+ if (success &&
+ bitmap->events_cleared < bitmap->mddev->events) {
+ bitmap->events_cleared = bitmap->mddev->events;
+ bitmap->need_sync = 1;
+ }
+
if (!success && ! (*bmc & NEEDED_MASK))
*bmc |= NEEDED_MASK;
diff --git a/include/linux/raid/bitmap.h b/include/linux/raid/bitmap.h
index 78bfdea24a8..e98900671ca 100644
--- a/include/linux/raid/bitmap.h
+++ b/include/linux/raid/bitmap.h
@@ -221,6 +221,7 @@ struct bitmap {
unsigned long syncchunk;
__u64 events_cleared;
+ int need_sync;
/* bitmap spinlock */
spinlock_t lock;