From: Robin Dong <sanbai@xxxxxxxxxx>
If part of the RAID456 array is not in sync, then a read-modify-write cycle will
update incorrect parity to new incorrect parity. If you subsequently get a
drive failure, any data on that drive in the not-in-sync region will be lost.
To avoid this, we:
1. In first bitmap_endwrite to a not-in-sync region, set the write-intent bit and
wake up resync thread.
2. When resync finishes, set the sync bit and clear write-intent bit.
Signed-off-by: Robin Dong <sanbai@xxxxxxxxxx>
Cc: NeilBrown <neilb@xxxxxxx>
---
drivers/md/bitmap.c | 51 ++++++++++++++++++++++++++++++++++++++++++++++++++-
drivers/md/bitmap.h | 2 ++
drivers/md/raid5.c | 11 +++++++++++
3 files changed, 63 insertions(+), 1 deletions(-)
diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index 0d894af..b4967c4 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -1447,6 +1447,24 @@ int bitmap_startwrite(struct bitmap *bitmap, sector_t offset, unsigned long sect
}
EXPORT_SYMBOL(bitmap_startwrite);
+void syncbitmap_endwrite(struct bitmap *bitmap, sector_t offset,
+ bitmap_counter_t *bmc)
+{
+ struct mddev *mddev = bitmap->mddev;
+
+ if (mddev->level >= 4 &&
+ offset > mddev->curr_resync_completed) {
+ *bmc |= NEEDED_MASK;
+ if (!test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) {
+ set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+ set_bit(MD_RECOVERY_SYNC, &mddev->recovery);
+ md_wakeup_thread(mddev->sync_thread);
+ sysfs_notify_dirent_safe(mddev->sysfs_action);
+ }
+ } else
+ syncbitmap_file_set_bit(bitmap, offset);
+}
+
void bitmap_endwrite(struct bitmap *bitmap, sector_t offset, unsigned long sectors,
int success, int behind)
{
@@ -1479,7 +1497,8 @@ void bitmap_endwrite(struct bitmap *bitmap, sector_t offset, unsigned long secto
sysfs_notify_dirent_safe(bitmap->sysfs_can_clear);
}
- syncbitmap_file_set_bit(bitmap, offset);
+ if (bitmap->mddev->bitmap_info.sync_bitmap)
+ syncbitmap_endwrite(bitmap, offset, bmc);
if (!success && !NEEDED(*bmc))
*bmc |= NEEDED_MASK;
@@ -1502,6 +1521,36 @@ void bitmap_endwrite(struct bitmap *bitmap, sector_t offset, unsigned long secto
}
EXPORT_SYMBOL(bitmap_endwrite);
+void bitmap_in_synced(struct bitmap *bitmap, sector_t offset,
+ unsigned long sectors)
+{
+ while (sectors) {
+ sector_t blocks;
+ unsigned long flags;
+ bitmap_counter_t *bmc;
+
+ spin_lock_irqsave(&bitmap->counts.lock, flags);
+ bmc = bitmap_get_counter(&bitmap->counts, offset, &blocks, 0);
+ if (!bmc) {
+ spin_unlock_irqrestore(&bitmap->counts.lock, flags);
+ return;
+ }
+
+ if (NEEDED(*bmc) || (!NEEDED(*bmc) && RESYNC(*bmc))) {
+ *bmc &= ~NEEDED_MASK;
+ syncbitmap_file_set_bit(bitmap, offset);
+ }
+
+ spin_unlock_irqrestore(&bitmap->counts.lock, flags);
+ offset += blocks;
+ if (sectors > blocks)
+ sectors -= blocks;
+ else
+ sectors = 0;
+ }
+}
+EXPORT_SYMBOL(bitmap_in_synced);
+
static int __bitmap_start_sync(struct bitmap *bitmap, sector_t offset, sector_t *blocks,
int degraded)
{
diff --git a/drivers/md/bitmap.h b/drivers/md/bitmap.h
index ddc30da..6d22d8b 100644
--- a/drivers/md/bitmap.h
+++ b/drivers/md/bitmap.h
@@ -253,6 +253,8 @@ int bitmap_startwrite(struct bitmap *bitmap, sector_t offset,
unsigned long sectors, int behind);
void bitmap_endwrite(struct bitmap *bitmap, sector_t offset,
unsigned long sectors, int success, int behind);
+void bitmap_in_synced(struct bitmap *bitmap, sector_t offset,
+ unsigned long sectors);
int bitmap_start_sync(struct bitmap *bitmap, sector_t offset, sector_t *blocks, int degraded);
void bitmap_end_sync(struct bitmap *bitmap, sector_t offset, sector_t *blocks, int aborted);
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 2bf094a..bb7de94 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -3622,6 +3622,8 @@ static void handle_stripe(struct stripe_head *sh)
if ((s.syncing || s.replacing) && s.locked == 0 &&
test_bit(STRIPE_INSYNC, &sh->state)) {
md_done_sync(conf->mddev, STRIPE_SECTORS, 1);
+ bitmap_in_synced(conf->mddev->bitmap, sh->sector,
+ STRIPE_SECTORS);
clear_bit(STRIPE_SYNCING, &sh->state);
if (test_and_clear_bit(R5_Overlap, &sh->dev[sh->pd_idx].flags))
wake_up(&conf->wait_for_overlap);
@@ -4690,6 +4692,15 @@ static inline sector_t sync_request(struct mddev *mddev, sector_t sector_nr, int
return sync_blocks * STRIPE_SECTORS; /* keep things rounded to whole stripes */
}
+ if (!test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery) &&
+ conf->fullsync &&
+ !syncbitmap_start_sync(mddev->bitmap, sector_nr, &sync_blocks) &&
+ sync_blocks >= STRIPE_SECTORS) {
+ sync_blocks /= STRIPE_SECTORS;
+ *skipped = 1;
+ return sync_blocks * STRIPE_SECTORS;
+ }
+
bitmap_cond_end_sync(mddev->bitmap, sector_nr);
sh = get_active_stripe(conf, sector_nr, 0, 1, 0);
--
1.7.1
--
To unsubscribe from this list: send the line "unsubscribe linux-raid" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
