Commit 3c6edc66 authored by Song Liu's avatar Song Liu Committed by Shaohua Li
Browse files

md/r5cache: after recovery, increase journal seq by 10000 



Currently, we increase journal entry seq by 10 after recovery.
However, this is not sufficient in the following case.

After crash the journal looks like

| seq+0 | +1 | +2 | +3 | +4 | +5 | +6 | +7 | ... | +11 | +12 |

If +1 is not valid, we dropped all entries from +1 to +12; and
write seq+10:

| seq+0 | +10 | +2 | +3 | +4 | +5 | +6 | +7 | ... | +11 | +12 |

However, if we write a big journal entry with seq+11, it will
connect with some stale journal entry:

| seq+0 | +10 |                     +11                 | +12 |

To reduce the risk of this issue, we increase seq by 10000 instead.

Shaohua: use 10000 instead of 1000. The risk should be very unlikely. The total
stripe cache size is less than 2k typically, and several stripes can fit into
one meta data block. So the total inflight meta data blocks would be quite
small, which means the the total sequence number used should be quite small.
The 10000 sequence number increase should be far more than safe.

Signed-off-by: default avatarSong Liu <songliubraving@fb.com>
Signed-off-by: default avatarShaohua Li <shli@fb.com>
parent 5c88f403

drivers/md/raid5-cache.c

+7 −7
Original line number Diff line number Diff line
@@ -2004,8 +2004,8 @@ static int r5c_recovery_flush_log(struct r5l_log *log, 
 * happens again, new recovery will start from meta 1. Since meta 2n is

 * valid now, recovery will think meta 3 is valid, which is wrong.

 * The solution is we create a new meta in meta2 with its seq == meta

 * 1's seq + 10 and let superblock points to meta2. The same recovery will

 * not think meta 3 is a valid meta, because its seq doesn't match

 * 1's seq + 10000 and let superblock points to meta2. The same recovery

 * will not think meta 3 is a valid meta, because its seq doesn't match

 */



/*
@@ -2035,7 +2035,7 @@ static int r5c_recovery_flush_log(struct r5l_log *log, 
 *   ---------------------------------------------

 *   ^                              ^

 *   |- log->last_checkpoint        |- ctx->pos+1

 *   |- log->last_cp_seq            |- ctx->seq+11

 *   |- log->last_cp_seq            |- ctx->seq+10001

 *

 * However, it is not safe to start the state machine yet, because data only

 * parities are not yet secured in RAID. To save these data only parities, we
@@ -2046,7 +2046,7 @@ static int r5c_recovery_flush_log(struct r5l_log *log, 
 *   -----------------------------------------------------------------

 *   ^                                                ^

 *   |- log->last_checkpoint                          |- ctx->pos+n

 *   |- log->last_cp_seq                              |- ctx->seq+10+n

 *   |- log->last_cp_seq                              |- ctx->seq+10000+n

 *

 * If failure happens again during this process, the recovery can safe start

 * again from log->last_checkpoint.
@@ -2058,7 +2058,7 @@ static int r5c_recovery_flush_log(struct r5l_log *log, 
 *   -----------------------------------------------------------------

 *                        ^                         ^

 *                        |- log->last_checkpoint   |- ctx->pos+n

 *                        |- log->last_cp_seq       |- ctx->seq+10+n

 *                        |- log->last_cp_seq       |- ctx->seq+10000+n

 *

 * Then we can safely start the state machine. If failure happens from this

 * point on, the recovery will start from new log->last_checkpoint.
@@ -2158,7 +2158,7 @@ static int r5l_recovery_log(struct r5l_log *log) 
		return ret;



	pos = ctx.pos;

       ctx.seq += 10;

	ctx.seq += 10000;



	if (ctx.data_only_stripes == 0) {

		log->next_checkpoint = ctx.pos;

CRA Git | Maintained and supported by SUSTech CRA and CCSE