[PATCH v3] blk: fix a wrong accounting of hd_struct->in_flight

[Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>]

Hi Jens,

Jens Axboe wrote:
> On 2010-10-14 14:48, Yasuaki Ishimatsu wrote:
>> Index: linux-2.6.36-rc7/block/blk-core.c
>> ===================================================================
>> --- linux-2.6.36-rc7.orig/block/blk-core.c	2010-10-07 05:39:52.000000000 +0900
>> +++ linux-2.6.36-rc7/block/blk-core.c	2010-10-14 17:25:43.000000000 +0900
>> @@ -66,9 +66,15 @@ static void drive_stat_acct(struct reque
>>  	cpu = part_stat_lock();
>>  	part = disk_map_sector_rcu(rq->rq_disk, blk_rq_pos(rq));
>>
>> -	if (!new_io)
>> +	if (!new_io) {
>> +		if (unlikely(rq->part != part)) {
>> +			part_dec_in_flight(rq->part, rw);
>> +			part_inc_in_flight(part, rw);
>> +			rq->part = part;
>> +		}
>>  		part_stat_inc(cpu, part, merges[rw]);
>> -	else {
>> +	} else {
>> +		rq->part = part;
>>  		part_round_stats(cpu, part);
>>  		part_inc_in_flight(part, rw);
>>  	}
> 
> I was thinking that we'd do away with the lookup always if ->part was
> already set. It will probably require a quiscing of IO on partition
> table reload, though.

O.K.
I removed extra part lookups. Following patch also fixed a wrong accounting of
hd_struct->in_flight. But I could not invent how to stop IOs when
reloading partition table. Do you have some idea?

Thsanks,
Yasuaki Ishimatsu
===

From: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>

/proc/diskstats would display a strange output as follows.

$ cat /proc/diskstats |grep sda
   8       0 sda 90524 7579 102154 20464 0 0 0 0 0 14096 20089
   8       1 sda1 19085 1352 21841 4209 0 0 0 0 4294967064 15689 4293424691
                                                ~~~~~~~~~~
   8       2 sda2 71252 3624 74891 15950 0 0 0 0 232 23995 1562390
   8       3 sda3 54 487 2188 92 0 0 0 0 0 88 92
   8       4 sda4 4 0 8 0 0 0 0 0 0 0 0
   8       5 sda5 81 2027 2130 138 0 0 0 0 0 87 137

Its reason is the wrong way of accounting hd_struct->in_flight. When a bio is
merged into a request belongs to different partition by ELEVATOR_FRONT_MERGE.

The detailed root cause is as follows.

Assuming that there are two partition, sda1 and sda2.

1. A request for sda2 is in request_queue. Hence sda1's hd_struct->in_flight
   is 0 and sda2's one is 1.

        | hd_struct->in_flight
   ---------------------------
   sda1 |          0
   sda2 |          1
   ---------------------------

2. A bio belongs to sda1 is issued and is merged into the request mentioned on
   step1 by ELEVATOR_BACK_MERGE. The first sector of the request is changed
   from sda2 region to sda1 region. However the two partition's
   hd_struct->in_flight are not changed.

        | hd_struct->in_flight
   ---------------------------
   sda1 |          0
   sda2 |          1
   ---------------------------

3. The request is finished and blk_account_io_done() is called. In this case,
   sda2's hd_struct->in_flight, not a sda1's one, is decremented.

        | hd_struct->in_flight
   ---------------------------
   sda1 |         -1
   sda2 |          1
   ---------------------------

The patch fixes the problem.

Signed-off-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
---
 block/blk-core.c       |   13 ++++++++-----
 block/blk-merge.c      |    2 +-
 include/linux/blkdev.h |    1 +
 3 files changed, 10 insertions(+), 6 deletions(-)

Index: linux-2.6.36-rc7/block/blk-core.c
===================================================================
--- linux-2.6.36-rc7.orig/block/blk-core.c	2010-10-15 09:21:37.000000000 +0900
+++ linux-2.6.36-rc7/block/blk-core.c	2010-10-15 09:44:23.000000000 +0900
@@ -64,13 +64,15 @@ static void drive_stat_acct(struct reque
 		return;

 	cpu = part_stat_lock();
-	part = disk_map_sector_rcu(rq->rq_disk, blk_rq_pos(rq));

-	if (!new_io)
+	if (!new_io) {
+		part = rq->part;
 		part_stat_inc(cpu, part, merges[rw]);
-	else {
+	} else {
+		part = disk_map_sector_rcu(rq->rq_disk, blk_rq_pos(rq));
 		part_round_stats(cpu, part);
 		part_inc_in_flight(part, rw);
+		rq->part = part;
 	}

 	part_stat_unlock();
@@ -128,6 +130,7 @@ void blk_rq_init(struct request_queue *q
 	rq->ref_count = 1;
 	rq->start_time = jiffies;
 	set_start_time_ns(rq);
+	rq->part = NULL;
 }
 EXPORT_SYMBOL(blk_rq_init);

@@ -1759,7 +1762,7 @@ static void blk_account_io_completion(st
 		int cpu;

 		cpu = part_stat_lock();
-		part = disk_map_sector_rcu(req->rq_disk, blk_rq_pos(req));
+		part = req->part;
 		part_stat_add(cpu, part, sectors[rw], bytes >> 9);
 		part_stat_unlock();
 	}
@@ -1779,7 +1782,7 @@ static void blk_account_io_done(struct r
 		int cpu;

 		cpu = part_stat_lock();
-		part = disk_map_sector_rcu(req->rq_disk, blk_rq_pos(req));
+		part = req->part;

 		part_stat_inc(cpu, part, ios[rw]);
 		part_stat_add(cpu, part, ticks[rw], duration);
Index: linux-2.6.36-rc7/block/blk-merge.c
===================================================================
--- linux-2.6.36-rc7.orig/block/blk-merge.c	2010-10-07 05:39:52.000000000 +0900
+++ linux-2.6.36-rc7/block/blk-merge.c	2010-10-15 09:38:45.000000000 +0900
@@ -343,7 +343,7 @@ static void blk_account_io_merge(struct
 		int cpu;

 		cpu = part_stat_lock();
-		part = disk_map_sector_rcu(req->rq_disk, blk_rq_pos(req));
+		part = rq->part;

 		part_round_stats(cpu, part);
 		part_dec_in_flight(part, rq_data_dir(req));
Index: linux-2.6.36-rc7/include/linux/blkdev.h
===================================================================
--- linux-2.6.36-rc7.orig/include/linux/blkdev.h	2010-10-15 09:21:37.000000000 +0900
+++ linux-2.6.36-rc7/include/linux/blkdev.h	2010-10-15 09:26:22.000000000 +0900
@@ -115,6 +115,7 @@ struct request {
 	void *elevator_private3;

 	struct gendisk *rq_disk;
+	struct hd_struct *part;
 	unsigned long start_time;
 #ifdef CONFIG_BLK_CGROUP
 	unsigned long long start_time_ns;