aboutsummaryrefslogtreecommitdiffstats
path: root/include/linux/genhd.h
diff options
context:
space:
mode:
authorJerome Marchand <jmarchan@redhat.com>2011-01-05 10:57:38 -0500
committerJens Axboe <jaxboe@fusionio.com>2011-01-05 10:57:38 -0500
commit09e099d4bafea3b15be003d548bdf94b4b6e0e17 (patch)
treea4199338ad73e88c0863bbfc6604c4972055f16d /include/linux/genhd.h
parente4a683c899cd5a49f8d684a054c95bd115a0c005 (diff)
block: fix accounting bug on cross partition merges
/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 by caching the partition lookup inside the request structure, hence making sure that the increment and decrement will always happen on the same partition struct. This also speeds up IO with accounting enabled, since it cuts down on the number of lookups we have to do. Also add a refcount to struct hd_struct to keep the partition in memory as long as users exist. We use kref_test_and_get() to ensure we don't add a reference to a partition which is going away. Signed-off-by: Jerome Marchand <jmarchan@redhat.com> Signed-off-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: stable@kernel.org Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
Diffstat (limited to 'include/linux/genhd.h')
-rw-r--r--include/linux/genhd.h2
1 files changed, 2 insertions, 0 deletions
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 7a7b9c1644e4..2ba2792a3dd4 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -116,6 +116,7 @@ struct hd_struct {
116 struct disk_stats dkstats; 116 struct disk_stats dkstats;
117#endif 117#endif
118 struct rcu_head rcu_head; 118 struct rcu_head rcu_head;
119 struct kref ref;
119}; 120};
120 121
121#define GENHD_FL_REMOVABLE 1 122#define GENHD_FL_REMOVABLE 1
@@ -583,6 +584,7 @@ extern struct hd_struct * __must_check add_partition(struct gendisk *disk,
583 sector_t len, int flags, 584 sector_t len, int flags,
584 struct partition_meta_info 585 struct partition_meta_info
585 *info); 586 *info);
587extern void __delete_partition(struct kref *ref);
586extern void delete_partition(struct gendisk *, int); 588extern void delete_partition(struct gendisk *, int);
587extern void printk_all_partitions(void); 589extern void printk_all_partitions(void);
588 590