summaryrefslogtreecommitdiffstats
path: root/include/linux/raid
diff options
context:
space:
mode:
authorNeilBrown <neilb@suse.de>2005-11-08 21:39:34 -0800
committerLinus Torvalds <torvalds@g5.osdl.org>2005-11-09 07:56:38 -0800
commita9701a30470856408d08657eb1bd7ae29a146190 (patch)
treeeb6ea8c82fdc1b50bf56abadeee63a935034cf27 /include/linux/raid
parentbd926c63b7a6843d3ce2728396c0891e54fce5c4 (diff)
downloadop-kernel-dev-a9701a30470856408d08657eb1bd7ae29a146190.zip
op-kernel-dev-a9701a30470856408d08657eb1bd7ae29a146190.tar.gz
[PATCH] md: support BIO_RW_BARRIER for md/raid1
We can only accept BARRIER requests if all slaves handle barriers, and that can, of course, change with time.... So we keep track of whether the whole array seems safe for barriers, and also whether each individual rdev handles barriers. We initially assumes barriers are OK. When writing the superblock we try a barrier, and if that fails, we flag things for no-barriers. This will usually clear the flags fairly quickly. If writing the superblock finds that BIO_RW_BARRIER is -ENOTSUPP, we need to resubmit, so introduce function "md_super_wait" which waits for requests to finish, and retries ENOTSUPP requests without the barrier flag. When writing the real raid1, write requests which were BIO_RW_BARRIER but which aresn't supported need to be retried. So raid1d is enhanced to do this, and when any bio write completes (i.e. no retry needed) we remove it from the r1bio, so that devices needing retry are easy to find. We should hardly ever get -ENOTSUPP errors when writing data to the raid. It should only happen if: 1/ the device used to support BARRIER, but now doesn't. Few devices change like this, though raid1 can! or 2/ the array has no persistent superblock, so there was no opportunity to pre-test for barriers when writing the superblock. Signed-off-by: Neil Brown <neilb@cse.unsw.edu.au> Signed-off-by: Neil Brown <neilb@suse.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Diffstat (limited to 'include/linux/raid')
-rw-r--r--include/linux/raid/md.h1
-rw-r--r--include/linux/raid/md_k.h8
-rw-r--r--include/linux/raid/raid1.h4
3 files changed, 12 insertions, 1 deletions
diff --git a/include/linux/raid/md.h b/include/linux/raid/md.h
index 91467a3..13e7c4b 100644
--- a/include/linux/raid/md.h
+++ b/include/linux/raid/md.h
@@ -89,6 +89,7 @@ extern void md_print_devices (void);
extern void md_super_write(mddev_t *mddev, mdk_rdev_t *rdev,
sector_t sector, int size, struct page *page);
+extern void md_super_wait(mddev_t *mddev);
extern int sync_page_io(struct block_device *bdev, sector_t sector, int size,
struct page *page, int rw);
diff --git a/include/linux/raid/md_k.h b/include/linux/raid/md_k.h
index 11629f9..d5854c2 100644
--- a/include/linux/raid/md_k.h
+++ b/include/linux/raid/md_k.h
@@ -122,6 +122,7 @@ struct mdk_rdev_s
#define Faulty 1 /* device is known to have a fault */
#define In_sync 2 /* device is in_sync with rest of array */
#define WriteMostly 4 /* Avoid reading if at all possible */
+#define BarriersNotsupp 5 /* BIO_RW_BARRIER is not supported */
int desc_nr; /* descriptor index in the superblock */
int raid_disk; /* role of device in array */
@@ -210,6 +211,13 @@ struct mddev_s
int degraded; /* whether md should consider
* adding a spare
*/
+ int barriers_work; /* initialised to true, cleared as soon
+ * as a barrier request to slave
+ * fails. Only supported
+ */
+ struct bio *biolist; /* bios that need to be retried
+ * because BIO_RW_BARRIER is not supported
+ */
atomic_t recovery_active; /* blocks scheduled, but not written */
wait_queue_head_t recovery_wait;
diff --git a/include/linux/raid/raid1.h b/include/linux/raid/raid1.h
index 60e19b6..292b98f 100644
--- a/include/linux/raid/raid1.h
+++ b/include/linux/raid/raid1.h
@@ -110,7 +110,9 @@ struct r1bio_s {
#define R1BIO_Uptodate 0
#define R1BIO_IsSync 1
#define R1BIO_Degraded 2
-#define R1BIO_BehindIO 3
+#define R1BIO_BehindIO 3
+#define R1BIO_Barrier 4
+#define R1BIO_BarrierRetry 5
/* For write-behind requests, we call bi_end_io when
* the last non-write-behind device completes, providing
* any write was successful. Otherwise we call when
OpenPOWER on IntegriCloud