aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorKeith Mannthey <kmannth@us.ibm.com>2008-11-25 10:24:35 +0100
committerJens Axboe <jens.axboe@oracle.com>2008-12-29 08:28:44 +0100
commit08bafc0341f2f7920e9045bc32c40299cac8c21b (patch)
treeab4ad0f73f457409239a98c050bf7edd47c03cf1
parent7c239517d9f18427fc2e7ed259fb3b866595f5af (diff)
block: Supress Buffer I/O errors when SCSI REQ_QUIET flag set
Allow the scsi request REQ_QUIET flag to be propagated to the buffer file system layer. The basic ideas is to pass the flag from the scsi request to the bio (block IO) and then to the buffer layer. The buffer layer can then suppress needless printks. This patch declutters the kernel log by removed the 40-50 (per lun) buffer io error messages seen during a boot in my multipath setup . It is a good chance any real errors will be missed in the "noise" it the logs without this patch. During boot I see blocks of messages like " __ratelimit: 211 callbacks suppressed Buffer I/O error on device sdm, logical block 5242879 Buffer I/O error on device sdm, logical block 5242879 Buffer I/O error on device sdm, logical block 5242847 Buffer I/O error on device sdm, logical block 1 Buffer I/O error on device sdm, logical block 5242878 Buffer I/O error on device sdm, logical block 5242879 Buffer I/O error on device sdm, logical block 5242879 Buffer I/O error on device sdm, logical block 5242879 Buffer I/O error on device sdm, logical block 5242879 Buffer I/O error on device sdm, logical block 5242872 " in my logs. My disk environment is multipath fiber channel using the SCSI_DH_RDAC code and multipathd. This topology includes an "active" and "ghost" path for each lun. IO's to the "ghost" path will never complete and the SCSI layer, via the scsi device handler rdac code, quick returns the IOs to theses paths and sets the REQ_QUIET scsi flag to suppress the scsi layer messages. I am wanting to extend the QUIET behavior to include the buffer file system layer to deal with these errors as well. I have been running this patch for a while now on several boxes without issue. A few runs of bonnie++ show no noticeable difference in performance in my setup. Thanks for John Stultz for the quiet_error finalization. Submitted-by: Keith Mannthey <kmannth@us.ibm.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
-rw-r--r--block/blk-core.c3
-rw-r--r--fs/buffer.c19
-rw-r--r--include/linux/bio.h1
-rw-r--r--include/linux/buffer_head.h1
4 files changed, 20 insertions, 4 deletions
diff --git a/block/blk-core.c b/block/blk-core.c
index 243d18b4ceb..20e1724ccb4 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -153,6 +153,9 @@ static void req_bio_endio(struct request *rq, struct bio *bio,
nbytes = bio->bi_size;
}
+ if (unlikely(rq->cmd_flags & REQ_QUIET))
+ set_bit(BIO_QUIET, &bio->bi_flags);
+
bio->bi_size -= nbytes;
bio->bi_sector += (nbytes >> 9);
diff --git a/fs/buffer.c b/fs/buffer.c
index 10179cfa115..776ae091d3b 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -99,10 +99,18 @@ __clear_page_buffers(struct page *page)
page_cache_release(page);
}
+
+static int quiet_error(struct buffer_head *bh)
+{
+ if (!test_bit(BH_Quiet, &bh->b_state) && printk_ratelimit())
+ return 0;
+ return 1;
+}
+
+
static void buffer_io_error(struct buffer_head *bh)
{
char b[BDEVNAME_SIZE];
-
printk(KERN_ERR "Buffer I/O error on device %s, logical block %Lu\n",
bdevname(bh->b_bdev, b),
(unsigned long long)bh->b_blocknr);
@@ -144,7 +152,7 @@ void end_buffer_write_sync(struct buffer_head *bh, int uptodate)
if (uptodate) {
set_buffer_uptodate(bh);
} else {
- if (!buffer_eopnotsupp(bh) && printk_ratelimit()) {
+ if (!buffer_eopnotsupp(bh) && !quiet_error(bh)) {
buffer_io_error(bh);
printk(KERN_WARNING "lost page write due to "
"I/O error on %s\n",
@@ -394,7 +402,7 @@ static void end_buffer_async_read(struct buffer_head *bh, int uptodate)
set_buffer_uptodate(bh);
} else {
clear_buffer_uptodate(bh);
- if (printk_ratelimit())
+ if (!quiet_error(bh))
buffer_io_error(bh);
SetPageError(page);
}
@@ -455,7 +463,7 @@ static void end_buffer_async_write(struct buffer_head *bh, int uptodate)
if (uptodate) {
set_buffer_uptodate(bh);
} else {
- if (printk_ratelimit()) {
+ if (!quiet_error(bh)) {
buffer_io_error(bh);
printk(KERN_WARNING "lost page write due to "
"I/O error on %s\n",
@@ -2913,6 +2921,9 @@ static void end_bio_bh_io_sync(struct bio *bio, int err)
set_bit(BH_Eopnotsupp, &bh->b_state);
}
+ if (unlikely (test_bit(BIO_QUIET,&bio->bi_flags)))
+ set_bit(BH_Quiet, &bh->b_state);
+
bh->b_end_io(bh, test_bit(BIO_UPTODATE, &bio->bi_flags));
bio_put(bio);
}
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 6a642098e5c..cf132bfbbac 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -117,6 +117,7 @@ struct bio {
#define BIO_CPU_AFFINE 8 /* complete bio on same CPU as submitted */
#define BIO_NULL_MAPPED 9 /* contains invalid user pages */
#define BIO_FS_INTEGRITY 10 /* fs owns integrity data, not block layer */
+#define BIO_QUIET 11 /* Make BIO Quiet */
#define bio_flagged(bio, flag) ((bio)->bi_flags & (1 << (flag)))
/*
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index 3ce64b90118..8605f8a74df 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -35,6 +35,7 @@ enum bh_state_bits {
BH_Ordered, /* ordered write */
BH_Eopnotsupp, /* operation not supported (barrier) */
BH_Unwritten, /* Buffer is allocated on disk but not written */
+ BH_Quiet, /* Buffer Error Prinks to be quiet */
BH_PrivateStart,/* not a state bit, but the first bit available
* for private allocation by other entities