[lkml]   [2010]   [Mar]   [30]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
Messages in this thread
Patch in this message
Subject[042/116] readahead: add blk_run_backing_dev
2.6.32-stable review patch.  If anyone has any objections, please let us know.


From: Hisashi Hifumi <>

commit 65a80b4c61f5b5f6eb0f5669c8fb120893bfb388 upstream.

I added blk_run_backing_dev on page_cache_async_readahead so readahead I/O
is unpluged to improve throughput on especially RAID environment.

The normal case is, if page N become uptodate at time T(N), then T(N) <=
T(N+1) holds. With RAID (and NFS to some degree), there is no strict
ordering, the data arrival time depends on runtime status of individual
disks, which breaks that formula. So in do_generic_file_read(), just
after submitting the async readahead IO request, the current page may well
be uptodate, so the page won't be locked, and the block device won't be
implicitly unplugged:

if (PageReadahead(page))
if (!PageUptodate(page))
goto page_not_up_to_date;

Therefore explicit unplugging can help.

Following is the test result with dd.

#dd if=testdir/testfile of=/dev/null bs=16384

1048576+0 records in
1048576+0 records out
17179869184 bytes (17 GB) copied, 224.182 seconds, 76.6 MB/s

1048576+0 records in
1048576+0 records out
17179869184 bytes (17 GB) copied, 206.465 seconds, 83.2 MB/s

(7Disks RAID-0 Array)

1054976+0 records in
1054976+0 records out
17284726784 bytes (17 GB) copied, 212.233 seconds, 81.4 MB/s

1054976+0 records out
17284726784 bytes (17 GB) copied, 198.878 seconds, 86.9 MB/s

(7Disks RAID-5 Array)

The patch was found to improve performance with the SCST scsi target
driver. See

[ unbust comment layout]
[ "fix" CONFIG_BLOCK=n]
Signed-off-by: Hisashi Hifumi <>
Acked-by: Wu Fengguang <>
Cc: Jens Axboe <>
Cc: KOSAKI Motohiro <>
Tested-by: Ronald <>
Cc: Bart Van Assche <>
Cc: Vladislav Bolkhovitin <>
Cc: Randy Dunlap <>
Signed-off-by: Andrew Morton <>
Signed-off-by: Linus Torvalds <>
Signed-off-by: Greg Kroah-Hartman <>

mm/readahead.c | 12 ++++++++++++
1 file changed, 12 insertions(+)

--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -553,5 +553,17 @@ page_cache_async_readahead(struct addres

/* do read-ahead */
ondemand_readahead(mapping, ra, filp, true, offset, req_size);
+ /*
+ * Normally the current page is !uptodate and lock_page() will be
+ * immediately called to implicitly unplug the device. However this
+ * is not always true for RAID conifgurations, where data arrives
+ * not strictly in their submission order. In this case we need to
+ * explicitly kick off the IO.
+ */
+ if (PageUptodate(page))
+ blk_run_backing_dev(mapping->backing_dev_info, NULL);

 \ /
  Last update: 2010-03-31 01:21    [W:0.831 / U:9.040 seconds]
©2003-2018 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site