* [PATCH 3/9] Use _META bio I/O types for metadata I/O
@ 2007-11-22 0:35 David Chinner
2007-11-23 17:37 ` Christoph Hellwig
0 siblings, 1 reply; 2+ messages in thread
From: David Chinner @ 2007-11-22 0:35 UTC (permalink / raw)
To: xfs-oss; +Cc: lkml
Improve metadata I/O merging in the elevator
Change all async metadata buffers to use [READ|WRITE]_META I/O types
so that the I/O doesn't get issued immediately. This allows merging
of adjacent metadata requests but still prioritises them over bulk
data. This shows a 10-15% improvement in sequential create speed of
small files.
Don't include the log buffers in this classification - leave them
as sync types so they are issued immediately.
Signed-off-by: Dave Chinner <dgc@sgi.com>
---
fs/xfs/linux-2.6/xfs_buf.c | 6 +++++-
include/linux/fs.h | 1 +
2 files changed, 6 insertions(+), 1 deletion(-)
Index: 2.6.x-xfs-new/fs/xfs/linux-2.6/xfs_buf.c
===================================================================
--- 2.6.x-xfs-new.orig/fs/xfs/linux-2.6/xfs_buf.c 2007-11-22 10:53:11.556186722 +1100
+++ 2.6.x-xfs-new/fs/xfs/linux-2.6/xfs_buf.c 2007-11-22 10:53:43.748024392 +1100
@@ -1175,10 +1175,14 @@ _xfs_buf_ioapply(
if (bp->b_flags & XBF_ORDERED) {
ASSERT(!(bp->b_flags & XBF_READ));
rw = WRITE_BARRIER;
- } else if (bp->b_flags & _XBF_RUN_QUEUES) {
+ } else if (bp->b_flags & XBF_LOG_BUFFER) {
ASSERT(!(bp->b_flags & XBF_READ_AHEAD));
bp->b_flags &= ~_XBF_RUN_QUEUES;
rw = (bp->b_flags & XBF_WRITE) ? WRITE_SYNC : READ_SYNC;
+ } else if (bp->b_flags & _XBF_RUN_QUEUES) {
+ ASSERT(!(bp->b_flags & XBF_READ_AHEAD));
+ bp->b_flags &= ~_XBF_RUN_QUEUES;
+ rw = (bp->b_flags & XBF_WRITE) ? WRITE_META : READ_META;
} else {
rw = (bp->b_flags & XBF_WRITE) ? WRITE :
(bp->b_flags & XBF_READ_AHEAD) ? READA : READ;
Index: 2.6.x-xfs-new/include/linux/fs.h
===================================================================
--- 2.6.x-xfs-new.orig/include/linux/fs.h 2007-11-22 10:47:21.965392742 +1100
+++ 2.6.x-xfs-new/include/linux/fs.h 2007-11-22 10:53:43.748024392 +1100
@@ -83,6 +83,7 @@ extern int dir_notify_enable;
#define READ_SYNC (READ | (1 << BIO_RW_SYNC))
#define READ_META (READ | (1 << BIO_RW_META))
#define WRITE_SYNC (WRITE | (1 << BIO_RW_SYNC))
+#define WRITE_META (WRITE | (1 << BIO_RW_META))
#define WRITE_BARRIER ((1 << BIO_RW) | (1 << BIO_RW_BARRIER))
#define SEL_IN 1
^ permalink raw reply [flat|nested] 2+ messages in thread
* Re: [PATCH 3/9] Use _META bio I/O types for metadata I/O
2007-11-22 0:35 [PATCH 3/9] Use _META bio I/O types for metadata I/O David Chinner
@ 2007-11-23 17:37 ` Christoph Hellwig
0 siblings, 0 replies; 2+ messages in thread
From: Christoph Hellwig @ 2007-11-23 17:37 UTC (permalink / raw)
To: David Chinner; +Cc: xfs-oss, lkml
On Thu, Nov 22, 2007 at 11:35:12AM +1100, David Chinner wrote:
> Improve metadata I/O merging in the elevator
>
> Change all async metadata buffers to use [READ|WRITE]_META I/O types
> so that the I/O doesn't get issued immediately. This allows merging
> of adjacent metadata requests but still prioritises them over bulk
> data. This shows a 10-15% improvement in sequential create speed of
> small files.
>
> Don't include the log buffers in this classification - leave them
> as sync types so they are issued immediately.
Looks good, and just including the trivial fs.h addition here might be
okay aswell.
^ permalink raw reply [flat|nested] 2+ messages in thread
end of thread, other threads:[~2007-11-23 17:37 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2007-11-22 0:35 [PATCH 3/9] Use _META bio I/O types for metadata I/O David Chinner
2007-11-23 17:37 ` Christoph Hellwig
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox