Commit 0141450f authored by Wu Fengguang's avatar Wu Fengguang Committed by Linus Torvalds

readahead: introduce FMODE_RANDOM for POSIX_FADV_RANDOM

This fixes inefficient page-by-page reads on POSIX_FADV_RANDOM.

POSIX_FADV_RANDOM used to set ra_pages=0, which leads to poor performance:
a 16K read will be carried out in 4 _sync_ 1-page reads.

In other places, ra_pages==0 means
- it's ramfs/tmpfs/hugetlbfs/sysfs/configfs
- some IO error happened
where multi-page read IO won't help or should be avoided.

POSIX_FADV_RANDOM actually want a different semantics: to disable the
*heuristic* readahead algorithm, and to use a dumb one which faithfully
submit read IO for whatever application requests.

So introduce a flag FMODE_RANDOM for POSIX_FADV_RANDOM.

Note that the random hint is not likely to help random reads performance
noticeably.  And it may be too permissive on huge request size (its IO
size is not limited by read_ahead_kb).

In Quentin's report (http://lkml.org/lkml/2009/12/24/145), the overall
(NFS read) performance of the application increased by 313%!
Tested-by: default avatarQuentin Barnes <qbarnes+nfs@yahoo-inc.com>
Signed-off-by: default avatarWu Fengguang <fengguang.wu@intel.com>
Cc: Nick Piggin <npiggin@suse.de>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Steven Whitehouse <swhiteho@redhat.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Trond Myklebust <Trond.Myklebust@netapp.com>
Cc: Chuck Lever <chuck.lever@oracle.com>
Cc: <stable@kernel.org>			[2.6.33.x]
Cc: <qbarnes+nfs@yahoo-inc.com>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
parent 42e49608
...@@ -87,6 +87,9 @@ struct inodes_stat_t { ...@@ -87,6 +87,9 @@ struct inodes_stat_t {
*/ */
#define FMODE_NOCMTIME ((__force fmode_t)2048) #define FMODE_NOCMTIME ((__force fmode_t)2048)
/* Expect random access pattern */
#define FMODE_RANDOM ((__force fmode_t)4096)
/* /*
* The below are the various read and write types that we support. Some of * The below are the various read and write types that we support. Some of
* them include behavioral modifiers that send information down to the * them include behavioral modifiers that send information down to the
......
...@@ -77,12 +77,20 @@ SYSCALL_DEFINE(fadvise64_64)(int fd, loff_t offset, loff_t len, int advice) ...@@ -77,12 +77,20 @@ SYSCALL_DEFINE(fadvise64_64)(int fd, loff_t offset, loff_t len, int advice)
switch (advice) { switch (advice) {
case POSIX_FADV_NORMAL: case POSIX_FADV_NORMAL:
file->f_ra.ra_pages = bdi->ra_pages; file->f_ra.ra_pages = bdi->ra_pages;
spin_lock(&file->f_lock);
file->f_mode &= ~FMODE_RANDOM;
spin_unlock(&file->f_lock);
break; break;
case POSIX_FADV_RANDOM: case POSIX_FADV_RANDOM:
file->f_ra.ra_pages = 0; spin_lock(&file->f_lock);
file->f_mode |= FMODE_RANDOM;
spin_unlock(&file->f_lock);
break; break;
case POSIX_FADV_SEQUENTIAL: case POSIX_FADV_SEQUENTIAL:
file->f_ra.ra_pages = bdi->ra_pages * 2; file->f_ra.ra_pages = bdi->ra_pages * 2;
spin_lock(&file->f_lock);
file->f_mode &= ~FMODE_RANDOM;
spin_unlock(&file->f_lock);
break; break;
case POSIX_FADV_WILLNEED: case POSIX_FADV_WILLNEED:
if (!mapping->a_ops->readpage) { if (!mapping->a_ops->readpage) {
......
...@@ -501,6 +501,12 @@ void page_cache_sync_readahead(struct address_space *mapping, ...@@ -501,6 +501,12 @@ void page_cache_sync_readahead(struct address_space *mapping,
if (!ra->ra_pages) if (!ra->ra_pages)
return; return;
/* be dumb */
if (filp->f_mode & FMODE_RANDOM) {
force_page_cache_readahead(mapping, filp, offset, req_size);
return;
}
/* do read-ahead */ /* do read-ahead */
ondemand_readahead(mapping, ra, filp, false, offset, req_size); ondemand_readahead(mapping, ra, filp, false, offset, req_size);
} }
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment