From 0141450f66c3c12a3aaa869748caa64241885cdf Mon Sep 17 00:00:00 2001 From: Wu Fengguang Date: Fri, 5 Mar 2010 13:42:03 -0800 Subject: 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: Quentin Barnes Signed-off-by: Wu Fengguang Cc: Nick Piggin Cc: Andi Kleen Cc: Steven Whitehouse Cc: David Howells Cc: Jonathan Corbet Cc: Al Viro Cc: Christoph Hellwig Cc: Trond Myklebust Cc: Chuck Lever Cc: [2.6.33.x] Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 3 +++ mm/fadvise.c | 10 +++++++++- mm/readahead.c | 6 ++++++ 3 files changed, 18 insertions(+), 1 deletion(-) diff --git a/include/linux/fs.h b/include/linux/fs.h index 4568962..be87edc 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -87,6 +87,9 @@ struct inodes_stat_t { */ #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 * them include behavioral modifiers that send information down to the diff --git a/mm/fadvise.c b/mm/fadvise.c index e433592..8d723c9 100644 --- a/mm/fadvise.c +++ b/mm/fadvise.c @@ -77,12 +77,20 @@ SYSCALL_DEFINE(fadvise64_64)(int fd, loff_t offset, loff_t len, int advice) switch (advice) { case POSIX_FADV_NORMAL: file->f_ra.ra_pages = bdi->ra_pages; + spin_lock(&file->f_lock); + file->f_mode &= ~FMODE_RANDOM; + spin_unlock(&file->f_lock); break; 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; case POSIX_FADV_SEQUENTIAL: 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; case POSIX_FADV_WILLNEED: if (!mapping->a_ops->readpage) { diff --git a/mm/readahead.c b/mm/readahead.c index 033bc13..337b20e 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -501,6 +501,12 @@ void page_cache_sync_readahead(struct address_space *mapping, if (!ra->ra_pages) return; + /* be dumb */ + if (filp->f_mode & FMODE_RANDOM) { + force_page_cache_readahead(mapping, filp, offset, req_size); + return; + } + /* do read-ahead */ ondemand_readahead(mapping, ra, filp, false, offset, req_size); } -- cgit v1.1