aboutsummaryrefslogtreecommitdiffstats
path: root/mm
diff options
context:
space:
mode:
authorNeilBrown <neilb@suse.de>2007-02-16 04:28:38 -0500
committerLinus Torvalds <torvalds@woody.linux-foundation.org>2007-02-16 11:14:01 -0500
commit29dbb3fc8020f025bc38b262ec494e19fd3eac02 (patch)
tree579877f8d80e04e0908253b782b8e58c742b3fe6 /mm
parent3160a711ef754758e7f85ae371cf900252c1a392 (diff)
[PATCH] knfsd: stop NFSD writes from being broken into lots of little writes to filesystem
When NFSD receives a write request, the data is typically in a number of 1448 byte segments and writev is used to collect them together. Unfortunately, generic_file_buffered_write passes these to the filesystem one at a time, so an e.g. 32K over-write becomes a series of partial-page writes to each page, causing the filesystem to have to pre-read those pages - wasted effort. generic_file_buffered_write handles one segment of the vector at a time as it has to pre-fault in each segment to avoid deadlocks. When writing from kernel-space (and nfsd does) this is not an issue, so generic_file_buffered_write does not need to break and iovec from nfsd into little pieces. This patch avoids the splitting when get_fs is KERNEL_DS as it is from NFSd. This issue was introduced by commit 6527c2bdf1f833cc18e8f42bd97973d583e4aa83 Acked-by: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Norman Weathers <norman.r.weathers@conocophillips.com> Cc: Vladimir V. Saveliev <vs@namesys.com> Signed-off-by: Neil Brown <neilb@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm')
-rw-r--r--mm/filemap.c32
1 files changed, 19 insertions, 13 deletions
diff --git a/mm/filemap.c b/mm/filemap.c
index 00414849a867..d1060b8d3cd6 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2079,21 +2079,27 @@ generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov,
2079 /* Limit the size of the copy to the caller's write size */ 2079 /* Limit the size of the copy to the caller's write size */
2080 bytes = min(bytes, count); 2080 bytes = min(bytes, count);
2081 2081
2082 /* 2082 /* We only need to worry about prefaulting when writes are from
2083 * Limit the size of the copy to that of the current segment, 2083 * user-space. NFSd uses vfs_writev with several non-aligned
2084 * because fault_in_pages_readable() doesn't know how to walk 2084 * segments in the vector, and limiting to one segment a time is
2085 * segments. 2085 * a noticeable performance for re-write
2086 */ 2086 */
2087 bytes = min(bytes, cur_iov->iov_len - iov_base); 2087 if (!segment_eq(get_fs(), KERNEL_DS)) {
2088 2088 /*
2089 /* 2089 * Limit the size of the copy to that of the current
2090 * Bring in the user page that we will copy from _first_. 2090 * segment, because fault_in_pages_readable() doesn't
2091 * Otherwise there's a nasty deadlock on copying from the 2091 * know how to walk segments.
2092 * same page as we're writing to, without it being marked 2092 */
2093 * up-to-date. 2093 bytes = min(bytes, cur_iov->iov_len - iov_base);
2094 */
2095 fault_in_pages_readable(buf, bytes);
2096 2094
2095 /*
2096 * Bring in the user page that we will copy from
2097 * _first_. Otherwise there's a nasty deadlock on
2098 * copying from the same page as we're writing to,
2099 * without it being marked up-to-date.
2100 */
2101 fault_in_pages_readable(buf, bytes);
2102 }
2097 page = __grab_cache_page(mapping,index,&cached_page,&lru_pvec); 2103 page = __grab_cache_page(mapping,index,&cached_page,&lru_pvec);
2098 if (!page) { 2104 if (!page) {
2099 status = -ENOMEM; 2105 status = -ENOMEM;