summaryrefslogtreecommitdiffstats
path: root/fs/eventpoll.c
diff options
context:
space:
mode:
authorEric Wong <normalperson@yhbt.net>2013-04-30 15:27:38 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2013-04-30 17:04:04 -0700
commit39732ca5af4b09f4db561149041ddad7211019a5 (patch)
tree654d9dc83e3884358e02dd7d765a22423334840d /fs/eventpoll.c
parent4a22f16636259f503847b0805e04824171b270fc (diff)
downloadlinux-39732ca5af4b09f4db561149041ddad7211019a5.tar.gz
linux-39732ca5af4b09f4db561149041ddad7211019a5.tar.bz2
linux-39732ca5af4b09f4db561149041ddad7211019a5.zip
epoll: trim epitem by one cache line
It is common for epoll users to have thousands of epitems, so saving a cache line on every allocation leads to large memory savings. Since epitem allocations are cache-aligned, reducing sizeof(struct epitem) from 136 bytes to 128 bytes will allow it to squeeze under a cache line boundary on x86_64. Via /sys/kernel/slab/eventpoll_epi, I see the following changes on my x86_64 Core2 Duo (which has 64-byte cache alignment): object_size : 192 => 128 objs_per_slab: 21 => 32 Also, add a BUILD_BUG_ON() to check for future accidental breakage. [akpm@linux-foundation.org: use __packed, for all architectures] Signed-off-by: Eric Wong <normalperson@yhbt.net> Cc: Davide Libenzi <davidel@xmailserver.org> Cc: Al Viro <viro@ZenIV.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'fs/eventpoll.c')
-rw-r--r--fs/eventpoll.c10
1 files changed, 9 insertions, 1 deletions
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 9fec1836057a..0e5eda068520 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -104,7 +104,7 @@
struct epoll_filefd {
struct file *file;
int fd;
-};
+} __packed;
/*
* Structure used to track possible nested calls, for too deep recursions
@@ -128,6 +128,8 @@ struct nested_calls {
/*
* Each file descriptor added to the eventpoll interface will
* have an entry of this type linked to the "rbr" RB tree.
+ * Avoid increasing the size of this struct, there can be many thousands
+ * of these on a server and we do not want this to take another cache line.
*/
struct epitem {
/* RB tree node used to link this structure to the eventpoll RB tree */
@@ -1964,6 +1966,12 @@ static int __init eventpoll_init(void)
/* Initialize the structure used to perform file's f_op->poll() calls */
ep_nested_calls_init(&poll_readywalk_ncalls);
+ /*
+ * We can have many thousands of epitems, so prevent this from
+ * using an extra cache line on 64-bit (and smaller) CPUs
+ */
+ BUILD_BUG_ON(sizeof(void *) <= 8 && sizeof(struct epitem) > 128);
+
/* Allocates slab cache used to allocate "struct epitem" items */
epi_cache = kmem_cache_create("eventpoll_epi", sizeof(struct epitem),
0, SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL);