diff options
| author | Mel Gorman <mel@csn.ul.ie> | 2007-10-16 01:25:52 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@woody.linux-foundation.org> | 2007-10-16 09:43:00 -0700 |
| commit | e12ba74d8ff3e2f73a583500d7095e406df4d093 (patch) | |
| tree | a0d3385b65f0b3e1e00b0bbf11b75e7538a93edb /fs/jbd/revoke.c | |
| parent | c361be55b3128474aa66d31092db330b07539103 (diff) | |
| download | linux-3.10-e12ba74d8ff3e2f73a583500d7095e406df4d093.tar.gz linux-3.10-e12ba74d8ff3e2f73a583500d7095e406df4d093.tar.bz2 linux-3.10-e12ba74d8ff3e2f73a583500d7095e406df4d093.zip | |
Group short-lived and reclaimable kernel allocations
This patch marks a number of allocations that are either short-lived such as
network buffers or are reclaimable such as inode allocations. When something
like updatedb is called, long-lived and unmovable kernel allocations tend to
be spread throughout the address space which increases fragmentation.
This patch groups these allocations together as much as possible by adding a
new MIGRATE_TYPE. The MIGRATE_RECLAIMABLE type is for allocations that can be
reclaimed on demand, but not moved. i.e. they can be migrated by deleting
them and re-reading the information from elsewhere.
Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Cc: Andy Whitcroft <apw@shadowen.org>
Cc: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'fs/jbd/revoke.c')
| -rw-r--r-- | fs/jbd/revoke.c | 6 |
1 files changed, 4 insertions, 2 deletions
diff --git a/fs/jbd/revoke.c b/fs/jbd/revoke.c index 62e13c8db13..ad2eacf570c 100644 --- a/fs/jbd/revoke.c +++ b/fs/jbd/revoke.c @@ -170,13 +170,15 @@ int __init journal_init_revoke_caches(void) { revoke_record_cache = kmem_cache_create("revoke_record", sizeof(struct jbd_revoke_record_s), - 0, SLAB_HWCACHE_ALIGN, NULL); + 0, + SLAB_HWCACHE_ALIGN|SLAB_TEMPORARY, + NULL); if (revoke_record_cache == 0) return -ENOMEM; revoke_table_cache = kmem_cache_create("revoke_table", sizeof(struct jbd_revoke_table_s), - 0, 0, NULL); + 0, SLAB_TEMPORARY, NULL); if (revoke_table_cache == 0) { kmem_cache_destroy(revoke_record_cache); revoke_record_cache = NULL; |