summaryrefslogtreecommitdiffstats
path: root/fs/btrfs/extent_map.c
diff options
context:
space:
mode:
authorLiu Bo <bo.li.liu@oracle.com>2012-08-27 10:52:20 -0600
committerChris Mason <chris.mason@fusionio.com>2012-10-01 15:19:05 -0400
commit4e2f84e63dc138eca91e89ccbc34f37732ce58f7 (patch)
tree31691a22773cf249fc289d8414be62b52d071513 /fs/btrfs/extent_map.c
parentca7e70f59078046db28501519308c2061b0e7a6f (diff)
downloadop-kernel-dev-4e2f84e63dc138eca91e89ccbc34f37732ce58f7.zip
op-kernel-dev-4e2f84e63dc138eca91e89ccbc34f37732ce58f7.tar.gz
Btrfs: improve fsync by filtering extents that we want
This is based on Josef's "Btrfs: turbo charge fsync". The above Josef's patch performs very good in random sync write test, because we won't have too much extents to merge. However, it does not performs good on the test: dd if=/dev/zero of=foobar bs=4k count=12500 oflag=sync The reason is when we do sequencial sync write, we need to merge the current extent just with the previous one, so that we can get accumulated extents to log: A(4k) --> AA(8k) --> AAA(12k) --> AAAA(16k) ... So we'll have to flush more and more checksum into log tree, which is the bottleneck according to my tests. But we can avoid this by telling fsync the real extents that are needed to be logged. With this, I did the above dd sync write test (size=50m), w/o (orig) w/ (josef's) w/ (this) SATA 104KB/s 109KB/s 121KB/s ramdisk 1.5MB/s 1.5MB/s 10.7MB/s (613%) Signed-off-by: Liu Bo <bo.li.liu@oracle.com>
Diffstat (limited to 'fs/btrfs/extent_map.c')
-rw-r--r--fs/btrfs/extent_map.c20
1 files changed, 20 insertions, 0 deletions
diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
index 1fe82cf..ac606f0 100644
--- a/fs/btrfs/extent_map.c
+++ b/fs/btrfs/extent_map.c
@@ -203,6 +203,8 @@ static void try_merge_map(struct extent_map_tree *tree, struct extent_map *em)
em->block_start = merge->block_start;
merge->in_tree = 0;
if (merge->generation > em->generation) {
+ em->mod_start = em->start;
+ em->mod_len = em->len;
em->generation = merge->generation;
list_move(&em->list, &tree->modified_extents);
}
@@ -222,6 +224,7 @@ static void try_merge_map(struct extent_map_tree *tree, struct extent_map *em)
rb_erase(&merge->rb_node, &tree->map);
merge->in_tree = 0;
if (merge->generation > em->generation) {
+ em->mod_len = em->len;
em->generation = merge->generation;
list_move(&em->list, &tree->modified_extents);
}
@@ -247,6 +250,7 @@ int unpin_extent_cache(struct extent_map_tree *tree, u64 start, u64 len,
{
int ret = 0;
struct extent_map *em;
+ bool prealloc = false;
write_lock(&tree->lock);
em = lookup_extent_mapping(tree, start, len);
@@ -259,8 +263,21 @@ int unpin_extent_cache(struct extent_map_tree *tree, u64 start, u64 len,
list_move(&em->list, &tree->modified_extents);
em->generation = gen;
clear_bit(EXTENT_FLAG_PINNED, &em->flags);
+ em->mod_start = em->start;
+ em->mod_len = em->len;
+
+ if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags)) {
+ prealloc = true;
+ clear_bit(EXTENT_FLAG_PREALLOC, &em->flags);
+ }
try_merge_map(tree, em);
+
+ if (prealloc) {
+ em->mod_start = em->start;
+ em->mod_len = em->len;
+ }
+
free_extent_map(em);
out:
write_unlock(&tree->lock);
@@ -298,6 +315,9 @@ int add_extent_mapping(struct extent_map_tree *tree,
}
atomic_inc(&em->refs);
+ em->mod_start = em->start;
+ em->mod_len = em->len;
+
try_merge_map(tree, em);
out:
return ret;
OpenPOWER on IntegriCloud