Skip to contentSkip to conversation

Btrfs: avoid unnecessary ordered extent cache resets

PATCH Superseded Filipe David Borba Manana 2 participants 3 messages Nov 22, 2013 Btrfs file system

lore
Share & tools
lore
#0 lore raw

PATCH 1/1 Btrfs: avoid unnecessary ordered extent cache resets

After an ordered extent completes, don't blindly reset the inode's ordered tree last accessed ordered extent pointer.

While running the xfstests I noticed that about 29% of the time the ordered extent to which tree->last pointed was not the same as our just completed ordered extent. After that I ran the following sysbench test (after a prepare phase) and noticed that about 68% of the time tree->last pointed to a different ordered extent too.

sysbench --test=fileio --file-num=32 --file-total-size=4G \
    --file-test-mode=rndwr --num-threads=512 \
    --file-block-size=32768 --max-time=60 --max-requests=0 run

Therefore reset tree->last on ordered extent removal only if it pointed to the ordered extent we're removing from the tree.

---
 fs/btrfs/ordered-data.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
fs/btrfs/ordered-data.c +2 -1
index 69582d5..b8c2ded 100644
@@ -520,7 +520,8 @@ void btrfs_remove_ordered_extent(struct inode *inode,
 	spin_lock_irq(&tree->lock);
 	node = &entry->rb_node;
 	rb_erase(node, &tree->tree);
-	tree->last = NULL;
+	if (tree->last == node)
+		tree->last = NULL;
 	set_bit(BTRFS_ORDERED_COMPLETE, &entry->flags);
 	spin_unlock_irq(&tree->lock);
 
Signature · 1 line
1.7.9.5
#1 lore raw
Quoted 10 lines · Filipe David Borba Manana

After an ordered extent completes, don't blindly reset the inode's ordered tree last accessed ordered extent pointer.

While running the xfstests I noticed that about 29% of the time the ordered extent to which tree->last pointed was not the same as our just completed ordered extent. After that I ran the following sysbench test (after a prepare phase) and noticed that about 68% of the time tree->last pointed to a different ordered extent too.

Quoted 7 lines
sysbench --test=fileio --file-num=32 --file-total-size=4G \
    --file-test-mode=rndwr --num-threads=512 \
    --file-block-size=32768 --max-time=60 --max-requests=0 run

Therefore reset tree->last on ordered extent removal only if it pointed to the ordered extent we're removing from the tree.

Well this is excellent, how much does it affect performance tho? I'm still going to take it, I'd just like to know how big of an impact it makes. Thanks,

Josef

#2 lore raw

PATCH v2 1/1 Btrfs: avoid unnecessary ordered extent cache resets

In reply to Filipe David Borba Manana

After an ordered extent completes, don't blindly reset the inode's ordered tree last accessed ordered extent pointer.

While running the xfstests I noticed that about 29% of the time the ordered extent to which tree->last pointed was not the same as our just completed ordered extent. After that I ran the following sysbench test (after a prepare phase) and noticed that about 68% of the time tree->last pointed to a different ordered extent too.

sysbench --test=fileio --file-num=32 --file-total-size=4G \
    --file-test-mode=rndwr --num-threads=512 \
    --file-block-size=32768 --max-time=60 --max-requests=0 run

Therefore reset tree->last on ordered extent removal only if it pointed to the ordered extent we're removing from the tree.

Results from 4 runs of the following test before and after applying this patch:

$ sysbench --test=fileio --file-num=32 --file-total-size=4G \
  --file-test-mode=seqwr --num-threads=512 \
  --file-block-size=32768 --max-time=60 --file-io-mode=sync prepare
$ sysbench --test=fileio --file-num=32 --file-total-size=4G \
  --file-test-mode=seqwr --num-threads=512 \
  --file-block-size=32768 --max-time=60 --file-io-mode=sync run

Before this path:

run 1 - 64.049Mb/sec
run 2 - 63.455Mb/sec
run 3 - 64.656Mb/sec
run 4 - 63.833Mb/sec

After this patch:

run 1 - 66.149Mb/sec
run 2 - 68.459Mb/sec
run 3 - 66.338Mb/sec
run 4 - 66.176Mb/sec

With random writes (--file-test-mode=rndwr) I had huge fluctuations on the results (+- 35% easily).

---

V2: Updated commit message with benchmark results.

 fs/btrfs/ordered-data.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
fs/btrfs/ordered-data.c +2 -1
index 69582d5..b8c2ded 100644
@@ -520,7 +520,8 @@ void btrfs_remove_ordered_extent(struct inode *inode,
 	spin_lock_irq(&tree->lock);
 	node = &entry->rb_node;
 	rb_erase(node, &tree->tree);
-	tree->last = NULL;
+	if (tree->last == node)
+		tree->last = NULL;
 	set_bit(BTRFS_ORDERED_COMPLETE, &entry->flags);
 	spin_unlock_irq(&tree->lock);
 
Signature · 1 line
1.7.9.5