Hi Chris.
I noticed performance of fsync() and write() with O_SYNC flag on Btrfs is
very slow as compared to ext3/4. I used blktrace to try to investigate the
cause of this. One of cause is that unplug is done by kblockd even if the I/O is
issued through fsync() or write() with O_SYNC flag. kblockd's unplug timeout
is 3msec, so unplug via blockd can decrease I/O response. To increase
fsync/osync write performance, speeding up unplug should be done here.
Btrfs's write I/O is issued via kernel thread, not via user application context
that calls fsync(). While waiting for page writeback, wait_on_page_writeback()
can not unplug I/O sometimes on Btrfs because submit_bio is not called from
user application context so when submit_bio is called from kernel thread,
wait_on_page_writeback() sleeps on io_schedule().
I introduced btrfs_wait_on_page_writeback() on following patch, this is replacement
of wait_on_page_writeback() for Btrfs. This does unplug every 1 tick while
waiting for page writeback.
I did a performance test using the sysbench.
# sysbench --num-threads=4 --max-requests=10000 --test=fileio --file-num=1
--file-block-size=4K --file-total-size=128M --file-test-mode=rndwr
--file-fsync-freq=5 run
The result was:
-2.6.29
Test execution summary:
total time: 628.1047s
total number of events: 10000
total time taken by event execution: 413.0834
per-request statistics:
min: 0.0000s
avg: 0.0413s
max: 1.9075s
approx. 95 percentile: 0.3712s
Threads fairness:
events (avg/stddev): 2500.0000/29.21
execution time (avg/stddev): 103.2708/4.04
-2.6.29-patched
Test execution summary:
total time: 579.8049s
total number of events: 10004
total time taken by event execution: 355.3098
per-request statistics:
min: 0.0000s
avg: 0.0355s
max: 1.7670s
approx. 95 percentile: 0.3154s
Threads fairness:
events (avg/stddev): 2501.0000/8.03
execution time (avg/stddev): 88.8274/1.94
This patch has some effect for performance improvement.
I think there are other reasons that should be fixed why fsync() or
write() with O_SYNC flag is slow on Btrfs.
Thanks.
Signed-off-by: Hisashi Hifumi <hifumi.hisashi@xxxxxxxxxxxxx>
diff -Nrup linux-2.6.29.org/fs/btrfs/ctree.h linux-2.6.29.btrfs/fs/btrfs/ctree.h
--- linux-2.6.29.org/fs/btrfs/ctree.h 2009-03-24 08:12:14.000000000 +0900
+++ linux-2.6.29.btrfs/fs/btrfs/ctree.h 2009-03-24 16:48:36.000000000 +0900
@@ -1703,6 +1703,14 @@ static inline struct dentry *fdentry(str
return file->f_path.dentry;
}
+extern void btrfs_wait_on_page_bit(struct page *page);
+
+static inline void btrfs_wait_on_page_writeback(struct page *page)
+{
+ if (PageWriteback(page))
+ btrfs_wait_on_page_bit(page);
+}
+
/* extent-tree.c */
int btrfs_lookup_extent(struct btrfs_root *root, u64 start, u64 len);
int btrfs_lookup_extent_ref(struct btrfs_trans_handle *trans,
diff -Nrup linux-2.6.29.org/fs/btrfs/extent-tree.c linux-2.6.29.btrfs/fs/btrfs/extent-tree.c
--- linux-2.6.29.org/fs/btrfs/extent-tree.c 2009-03-24 08:12:14.000000000 +0900
+++ linux-2.6.29.btrfs/fs/btrfs/extent-tree.c 2009-03-24 15:34:12.000000000 +0900
@@ -4529,7 +4529,7 @@ again:
goto out_unlock;
}
}
- wait_on_page_writeback(page);
+ btrfs_wait_on_page_writeback(page);
page_start = (u64)page->index << PAGE_CACHE_SHIFT;
page_end = page_start + PAGE_CACHE_SIZE - 1;
diff -Nrup linux-2.6.29.org/fs/btrfs/extent_io.c linux-2.6.29.btrfs/fs/btrfs/extent_io.c
--- linux-2.6.29.org/fs/btrfs/extent_io.c 2009-03-24 08:12:14.000000000 +0900
+++ linux-2.6.29.btrfs/fs/btrfs/extent_io.c 2009-03-24 15:34:30.000000000 +0900
@@ -2423,7 +2423,7 @@ retry:
if (wbc->sync_mode != WB_SYNC_NONE) {
if (PageWriteback(page))
flush_fn(data);
- wait_on_page_writeback(page);
+ btrfs_wait_on_page_writeback(page);
}
if (PageWriteback(page) ||
diff -Nrup linux-2.6.29.org/fs/btrfs/file.c linux-2.6.29.btrfs/fs/btrfs/file.c
--- linux-2.6.29.org/fs/btrfs/file.c 2009-03-24 08:12:14.000000000 +0900
+++ linux-2.6.29.btrfs/fs/btrfs/file.c 2009-03-24 15:34:49.000000000 +0900
@@ -967,7 +967,7 @@ again:
err = -ENOMEM;
BUG_ON(1);
}
- wait_on_page_writeback(pages[i]);
+ btrfs_wait_on_page_writeback(pages[i]);
}
if (start_pos < inode->i_size) {
struct btrfs_ordered_extent *ordered;
diff -Nrup linux-2.6.29.org/fs/btrfs/inode.c linux-2.6.29.btrfs/fs/btrfs/inode.c
--- linux-2.6.29.org/fs/btrfs/inode.c 2009-03-24 08:12:14.000000000 +0900
+++ linux-2.6.29.btrfs/fs/btrfs/inode.c 2009-03-24 15:35:23.000000000 +0900
@@ -2733,7 +2733,7 @@ again:
goto out_unlock;
}
}
- wait_on_page_writeback(page);
+ btrfs_wait_on_page_writeback(page);
lock_extent(io_tree, page_start, page_end, GFP_NOFS);
set_page_extent_mapped(page);
@@ -4240,7 +4240,7 @@ static void btrfs_invalidatepage(struct
u64 page_start = page_offset(page);
u64 page_end = page_start + PAGE_CACHE_SIZE - 1;
- wait_on_page_writeback(page);
+ btrfs_wait_on_page_writeback(page);
tree = &BTRFS_I(page->mapping->host)->io_tree;
if (offset) {
btrfs_releasepage(page, GFP_NOFS);
@@ -4322,7 +4322,7 @@ again:
/* page got truncated out from underneath us */
goto out_unlock;
}
- wait_on_page_writeback(page);
+ btrfs_wait_on_page_writeback(page);
lock_extent(io_tree, page_start, page_end, GFP_NOFS);
set_page_extent_mapped(page);
diff -Nrup linux-2.6.29.org/fs/btrfs/ioctl.c linux-2.6.29.btrfs/fs/btrfs/ioctl.c
--- linux-2.6.29.org/fs/btrfs/ioctl.c 2009-03-24 08:12:14.000000000 +0900
+++ linux-2.6.29.btrfs/fs/btrfs/ioctl.c 2009-03-24 15:35:46.000000000 +0900
@@ -400,7 +400,7 @@ again:
}
}
- wait_on_page_writeback(page);
+ btrfs_wait_on_page_writeback(page);
page_start = (u64)page->index << PAGE_CACHE_SHIFT;
page_end = page_start + PAGE_CACHE_SIZE - 1;
diff -Nrup linux-2.6.29.org/fs/btrfs/ordered-data.c linux-2.6.29.btrfs/fs/btrfs/ordered-data.c
--- linux-2.6.29.org/fs/btrfs/ordered-data.c 2009-03-24 08:12:14.000000000 +0900
+++ linux-2.6.29.btrfs/fs/btrfs/ordered-data.c 2009-03-25 11:04:32.000000000 +0900
@@ -21,6 +21,7 @@
#include <linux/blkdev.h>
#include <linux/writeback.h>
#include <linux/pagevec.h>
+#include <linux/hash.h>
#include "ctree.h"
#include "transaction.h"
#include "btrfs_inode.h"
@@ -673,6 +674,46 @@ int btrfs_fdatawrite_range(struct addres
return btrfs_writepages(mapping, &wbc);
}
+static void process_timeout(unsigned long __data)
+{
+ wake_up_process((struct task_struct *)__data);
+}
+
+static int btrfs_sync_page(void *word)
+{
+ struct address_space *mapping;
+ struct page *page;
+ struct timer_list timer;
+
+ page = container_of((unsigned long *)word, struct page, flags);
+
+ smp_mb();
+ mapping = page->mapping;
+ if (mapping && mapping->a_ops && mapping->a_ops->sync_page)
+ mapping->a_ops->sync_page(page);
+ setup_timer(&timer, process_timeout, (unsigned long)current);
+ __mod_timer(&timer, jiffies + 1);
+ io_schedule();
+ del_timer_sync(&timer);
+ return 0;
+}
+
+static wait_queue_head_t *page_waitqueue(struct page *page)
+{
+ const struct zone *zone = page_zone(page);
+
+ return &zone->wait_table[hash_ptr(page, zone->wait_table_bits)];
+}
+
+void btrfs_wait_on_page_bit(struct page *page)
+{
+ DEFINE_WAIT_BIT(wait, &page->flags, PG_writeback);
+
+ if (test_bit(PG_writeback, &page->flags))
+ __wait_on_bit(page_waitqueue(page), &wait, btrfs_sync_page,
+ TASK_UNINTERRUPTIBLE);
+}
+
/**
* taken from mm/filemap.c because it isn't exported
*
@@ -710,7 +751,7 @@ int btrfs_wait_on_page_writeback_range(s
if (page->index > end)
continue;
- wait_on_page_writeback(page);
+ btrfs_wait_on_page_writeback(page);
if (PageError(page))
ret = -EIO;
}
diff -Nrup linux-2.6.29.org/fs/btrfs/transaction.c linux-2.6.29.btrfs/fs/btrfs/transaction.c
--- linux-2.6.29.org/fs/btrfs/transaction.c 2009-03-24 08:12:14.000000000 +0900
+++ linux-2.6.29.btrfs/fs/btrfs/transaction.c 2009-03-24 15:37:19.000000000 +0900
@@ -352,7 +352,7 @@ int btrfs_write_and_wait_marked_extents(
if (PageWriteback(page)) {
if (PageDirty(page))
- wait_on_page_writeback(page);
+ btrfs_wait_on_page_writeback(page);
else {
unlock_page(page);
page_cache_release(page);
@@ -380,12 +380,12 @@ int btrfs_write_and_wait_marked_extents(
continue;
if (PageDirty(page)) {
btree_lock_page_hook(page);
- wait_on_page_writeback(page);
+ btrfs_wait_on_page_writeback(page);
err = write_one_page(page, 0);
if (err)
werr = err;
}
- wait_on_page_writeback(page);
+ btrfs_wait_on_page_writeback(page);
page_cache_release(page);
cond_resched();
}
--
To unsubscribe from this list: send the line "unsubscribe linux-btrfs" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
