From 6e34eeddf7deec1444bbddab533f03f520d8458c Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Tue, 7 Apr 2009 18:12:43 -0400 Subject: block_write_full_page: switch synchronous writes to use WRITE_SYNC_PLUG Now that we have a distinction between WRITE_SYNC and WRITE_SYNC_PLUG, use WRITE_SYNC_PLUG in __block_write_full_page() to avoid unplugging the block device I/O queue between each page that gets flushed out. Otherwise, when we run sync() or fsync() and we need to write out a large number of pages, the block device queue will get unplugged between for every page that is flushed out, which will be a pretty serious performance regression caused by commit a64c8610. Signed-off-by: "Theodore Ts'o" --- fs/buffer.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/buffer.c b/fs/buffer.c index 6e35762b6169..13edf7ad3ff1 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -1596,6 +1596,16 @@ EXPORT_SYMBOL(unmap_underlying_metadata); * locked buffer. This only can happen if someone has written the buffer * directly, with submit_bh(). At the address_space level PageWriteback * prevents this contention from occurring. + * + * If block_write_full_page() is called with wbc->sync_mode == + * WB_SYNC_ALL, the writes are posted using WRITE_SYNC_PLUG; this + * causes the writes to be flagged as synchronous writes, but the + * block device queue will NOT be unplugged, since usually many pages + * will be pushed to the out before the higher-level caller actually + * waits for the writes to be completed. The various wait functions, + * such as wait_on_writeback_range() will ultimately call sync_page() + * which will ultimately call blk_run_backing_dev(), which will end up + * unplugging the device queue. */ static int __block_write_full_page(struct inode *inode, struct page *page, get_block_t *get_block, struct writeback_control *wbc) @@ -1606,7 +1616,8 @@ static int __block_write_full_page(struct inode *inode, struct page *page, struct buffer_head *bh, *head; const unsigned blocksize = 1 << inode->i_blkbits; int nr_underway = 0; - int write_op = (wbc->sync_mode == WB_SYNC_ALL ? WRITE_SYNC : WRITE); + int write_op = (wbc->sync_mode == WB_SYNC_ALL ? + WRITE_SYNC_PLUG : WRITE); BUG_ON(!PageLocked(page)); -- cgit v1.2.2