@@ -551,26 +551,26 @@ static void run_one_async_free(struct btrfs_work *work)
static bool should_async_write(struct btrfs_bio *bbio)
{
+ struct btrfs_fs_info *fs_info = bbio->inode->root->fs_info;
+
+ /*
+ * Submit synchronously if the checksum implementation is fast.
+ */
+ if (test_bit(BTRFS_FS_CSUM_IMPL_FAST, &fs_info->flags))
+ return false;
+
/*
* Try to defer the submission to a workqueue to parallelize the
- * checksum calculation unless the I/O is issued synchronously.
+ * checksum calculation only if the I/O is issued asynchronously.
*/
if (op_is_sync(bbio->bio.bi_opf))
return false;
/*
- * Submit metadata writes synchronously if the checksum implementation
- * is fast, or we are on a zoned device that wants I/O to be submitted
- * in order.
+ * Zoned devices require I/O to be submitted in order.
*/
- if (bbio->bio.bi_opf & REQ_META) {
- struct btrfs_fs_info *fs_info = bbio->inode->root->fs_info;
-
- if (btrfs_is_zoned(fs_info))
- return false;
- if (test_bit(BTRFS_FS_CSUM_IMPL_FAST, &fs_info->flags))
- return false;
- }
+ if ((bbio->bio.bi_opf & REQ_META) && btrfs_is_zoned(fs_info))
+ return false;
return true;
}
Most modern hardware supports very fast accelerated crc32c calculation. If that is supported the CPU overhead of the checksum calculation is very limited, and offloading the calculation to special worker threads has a lot of overhead for no gain. E.g. on an Intel Optane device is actually very much slows down even 1M buffered writes with fio: Unpatched: write: IOPS=3316, BW=3316MiB/s (3477MB/s)(200GiB/61757msec); 0 zone resets With synchronous CRCs: write: IOPS=4882, BW=4882MiB/s (5119MB/s)(200GiB/41948msec); 0 zone resets With a lot of variation during the unpatch run going down as low as 1100MB/s, while the synchronous CRC version has about the same peak write speed but much lower dips, and fewer kworkers churning around. Both tests had fio saturated at 100% CPU. (thanks to Jens Axboe via Chris Mason for the benchmarking) Signed-off-by: Christoph Hellwig <hch@lst.de> --- fs/btrfs/bio.c | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-)