From 2b2861362f7dd09cc3167df8fddb6e2cb475018a Mon Sep 17 00:00:00 2001 From: Brian Behlendorf Date: Wed, 29 Aug 2012 11:52:47 -0700 Subject: [PATCH] Clear PG_writeback after zil_commit() for sync I/O When writing via ->writepage() the writeback bit was always cleared as part of the txg commit callback. However, when the I/O is also being written synchronsously to the zil we can immediately clear this bit. There is no need to wait for the subsequent TXG sync since the data is already safe on stable storage. This has been observed to reduce the msync(2) delay from up to 5 seconds down 10s of miliseconds. One workload which is expected to benefit from this are the intermittent samba hands described in issue #700. Signed-off-by: Brian Behlendorf Closes #700 Closes #907 --- module/zfs/zfs_vnops.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/module/zfs/zfs_vnops.c b/module/zfs/zfs_vnops.c index 2da5fec86..755d0575a 100644 --- a/module/zfs/zfs_vnops.c +++ b/module/zfs/zfs_vnops.c @@ -3797,6 +3797,7 @@ zfs_putpage(struct inode *ip, struct page *pp, struct writeback_control *wbc) uint64_t mtime[2], ctime[2]; sa_bulk_attr_t bulk[3]; int cnt = 0; + int sync; ASSERT(PageLocked(pp)); @@ -3833,7 +3834,10 @@ zfs_putpage(struct inode *ip, struct page *pp, struct writeback_control *wbc) tx = dmu_tx_create(zsb->z_os); - dmu_tx_callback_register(tx, zfs_putpage_commit_cb, pp); + sync = ((zsb->z_os->os_sync == ZFS_SYNC_ALWAYS) || + (wbc->sync_mode == WB_SYNC_ALL)); + if (!sync) + dmu_tx_callback_register(tx, zfs_putpage_commit_cb, pp); dmu_tx_hold_write(tx, zp->z_id, pgoff, pglen); @@ -3862,9 +3866,10 @@ zfs_putpage(struct inode *ip, struct page *pp, struct writeback_control *wbc) dmu_tx_commit(tx); ASSERT3S(err, ==, 0); - if ((zsb->z_os->os_sync == ZFS_SYNC_ALWAYS) || - (wbc->sync_mode == WB_SYNC_ALL)) + if (sync) { zil_commit(zsb->z_log, zp->z_id); + zfs_putpage_commit_cb(pp, err); + } return (err); }