From a8d770d987ee20b59fba6c37d7f0f2a351913c4b Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Mon, 6 Apr 2009 18:44:54 +0200 Subject: xfs: use xfs_sync_inodes() for device flushing Currently xfs_device_flush calls sync_blockdev() which is a no-op for XFS as all it's metadata is held in a different address to the one sync_blockdev() works on. Call xfs_sync_inodes() instead to flush all the delayed allocation blocks out. To do this as efficiently as possible, do it via two passes - one to do an async flush of all the dirty blocks and a second to wait for all the IO to complete. This requires some modification to the xfs-sync_inodes_ag() flush code to do efficiently. Signed-off-by: Dave Chinner Reviewed-by: Christoph Hellwig --- fs/xfs/linux-2.6/xfs_sync.c | 43 +++++++++++++++++++++++++------------------ 1 file changed, 25 insertions(+), 18 deletions(-) (limited to 'fs/xfs/linux-2.6/xfs_sync.c') diff --git a/fs/xfs/linux-2.6/xfs_sync.c b/fs/xfs/linux-2.6/xfs_sync.c index a608e72fa40..88caafc8ef1 100644 --- a/fs/xfs/linux-2.6/xfs_sync.c +++ b/fs/xfs/linux-2.6/xfs_sync.c @@ -62,12 +62,6 @@ xfs_sync_inodes_ag( uint32_t first_index = 0; int error = 0; int last_error = 0; - int fflag = XFS_B_ASYNC; - - if (flags & SYNC_DELWRI) - fflag = XFS_B_DELWRI; - if (flags & SYNC_WAIT) - fflag = 0; /* synchronous overrides all */ do { struct inode *inode; @@ -128,11 +122,23 @@ xfs_sync_inodes_ag( * If we have to flush data or wait for I/O completion * we need to hold the iolock. */ - if ((flags & SYNC_DELWRI) && VN_DIRTY(inode)) { - xfs_ilock(ip, XFS_IOLOCK_SHARED); - lock_flags |= XFS_IOLOCK_SHARED; - error = xfs_flush_pages(ip, 0, -1, fflag, FI_NONE); - if (flags & SYNC_IOWAIT) + if (flags & SYNC_DELWRI) { + if (VN_DIRTY(inode)) { + if (flags & SYNC_TRYLOCK) { + if (xfs_ilock_nowait(ip, XFS_IOLOCK_SHARED)) + lock_flags |= XFS_IOLOCK_SHARED; + } else { + xfs_ilock(ip, XFS_IOLOCK_SHARED); + lock_flags |= XFS_IOLOCK_SHARED; + } + if (lock_flags & XFS_IOLOCK_SHARED) { + error = xfs_flush_pages(ip, 0, -1, + (flags & SYNC_WAIT) ? 0 + : XFS_B_ASYNC, + FI_NONE); + } + } + if (VN_CACHED(inode) && (flags & SYNC_IOWAIT)) xfs_ioend_wait(ip); } xfs_ilock(ip, XFS_ILOCK_SHARED); @@ -400,9 +406,9 @@ xfs_syncd_queue_work( void *data, void (*syncer)(struct xfs_mount *, void *)) { - struct bhv_vfs_sync_work *work; + struct xfs_sync_work *work; - work = kmem_alloc(sizeof(struct bhv_vfs_sync_work), KM_SLEEP); + work = kmem_alloc(sizeof(struct xfs_sync_work), KM_SLEEP); INIT_LIST_HEAD(&work->w_list); work->w_syncer = syncer; work->w_data = data; @@ -445,23 +451,24 @@ xfs_flush_inode( * (IOW, "If at first you don't succeed, use a Bigger Hammer"). */ STATIC void -xfs_flush_device_work( +xfs_flush_inodes_work( struct xfs_mount *mp, void *arg) { struct inode *inode = arg; - sync_blockdev(mp->m_super->s_bdev); + xfs_sync_inodes(mp, SYNC_DELWRI | SYNC_TRYLOCK); + xfs_sync_inodes(mp, SYNC_DELWRI | SYNC_TRYLOCK | SYNC_IOWAIT); iput(inode); } void -xfs_flush_device( +xfs_flush_inodes( xfs_inode_t *ip) { struct inode *inode = VFS_I(ip); igrab(inode); - xfs_syncd_queue_work(ip->i_mount, inode, xfs_flush_device_work); + xfs_syncd_queue_work(ip->i_mount, inode, xfs_flush_inodes_work); delay(msecs_to_jiffies(500)); xfs_log_force(ip->i_mount, (xfs_lsn_t)0, XFS_LOG_FORCE|XFS_LOG_SYNC); } @@ -497,7 +504,7 @@ xfssyncd( { struct xfs_mount *mp = arg; long timeleft; - bhv_vfs_sync_work_t *work, *n; + xfs_sync_work_t *work, *n; LIST_HEAD (tmp); set_freezable(); -- cgit v1.2.3 From 5825294edd3364cbba6514f70d88debec4f6cec7 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Mon, 6 Apr 2009 18:45:44 +0200 Subject: xfs: make inode flush at ENOSPC synchronous When we are writing to a single file and hit ENOSPC, we trigger a background flush of the inode and try again. Because we hold page locks and the iolock, the flush won't proceed until after we release these locks. This occurs once we've given up and ENOSPC has been reported. Hence if this one is the only dirty inode in the system, we'll get an ENOSPC prematurely. To fix this, remove the async flush from the allocation routines and move it to the top of the write path where we can do a synchronous flush and retry the write again. Only retry once as a second ENOSPC indicates that we really are ENOSPC. This avoids a page cache deadlock when trying to do this flush synchronously in the allocation layer that was identified by Mikulas Patocka. Signed-off-by: Dave Chinner Reviewed-by: Christoph Hellwig --- fs/xfs/linux-2.6/xfs_sync.c | 25 ------------------------- 1 file changed, 25 deletions(-) (limited to 'fs/xfs/linux-2.6/xfs_sync.c') diff --git a/fs/xfs/linux-2.6/xfs_sync.c b/fs/xfs/linux-2.6/xfs_sync.c index 88caafc8ef1..73cf8dc1973 100644 --- a/fs/xfs/linux-2.6/xfs_sync.c +++ b/fs/xfs/linux-2.6/xfs_sync.c @@ -426,31 +426,6 @@ xfs_syncd_queue_work( * heads, looking about for more room... */ STATIC void -xfs_flush_inode_work( - struct xfs_mount *mp, - void *arg) -{ - struct inode *inode = arg; - filemap_flush(inode->i_mapping); - iput(inode); -} - -void -xfs_flush_inode( - xfs_inode_t *ip) -{ - struct inode *inode = VFS_I(ip); - - igrab(inode); - xfs_syncd_queue_work(ip->i_mount, inode, xfs_flush_inode_work); - delay(msecs_to_jiffies(500)); -} - -/* - * This is the "bigger hammer" version of xfs_flush_inode_work... - * (IOW, "If at first you don't succeed, use a Bigger Hammer"). - */ -STATIC void xfs_flush_inodes_work( struct xfs_mount *mp, void *arg) -- cgit v1.2.3 From e43afd72d2455defd63a3f94f22fa09b586e58ed Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Mon, 6 Apr 2009 18:47:27 +0200 Subject: xfs: block callers of xfs_flush_inodes() correctly xfs_flush_inodes() currently uses a magic timeout to wait for some inodes to be flushed before returning. This isn't really reliable but used to be the best that could be done due to deadlock potential of waiting for the entire flush. Now the inode flush is safe to execute while we hold page and inode locks, we can wait for all the inodes to flush synchronously. Convert the wait mechanism to a completion to do this efficiently. This should remove all remaining spurious ENOSPC errors from the delayed allocation reservation path. This is extracted almost line for line from a larger patch from Mikulas Patocka. Signed-off-by: Mikulas Patocka Signed-off-by: Dave Chinner Reviewed-by: Christoph Hellwig --- fs/xfs/linux-2.6/xfs_sync.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) (limited to 'fs/xfs/linux-2.6/xfs_sync.c') diff --git a/fs/xfs/linux-2.6/xfs_sync.c b/fs/xfs/linux-2.6/xfs_sync.c index 73cf8dc1973..f7ba76633c2 100644 --- a/fs/xfs/linux-2.6/xfs_sync.c +++ b/fs/xfs/linux-2.6/xfs_sync.c @@ -404,7 +404,8 @@ STATIC void xfs_syncd_queue_work( struct xfs_mount *mp, void *data, - void (*syncer)(struct xfs_mount *, void *)) + void (*syncer)(struct xfs_mount *, void *), + struct completion *completion) { struct xfs_sync_work *work; @@ -413,6 +414,7 @@ xfs_syncd_queue_work( work->w_syncer = syncer; work->w_data = data; work->w_mount = mp; + work->w_completion = completion; spin_lock(&mp->m_sync_lock); list_add_tail(&work->w_list, &mp->m_sync_list); spin_unlock(&mp->m_sync_lock); @@ -441,10 +443,11 @@ xfs_flush_inodes( xfs_inode_t *ip) { struct inode *inode = VFS_I(ip); + DECLARE_COMPLETION_ONSTACK(completion); igrab(inode); - xfs_syncd_queue_work(ip->i_mount, inode, xfs_flush_inodes_work); - delay(msecs_to_jiffies(500)); + xfs_syncd_queue_work(ip->i_mount, inode, xfs_flush_inodes_work, &completion); + wait_for_completion(&completion); xfs_log_force(ip->i_mount, (xfs_lsn_t)0, XFS_LOG_FORCE|XFS_LOG_SYNC); } @@ -514,6 +517,8 @@ xfssyncd( list_del(&work->w_list); if (work == &mp->m_sync_work) continue; + if (work->w_completion) + complete(work->w_completion); kmem_free(work); } } @@ -527,6 +532,7 @@ xfs_syncd_init( { mp->m_sync_work.w_syncer = xfs_sync_worker; mp->m_sync_work.w_mount = mp; + mp->m_sync_work.w_completion = NULL; mp->m_sync_task = kthread_run(xfssyncd, mp, "xfssyncd"); if (IS_ERR(mp->m_sync_task)) return -PTR_ERR(mp->m_sync_task); -- cgit v1.2.3