From 66d834ea603d61bd90fedad90300ca91c5bba0a3 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 15 Feb 2010 09:44:49 +0000 Subject: xfs: implement optimized fdatasync Allow us to track the difference between timestamp and size updates by using mark_inode_dirty from the I/O completion code, and checking the VFS inode flags in xfs_file_fsync. Signed-off-by: Christoph Hellwig Reviewed-by: Dave Chinner Signed-off-by: Alex Elder --- fs/xfs/linux-2.6/xfs_aops.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'fs/xfs/linux-2.6/xfs_aops.c') diff --git a/fs/xfs/linux-2.6/xfs_aops.c b/fs/xfs/linux-2.6/xfs_aops.c index 66abe36c1213..ce369a816ce3 100644 --- a/fs/xfs/linux-2.6/xfs_aops.c +++ b/fs/xfs/linux-2.6/xfs_aops.c @@ -187,7 +187,7 @@ xfs_setfilesize( isize = xfs_ioend_new_eof(ioend); if (isize) { ip->i_d.di_size = isize; - xfs_mark_inode_dirty_sync(ip); + xfs_mark_inode_dirty(ip); } xfs_iunlock(ip, XFS_ILOCK_EXCL); @@ -341,7 +341,7 @@ xfs_submit_ioend_bio( * but don't update the inode size until I/O completion. */ if (xfs_ioend_new_eof(ioend)) - xfs_mark_inode_dirty_sync(XFS_I(ioend->io_inode)); + xfs_mark_inode_dirty(XFS_I(ioend->io_inode)); submit_bio(wbc->sync_mode == WB_SYNC_ALL ? WRITE_SYNC_PLUG : WRITE, bio); -- cgit v1.2.3 From 77d7a0c2eeb285c9069e15396703d0cb9690ac50 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Wed, 17 Feb 2010 05:36:29 +0000 Subject: xfs: Non-blocking inode locking in IO completion The introduction of barriers to loop devices has created a new IO order completion dependency that XFS does not handle. The loop device implements barriers using fsync and so turns a log IO in the XFS filesystem on the loop device into a data IO in the backing filesystem. That is, the completion of log IOs in the loop filesystem are now dependent on completion of data IO in the backing filesystem. This can cause deadlocks when a flush daemon issues a log force with an inode locked because the IO completion of IO on the inode is blocked by the inode lock. This in turn prevents further data IO completion from occuring on all XFS filesystems on that CPU (due to the shared nature of the completion queues). This then prevents the log IO from completing because the log is waiting for data IO completion as well. The fix for this new completion order dependency issue is to make the IO completion inode locking non-blocking. If the inode lock can't be grabbed, simply requeue the IO completion back to the work queue so that it can be processed later. This prevents the completion queue from being blocked and allows data IO completion on other inodes to proceed, hence avoiding completion order dependent deadlocks. Signed-off-by: Dave Chinner Reviewed-by: Christoph Hellwig Signed-off-by: Alex Elder --- fs/xfs/linux-2.6/xfs_aops.c | 93 +++++++++++++++++++++++++++------------------ 1 file changed, 56 insertions(+), 37 deletions(-) (limited to 'fs/xfs/linux-2.6/xfs_aops.c') diff --git a/fs/xfs/linux-2.6/xfs_aops.c b/fs/xfs/linux-2.6/xfs_aops.c index ce369a816ce3..b493c63976cd 100644 --- a/fs/xfs/linux-2.6/xfs_aops.c +++ b/fs/xfs/linux-2.6/xfs_aops.c @@ -163,14 +163,17 @@ xfs_ioend_new_eof( } /* - * Update on-disk file size now that data has been written to disk. - * The current in-memory file size is i_size. If a write is beyond - * eof i_new_size will be the intended file size until i_size is - * updated. If this write does not extend all the way to the valid - * file size then restrict this update to the end of the write. + * Update on-disk file size now that data has been written to disk. The + * current in-memory file size is i_size. If a write is beyond eof i_new_size + * will be the intended file size until i_size is updated. If this write does + * not extend all the way to the valid file size then restrict this update to + * the end of the write. + * + * This function does not block as blocking on the inode lock in IO completion + * can lead to IO completion order dependency deadlocks.. If it can't get the + * inode ilock it will return EAGAIN. Callers must handle this. */ - -STATIC void +STATIC int xfs_setfilesize( xfs_ioend_t *ioend) { @@ -181,9 +184,11 @@ xfs_setfilesize( ASSERT(ioend->io_type != IOMAP_READ); if (unlikely(ioend->io_error)) - return; + return 0; + + if (!xfs_ilock_nowait(ip, XFS_ILOCK_EXCL)) + return EAGAIN; - xfs_ilock(ip, XFS_ILOCK_EXCL); isize = xfs_ioend_new_eof(ioend); if (isize) { ip->i_d.di_size = isize; @@ -191,6 +196,28 @@ xfs_setfilesize( } xfs_iunlock(ip, XFS_ILOCK_EXCL); + return 0; +} + +/* + * Schedule IO completion handling on a xfsdatad if this was + * the final hold on this ioend. If we are asked to wait, + * flush the workqueue. + */ +STATIC void +xfs_finish_ioend( + xfs_ioend_t *ioend, + int wait) +{ + if (atomic_dec_and_test(&ioend->io_remaining)) { + struct workqueue_struct *wq; + + wq = (ioend->io_type == IOMAP_UNWRITTEN) ? + xfsconvertd_workqueue : xfsdatad_workqueue; + queue_work(wq, &ioend->io_work); + if (wait) + flush_workqueue(wq); + } } /* @@ -198,11 +225,11 @@ xfs_setfilesize( */ STATIC void xfs_end_io( - struct work_struct *work) + struct work_struct *work) { - xfs_ioend_t *ioend = - container_of(work, xfs_ioend_t, io_work); - struct xfs_inode *ip = XFS_I(ioend->io_inode); + xfs_ioend_t *ioend = container_of(work, xfs_ioend_t, io_work); + struct xfs_inode *ip = XFS_I(ioend->io_inode); + int error; /* * For unwritten extents we need to issue transactions to convert a @@ -210,7 +237,6 @@ xfs_end_io( */ if (ioend->io_type == IOMAP_UNWRITTEN && likely(!ioend->io_error && !XFS_FORCED_SHUTDOWN(ip->i_mount))) { - int error; error = xfs_iomap_write_unwritten(ip, ioend->io_offset, ioend->io_size); @@ -222,30 +248,23 @@ xfs_end_io( * We might have to update the on-disk file size after extending * writes. */ - if (ioend->io_type != IOMAP_READ) - xfs_setfilesize(ioend); - xfs_destroy_ioend(ioend); -} - -/* - * Schedule IO completion handling on a xfsdatad if this was - * the final hold on this ioend. If we are asked to wait, - * flush the workqueue. - */ -STATIC void -xfs_finish_ioend( - xfs_ioend_t *ioend, - int wait) -{ - if (atomic_dec_and_test(&ioend->io_remaining)) { - struct workqueue_struct *wq; - - wq = (ioend->io_type == IOMAP_UNWRITTEN) ? - xfsconvertd_workqueue : xfsdatad_workqueue; - queue_work(wq, &ioend->io_work); - if (wait) - flush_workqueue(wq); + if (ioend->io_type != IOMAP_READ) { + error = xfs_setfilesize(ioend); + ASSERT(!error || error == EAGAIN); } + + /* + * If we didn't complete processing of the ioend, requeue it to the + * tail of the workqueue for another attempt later. Otherwise destroy + * it. + */ + if (error == EAGAIN) { + atomic_inc(&ioend->io_remaining); + xfs_finish_ioend(ioend, 0); + /* ensure we don't spin on blocked ioends */ + delay(1); + } else + xfs_destroy_ioend(ioend); } /* -- cgit v1.2.3 From 694189328a7e566cb84bd3205503a42b60e87882 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Thu, 4 Mar 2010 00:57:09 +0000 Subject: xfs: Fix a build warning in xfs_aops.c Fix a build warning that slipped through. Dave Chinner had posted an updated version of his patch but the previous version--without this fix--was what got committed. Reported-by: Stephen Rothwell Signed-off-by: Stephen Rothwell Signed-off-by: Dave Chinner Signed-off-by: Alex Elder --- fs/xfs/linux-2.6/xfs_aops.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs/xfs/linux-2.6/xfs_aops.c') diff --git a/fs/xfs/linux-2.6/xfs_aops.c b/fs/xfs/linux-2.6/xfs_aops.c index b493c63976cd..793908a8a09b 100644 --- a/fs/xfs/linux-2.6/xfs_aops.c +++ b/fs/xfs/linux-2.6/xfs_aops.c @@ -229,7 +229,7 @@ xfs_end_io( { xfs_ioend_t *ioend = container_of(work, xfs_ioend_t, io_work); struct xfs_inode *ip = XFS_I(ioend->io_inode); - int error; + int error = 0; /* * For unwritten extents we need to issue transactions to convert a -- cgit v1.2.3 From 3ed3a4343b79a79d10e31f85f2d1afabcead76c6 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Fri, 5 Mar 2010 02:00:42 +0000 Subject: xfs: truncate delalloc extents when IO fails in writeback We currently use block_invalidatepage() to clean up pages where I/O fails in ->writepage(). Unfortunately, if the page has delalloc regions on it, we fail to remove the delalloc regions when we invalidate the page. This can result in tripping a BUG() in xfs_get_blocks() later on if a direct IO read is done on that same region - the delalloc extent is returned when none is supposed to be there. Fix this by truncating away the delalloc regions on the page before invalidating it. Because they are delalloc, we can do this without needing a transaction. Indeed - if we get ENOSPC errors, we have to be able to do this truncation without a transaction as there is no space left for block reservation (typically why we see a ENOSPC in writeback). Signed-off-by: Dave Chinner Reviewed-by: Christoph Hellwig Signed-off-by: Alex Elder --- fs/xfs/linux-2.6/xfs_aops.c | 124 ++++++++++++++++++++++++++++++++++++++++---- 1 file changed, 114 insertions(+), 10 deletions(-) (limited to 'fs/xfs/linux-2.6/xfs_aops.c') diff --git a/fs/xfs/linux-2.6/xfs_aops.c b/fs/xfs/linux-2.6/xfs_aops.c index 793908a8a09b..9083357f9e44 100644 --- a/fs/xfs/linux-2.6/xfs_aops.c +++ b/fs/xfs/linux-2.6/xfs_aops.c @@ -39,6 +39,7 @@ #include "xfs_iomap.h" #include "xfs_vnodeops.h" #include "xfs_trace.h" +#include "xfs_bmap.h" #include #include #include @@ -893,6 +894,118 @@ xfs_cluster_write( } } +STATIC void +xfs_vm_invalidatepage( + struct page *page, + unsigned long offset) +{ + trace_xfs_invalidatepage(page->mapping->host, page, offset); + block_invalidatepage(page, offset); +} + +/* + * If the page has delalloc buffers on it, we need to punch them out before we + * invalidate the page. If we don't, we leave a stale delalloc mapping on the + * inode that can trip a BUG() in xfs_get_blocks() later on if a direct IO read + * is done on that same region - the delalloc extent is returned when none is + * supposed to be there. + * + * We prevent this by truncating away the delalloc regions on the page before + * invalidating it. Because they are delalloc, we can do this without needing a + * transaction. Indeed - if we get ENOSPC errors, we have to be able to do this + * truncation without a transaction as there is no space left for block + * reservation (typically why we see a ENOSPC in writeback). + * + * This is not a performance critical path, so for now just do the punching a + * buffer head at a time. + */ +STATIC void +xfs_aops_discard_page( + struct page *page) +{ + struct inode *inode = page->mapping->host; + struct xfs_inode *ip = XFS_I(inode); + struct buffer_head *bh, *head; + loff_t offset = page_offset(page); + ssize_t len = 1 << inode->i_blkbits; + + if (!xfs_is_delayed_page(page, IOMAP_DELAY)) + goto out_invalidate; + + xfs_fs_cmn_err(CE_ALERT, ip->i_mount, + "page discard on page %p, inode 0x%llx, offset %llu.", + page, ip->i_ino, offset); + + xfs_ilock(ip, XFS_ILOCK_EXCL); + bh = head = page_buffers(page); + do { + int done; + xfs_fileoff_t offset_fsb; + xfs_bmbt_irec_t imap; + int nimaps = 1; + int error; + xfs_fsblock_t firstblock; + xfs_bmap_free_t flist; + + if (!buffer_delay(bh)) + goto next_buffer; + + offset_fsb = XFS_B_TO_FSBT(ip->i_mount, offset); + + /* + * Map the range first and check that it is a delalloc extent + * before trying to unmap the range. Otherwise we will be + * trying to remove a real extent (which requires a + * transaction) or a hole, which is probably a bad idea... + */ + error = xfs_bmapi(NULL, ip, offset_fsb, 1, + XFS_BMAPI_ENTIRE, NULL, 0, &imap, + &nimaps, NULL, NULL); + + if (error) { + /* something screwed, just bail */ + xfs_fs_cmn_err(CE_ALERT, ip->i_mount, + "page discard failed delalloc mapping lookup."); + break; + } + if (!nimaps) { + /* nothing there */ + goto next_buffer; + } + if (imap.br_startblock != DELAYSTARTBLOCK) { + /* been converted, ignore */ + goto next_buffer; + } + WARN_ON(imap.br_blockcount == 0); + + /* + * Note: while we initialise the firstblock/flist pair, they + * should never be used because blocks should never be + * allocated or freed for a delalloc extent and hence we need + * don't cancel or finish them after the xfs_bunmapi() call. + */ + xfs_bmap_init(&flist, &firstblock); + error = xfs_bunmapi(NULL, ip, offset_fsb, 1, 0, 1, &firstblock, + &flist, NULL, &done); + + ASSERT(!flist.xbf_count && !flist.xbf_first); + if (error) { + /* something screwed, just bail */ + xfs_fs_cmn_err(CE_ALERT, ip->i_mount, + "page discard unable to remove delalloc mapping."); + break; + } +next_buffer: + offset += len; + + } while ((bh = bh->b_this_page) != head); + + xfs_iunlock(ip, XFS_ILOCK_EXCL); +out_invalidate: + xfs_vm_invalidatepage(page, 0); + return; +} + /* * Calling this without startio set means we are being asked to make a dirty * page ready for freeing it's buffers. When called with startio set then @@ -1144,7 +1257,7 @@ error: */ if (err != -EAGAIN) { if (!unmapped) - block_invalidatepage(page, 0); + xfs_aops_discard_page(page); ClearPageUptodate(page); } return err; @@ -1554,15 +1667,6 @@ xfs_vm_readpages( return mpage_readpages(mapping, pages, nr_pages, xfs_get_blocks); } -STATIC void -xfs_vm_invalidatepage( - struct page *page, - unsigned long offset) -{ - trace_xfs_invalidatepage(page->mapping->host, page, offset); - block_invalidatepage(page, offset); -} - const struct address_space_operations xfs_address_space_operations = { .readpage = xfs_vm_readpage, .readpages = xfs_vm_readpages, -- cgit v1.2.3 From e8c3753ce4cd6a805ebcfdb3aa6d30e6f4b8b3e0 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Mon, 15 Mar 2010 02:36:35 +0000 Subject: xfs: don't warn about page discards on shutdown If we are doing a forced shutdown, we can get lots of noise about delalloc pages being discarded. This is happens by design during a forced shutdown, so don't spam the logs with these messages. Signed-off-by: Dave Chinner Reviewed-by: Christoph Hellwig Signed-off-by: Alex Elder --- fs/xfs/linux-2.6/xfs_aops.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) (limited to 'fs/xfs/linux-2.6/xfs_aops.c') diff --git a/fs/xfs/linux-2.6/xfs_aops.c b/fs/xfs/linux-2.6/xfs_aops.c index 9083357f9e44..99628508cb11 100644 --- a/fs/xfs/linux-2.6/xfs_aops.c +++ b/fs/xfs/linux-2.6/xfs_aops.c @@ -932,6 +932,9 @@ xfs_aops_discard_page( if (!xfs_is_delayed_page(page, IOMAP_DELAY)) goto out_invalidate; + if (XFS_FORCED_SHUTDOWN(ip->i_mount)) + goto out_invalidate; + xfs_fs_cmn_err(CE_ALERT, ip->i_mount, "page discard on page %p, inode 0x%llx, offset %llu.", page, ip->i_ino, offset); @@ -964,8 +967,10 @@ xfs_aops_discard_page( if (error) { /* something screwed, just bail */ - xfs_fs_cmn_err(CE_ALERT, ip->i_mount, - "page discard failed delalloc mapping lookup."); + if (!XFS_FORCED_SHUTDOWN(ip->i_mount)) { + xfs_fs_cmn_err(CE_ALERT, ip->i_mount, + "page discard failed delalloc mapping lookup."); + } break; } if (!nimaps) { @@ -991,8 +996,10 @@ xfs_aops_discard_page( ASSERT(!flist.xbf_count && !flist.xbf_first); if (error) { /* something screwed, just bail */ - xfs_fs_cmn_err(CE_ALERT, ip->i_mount, + if (!XFS_FORCED_SHUTDOWN(ip->i_mount)) { + xfs_fs_cmn_err(CE_ALERT, ip->i_mount, "page discard unable to remove delalloc mapping."); + } break; } next_buffer: -- cgit v1.2.3