summaryrefslogtreecommitdiff
path: root/fs/xfs/xfs_iomap.c
diff options
context:
space:
mode:
authorDave Chinner <dchinner@redhat.com>2012-10-08 21:56:04 +1100
committerBen Myers <bpm@sgi.com>2012-10-17 12:01:25 -0500
commit9aa05000f2b7cab4be582afba64af10b2d74727e (patch)
tree530f939b017f5c5e8729edc28da0773c20b1986b /fs/xfs/xfs_iomap.c
parentcf2931db2d189ce0583be7ae880d7e3f8c15f623 (diff)
xfs: xfs_sync_data is redundant.
We don't do any data writeback from XFS any more - the VFS is completely responsible for that, including for freeze. We can replace the remaining caller with a VFS level function that achieves the same thing, but without conflicting with current writeback work. This means we can remove the flush_work and xfs_flush_inodes() - the VFS functionality completely replaces the internal flush queue for doing this writeback work in a separate context to avoid stack overruns. This does have one complication - it cannot be called with page locks held. Hence move the flushing of delalloc space when ENOSPC occurs back up into xfs_file_aio_buffered_write when we don't hold any locks that will stall writeback. Unfortunately, writeback_inodes_sb_if_idle() is not sufficient to trigger delalloc conversion fast enough to prevent spurious ENOSPC whent here are hundreds of writers, thousands of small files and GBs of free RAM. Hence we need to use sync_sb_inodes() to block callers while we wait for writeback like the previous xfs_flush_inodes implementation did. That means we have to hold the s_umount lock here, but because this call can nest inside i_mutex (the parent directory in the create case, held by the VFS), we have to use down_read_trylock() to avoid potential deadlocks. In practice, this trylock will succeed on almost every attempt as unmount/remount type operations are exceedingly rare. Note: we always need to pass a count of zero to generic_file_buffered_write() as the previously written byte count. We only do this by accident before this patch by the virtue of ret always being zero when there are no errors. Make this explicit rather than needing to specifically zero ret in the ENOSPC retry case. Signed-off-by: Dave Chinner <dchinner@redhat.com> Tested-by: Brian Foster <bfoster@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Ben Myers <bpm@sgi.com>
Diffstat (limited to 'fs/xfs/xfs_iomap.c')
-rw-r--r--fs/xfs/xfs_iomap.c23
1 files changed, 7 insertions, 16 deletions
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 973dff6ad935..f858b903678e 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -373,7 +373,7 @@ xfs_iomap_write_delay(
xfs_extlen_t extsz;
int nimaps;
xfs_bmbt_irec_t imap[XFS_WRITE_IMAPS];
- int prealloc, flushed = 0;
+ int prealloc;
int error;
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
@@ -434,26 +434,17 @@ retry:
}
/*
- * If bmapi returned us nothing, we got either ENOSPC or EDQUOT. For
- * ENOSPC, * flush all other inodes with delalloc blocks to free up
- * some of the excess reserved metadata space. For both cases, retry
+ * If bmapi returned us nothing, we got either ENOSPC or EDQUOT. Retry
* without EOF preallocation.
*/
if (nimaps == 0) {
trace_xfs_delalloc_enospc(ip, offset, count);
- if (flushed)
- return XFS_ERROR(error ? error : ENOSPC);
-
- if (error == ENOSPC) {
- xfs_iunlock(ip, XFS_ILOCK_EXCL);
- xfs_flush_inodes(ip);
- xfs_ilock(ip, XFS_ILOCK_EXCL);
+ if (prealloc) {
+ prealloc = 0;
+ error = 0;
+ goto retry;
}
-
- flushed = 1;
- error = 0;
- prealloc = 0;
- goto retry;
+ return XFS_ERROR(error ? error : ENOSPC);
}
if (!(imap[0].br_startblock || XFS_IS_REALTIME_INODE(ip)))