From 13e6d5cdde0e785aa943810f08b801cadd0935df Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 31 Aug 2009 21:00:31 -0300 Subject: xfs: merge fsync and O_SYNC handling The guarantees for O_SYNC are exactly the same as the ones we need to make for an fsync call (and given that Linux O_SYNC is O_DSYNC the equivalent is fdadatasync, but we treat both the same in XFS), except with a range data writeout. Jan Kara has started unifying these two path for filesystems using the generic helpers, and I've started to look at XFS. The actual transaction commited by xfs_fsync and xfs_write_sync_logforce has a different transaction number, but actually is exactly the same. We'll only use the fsync transaction going forward. One major difference is that xfs_write_sync_logforce never issues a cache flush unless we commit a transaction causing that as a side-effect, which is an obvious bug in the O_SYNC handling. Second all the locking and i_update_size vs i_update_core changes from 978b7237123d007b9fa983af6e0e2fa8f97f9934 never made it to xfs_write_sync_logforce, so we add them back. To make xfs_fsync easily usable from the O_SYNC path, the filemap_fdatawait call is moved up to xfs_file_fsync, so that we don't wait on the whole file after we already waited for our portion in xfs_write. We'll also use a plain call to filemap_write_and_wait_range instead of the previous sync_page_rang which did it in two steps including an half-hearted inode write out that doesn't help us. Once we're done with this also remove the now useless i_update_size tracking. Signed-off-by: Christoph Hellwig Reviewed-by: Felix Blyakher Signed-off-by: Felix Blyakher --- fs/xfs/xfs_rw.c | 84 --------------------------------------------------------- 1 file changed, 84 deletions(-) (limited to 'fs/xfs/xfs_rw.c') diff --git a/fs/xfs/xfs_rw.c b/fs/xfs/xfs_rw.c index fea68615ed2..3f816ad7ff1 100644 --- a/fs/xfs/xfs_rw.c +++ b/fs/xfs/xfs_rw.c @@ -87,90 +87,6 @@ xfs_write_clear_setuid( return 0; } -/* - * Handle logging requirements of various synchronous types of write. - */ -int -xfs_write_sync_logforce( - xfs_mount_t *mp, - xfs_inode_t *ip) -{ - int error = 0; - - /* - * If we're treating this as O_DSYNC and we have not updated the - * size, force the log. - */ - if (!(mp->m_flags & XFS_MOUNT_OSYNCISOSYNC) && - !(ip->i_update_size)) { - xfs_inode_log_item_t *iip = ip->i_itemp; - - /* - * If an allocation transaction occurred - * without extending the size, then we have to force - * the log up the proper point to ensure that the - * allocation is permanent. We can't count on - * the fact that buffered writes lock out direct I/O - * writes - the direct I/O write could have extended - * the size nontransactionally, then finished before - * we started. xfs_write_file will think that the file - * didn't grow but the update isn't safe unless the - * size change is logged. - * - * Force the log if we've committed a transaction - * against the inode or if someone else has and - * the commit record hasn't gone to disk (e.g. - * the inode is pinned). This guarantees that - * all changes affecting the inode are permanent - * when we return. - */ - if (iip && iip->ili_last_lsn) { - error = _xfs_log_force(mp, iip->ili_last_lsn, - XFS_LOG_FORCE | XFS_LOG_SYNC, NULL); - } else if (xfs_ipincount(ip) > 0) { - error = _xfs_log_force(mp, (xfs_lsn_t)0, - XFS_LOG_FORCE | XFS_LOG_SYNC, NULL); - } - - } else { - xfs_trans_t *tp; - - /* - * O_SYNC or O_DSYNC _with_ a size update are handled - * the same way. - * - * If the write was synchronous then we need to make - * sure that the inode modification time is permanent. - * We'll have updated the timestamp above, so here - * we use a synchronous transaction to log the inode. - * It's not fast, but it's necessary. - * - * If this a dsync write and the size got changed - * non-transactionally, then we need to ensure that - * the size change gets logged in a synchronous - * transaction. - */ - tp = xfs_trans_alloc(mp, XFS_TRANS_WRITE_SYNC); - if ((error = xfs_trans_reserve(tp, 0, - XFS_SWRITE_LOG_RES(mp), - 0, 0, 0))) { - /* Transaction reserve failed */ - xfs_trans_cancel(tp, 0); - } else { - /* Transaction reserve successful */ - xfs_ilock(ip, XFS_ILOCK_EXCL); - xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL); - xfs_trans_ihold(tp, ip); - xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); - xfs_trans_set_sync(tp); - error = xfs_trans_commit(tp, 0); - xfs_iunlock(ip, XFS_ILOCK_EXCL); - } - } - - return error; -} - /* * Force a shutdown of the filesystem instantly while keeping * the filesystem consistent. We don't do an unmount here; just shutdown -- cgit