diff options
| -rw-r--r-- | fs/xfs/xfs_file.c | 75 | ||||
| -rw-r--r-- | fs/xfs/xfs_inode.c | 25 | ||||
| -rw-r--r-- | fs/xfs/xfs_inode_item.c | 72 | ||||
| -rw-r--r-- | fs/xfs/xfs_inode_item.h | 10 | ||||
| -rw-r--r-- | fs/xfs/xfs_iomap.c | 15 |
5 files changed, 128 insertions, 69 deletions
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index f96fbf5c54c9..2702fef2c90c 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -75,52 +75,47 @@ xfs_dir_fsync( return xfs_log_force_inode(ip); } -static xfs_csn_t -xfs_fsync_seq( - struct xfs_inode *ip, - bool datasync) -{ - if (!xfs_ipincount(ip)) - return 0; - if (datasync && !(ip->i_itemp->ili_fsync_fields & ~XFS_ILOG_TIMESTAMP)) - return 0; - return ip->i_itemp->ili_commit_seq; -} - /* - * All metadata updates are logged, which means that we just have to flush the - * log up to the latest LSN that touched the inode. + * All metadata updates are logged, which means that we just have to push the + * journal to the required sequence number than holds the updates. We track + * datasync commits separately to full sync commits, and hence only need to + * select the correct sequence number for the log force here. * - * If we have concurrent fsync/fdatasync() calls, we need them to all block on - * the log force before we clear the ili_fsync_fields field. This ensures that - * we don't get a racing sync operation that does not wait for the metadata to - * hit the journal before returning. If we race with clearing ili_fsync_fields, - * then all that will happen is the log force will do nothing as the lsn will - * already be on disk. We can't race with setting ili_fsync_fields because that - * is done under XFS_ILOCK_EXCL, and that can't happen because we hold the lock - * shared until after the ili_fsync_fields is cleared. + * We don't have to serialise against concurrent modifications, as we do not + * have to wait for modifications that have not yet completed. We define a + * transaction commit as completing when the commit sequence number is updated, + * hence if the sequence number has not updated, the sync operation has been + * run before the commit completed and we don't have to wait for it. + * + * If we have concurrent fsync/fdatasync() calls, the sequence numbers remain + * set on the log item until - at least - the journal flush completes. In + * reality, they are only cleared when the inode is fully unpinned (i.e. + * persistent in the journal and not dirty in the CIL), and so we rely on + * xfs_log_force_seq() either skipping sequences that have been persisted or + * waiting on sequences that are still in flight to correctly order concurrent + * sync operations. */ -static int +static int xfs_fsync_flush_log( struct xfs_inode *ip, bool datasync, int *log_flushed) { - int error = 0; - xfs_csn_t seq; + struct xfs_inode_log_item *iip = ip->i_itemp; + xfs_csn_t seq = 0; - xfs_ilock(ip, XFS_ILOCK_SHARED); - seq = xfs_fsync_seq(ip, datasync); - if (seq) { - error = xfs_log_force_seq(ip->i_mount, seq, XFS_LOG_SYNC, - log_flushed); + spin_lock(&iip->ili_lock); + if (datasync) + seq = iip->ili_datasync_seq; + else + seq = iip->ili_commit_seq; + spin_unlock(&iip->ili_lock); - spin_lock(&ip->i_itemp->ili_lock); - ip->i_itemp->ili_fsync_fields = 0; - spin_unlock(&ip->i_itemp->ili_lock); - } - xfs_iunlock(ip, XFS_ILOCK_SHARED); - return error; + if (!seq) + return 0; + + return xfs_log_force_seq(ip->i_mount, seq, XFS_LOG_SYNC, + log_flushed); } STATIC int @@ -158,12 +153,10 @@ xfs_file_fsync( error = blkdev_issue_flush(mp->m_ddev_targp->bt_bdev); /* - * Any inode that has dirty modifications in the log is pinned. The - * racy check here for a pinned inode will not catch modifications - * that happen concurrently to the fsync call, but fsync semantics - * only require to sync previously completed I/O. + * If the inode has a inode log item attached, it may need the journal + * flushed to persist any changes the log item might be tracking. */ - if (xfs_ipincount(ip)) { + if (ip->i_itemp) { err2 = xfs_fsync_flush_log(ip, datasync, &log_flushed); if (err2 && !error) error = err2; diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 2bfe87b09c2a..047a5260cf70 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -1667,7 +1667,6 @@ retry: spin_lock(&iip->ili_lock); iip->ili_last_fields = iip->ili_fields; iip->ili_fields = 0; - iip->ili_fsync_fields = 0; spin_unlock(&iip->ili_lock); ASSERT(iip->ili_last_fields); @@ -1832,12 +1831,20 @@ static void xfs_iunpin( struct xfs_inode *ip) { - xfs_assert_ilocked(ip, XFS_ILOCK_EXCL | XFS_ILOCK_SHARED); + struct xfs_inode_log_item *iip = ip->i_itemp; + xfs_csn_t seq = 0; trace_xfs_inode_unpin_nowait(ip, _RET_IP_); + xfs_assert_ilocked(ip, XFS_ILOCK_EXCL | XFS_ILOCK_SHARED); + + spin_lock(&iip->ili_lock); + seq = iip->ili_commit_seq; + spin_unlock(&iip->ili_lock); + if (!seq) + return; /* Give the log a push to start the unpinning I/O */ - xfs_log_force_seq(ip->i_mount, ip->i_itemp->ili_commit_seq, 0, NULL); + xfs_log_force_seq(ip->i_mount, seq, 0, NULL); } @@ -2504,7 +2511,6 @@ flush_out: spin_lock(&iip->ili_lock); iip->ili_last_fields = iip->ili_fields; iip->ili_fields = 0; - iip->ili_fsync_fields = 0; set_bit(XFS_LI_FLUSHING, &iip->ili_item.li_flags); spin_unlock(&iip->ili_lock); @@ -2663,12 +2669,15 @@ int xfs_log_force_inode( struct xfs_inode *ip) { + struct xfs_inode_log_item *iip = ip->i_itemp; xfs_csn_t seq = 0; - xfs_ilock(ip, XFS_ILOCK_SHARED); - if (xfs_ipincount(ip)) - seq = ip->i_itemp->ili_commit_seq; - xfs_iunlock(ip, XFS_ILOCK_SHARED); + if (!iip) + return 0; + + spin_lock(&iip->ili_lock); + seq = iip->ili_commit_seq; + spin_unlock(&iip->ili_lock); if (!seq) return 0; diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c index 678ca95793e0..1bd411a1114c 100644 --- a/fs/xfs/xfs_inode_item.c +++ b/fs/xfs/xfs_inode_item.c @@ -187,13 +187,16 @@ xfs_inode_item_precommit( } /* - * Record the specific change for fdatasync optimisation. This allows - * fdatasync to skip log forces for inodes that are only timestamp - * dirty. Once we've processed the XFS_ILOG_IVERSION flag, convert it - * to XFS_ILOG_CORE so that the actual on-disk dirty tracking - * (ili_fields) correctly tracks that the version has changed. + * Store the dirty flags back into the inode item as this state is used + * later on in xfs_inode_item_committing() to determine whether the + * transaction is relevant to fsync state or not. + */ + iip->ili_dirty_flags = flags; + + /* + * Convert the flags on-disk fields that have been modified in the + * transaction so that ili_fields tracks the changes correctly. */ - iip->ili_fsync_fields |= (flags & ~XFS_ILOG_IVERSION); if (flags & XFS_ILOG_IVERSION) flags = ((flags & ~XFS_ILOG_IVERSION) | XFS_ILOG_CORE); @@ -207,12 +210,6 @@ xfs_inode_item_precommit( spin_unlock(&iip->ili_lock); xfs_inode_item_precommit_check(ip); - - /* - * We are done with the log item transaction dirty state, so clear it so - * that it doesn't pollute future transactions. - */ - iip->ili_dirty_flags = 0; return 0; } @@ -722,13 +719,24 @@ xfs_inode_item_unpin( struct xfs_log_item *lip, int remove) { - struct xfs_inode *ip = INODE_ITEM(lip)->ili_inode; + struct xfs_inode_log_item *iip = INODE_ITEM(lip); + struct xfs_inode *ip = iip->ili_inode; trace_xfs_inode_unpin(ip, _RET_IP_); ASSERT(lip->li_buf || xfs_iflags_test(ip, XFS_ISTALE)); ASSERT(atomic_read(&ip->i_pincount) > 0); - if (atomic_dec_and_test(&ip->i_pincount)) + + /* + * If this is the last unpin, then the inode no longer needs a journal + * flush to persist it. Hence we can clear the commit sequence numbers + * as a fsync/fdatasync operation on the inode at this point is a no-op. + */ + if (atomic_dec_and_lock(&ip->i_pincount, &iip->ili_lock)) { + iip->ili_commit_seq = 0; + iip->ili_datasync_seq = 0; + spin_unlock(&iip->ili_lock); wake_up_bit(&ip->i_flags, __XFS_IPINNED_BIT); + } } STATIC uint @@ -851,12 +859,45 @@ xfs_inode_item_committed( return lsn; } +/* + * The modification is now complete, so before we unlock the inode we need to + * update the commit sequence numbers for data integrity journal flushes. We + * always record the commit sequence number (ili_commit_seq) so that anything + * that needs a full journal sync will capture all of this modification. + * + * We then + * check if the changes will impact a datasync (O_DSYNC) journal flush. If the + * changes will require a datasync flush, then we also record the sequence in + * ili_datasync_seq. + * + * These commit sequence numbers will get cleared atomically with the inode being + * unpinned (i.e. pin count goes to zero), and so it will only be set when the + * inode is dirty in the journal. This removes the need for checking if the + * inode is pinned to determine if a journal flush is necessary, and hence + * removes the need for holding the ILOCK_SHARED in xfs_file_fsync() to + * serialise pin counts against commit sequence number updates. + * + */ STATIC void xfs_inode_item_committing( struct xfs_log_item *lip, xfs_csn_t seq) { - INODE_ITEM(lip)->ili_commit_seq = seq; + struct xfs_inode_log_item *iip = INODE_ITEM(lip); + + spin_lock(&iip->ili_lock); + iip->ili_commit_seq = seq; + if (iip->ili_dirty_flags & ~(XFS_ILOG_IVERSION | XFS_ILOG_TIMESTAMP)) + iip->ili_datasync_seq = seq; + spin_unlock(&iip->ili_lock); + + /* + * Clear the per-transaction dirty flags now that we have finished + * recording the transaction's inode modifications in the CIL and are + * about to release and (maybe) unlock the inode. + */ + iip->ili_dirty_flags = 0; + return xfs_inode_item_release(lip); } @@ -1048,7 +1089,6 @@ xfs_iflush_abort_clean( { iip->ili_last_fields = 0; iip->ili_fields = 0; - iip->ili_fsync_fields = 0; iip->ili_flush_lsn = 0; iip->ili_item.li_buf = NULL; list_del_init(&iip->ili_item.li_bio_list); diff --git a/fs/xfs/xfs_inode_item.h b/fs/xfs/xfs_inode_item.h index ba92ce11a011..2ddcca41714f 100644 --- a/fs/xfs/xfs_inode_item.h +++ b/fs/xfs/xfs_inode_item.h @@ -32,9 +32,17 @@ struct xfs_inode_log_item { spinlock_t ili_lock; /* flush state lock */ unsigned int ili_last_fields; /* fields when flushed */ unsigned int ili_fields; /* fields to be logged */ - unsigned int ili_fsync_fields; /* logged since last fsync */ xfs_lsn_t ili_flush_lsn; /* lsn at last flush */ + + /* + * We record the sequence number for every inode modification, as + * well as those that only require fdatasync operations for data + * integrity. This allows optimisation of the O_DSYNC/fdatasync path + * without needing to track what modifications the journal is currently + * carrying for the inode. These are protected by the above ili_lock. + */ xfs_csn_t ili_commit_seq; /* last transaction commit */ + xfs_csn_t ili_datasync_seq; /* for datasync optimisation */ }; static inline int xfs_inode_clean(struct xfs_inode *ip) diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 2570d0a66047..d3f6e3e42a11 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -149,9 +149,18 @@ xfs_bmbt_to_iomap( iomap->bdev = target->bt_bdev; iomap->flags = iomap_flags; - if (xfs_ipincount(ip) && - (ip->i_itemp->ili_fsync_fields & ~XFS_ILOG_TIMESTAMP)) - iomap->flags |= IOMAP_F_DIRTY; + /* + * If the inode is dirty for datasync purposes, let iomap know so it + * doesn't elide the IO completion journal flushes on O_DSYNC IO. + */ + if (ip->i_itemp) { + struct xfs_inode_log_item *iip = ip->i_itemp; + + spin_lock(&iip->ili_lock); + if (iip->ili_datasync_seq) + iomap->flags |= IOMAP_F_DIRTY; + spin_unlock(&iip->ili_lock); + } iomap->validity_cookie = sequence_cookie; return 0; |