Message ID | 20200601214251.4167140-26-david@fromorbit.com (mailing list archive) |
---|---|
State | Superseded |
Headers | show |
Series | xfs: rework inode flushing to make inode reclaim fully asynchronous | expand |
On Tue, Jun 02, 2020 at 07:42:46AM +1000, Dave Chinner wrote: > From: Dave Chinner <dchinner@redhat.com> > > Rather than attach inodes to the cluster buffer just when we are > doing IO, attach the inodes to the cluster buffer when they are > dirtied. The means the buffer always carries a list of dirty inodes > that reference it, and we can use that list to make more fundamental > changes to inode writeback that aren't otherwise possible. > > Signed-off-by: Dave Chinner <dchinner@redhat.com> Looks straightforward. Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com> --D > --- > fs/xfs/libxfs/xfs_trans_inode.c | 9 ++++++--- > fs/xfs/xfs_buf_item.c | 1 + > fs/xfs/xfs_icache.c | 1 + > fs/xfs/xfs_inode.c | 24 +++++------------------- > fs/xfs/xfs_inode_item.c | 14 ++++++++------ > 5 files changed, 21 insertions(+), 28 deletions(-) > > diff --git a/fs/xfs/libxfs/xfs_trans_inode.c b/fs/xfs/libxfs/xfs_trans_inode.c > index 1e7147b90725e..5e7634c13ce78 100644 > --- a/fs/xfs/libxfs/xfs_trans_inode.c > +++ b/fs/xfs/libxfs/xfs_trans_inode.c > @@ -164,13 +164,16 @@ xfs_trans_log_inode( > /* > * We need an explicit buffer reference for the log item but > * don't want the buffer to remain attached to the transaction. > - * Hold the buffer but release the transaction reference. > + * Hold the buffer but release the transaction reference once > + * we've attached the inode log item to the buffer log item > + * list. > */ > xfs_buf_hold(bp); > - xfs_trans_brelse(tp, bp); > - > spin_lock(&iip->ili_lock); > iip->ili_item.li_buf = bp; > + bp->b_flags |= _XBF_INODES; > + list_add_tail(&iip->ili_item.li_bio_list, &bp->b_li_list); > + xfs_trans_brelse(tp, bp); > } > > /* > diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c > index 9739d64a46443..6e7a2d460a675 100644 > --- a/fs/xfs/xfs_buf_item.c > +++ b/fs/xfs/xfs_buf_item.c > @@ -465,6 +465,7 @@ xfs_buf_item_unpin( > if (bip->bli_flags & XFS_BLI_STALE_INODE) { > xfs_buf_item_done(bp); > xfs_iflush_done(bp); > + ASSERT(list_empty(&bp->b_li_list)); > } else { > xfs_trans_ail_delete(lip, SHUTDOWN_LOG_IO_ERROR); > xfs_buf_item_relse(bp); > diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c > index 4fe6f250e8448..ed386bc930977 100644 > --- a/fs/xfs/xfs_icache.c > +++ b/fs/xfs/xfs_icache.c > @@ -115,6 +115,7 @@ __xfs_inode_free( > { > /* asserts to verify all state is correct here */ > ASSERT(atomic_read(&ip->i_pincount) == 0); > + ASSERT(!ip->i_itemp || list_empty(&ip->i_itemp->ili_item.li_bio_list)); > XFS_STATS_DEC(ip->i_mount, vn_active); > > call_rcu(&VFS_I(ip)->i_rcu, xfs_inode_free_callback); > diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c > index fb4c614c64fda..af65acd24ec4e 100644 > --- a/fs/xfs/xfs_inode.c > +++ b/fs/xfs/xfs_inode.c > @@ -2584,27 +2584,24 @@ xfs_ifree_mark_inode_stale( > ASSERT(iip->ili_last_fields); > goto out_iunlock; > } > - ASSERT(!iip || list_empty(&iip->ili_item.li_bio_list)); > > /* > - * Clean inodes can be released immediately. Everything else has to go > - * through xfs_iflush_abort() on journal commit as the flock > - * synchronises removal of the inode from the cluster buffer against > - * inode reclaim. > + * Inodes not attached to the buffer can be released immediately. > + * Everything else has to go through xfs_iflush_abort() on journal > + * commit as the flock synchronises removal of the inode from the > + * cluster buffer against inode reclaim. > */ > - if (xfs_inode_clean(ip)) { > + if (!iip || list_empty(&iip->ili_item.li_bio_list)) { > xfs_ifunlock(ip); > goto out_iunlock; > } > > /* we have a dirty inode in memory that has not yet been flushed. */ > - ASSERT(iip->ili_fields); > 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); > - list_add_tail(&iip->ili_item.li_bio_list, &bp->b_li_list); > ASSERT(iip->ili_last_fields); > > out_iunlock: > @@ -3819,19 +3816,8 @@ xfs_iflush_int( > xfs_trans_ail_copy_lsn(mp->m_ail, &iip->ili_flush_lsn, > &iip->ili_item.li_lsn); > > - /* > - * Attach the inode item callback to the buffer whether the flush > - * succeeded or not. If not, the caller will shut down and fail I/O > - * completion on the buffer to remove the inode from the AIL and release > - * the flush lock. > - */ > - bp->b_flags |= _XBF_INODES; > - list_add_tail(&iip->ili_item.li_bio_list, &bp->b_li_list); > - > /* generate the checksum. */ > xfs_dinode_calc_crc(mp, dip); > - > - ASSERT(!list_empty(&bp->b_li_list)); > return error; > } > > diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c > index 0a7720b7a821a..66675b75de3ec 100644 > --- a/fs/xfs/xfs_inode_item.c > +++ b/fs/xfs/xfs_inode_item.c > @@ -665,10 +665,7 @@ xfs_inode_item_destroy( > * > * Note: Now that we attach the log item to the buffer when we first log the > * inode in memory, we can have unflushed inodes on the buffer list here. These > - * inodes will have a zero ili_last_fields, so skip over them here. We do > - * this check -after- we've checked for stale inodes, because we're guaranteed > - * to have XFS_ISTALE set in the case that dirty inodes are in the CIL and have > - * not yet had their dirtying transactions committed to disk. > + * inodes will have a zero ili_last_fields, so skip over them here. > */ > void > xfs_iflush_done( > @@ -686,8 +683,8 @@ xfs_iflush_done( > */ > list_for_each_entry_safe(lip, n, &bp->b_li_list, li_bio_list) { > iip = INODE_ITEM(lip); > + > if (xfs_iflags_test(iip->ili_inode, XFS_ISTALE)) { > - list_del_init(&lip->li_bio_list); > xfs_iflush_abort(iip->ili_inode); > continue; > } > @@ -740,12 +737,16 @@ xfs_iflush_done( > /* > * Remove the reference to the cluster buffer if the inode is > * clean in memory. Drop the buffer reference once we've dropped > - * the locks we hold. > + * the locks we hold. If the inode is dirty in memory, we need > + * to put the inode item back on the buffer list for another > + * pass through the flush machinery. > */ > ASSERT(iip->ili_item.li_buf == bp); > if (!iip->ili_fields) { > iip->ili_item.li_buf = NULL; > drop_buffer = true; > + } else { > + list_add(&lip->li_bio_list, &bp->b_li_list); > } > iip->ili_last_fields = 0; > iip->ili_flush_lsn = 0; > @@ -789,6 +790,7 @@ xfs_iflush_abort( > iip->ili_flush_lsn = 0; > bp = iip->ili_item.li_buf; > iip->ili_item.li_buf = NULL; > + list_del_init(&iip->ili_item.li_bio_list); > spin_unlock(&iip->ili_lock); > } > xfs_ifunlock(ip); > -- > 2.26.2.761.g0e0b3e54be >
diff --git a/fs/xfs/libxfs/xfs_trans_inode.c b/fs/xfs/libxfs/xfs_trans_inode.c index 1e7147b90725e..5e7634c13ce78 100644 --- a/fs/xfs/libxfs/xfs_trans_inode.c +++ b/fs/xfs/libxfs/xfs_trans_inode.c @@ -164,13 +164,16 @@ xfs_trans_log_inode( /* * We need an explicit buffer reference for the log item but * don't want the buffer to remain attached to the transaction. - * Hold the buffer but release the transaction reference. + * Hold the buffer but release the transaction reference once + * we've attached the inode log item to the buffer log item + * list. */ xfs_buf_hold(bp); - xfs_trans_brelse(tp, bp); - spin_lock(&iip->ili_lock); iip->ili_item.li_buf = bp; + bp->b_flags |= _XBF_INODES; + list_add_tail(&iip->ili_item.li_bio_list, &bp->b_li_list); + xfs_trans_brelse(tp, bp); } /* diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c index 9739d64a46443..6e7a2d460a675 100644 --- a/fs/xfs/xfs_buf_item.c +++ b/fs/xfs/xfs_buf_item.c @@ -465,6 +465,7 @@ xfs_buf_item_unpin( if (bip->bli_flags & XFS_BLI_STALE_INODE) { xfs_buf_item_done(bp); xfs_iflush_done(bp); + ASSERT(list_empty(&bp->b_li_list)); } else { xfs_trans_ail_delete(lip, SHUTDOWN_LOG_IO_ERROR); xfs_buf_item_relse(bp); diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index 4fe6f250e8448..ed386bc930977 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -115,6 +115,7 @@ __xfs_inode_free( { /* asserts to verify all state is correct here */ ASSERT(atomic_read(&ip->i_pincount) == 0); + ASSERT(!ip->i_itemp || list_empty(&ip->i_itemp->ili_item.li_bio_list)); XFS_STATS_DEC(ip->i_mount, vn_active); call_rcu(&VFS_I(ip)->i_rcu, xfs_inode_free_callback); diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index fb4c614c64fda..af65acd24ec4e 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -2584,27 +2584,24 @@ xfs_ifree_mark_inode_stale( ASSERT(iip->ili_last_fields); goto out_iunlock; } - ASSERT(!iip || list_empty(&iip->ili_item.li_bio_list)); /* - * Clean inodes can be released immediately. Everything else has to go - * through xfs_iflush_abort() on journal commit as the flock - * synchronises removal of the inode from the cluster buffer against - * inode reclaim. + * Inodes not attached to the buffer can be released immediately. + * Everything else has to go through xfs_iflush_abort() on journal + * commit as the flock synchronises removal of the inode from the + * cluster buffer against inode reclaim. */ - if (xfs_inode_clean(ip)) { + if (!iip || list_empty(&iip->ili_item.li_bio_list)) { xfs_ifunlock(ip); goto out_iunlock; } /* we have a dirty inode in memory that has not yet been flushed. */ - ASSERT(iip->ili_fields); 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); - list_add_tail(&iip->ili_item.li_bio_list, &bp->b_li_list); ASSERT(iip->ili_last_fields); out_iunlock: @@ -3819,19 +3816,8 @@ xfs_iflush_int( xfs_trans_ail_copy_lsn(mp->m_ail, &iip->ili_flush_lsn, &iip->ili_item.li_lsn); - /* - * Attach the inode item callback to the buffer whether the flush - * succeeded or not. If not, the caller will shut down and fail I/O - * completion on the buffer to remove the inode from the AIL and release - * the flush lock. - */ - bp->b_flags |= _XBF_INODES; - list_add_tail(&iip->ili_item.li_bio_list, &bp->b_li_list); - /* generate the checksum. */ xfs_dinode_calc_crc(mp, dip); - - ASSERT(!list_empty(&bp->b_li_list)); return error; } diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c index 0a7720b7a821a..66675b75de3ec 100644 --- a/fs/xfs/xfs_inode_item.c +++ b/fs/xfs/xfs_inode_item.c @@ -665,10 +665,7 @@ xfs_inode_item_destroy( * * Note: Now that we attach the log item to the buffer when we first log the * inode in memory, we can have unflushed inodes on the buffer list here. These - * inodes will have a zero ili_last_fields, so skip over them here. We do - * this check -after- we've checked for stale inodes, because we're guaranteed - * to have XFS_ISTALE set in the case that dirty inodes are in the CIL and have - * not yet had their dirtying transactions committed to disk. + * inodes will have a zero ili_last_fields, so skip over them here. */ void xfs_iflush_done( @@ -686,8 +683,8 @@ xfs_iflush_done( */ list_for_each_entry_safe(lip, n, &bp->b_li_list, li_bio_list) { iip = INODE_ITEM(lip); + if (xfs_iflags_test(iip->ili_inode, XFS_ISTALE)) { - list_del_init(&lip->li_bio_list); xfs_iflush_abort(iip->ili_inode); continue; } @@ -740,12 +737,16 @@ xfs_iflush_done( /* * Remove the reference to the cluster buffer if the inode is * clean in memory. Drop the buffer reference once we've dropped - * the locks we hold. + * the locks we hold. If the inode is dirty in memory, we need + * to put the inode item back on the buffer list for another + * pass through the flush machinery. */ ASSERT(iip->ili_item.li_buf == bp); if (!iip->ili_fields) { iip->ili_item.li_buf = NULL; drop_buffer = true; + } else { + list_add(&lip->li_bio_list, &bp->b_li_list); } iip->ili_last_fields = 0; iip->ili_flush_lsn = 0; @@ -789,6 +790,7 @@ xfs_iflush_abort( iip->ili_flush_lsn = 0; bp = iip->ili_item.li_buf; iip->ili_item.li_buf = NULL; + list_del_init(&iip->ili_item.li_bio_list); spin_unlock(&iip->ili_lock); } xfs_ifunlock(ip);