From da353b0d64e070ae7c5342a0d56ec20ae9ef5cfb Mon Sep 17 00:00:00 2001 From: David Chinner Date: Tue, 28 Aug 2007 14:00:13 +1000 Subject: [XFS] Radix tree based inode caching One of the perpetual scaling problems XFS has is indexing it's incore inodes. We currently uses hashes and the default hash sizes chosen can only ever be a tradeoff between memory consumption and the maximum realistic size of the cache. As a result, anyone who has millions of inodes cached on a filesystem needs to tunes the size of the cache via the ihashsize mount option to allow decent scalability with inode cache operations. A further problem is the separate inode cluster hash, whose size is based on the ihashsize but is smaller, and so under certain conditions (sparse cluster cache population) this can become a limitation long before the inode hash is causing issues. The following patchset removes the inode hash and cluster hash and replaces them with radix trees to avoid the scalability limitations of the hashes. It also reduces the size of the inodes by 3 pointers.... SGI-PV: 969561 SGI-Modid: xfs-linux-melb:xfs-kern:29481a Signed-off-by: David Chinner Signed-off-by: Christoph Hellwig Signed-off-by: Tim Shimmin --- fs/xfs/xfs_vnodeops.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'fs/xfs/xfs_vnodeops.c') diff --git a/fs/xfs/xfs_vnodeops.c b/fs/xfs/xfs_vnodeops.c index bde4a1ad90f2..15bc01b2d6a0 100644 --- a/fs/xfs/xfs_vnodeops.c +++ b/fs/xfs/xfs_vnodeops.c @@ -3876,7 +3876,7 @@ xfs_finish_reclaim( int locked, int sync_mode) { - xfs_ihash_t *ih = ip->i_hash; + xfs_perag_t *pag = xfs_get_perag(ip->i_mount, ip->i_ino); bhv_vnode_t *vp = XFS_ITOV_NULL(ip); int error; @@ -3888,12 +3888,12 @@ xfs_finish_reclaim( * Once we have the XFS_IRECLAIM flag set it will not touch * us. */ - write_lock(&ih->ih_lock); + write_lock(&pag->pag_ici_lock); spin_lock(&ip->i_flags_lock); if (__xfs_iflags_test(ip, XFS_IRECLAIM) || (!__xfs_iflags_test(ip, XFS_IRECLAIMABLE) && vp == NULL)) { spin_unlock(&ip->i_flags_lock); - write_unlock(&ih->ih_lock); + write_unlock(&pag->pag_ici_lock); if (locked) { xfs_ifunlock(ip); xfs_iunlock(ip, XFS_ILOCK_EXCL); @@ -3902,7 +3902,8 @@ xfs_finish_reclaim( } __xfs_iflags_set(ip, XFS_IRECLAIM); spin_unlock(&ip->i_flags_lock); - write_unlock(&ih->ih_lock); + write_unlock(&pag->pag_ici_lock); + xfs_put_perag(ip->i_mount, pag); /* * If the inode is still dirty, then flush it out. If the inode -- cgit v1.2.1