This patch generally looks good to me, but with so much RCU magic I'd prefer
if Paul & Eric could look over it.
On Mon, Nov 08, 2010 at 07:55:10PM +1100, Dave Chinner wrote:
> From: Dave Chinner <dchinner@xxxxxxxxxx>
>
> With delayed logging greatly increasing the sustained parallelism of inode
> operations, the inode cache locking is showing significant read vs write
> contention when inode reclaim runs at the same time as lookups. There is
> also a lot more write lock acquistions than there are read locks (4:1 ratio)
> so the read locking is not really buying us much in the way of parallelism.
>
> To avoid the read vs write contention, change the cache to use RCU locking on
> the read side. To avoid needing to RCU free every single inode, use the built
> in slab RCU freeing mechanism. This requires us to be able to detect lookups
> of
> freed inodes, so en??ure that ever freed inode has an inode number of zero and
> the XFS_IRECLAIM flag set. We already check the XFS_IRECLAIM flag in cache hit
> lookup path, but also add a check for a zero inode number as well.
>
> We canthen convert all the read locking lockups to use RCU read side locking
> and hence remove all read side locking.
>
> Signed-off-by: Dave Chinner <dchinner@xxxxxxxxxx>
> Reviewed-by: Alex Elder <aelder@xxxxxxx>
> ---
> fs/xfs/linux-2.6/xfs_iops.c | 7 +++++-
> fs/xfs/linux-2.6/xfs_sync.c | 13 +++++++++--
> fs/xfs/quota/xfs_qm_syscalls.c | 3 ++
> fs/xfs/xfs_iget.c | 44 ++++++++++++++++++++++++++++++---------
> fs/xfs/xfs_inode.c | 22 ++++++++++++-------
> 5 files changed, 67 insertions(+), 22 deletions(-)
>
> diff --git a/fs/xfs/linux-2.6/xfs_iops.c b/fs/xfs/linux-2.6/xfs_iops.c
> index 8b46867..909bd9c 100644
> --- a/fs/xfs/linux-2.6/xfs_iops.c
> +++ b/fs/xfs/linux-2.6/xfs_iops.c
> @@ -757,6 +757,8 @@ xfs_diflags_to_iflags(
> * We don't use the VFS inode hash for lookups anymore, so make the inode
> look
> * hashed to the VFS by faking it. This avoids needing to touch inode hash
> * locks in this path, but makes the VFS believe the inode is validly hashed.
> + * We initialise i_state and i_hash under the i_lock so that we follow the
> same
> + * setup rules that the rest of the VFS follows.
> */
> void
> xfs_setup_inode(
> @@ -765,10 +767,13 @@ xfs_setup_inode(
> struct inode *inode = &ip->i_vnode;
>
> inode->i_ino = ip->i_ino;
> +
> + spin_lock(&inode->i_lock);
> inode->i_state = I_NEW;
> + hlist_nulls_add_fake(&inode->i_hash);
> + spin_unlock(&inode->i_lock);
This screams for another VFS helper, even if it's XFS-specific for now.
Having to duplicate inode.c-private locking rules in XFS seems a bit
nasty to me.
>
> inode_sb_list_add(inode);
> - hlist_nulls_add_fake(&inode->i_hash);
>
> inode->i_mode = ip->i_d.di_mode;
> inode->i_nlink = ip->i_d.di_nlink;
> diff --git a/fs/xfs/linux-2.6/xfs_sync.c b/fs/xfs/linux-2.6/xfs_sync.c
> index afb0d7c..9a53cc9 100644
> --- a/fs/xfs/linux-2.6/xfs_sync.c
> +++ b/fs/xfs/linux-2.6/xfs_sync.c
> @@ -53,6 +53,10 @@ xfs_inode_ag_walk_grab(
> {
> struct inode *inode = VFS_I(ip);
>
> + /* check for stale RCU freed inode */
> + if (!ip->i_ino)
> + return ENOENT;
Assuming i_ino is never 0 is fine for XFS, unlike for the generic VFS
code, so ACK.
> /* nothing to sync during shutdown */
> if (XFS_FORCED_SHUTDOWN(ip->i_mount))
> return EFSCORRUPTED;
> @@ -98,12 +102,12 @@ restart:
> int error = 0;
> int i;
>
> - read_lock(&pag->pag_ici_lock);
> + rcu_read_lock();
> nr_found = radix_tree_gang_lookup(&pag->pag_ici_root,
> (void **)batch, first_index,
> XFS_LOOKUP_BATCH);
> if (!nr_found) {
> - read_unlock(&pag->pag_ici_lock);
> + rcu_read_unlock();
> break;
> }
>
> @@ -129,7 +133,7 @@ restart:
> }
>
> /* unlock now we've grabbed the inodes. */
> - read_unlock(&pag->pag_ici_lock);
> + rcu_read_unlock();
>
> for (i = 0; i < nr_found; i++) {
> if (!batch[i])
> @@ -639,6 +643,9 @@ xfs_reclaim_inode_grab(
> struct xfs_inode *ip,
> int flags)
> {
> + /* check for stale RCU freed inode */
> + if (!ip->i_ino)
> + return 1;
>
> /*
> * do some unlocked checks first to avoid unnecceary lock traffic.
> diff --git a/fs/xfs/quota/xfs_qm_syscalls.c b/fs/xfs/quota/xfs_qm_syscalls.c
> index bdebc18..8b207fc 100644
> --- a/fs/xfs/quota/xfs_qm_syscalls.c
> +++ b/fs/xfs/quota/xfs_qm_syscalls.c
> @@ -875,6 +875,9 @@ xfs_dqrele_inode(
> struct xfs_perag *pag,
> int flags)
> {
> + if (!ip->i_ino)
> + return ENOENT;
> +
Why do we need the check here again? Having it in
xfs_inode_ag_walk_grab should be enough.
> /* skip quota inodes */
> if (ip == ip->i_mount->m_quotainfo->qi_uquotaip ||
> ip == ip->i_mount->m_quotainfo->qi_gquotaip) {
> diff --git a/fs/xfs/xfs_iget.c b/fs/xfs/xfs_iget.c
> index 18991a9..edeb918 100644
> --- a/fs/xfs/xfs_iget.c
> +++ b/fs/xfs/xfs_iget.c
> @@ -69,6 +69,7 @@ xfs_inode_alloc(
> ASSERT(atomic_read(&ip->i_pincount) == 0);
> ASSERT(!spin_is_locked(&ip->i_flags_lock));
> ASSERT(completion_done(&ip->i_flush));
> + ASSERT(ip->i_ino == 0);
>
> mrlock_init(&ip->i_iolock, MRLOCK_BARRIER, "xfsio", ip->i_ino);
>
> @@ -86,9 +87,6 @@ xfs_inode_alloc(
> ip->i_new_size = 0;
> ip->i_dirty_releases = 0;
>
> - /* prevent anyone from using this yet */
> - VFS_I(ip)->i_state = I_NEW;
> -
> return ip;
> }
>
> @@ -135,6 +133,16 @@ xfs_inode_free(
> ASSERT(!spin_is_locked(&ip->i_flags_lock));
> ASSERT(completion_done(&ip->i_flush));
>
> + /*
> + * because we use SLAB_DESTROY_BY_RCU freeing, ensure the inode
> + * always appears to be reclaimed with an invalid inode number
> + * when in the free state. The ip->i_flags_lock provides the barrier
> + * against lookup races.
> + */
> + spin_lock(&ip->i_flags_lock);
> + ip->i_flags = XFS_IRECLAIM;
> + ip->i_ino = 0;
> + spin_unlock(&ip->i_flags_lock);
> kmem_zone_free(xfs_inode_zone, ip);
> }
>
> @@ -146,12 +154,28 @@ xfs_iget_cache_hit(
> struct xfs_perag *pag,
> struct xfs_inode *ip,
> int flags,
> - int lock_flags) __releases(pag->pag_ici_lock)
> + int lock_flags) __releases(RCU)
> {
> struct inode *inode = VFS_I(ip);
> struct xfs_mount *mp = ip->i_mount;
> int error;
>
> + /*
> + * check for re-use of an inode within an RCU grace period due to the
> + * radix tree nodes not being updated yet. We monitor for this by
> + * setting the inode number to zero before freeing the inode structure.
> + * We don't need to recheck this after taking the i_flags_lock because
> + * the check against XFS_IRECLAIM will catch a freed inode.
> + */
> + if (ip->i_ino == 0) {
> + trace_xfs_iget_skip(ip);
> + XFS_STATS_INC(xs_ig_frecycle);
> + rcu_read_unlock();
> + /* Expire the grace period so we don't trip over it again. */
> + synchronize_rcu();
> + return EAGAIN;
> + }
> +
> spin_lock(&ip->i_flags_lock);
>
> /*
> @@ -195,7 +219,7 @@ xfs_iget_cache_hit(
> ip->i_flags |= XFS_IRECLAIM;
>
> spin_unlock(&ip->i_flags_lock);
> - read_unlock(&pag->pag_ici_lock);
> + rcu_read_unlock();
>
> error = -inode_init_always(mp->m_super, inode);
> if (error) {
> @@ -203,7 +227,7 @@ xfs_iget_cache_hit(
> * Re-initializing the inode failed, and we are in deep
> * trouble. Try to re-add it to the reclaim list.
> */
> - read_lock(&pag->pag_ici_lock);
> + rcu_read_lock();
> spin_lock(&ip->i_flags_lock);
>
> ip->i_flags &= ~XFS_INEW;
> @@ -231,7 +255,7 @@ xfs_iget_cache_hit(
>
> /* We've got a live one. */
> spin_unlock(&ip->i_flags_lock);
> - read_unlock(&pag->pag_ici_lock);
> + rcu_read_unlock();
> trace_xfs_iget_hit(ip);
> }
>
> @@ -245,7 +269,7 @@ xfs_iget_cache_hit(
>
> out_error:
> spin_unlock(&ip->i_flags_lock);
> - read_unlock(&pag->pag_ici_lock);
> + rcu_read_unlock();
> return error;
> }
>
> @@ -376,7 +400,7 @@ xfs_iget(
>
> again:
> error = 0;
> - read_lock(&pag->pag_ici_lock);
> + rcu_read_lock();
> ip = radix_tree_lookup(&pag->pag_ici_root, agino);
>
> if (ip) {
> @@ -384,7 +408,7 @@ again:
> if (error)
> goto out_error_or_again;
> } else {
> - read_unlock(&pag->pag_ici_lock);
> + rcu_read_unlock();
> XFS_STATS_INC(xs_ig_missed);
>
> error = xfs_iget_cache_miss(mp, pag, tp, ino, &ip,
> diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
> index 108c7a0..25becb1 100644
> --- a/fs/xfs/xfs_inode.c
> +++ b/fs/xfs/xfs_inode.c
> @@ -2000,13 +2000,14 @@ xfs_ifree_cluster(
> */
> for (i = 0; i < ninodes; i++) {
> retry:
> - read_lock(&pag->pag_ici_lock);
> + rcu_read_lock();
> ip = radix_tree_lookup(&pag->pag_ici_root,
> XFS_INO_TO_AGINO(mp, (inum + i)));
>
> /* Inode not in memory or stale, nothing to do */
> - if (!ip || xfs_iflags_test(ip, XFS_ISTALE)) {
> - read_unlock(&pag->pag_ici_lock);
> + if (!ip || !ip->i_ino ||
> + xfs_iflags_test(ip, XFS_ISTALE)) {
> + rcu_read_unlock();
> continue;
> }
>
> @@ -2019,11 +2020,11 @@ retry:
> */
> if (ip != free_ip &&
> !xfs_ilock_nowait(ip, XFS_ILOCK_EXCL)) {
> - read_unlock(&pag->pag_ici_lock);
> + rcu_read_unlock();
> delay(1);
> goto retry;
> }
> - read_unlock(&pag->pag_ici_lock);
> + rcu_read_unlock();
>
> xfs_iflock(ip);
> xfs_iflags_set(ip, XFS_ISTALE);
> @@ -2629,7 +2630,7 @@ xfs_iflush_cluster(
>
> mask = ~(((XFS_INODE_CLUSTER_SIZE(mp) >> mp->m_sb.sb_inodelog)) - 1);
> first_index = XFS_INO_TO_AGINO(mp, ip->i_ino) & mask;
> - read_lock(&pag->pag_ici_lock);
> + rcu_read_lock();
> /* really need a gang lookup range call here */
> nr_found = radix_tree_gang_lookup(&pag->pag_ici_root, (void**)ilist,
> first_index, inodes_per_cluster);
> @@ -2640,6 +2641,11 @@ xfs_iflush_cluster(
> iq = ilist[i];
> if (iq == ip)
> continue;
> +
> + /* check we've got a valid inode */
> + if (!iq->i_ino)
> + continue;
> +
> /* if the inode lies outside this cluster, we're done. */
> if ((XFS_INO_TO_AGINO(mp, iq->i_ino) & mask) != first_index)
> break;
> @@ -2692,7 +2698,7 @@ xfs_iflush_cluster(
> }
>
> out_free:
> - read_unlock(&pag->pag_ici_lock);
> + rcu_read_unlock();
> kmem_free(ilist);
> out_put:
> xfs_perag_put(pag);
> @@ -2704,7 +2710,7 @@ cluster_corrupt_out:
> * Corruption detected in the clustering loop. Invalidate the
> * inode buffer and shut down the filesystem.
> */
> - read_unlock(&pag->pag_ici_lock);
> + rcu_read_unlock();
> /*
> * Clean up the buffer. If it was B_DELWRI, just release it --
> * brelse can handle it with no problems. If not, shut down the
> --
> 1.7.2.3
>
> _______________________________________________
> xfs mailing list
> xfs@xxxxxxxxxxx
> http://oss.sgi.com/mailman/listinfo/xfs
---end quoted text---
|