xfs: per-cpu deferred inode inactivation queues

Move inode inactivation to background work contexts so that it no
longer runs in the context that releases the final reference to an
inode. This will allow process work that ends up blocking on
inactivation to continue doing work while the filesytem processes
the inactivation in the background.

A typical demonstration of this is unlinking an inode with lots of
extents. The extents are removed during inactivation, so this blocks
the process that unlinked the inode from the directory structure. By
moving the inactivation to the background process, the userspace
applicaiton can keep working (e.g. unlinking the next inode in the
directory) while the inactivation work on the previous inode is
done by a different CPU.

The implementation of the queue is relatively simple. We use a
per-cpu lockless linked list (llist) to queue inodes for
inactivation without requiring serialisation mechanisms, and a work
item to allow the queue to be processed by a CPU bound worker
thread. We also keep a count of the queue depth so that we can
trigger work after a number of deferred inactivations have been
queued.

The use of a bound workqueue with a single work depth allows the
workqueue to run one work item per CPU. We queue the work item on
the CPU we are currently running on, and so this essentially gives
us affine per-cpu worker threads for the per-cpu queues. THis
maintains the effective CPU affinity that occurs within XFS at the
AG level due to all objects in a directory being local to an AG.
Hence inactivation work tends to run on the same CPU that last
accessed all the objects that inactivation accesses and this
maintains hot CPU caches for unlink workloads.

A depth of 32 inodes was chosen to match the number of inodes in an
inode cluster buffer. This hopefully allows sequential
allocation/unlink behaviours to defering inactivation of all the
inodes in a single cluster buffer at a time, further helping
maintain hot CPU and buffer cache accesses while running
inactivations.

A hard per-cpu queue throttle of 256 inode has been set to avoid
runaway queuing when inodes that take a long to time inactivate are
being processed. For example, when unlinking inodes with large
numbers of extents that can take a lot of processing to free.

Signed-off-by: Dave Chinner <dchinner@redhat.com>
[djwong: tweak comments and tracepoints, convert opflags to state bits]
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Darrick J. Wong <djwong@kernel.org>

1 files changed, 48 insertions, 2 deletions

diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 19260291ff8b..cd56ac7c39a6 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -157,6 +157,45 @@ DEFINE_PERAG_REF_EVENT(xfs_perag_put);
 DEFINE_PERAG_REF_EVENT(xfs_perag_set_inode_tag);
 DEFINE_PERAG_REF_EVENT(xfs_perag_clear_inode_tag);
 
+DECLARE_EVENT_CLASS(xfs_fs_class,
+	TP_PROTO(struct xfs_mount *mp, void *caller_ip),
+	TP_ARGS(mp, caller_ip),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(unsigned long long, mflags)
+		__field(unsigned long, opstate)
+		__field(unsigned long, sbflags)
+		__field(void *, caller_ip)
+	),
+	TP_fast_assign(
+		if (mp) {
+			__entry->dev = mp->m_super->s_dev;
+			__entry->mflags = mp->m_flags;
+			__entry->opstate = mp->m_opstate;
+			__entry->sbflags = mp->m_super->s_flags;
+		}
+		__entry->caller_ip = caller_ip;
+	),
+	TP_printk("dev %d:%d m_flags 0x%llx opstate (%s) s_flags 0x%lx caller %pS",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->mflags,
+		  __print_flags(__entry->opstate, "|", XFS_OPSTATE_STRINGS),
+		  __entry->sbflags,
+		  __entry->caller_ip)
+);
+
+#define DEFINE_FS_EVENT(name)	\
+DEFINE_EVENT(xfs_fs_class, name,					\
+	TP_PROTO(struct xfs_mount *mp, void *caller_ip), \
+	TP_ARGS(mp, caller_ip))
+DEFINE_FS_EVENT(xfs_inodegc_flush);
+DEFINE_FS_EVENT(xfs_inodegc_start);
+DEFINE_FS_EVENT(xfs_inodegc_stop);
+DEFINE_FS_EVENT(xfs_inodegc_worker);
+DEFINE_FS_EVENT(xfs_inodegc_queue);
+DEFINE_FS_EVENT(xfs_inodegc_throttle);
+DEFINE_FS_EVENT(xfs_fs_sync_fs);
+
 DECLARE_EVENT_CLASS(xfs_ag_class,
 	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno),
 	TP_ARGS(mp, agno),
@@ -616,14 +655,17 @@ DECLARE_EVENT_CLASS(xfs_inode_class,
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
 		__field(xfs_ino_t, ino)
+		__field(unsigned long, iflags)
 	),
 	TP_fast_assign(
 		__entry->dev = VFS_I(ip)->i_sb->s_dev;
 		__entry->ino = ip->i_ino;
+		__entry->iflags = ip->i_flags;
 	),
-	TP_printk("dev %d:%d ino 0x%llx",
+	TP_printk("dev %d:%d ino 0x%llx iflags 0x%lx",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
-		  __entry->ino)
+		  __entry->ino,
+		  __entry->iflags)
 )
 
 #define DEFINE_INODE_EVENT(name) \
@@ -667,6 +709,10 @@ DEFINE_INODE_EVENT(xfs_inode_free_eofblocks_invalid);
 DEFINE_INODE_EVENT(xfs_inode_set_cowblocks_tag);
 DEFINE_INODE_EVENT(xfs_inode_clear_cowblocks_tag);
 DEFINE_INODE_EVENT(xfs_inode_free_cowblocks_invalid);
+DEFINE_INODE_EVENT(xfs_inode_set_reclaimable);
+DEFINE_INODE_EVENT(xfs_inode_reclaiming);
+DEFINE_INODE_EVENT(xfs_inode_set_need_inactive);
+DEFINE_INODE_EVENT(xfs_inode_inactivating);
 
 /*
  * ftrace's __print_symbolic requires that all enum values be wrapped in the