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>
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index ed70645..e6f8675 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -57,6 +57,17 @@ struct xfs_error_cfg {
};
/*
+ * Per-cpu deferred inode inactivation GC lists.
+ */
+struct xfs_inodegc {
+ struct llist_head list;
+ struct work_struct work;
+
+ /* approximate count of inodes in the list */
+ unsigned int items;
+};
+
+/*
* The struct xfsmount layout is optimised to separate read-mostly variables
* from variables that are frequently modified. We put the read-mostly variables
* first, then place all the other variables at the end.
@@ -83,6 +94,8 @@ typedef struct xfs_mount {
xfs_buftarg_t *m_logdev_targp;/* ptr to log device */
xfs_buftarg_t *m_rtdev_targp; /* ptr to rt device */
struct list_head m_mount_list; /* global mount list */
+ void __percpu *m_inodegc; /* percpu inodegc structures */
+
/*
* Optional cache of rt summary level per bitmap block with the
* invariant that m_rsum_cache[bbno] <= the minimum i for which
@@ -95,8 +108,9 @@ typedef struct xfs_mount {
struct workqueue_struct *m_unwritten_workqueue;
struct workqueue_struct *m_cil_workqueue;
struct workqueue_struct *m_reclaim_workqueue;
- struct workqueue_struct *m_gc_workqueue;
struct workqueue_struct *m_sync_workqueue;
+ struct workqueue_struct *m_blockgc_wq;
+ struct workqueue_struct *m_inodegc_wq;
int m_bsize; /* fs logical block size */
uint8_t m_blkbit_log; /* blocklog + NBBY */
@@ -137,6 +151,7 @@ typedef struct xfs_mount {
struct xfs_ino_geometry m_ino_geo; /* inode geometry */
struct xfs_trans_resv m_resv; /* precomputed res values */
/* low free space thresholds */
+ unsigned long m_opstate; /* dynamic state flags */
bool m_always_cow;
bool m_fail_unmount;
bool m_finobt_nores; /* no per-AG finobt resv. */
@@ -260,6 +275,32 @@ typedef struct xfs_mount {
#define XFS_MOUNT_DAX_NEVER (1ULL << 27)
/*
+ * If set, inactivation worker threads will be scheduled to process queued
+ * inodegc work. If not, queued inodes remain in memory waiting to be
+ * processed.
+ */
+#define XFS_OPSTATE_INODEGC_ENABLED 0
+
+#define __XFS_IS_OPSTATE(name, NAME) \
+static inline bool xfs_is_ ## name (struct xfs_mount *mp) \
+{ \
+ return test_bit(XFS_OPSTATE_ ## NAME, &mp->m_opstate); \
+} \
+static inline bool xfs_clear_ ## name (struct xfs_mount *mp) \
+{ \
+ return test_and_clear_bit(XFS_OPSTATE_ ## NAME, &mp->m_opstate); \
+} \
+static inline bool xfs_set_ ## name (struct xfs_mount *mp) \
+{ \
+ return test_and_set_bit(XFS_OPSTATE_ ## NAME, &mp->m_opstate); \
+}
+
+__XFS_IS_OPSTATE(inodegc_enabled, INODEGC_ENABLED)
+
+#define XFS_OPSTATE_STRINGS \
+ { (1UL << XFS_OPSTATE_INODEGC_ENABLED), "inodegc" }
+
+/*
* Max and min values for mount-option defined I/O
* preallocation sizes.
*/