mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-09-13 14:14:37 +00:00
ab23a77687
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> |
||
|---|---|---|
| .. | ||
| libxfs | ||
| scrub | ||
| Kconfig | ||
| kmem.c | ||
| kmem.h | ||
| Makefile | ||
| mrlock.h | ||
| xfs.h | ||
| xfs_acl.c | ||
| xfs_acl.h | ||
| xfs_aops.c | ||
| xfs_aops.h | ||
| xfs_attr_inactive.c | ||
| xfs_attr_list.c | ||
| xfs_bio_io.c | ||
| xfs_bmap_item.c | ||
| xfs_bmap_item.h | ||
| xfs_bmap_util.c | ||
| xfs_bmap_util.h | ||
| xfs_buf.c | ||
| xfs_buf.h | ||
| xfs_buf_item.c | ||
| xfs_buf_item.h | ||
| xfs_buf_item_recover.c | ||
| xfs_dir2_readdir.c | ||
| xfs_discard.c | ||
| xfs_discard.h | ||
| xfs_dquot.c | ||
| xfs_dquot.h | ||
| xfs_dquot_item.c | ||
| xfs_dquot_item.h | ||
| xfs_dquot_item_recover.c | ||
| xfs_error.c | ||
| xfs_error.h | ||
| xfs_export.c | ||
| xfs_export.h | ||
| xfs_extent_busy.c | ||
| xfs_extent_busy.h | ||
| xfs_extfree_item.c | ||
| xfs_extfree_item.h | ||
| xfs_file.c | ||
| xfs_filestream.c | ||
| xfs_filestream.h | ||
| xfs_fsmap.c | ||
| xfs_fsmap.h | ||
| xfs_fsops.c | ||
| xfs_fsops.h | ||
| xfs_globals.c | ||
| xfs_health.c | ||
| xfs_icache.c | ||
| xfs_icache.h | ||
| xfs_icreate_item.c | ||
| xfs_icreate_item.h | ||
| xfs_inode.c | ||
| xfs_inode.h | ||
| xfs_inode_item.c | ||
| xfs_inode_item.h | ||
| xfs_inode_item_recover.c | ||
| xfs_ioctl.c | ||
| xfs_ioctl.h | ||
| xfs_ioctl32.c | ||
| xfs_ioctl32.h | ||
| xfs_iomap.c | ||
| xfs_iomap.h | ||
| xfs_iops.c | ||
| xfs_iops.h | ||
| xfs_itable.c | ||
| xfs_itable.h | ||
| xfs_iwalk.c | ||
| xfs_iwalk.h | ||
| xfs_linux.h | ||
| xfs_log.c | ||
| xfs_log.h | ||
| xfs_log_cil.c | ||
| xfs_log_priv.h | ||
| xfs_log_recover.c | ||
| xfs_message.c | ||
| xfs_message.h | ||
| xfs_mount.c | ||
| xfs_mount.h | ||
| xfs_mru_cache.c | ||
| xfs_mru_cache.h | ||
| xfs_ondisk.h | ||
| xfs_pnfs.c | ||
| xfs_pnfs.h | ||
| xfs_pwork.c | ||
| xfs_pwork.h | ||
| xfs_qm.c | ||
| xfs_qm.h | ||
| xfs_qm_bhv.c | ||
| xfs_qm_syscalls.c | ||
| xfs_quota.h | ||
| xfs_quotaops.c | ||
| xfs_refcount_item.c | ||
| xfs_refcount_item.h | ||
| xfs_reflink.c | ||
| xfs_reflink.h | ||
| xfs_rmap_item.c | ||
| xfs_rmap_item.h | ||
| xfs_rtalloc.c | ||
| xfs_rtalloc.h | ||
| xfs_stats.c | ||
| xfs_stats.h | ||
| xfs_super.c | ||
| xfs_super.h | ||
| xfs_symlink.c | ||
| xfs_symlink.h | ||
| xfs_sysctl.c | ||
| xfs_sysctl.h | ||
| xfs_sysfs.c | ||
| xfs_sysfs.h | ||
| xfs_trace.c | ||
| xfs_trace.h | ||
| xfs_trans.c | ||
| xfs_trans.h | ||
| xfs_trans_ail.c | ||
| xfs_trans_buf.c | ||
| xfs_trans_dquot.c | ||
| xfs_trans_priv.h | ||
| xfs_xattr.c | ||