c/mirror_zfs
1
0
Fork 0
mirror of https://git.proxmox.com/git/mirror_zfs.git synced 2026-05-24 19:28:53 +03:00
Code Issues Packages Projects Releases Wiki Activity

Optimize allocation throttling

Browse Source 
Remove mc_lock use from metaslab_class_throttle_*().  The math there
is based on refcounts and so atomic, so the only race possible there
is between zfs_refcount_count() and zfs_refcount_add().  But in most
cases metaslab_class_throttle_reserve() is called with the allocator
lock held, which covers the race.  In cases where the lock is not
held, GANG_ALLOCATION() or METASLAB_MUST_RESERVE are set, and so we
do not use zfs_refcount_count().  And even if we assume some other
non-existing scenario, the worst that may happen from this race is
few more I/Os get to allocation earlier, that is not a problem.

Move locks and data of different allocators into different cache
lines to avoid false sharing.  Group spa_alloc_* arrays together
into single array of aligned struct spa_alloc spa_allocs.  Align
struct metaslab_class_allocator.

Reviewed-by: Paul Dagnelie <pcd@delphix.com>
Reviewed-by: Ryan Moeller <ryan@iXsystems.com>
Reviewed-by: Don Brady <don.brady@delphix.com>
Signed-off-by: Alexander Motin <mav@FreeBSD.org>
Sponsored-By: iXsystems, Inc.
Closes #12314
This commit is contained in:
Alexander Motin
2021-07-21 08:40:36 -04:00
committed by GitHub
parent bc93935ef0
commit 1b50749ce9
6 changed files with 45 additions and 58 deletions
Download Patch File Download Diff File Expand all files Collapse all files
module/zfs/spa_misc.c
+9 -12
View File
@@ -700,13 +700,12 @@ spa_add(const char *name, nvlist_t *config, const char *altroot)
spa->spa_root = spa_strdup(altroot);
spa->spa_alloc_count = spa_allocators;
spa->spa_alloc_locks = kmem_zalloc(spa->spa_alloc_count *
sizeof (kmutex_t), KM_SLEEP);
spa->spa_alloc_trees = kmem_zalloc(spa->spa_alloc_count *
sizeof (avl_tree_t), KM_SLEEP);
spa->spa_allocs = kmem_zalloc(spa->spa_alloc_count *
sizeof (spa_alloc_t), KM_SLEEP);
for (int i = 0; i < spa->spa_alloc_count; i++) {
mutex_init(&spa->spa_alloc_locks[i], NULL, MUTEX_DEFAULT, NULL);
avl_create(&spa->spa_alloc_trees[i], zio_bookmark_compare,
mutex_init(&spa->spa_allocs[i].spaa_lock, NULL, MUTEX_DEFAULT,
NULL);
avl_create(&spa->spa_allocs[i].spaa_tree, zio_bookmark_compare,
sizeof (zio_t), offsetof(zio_t, io_alloc_node));
}
avl_create(&spa->spa_metaslabs_by_flushed, metaslab_sort_by_flushed,
@@ -799,13 +798,11 @@ spa_remove(spa_t *spa)
}
for (int i = 0; i < spa->spa_alloc_count; i++) {
avl_destroy(&spa->spa_alloc_trees[i]);
mutex_destroy(&spa->spa_alloc_locks[i]);
avl_destroy(&spa->spa_allocs[i].spaa_tree);
mutex_destroy(&spa->spa_allocs[i].spaa_lock);
}
kmem_free(spa->spa_alloc_locks, spa->spa_alloc_count *
sizeof (kmutex_t));
kmem_free(spa->spa_alloc_trees, spa->spa_alloc_count *
sizeof (avl_tree_t));
kmem_free(spa->spa_allocs, spa->spa_alloc_count *
sizeof (spa_alloc_t));
avl_destroy(&spa->spa_metaslabs_by_flushed);
avl_destroy(&spa->spa_sm_logs_by_txg);