Illumos #3329, #3330, #3331, #3335

3329 spa_sync() spends 10-20% of its time in spa_free_sync_cb()
3330 space_seg_t should have its own kmem_cache
3331 deferred frees should happen after sync_pass 1
3335 make SYNC_PASS_* constants tunable

Reviewed by: Adam Leventhal <[email protected]>
Reviewed by: Matt Ahrens <[email protected]>
Reviewed by: Christopher Siden <[email protected]>
Reviewed by: Eric Schrock <[email protected]>
Reviewed by: Richard Lowe <[email protected]>
Reviewed by: Dan McDonald <[email protected]>
Approved by: Eric Schrock <[email protected]>

References:
  illumos/illumos-gate@01f55e48fb4d524eaf70687728aa51b7762e2e97
  https://www.illumos.org/issues/3329
  https://www.illumos.org/issues/3330
  https://www.illumos.org/issues/3331
  https://www.illumos.org/issues/3335

Ported-by: Brian Behlendorf <[email protected]>

1 files changed, 34 insertions, 8 deletions

diff --git a/module/zfs/space_map.c b/module/zfs/space_map.c
index 9c0cdb6be..d99c7c0b3 100644
--- a/module/zfs/space_map.c
+++ b/module/zfs/space_map.c
@@ -29,6 +29,23 @@
 #include <sys/zio.h>
 #include <sys/space_map.h>
 
+static kmem_cache_t *space_seg_cache;
+
+void
+space_map_init(void)
+{
+	ASSERT(space_seg_cache == NULL);
+	space_seg_cache = kmem_cache_create("space_seg_cache",
+	    sizeof (space_seg_t), 0, NULL, NULL, NULL, NULL, NULL, 0);
+}
+
+void
+space_map_fini(void)
+{
+	kmem_cache_destroy(space_seg_cache);
+	space_seg_cache = NULL;
+}
+
 /*
  * Space map routines.
  * NOTE: caller is responsible for all locking.
@@ -121,7 +138,7 @@ space_map_add(space_map_t *sm, uint64_t start, uint64_t size)
 			avl_remove(sm->sm_pp_root, ss_after);
 		}
 		ss_after->ss_start = ss_before->ss_start;
-		kmem_free(ss_before, sizeof (*ss_before));
+		kmem_cache_free(space_seg_cache, ss_before);
 		ss = ss_after;
 	} else if (merge_before) {
 		ss_before->ss_end = end;
@@ -134,7 +151,7 @@ space_map_add(space_map_t *sm, uint64_t start, uint64_t size)
 			avl_remove(sm->sm_pp_root, ss_after);
 		ss = ss_after;
 	} else {
-		ss = kmem_alloc(sizeof (*ss), KM_PUSHPAGE);
+		ss = kmem_cache_alloc(space_seg_cache, KM_PUSHPAGE);
 		ss->ss_start = start;
 		ss->ss_end = end;
 		avl_insert(&sm->sm_root, ss, where);
@@ -181,7 +198,7 @@ space_map_remove(space_map_t *sm, uint64_t start, uint64_t size)
 		avl_remove(sm->sm_pp_root, ss);
 
 	if (left_over && right_over) {
-		newseg = kmem_alloc(sizeof (*newseg), KM_PUSHPAGE);
+		newseg = kmem_cache_alloc(space_seg_cache, KM_PUSHPAGE);
 		newseg->ss_start = end;
 		newseg->ss_end = ss->ss_end;
 		ss->ss_end = start;
@@ -194,7 +211,7 @@ space_map_remove(space_map_t *sm, uint64_t start, uint64_t size)
 		ss->ss_start = end;
 	} else {
 		avl_remove(&sm->sm_root, ss);
-		kmem_free(ss, sizeof (*ss));
+		kmem_cache_free(space_seg_cache, ss);
 		ss = NULL;
 	}
 
@@ -234,7 +251,7 @@ space_map_vacate(space_map_t *sm, space_map_func_t *func, space_map_t *mdest)
 	while ((ss = avl_destroy_nodes(&sm->sm_root, &cookie)) != NULL) {
 		if (func != NULL)
 			func(mdest, ss->ss_start, ss->ss_end - ss->ss_start);
-		kmem_free(ss, sizeof (*ss));
+		kmem_cache_free(space_seg_cache, ss);
 	}
 	sm->sm_space = 0;
 }
@@ -406,7 +423,7 @@ space_map_sync(space_map_t *sm, uint8_t maptype,
 	spa_t *spa = dmu_objset_spa(os);
 	void *cookie = NULL;
 	space_seg_t *ss;
-	uint64_t bufsize, start, size, run_len;
+	uint64_t bufsize, start, size, run_len, delta, sm_space;
 	uint64_t *entry, *entry_map, *entry_map_end;
 
 	ASSERT(MUTEX_HELD(sm->sm_lock));
@@ -435,11 +452,13 @@ space_map_sync(space_map_t *sm, uint8_t maptype,
 	    SM_DEBUG_SYNCPASS_ENCODE(spa_sync_pass(spa)) |
 	    SM_DEBUG_TXG_ENCODE(dmu_tx_get_txg(tx));
 
+	delta = 0;
+	sm_space = sm->sm_space;
 	while ((ss = avl_destroy_nodes(&sm->sm_root, &cookie)) != NULL) {
 		size = ss->ss_end - ss->ss_start;
 		start = (ss->ss_start - sm->sm_start) >> sm->sm_shift;
 
-		sm->sm_space -= size;
+		delta += size;
 		size >>= sm->sm_shift;
 
 		while (size) {
@@ -461,7 +480,7 @@ space_map_sync(space_map_t *sm, uint8_t maptype,
 			start += run_len;
 			size -= run_len;
 		}
-		kmem_free(ss, sizeof (*ss));
+		kmem_cache_free(space_seg_cache, ss);
 	}
 
 	if (entry != entry_map) {
@@ -473,8 +492,15 @@ space_map_sync(space_map_t *sm, uint8_t maptype,
 		smo->smo_objsize += size;
 	}
 
+	/*
+	 * Ensure that the space_map's accounting wasn't changed
+	 * while we were in the middle of writing it out.
+	 */
+	VERIFY3U(sm->sm_space, ==, sm_space);
+
 	zio_buf_free(entry_map, bufsize);
 
+	sm->sm_space -= delta;
 	VERIFY3U(sm->sm_space, ==, 0);
 }