MFV r336948: 9112 Improve allocation performance on high-end systems

On high-end systems running async sequential write workloads, especially
NUMA systems with flash or NVMe storage, one significant performance
bottleneck is selecting a metaslab to do allocations from. This process
can be parallelized, providing significant performance increases for
these workloads.

illumos/illumos-gate@f78cdc34af236a6199dd9e21376f4a46348c0d56

Reviewed by: Matthew Ahrens <mahrens@delphix.com>
Reviewed by: George Wilson <george.wilson@delphix.com>
Reviewed by: Serapheim Dimitropoulos <serapheim.dimitro@delphix.com>
Reviewed by: Alexander Motin <mav@FreeBSD.org>
Approved by: Gordon Ross <gwr@nexenta.com>
Author: Paul Dagnelie <pcd@delphix.com>

1 files changed, 10 insertions, 8 deletions

diff --git a/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/sys/metaslab.h b/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/sys/metaslab.h
index 8de77532ee75..0509e95b1587 100644
--- a/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/sys/metaslab.h
+++ b/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/sys/metaslab.h
@@ -20,7 +20,7 @@
  */
 /*
  * Copyright (c) 2005, 2010, Oracle and/or its affiliates. All rights reserved.
- * Copyright (c) 2011, 2017 by Delphix. All rights reserved.
+ * Copyright (c) 2011, 2018 by Delphix. All rights reserved.
  */
 
 #ifndef _SYS_METASLAB_H
@@ -65,9 +65,10 @@ uint64_t metaslab_block_maxsize(metaslab_t *);
 #define	METASLAB_DONT_THROTTLE		0x10
 
 int metaslab_alloc(spa_t *, metaslab_class_t *, uint64_t,
-    blkptr_t *, int, uint64_t, blkptr_t *, int, zio_alloc_list_t *, zio_t *);
+    blkptr_t *, int, uint64_t, blkptr_t *, int, zio_alloc_list_t *, zio_t *,
+    int);
 int metaslab_alloc_dva(spa_t *, metaslab_class_t *, uint64_t,
-    dva_t *, int, dva_t *, uint64_t, int, zio_alloc_list_t *);
+    dva_t *, int, dva_t *, uint64_t, int, zio_alloc_list_t *, int);
 void metaslab_free(spa_t *, const blkptr_t *, uint64_t, boolean_t);
 void metaslab_free_concrete(vdev_t *, uint64_t, uint64_t, boolean_t);
 void metaslab_free_dva(spa_t *, const dva_t *, boolean_t);
@@ -88,9 +89,9 @@ int metaslab_class_validate(metaslab_class_t *);
 void metaslab_class_histogram_verify(metaslab_class_t *);
 uint64_t metaslab_class_fragmentation(metaslab_class_t *);
 uint64_t metaslab_class_expandable_space(metaslab_class_t *);
-boolean_t metaslab_class_throttle_reserve(metaslab_class_t *, int,
+boolean_t metaslab_class_throttle_reserve(metaslab_class_t *, int, int,
     zio_t *, int);
-void metaslab_class_throttle_unreserve(metaslab_class_t *, int, zio_t *);
+void metaslab_class_throttle_unreserve(metaslab_class_t *, int, int, zio_t *);
 
 void metaslab_class_space_update(metaslab_class_t *, int64_t, int64_t,
     int64_t, int64_t);
@@ -100,7 +101,7 @@ uint64_t metaslab_class_get_dspace(metaslab_class_t *);
 uint64_t metaslab_class_get_deferred(metaslab_class_t *);
 uint64_t metaslab_class_get_minblocksize(metaslab_class_t *mc);
 
-metaslab_group_t *metaslab_group_create(metaslab_class_t *, vdev_t *);
+metaslab_group_t *metaslab_group_create(metaslab_class_t *, vdev_t *, int);
 void metaslab_group_destroy(metaslab_group_t *);
 void metaslab_group_activate(metaslab_group_t *);
 void metaslab_group_passivate(metaslab_group_t *);
@@ -109,8 +110,9 @@ uint64_t metaslab_group_get_space(metaslab_group_t *);
 void metaslab_group_histogram_verify(metaslab_group_t *);
 uint64_t metaslab_group_fragmentation(metaslab_group_t *);
 void metaslab_group_histogram_remove(metaslab_group_t *, metaslab_t *);
-void metaslab_group_alloc_decrement(spa_t *, uint64_t, void *, int);
-void metaslab_group_alloc_verify(spa_t *, const blkptr_t *, void *);
+void metaslab_group_alloc_decrement(spa_t *, uint64_t, void *, int, int,
+    boolean_t);
+void metaslab_group_alloc_verify(spa_t *, const blkptr_t *, void *, int);
 
 #ifdef	__cplusplus
 }