MFC r315896: MFV r315290, r315291: 7303 dynamic metaslab selection

illumos/illumos-gate@8363e80ae72609660f6090766ca8c2c18aa53f0c
https://github.com/illumos/illumos-gate/commit/8363e80ae72609660f6090766ca8c2c18

https://www.illumos.org/issues/7303

  This change introduces a new weighting algorithm to improve metaslab selection
.
  The new weighting algorithm relies on the SPACEMAP_HISTOGRAM feature. As a res
ult,
  the metaslab weight now encodes the type of weighting algorithm used
  (size-based vs segment-based).

  This also introduce a new allocation tracing facility and two new dcmds to hel
p
  debug allocation problems. Each zio now contains a zio_alloc_list_t structure
  that is populated as the zio goes through the allocations stage. Here's an
  example of how to use the tracing facility:

> c5ec000::print zio_t io_alloc_list | ::walk list | ::metaslab_trace
  MSID    DVA    ASIZE      WEIGHT             RESULT               VDEV
     -      0      400           0    NOT_ALLOCATABLE           ztest.0a
     -      0      400           0    NOT_ALLOCATABLE           ztest.0a
     -      0      400           0             ENOSPC           ztest.0a
     -      0      200           0    NOT_ALLOCATABLE           ztest.0a
     -      0      200           0    NOT_ALLOCATABLE           ztest.0a
     -      0      200           0             ENOSPC           ztest.0a
     1      0      400      1 x 8M            17b1a00           ztest.0a

> 1ff2400::print zio_t io_alloc_list | ::walk list | ::metaslab_trace
  MSID    DVA    ASIZE      WEIGHT             RESULT               VDEV
     -      0      200           0    NOT_ALLOCATABLE           mirror-2
     -      0      200           0    NOT_ALLOCATABLE           mirror-0
     1      0      200      1 x 4M            112ae00           mirror-1
     -      1      200           0    NOT_ALLOCATABLE           mirror-2
     -      1      200           0    NOT_ALLOCATABLE           mirror-0
     1      1      200      1 x 4M            112b000           mirror-1
     -      2      200           0    NOT_ALLOCATABLE           mirror-2

  If the metaslab is using segment-based weighting then the WEIGHT column will
  display the number of segments available in the bucket where the allocation
  attempt was made.

Author: George Wilson <george.wilson@delphix.com>
Reviewed by: Alex Reece <alex@delphix.com>
Reviewed by: Chris Siden <christopher.siden@delphix.com>
Reviewed by: Dan Kimmel <dan.kimmel@delphix.com>
Reviewed by: Matthew Ahrens <mahrens@delphix.com>
Reviewed by: Paul Dagnelie <paul.dagnelie@delphix.com>
Reviewed by: Pavel Zakharov <pavel.zakharov@delphix.com>
Reviewed by: Prakash Surya <prakash.surya@delphix.com>
Reviewed by: Don Brady <don.brady@intel.com>
Approved by: Richard Lowe <richlowe@richlowe.net>

3 files changed, 27 insertions, 5 deletions

diff --git a/cddl/contrib/opensolaris/cmd/zdb/zdb.c b/cddl/contrib/opensolaris/cmd/zdb/zdb.c
index 482e560..743641b 100644
--- a/cddl/contrib/opensolaris/cmd/zdb/zdb.c
+++ b/cddl/contrib/opensolaris/cmd/zdb/zdb.c
@@ -2585,10 +2585,21 @@ zdb_leak_init(spa_t *spa, zdb_cb_t *zcb)
 
 	if (!dump_opt['L']) {
 		vdev_t *rvd = spa->spa_root_vdev;
+
+		/*
+		 * We are going to be changing the meaning of the metaslab's
+		 * ms_tree.  Ensure that the allocator doesn't try to
+		 * use the tree.
+		 */
+		spa->spa_normal_class->mc_ops = &zdb_metaslab_ops;
+		spa->spa_log_class->mc_ops = &zdb_metaslab_ops;
+
 		for (uint64_t c = 0; c < rvd->vdev_children; c++) {
 			vdev_t *vd = rvd->vdev_child[c];
+			metaslab_group_t *mg = vd->vdev_mg;
 			for (uint64_t m = 0; m < vd->vdev_ms_count; m++) {
 				metaslab_t *msp = vd->vdev_ms[m];
+				ASSERT3P(msp->ms_group, ==, mg);
 				mutex_enter(&msp->ms_lock);
 				metaslab_unload(msp);
 
@@ -2609,8 +2620,6 @@ zdb_leak_init(spa_t *spa, zdb_cb_t *zcb)
 					    (longlong_t)m,
 					    (longlong_t)vd->vdev_ms_count);
 
-					msp->ms_ops = &zdb_metaslab_ops;
-
 					/*
 					 * We don't want to spend the CPU
 					 * manipulating the size-ordered
@@ -2620,7 +2629,10 @@ zdb_leak_init(spa_t *spa, zdb_cb_t *zcb)
 					msp->ms_tree->rt_ops = NULL;
 					VERIFY0(space_map_load(msp->ms_sm,
 					    msp->ms_tree, SM_ALLOC));
-					msp->ms_loaded = B_TRUE;
+
+					if (!msp->ms_loaded) {
+						msp->ms_loaded = B_TRUE;
+					}
 				}
 				mutex_exit(&msp->ms_lock);
 			}
@@ -2642,8 +2654,10 @@ zdb_leak_fini(spa_t *spa)
 		vdev_t *rvd = spa->spa_root_vdev;
 		for (int c = 0; c < rvd->vdev_children; c++) {
 			vdev_t *vd = rvd->vdev_child[c];
+			metaslab_group_t *mg = vd->vdev_mg;
 			for (int m = 0; m < vd->vdev_ms_count; m++) {
 				metaslab_t *msp = vd->vdev_ms[m];
+				ASSERT3P(mg, ==, msp->ms_group);
 				mutex_enter(&msp->ms_lock);
 
 				/*
@@ -2657,7 +2671,10 @@ zdb_leak_fini(spa_t *spa)
 				 * from the ms_tree.
 				 */
 				range_tree_vacate(msp->ms_tree, zdb_leak, vd);
-				msp->ms_loaded = B_FALSE;
+
+				if (msp->ms_loaded) {
+					msp->ms_loaded = B_FALSE;
+				}
 
 				mutex_exit(&msp->ms_lock);
 			}
diff --git a/cddl/contrib/opensolaris/cmd/ztest/ztest.c b/cddl/contrib/opensolaris/cmd/ztest/ztest.c
index bfc80e3..491bd6b 100644
--- a/cddl/contrib/opensolaris/cmd/ztest/ztest.c
+++ b/cddl/contrib/opensolaris/cmd/ztest/ztest.c
@@ -173,7 +173,7 @@ static const ztest_shared_opts_t ztest_opts_defaults = {
 	.zo_mirrors = 2,
 	.zo_raidz = 4,
 	.zo_raidz_parity = 1,
-	.zo_vdev_size = SPA_MINDEVSIZE * 2,
+	.zo_vdev_size = SPA_MINDEVSIZE * 4,	/* 256m default size */
 	.zo_datasets = 7,
 	.zo_threads = 23,
 	.zo_passtime = 60,		/* 60 seconds */
diff --git a/cddl/contrib/opensolaris/lib/libzpool/common/kernel.c b/cddl/contrib/opensolaris/lib/libzpool/common/kernel.c
index a7fc128..701f0b4 100644
--- a/cddl/contrib/opensolaris/lib/libzpool/common/kernel.c
+++ b/cddl/contrib/opensolaris/lib/libzpool/common/kernel.c
@@ -97,6 +97,11 @@ kstat_create(char *module, int instance, char *name, char *class,
 
 /*ARGSUSED*/
 void
+kstat_named_init(kstat_named_t *knp, const char *name, uchar_t type)
+{}
+
+/*ARGSUSED*/
+void
 kstat_install(kstat_t *ksp)
 {}