4976 zfs should only avoid writing to a failing non-redundant top-lev…

…el vdev

4977 mdb error in ::spa_space from space_cb() if a metaslab's ms_sm is NULL
4978 ztest fails in get_metaslab_refcount()
4979 extend free space histogram to device and pool
4980 metaslabs should have a fragmentation metric
4981 remove fragmented ops vector from block allocator
4982 space_map object should proactively upgrade when feature is enabled
4983 need to collect metaslab information via mdb
4984 device selection should use fragmentation metric
Reviewed by: Matthew Ahrens <mahrens@delphix.com>
Reviewed by: Adam Leventhal <adam.leventhal@delphix.com>
Reviewed by: Christopher Siden <christopher.siden@delphix.com>
Approved by: Garrett D'Amore <garrett@damore.org>

usr/src/cmd/zdb/zdb.c

@@ -111,11 +111,11 @@ static void
 usage(void)
 {
 	(void) fprintf(stderr,
-	    "Usage: %s [-CumdibcsDvhLXFPA] [-t txg] [-e [-p path...]] "
-	    "[-U config] [-M inflight I/Os] [-x dumpdir] poolname [object...]\n"
+	    "Usage: %s [-CumMdibcsDvhLXFPA] [-t txg] [-e [-p path...]] "
+	    "[-U config] [-I inflight I/Os] [-x dumpdir] poolname [object...]\n"
 	    "       %s [-divPA] [-e -p path...] [-U config] dataset "
 	    "[object...]\n"
-	    "       %s -m [-LXFPA] [-t txg] [-e [-p path...]] [-U config] "
+	    "       %s -mM [-LXFPA] [-t txg] [-e [-p path...]] [-U config] "
 	    "poolname [vdev [metaslab...]]\n"
 	    "       %s -R [-A] [-e [-p path...]] poolname "
 	    "vdev:offset:size[:flags]\n"
@@ -138,6 +138,7 @@ usage(void)
 	(void) fprintf(stderr, "        -h pool history\n");
 	(void) fprintf(stderr, "        -b block statistics\n");
 	(void) fprintf(stderr, "        -m metaslabs\n");
+	(void) fprintf(stderr, "        -M metaslab groups\n");
 	(void) fprintf(stderr, "        -c checksum all metadata (twice for "
 	    "all data) blocks\n");
 	(void) fprintf(stderr, "        -s report stats on zdb's I/O\n");
@@ -168,7 +169,7 @@ usage(void)
 	(void) fprintf(stderr, "        -P print numbers in parseable form\n");
 	(void) fprintf(stderr, "        -t <txg> -- highest txg to use when "
 	    "searching for uberblocks\n");
-	(void) fprintf(stderr, "        -M <number of inflight I/Os> -- "
+	(void) fprintf(stderr, "        -I <number of inflight I/Os> -- "
 	    "specify the maximum number of "
 	    "checksumming I/Os [default is 200]\n");
 	(void) fprintf(stderr, "Specify an option more than once (e.g. -bb) "
@@ -548,7 +549,7 @@ get_metaslab_refcount(vdev_t *vd)
 {
 	int refcount = 0;
 
-	if (vd->vdev_top == vd) {
+	if (vd->vdev_top == vd && !vd->vdev_removing) {
 		for (int m = 0; m < vd->vdev_ms_count; m++) {
 			space_map_t *sm = vd->vdev_ms[m]->ms_sm;
 
@@ -686,9 +687,10 @@ dump_metaslab(metaslab_t *msp)
 		 * The space map histogram represents free space in chunks
 		 * of sm_shift (i.e. bucket 0 refers to 2^sm_shift).
 		 */
-		(void) printf("\tOn-disk histogram:\n");
+		(void) printf("\tOn-disk histogram:\t\tfragmentation %llu\n",
+		    (u_longlong_t)msp->ms_fragmentation);
 		dump_histogram(sm->sm_phys->smp_histogram,
-		    SPACE_MAP_HISTOGRAM_SIZE(sm), sm->sm_shift);
+		    SPACE_MAP_HISTOGRAM_SIZE, sm->sm_shift);
 	}
 
 	if (dump_opt['d'] > 5 || dump_opt['m'] > 3) {
@@ -712,6 +714,47 @@ print_vdev_metaslab_header(vdev_t *vd)
 	    "---------------", "-------------");
 }
 
+static void
+dump_metaslab_groups(spa_t *spa)
+{
+	vdev_t *rvd = spa->spa_root_vdev;
+	metaslab_class_t *mc = spa_normal_class(spa);
+	uint64_t fragmentation;
+
+	metaslab_class_histogram_verify(mc);
+
+	for (int c = 0; c < rvd->vdev_children; c++) {
+		vdev_t *tvd = rvd->vdev_child[c];
+		metaslab_group_t *mg = tvd->vdev_mg;
+
+		if (mg->mg_class != mc)
+			continue;
+
+		metaslab_group_histogram_verify(mg);
+		mg->mg_fragmentation = metaslab_group_fragmentation(mg);
+
+		(void) printf("\tvdev %10llu\t\tmetaslabs%5llu\t\t"
+		    "fragmentation",
+		    (u_longlong_t)tvd->vdev_id,
+		    (u_longlong_t)tvd->vdev_ms_count);
+		if (mg->mg_fragmentation == ZFS_FRAG_INVALID) {
+			(void) printf("%3s\n", "-");
+		} else {
+			(void) printf("%3llu%%\n",
+			    (u_longlong_t)mg->mg_fragmentation);
+		}
+		dump_histogram(mg->mg_histogram, RANGE_TREE_HISTOGRAM_SIZE, 0);
+	}
+
+	(void) printf("\tpool %s\tfragmentation", spa_name(spa));
+	fragmentation = metaslab_class_fragmentation(mc);
+	if (fragmentation == ZFS_FRAG_INVALID)
+		(void) printf("\t%3s\n", "-");
+	else
+		(void) printf("\t%3llu%%\n", (u_longlong_t)fragmentation);
+	dump_histogram(mc->mc_histogram, RANGE_TREE_HISTOGRAM_SIZE, 0);
+}
+
 static void
 dump_metaslabs(spa_t *spa)
 {
@@ -2340,8 +2383,7 @@ zdb_leak(void *arg, uint64_t start, uint64_t size)
 }
 
 static metaslab_ops_t zdb_metaslab_ops = {
-	NULL,	/* alloc */
-	NULL	/* fragmented */
+	NULL	/* alloc */
 };
 
 static void
@@ -2836,6 +2878,8 @@ dump_zpool(spa_t *spa)
 
 	if (dump_opt['d'] > 2 || dump_opt['m'])
 		dump_metaslabs(spa);
+	if (dump_opt['M'])
+		dump_metaslab_groups(spa);
 
 	if (dump_opt['d'] || dump_opt['i']) {
 		dump_dir(dp->dp_meta_objset);
@@ -3330,7 +3374,7 @@ main(int argc, char **argv)
 	dprintf_setup(&argc, argv);
 
 	while ((c = getopt(argc, argv,
-	    "bcdhilmM:suCDRSAFLXx:evp:t:U:P")) != -1) {
+	    "bcdhilmMI:suCDRSAFLXx:evp:t:U:P")) != -1) {
 		switch (c) {
 		case 'b':
 		case 'c':
@@ -3343,6 +3387,7 @@ main(int argc, char **argv)
 		case 'u':
 		case 'C':
 		case 'D':
+		case 'M':
 		case 'R':
 		case 'S':
 			dump_opt[c]++;
@@ -3356,10 +3401,7 @@ main(int argc, char **argv)
 		case 'P':
 			dump_opt[c]++;
 			break;
-		case 'v':
-			verbose++;
-			break;
-		case 'M':
+		case 'I':
 			max_inflight = strtoull(optarg, NULL, 0);
 			if (max_inflight == 0) {
 				(void) fprintf(stderr, "maximum number "
@@ -3383,9 +3425,6 @@ main(int argc, char **argv)
 			}
 			searchdirs[nsearch++] = optarg;
 			break;
-		case 'x':
-			vn_dumpdir = optarg;
-			break;
 		case 't':
 			max_txg = strtoull(optarg, NULL, 0);
 			if (max_txg < TXG_INITIAL) {
@@ -3397,6 +3436,12 @@ main(int argc, char **argv)
 		case 'U':
 			spa_config_path = optarg;
 			break;
+		case 'v':
+			verbose++;
+			break;
+		case 'x':
+			vn_dumpdir = optarg;
+			break;
 		default:
 			usage();
 			break;

usr/src/cmd/zpool/zpool_main.c

@@ -2754,10 +2754,15 @@ print_one_column(zpool_prop_t prop, uint64_t value, boolean_t scripted)
 	boolean_t fixed;
 	size_t width = zprop_width(prop, &fixed, ZFS_TYPE_POOL);
 
-	zfs_nicenum(value, propval, sizeof (propval));
 
 	if (prop == ZPOOL_PROP_EXPANDSZ && value == 0)
 		(void) strlcpy(propval, "-", sizeof (propval));
+	else if (prop == ZPOOL_PROP_FRAGMENTATION && value == ZFS_FRAG_INVALID)
+		(void) strlcpy(propval, "-", sizeof (propval));
+	else if (prop == ZPOOL_PROP_FRAGMENTATION)
+		(void) snprintf(propval, sizeof (propval), "%llu%%", value);
+	else
+		zfs_nicenum(value, propval, sizeof (propval));
 
 	if (scripted)
 		(void) printf("\t%s", propval);
@@ -2790,16 +2795,18 @@ print_list_stats(zpool_handle_t *zhp, const char *name, nvlist_t *nv,
 		/* only toplevel vdevs have capacity stats */
 		if (vs->vs_space == 0) {
 			if (scripted)
-				(void) printf("\t-\t-\t-");
+				(void) printf("\t-\t-\t-\t-");
 			else
-				(void) printf("      -      -      -");
+				(void) printf("      -      -      -      -");
 		} else {
 			print_one_column(ZPOOL_PROP_SIZE, vs->vs_space,
 			    scripted);
 			print_one_column(ZPOOL_PROP_CAPACITY, vs->vs_alloc,
 			    scripted);
 			print_one_column(ZPOOL_PROP_FREE,
 			    vs->vs_space - vs->vs_alloc, scripted);
+			print_one_column(ZPOOL_PROP_FRAGMENTATION,
+			    vs->vs_fragmentation, scripted);
 		}
 		print_one_column(ZPOOL_PROP_EXPANDSZ, vs->vs_esize,
 		    scripted);
@@ -2885,8 +2892,8 @@ zpool_do_list(int argc, char **argv)
 	int ret;
 	list_cbdata_t cb = { 0 };
 	static char default_props[] =
-	    "name,size,allocated,free,expandsize,capacity,dedupratio,"
-	    "health,altroot";
+	    "name,size,allocated,free,fragmentation,expandsize,capacity,"
+	    "dedupratio,health,altroot";
 	char *props = default_props;
 	unsigned long interval = 0, count = 0;
 	zpool_list_t *list;

usr/src/common/zfs/zpool_prop.c

@@ -21,7 +21,7 @@
 /*
  * Copyright (c) 2007, 2010, Oracle and/or its affiliates. All rights reserved.
  * Copyright 2011 Nexenta Systems, Inc. All rights reserved.
- * Copyright (c) 2012 by Delphix. All rights reserved.
+ * Copyright (c) 2012, 2014 by Delphix. All rights reserved.
  */
 
 #include <sys/zio.h>
@@ -87,6 +87,8 @@ zpool_prop_init(void)
 	    PROP_READONLY, ZFS_TYPE_POOL, "<size>", "ALLOC");
 	zprop_register_number(ZPOOL_PROP_EXPANDSZ, "expandsize", 0,
 	    PROP_READONLY, ZFS_TYPE_POOL, "<size>", "EXPANDSZ");
+	zprop_register_number(ZPOOL_PROP_FRAGMENTATION, "fragmentation", 0,
+	    PROP_READONLY, ZFS_TYPE_POOL, "<percent>", "FRAG");
 	zprop_register_number(ZPOOL_PROP_CAPACITY, "capacity", 0, PROP_READONLY,
 	    ZFS_TYPE_POOL, "<size>", "CAP");
 	zprop_register_number(ZPOOL_PROP_GUID, "guid", 0, PROP_READONLY,

usr/src/lib/libzfs/common/libzfs_pool.c

@@ -294,6 +294,14 @@ zpool_get_prop(zpool_handle_t *zhp, zpool_prop_t prop, char *buf, size_t len,
 				    (u_longlong_t)intval);
 			}
 			break;
+		case ZPOOL_PROP_FRAGMENTATION:
+			if (intval == UINT64_MAX) {
+				(void) strlcpy(buf, "-", len);
+			} else {
+				(void) snprintf(buf, len, "%llu%%",
+				    (u_longlong_t)intval);
+			}
+			break;
 
 		case ZPOOL_PROP_DEDUPRATIO:
 			(void) snprintf(buf, len, "%llu.%02llux",

usr/src/man/man1m/zdb.1m

@@ -19,16 +19,16 @@
 \fBzdb\fR - Display zpool debugging and consistency information
 
 .SH "SYNOPSIS"
-\fBzdb\fR [-CumdibcsDvhLXFPA] [-e [-p \fIpath\fR...]] [-t \fItxg\fR]
-    [-U \fIcache\fR] [-M \fIinflight I/Os\fR] [-x \fIdumpdir\fR]
+\fBzdb\fR [-CumdibcsDvhLMXFPA] [-e [-p \fIpath\fR...]] [-t \fItxg\fR]
+    [-U \fIcache\fR] [-I \fIinflight I/Os\fR] [-x \fIdumpdir\fR]
     [\fIpoolname\fR [\fIobject\fR ...]]
 
 .P
 \fBzdb\fR [-divPA] [-e [-p \fIpath\fR...]] [-U \fIcache\fR]
     \fIdataset\fR [\fIobject\fR ...]
 
 .P
-\fBzdb\fR -m [-LXFPA] [-t \fItxg\fR] [-e [-p \fIpath\fR...]] [-U \fIcache\fR]
+\fBzdb\fR -m [-MLXFPA] [-t \fItxg\fR] [-e [-p \fIpath\fR...]] [-U \fIcache\fR]
     \fIpoolname\fR [\fIvdev\fR [\fImetaslab\fR ...]]
 
 .P
@@ -194,6 +194,21 @@ verifies that all non-free blocks are referenced, which can be very expensive.
 .sp .6
 .RS 4n
 Display the offset, spacemap, and free space of each metaslab.
+When specified twice, also display information about the on-disk free
+space histogram associated with each metaslab. When specified three time,
+display the maximum contiguous free space, the in-core free space histogram,
+and the percentage of free space in each space map.  When specified
+four times display every spacemap record.
+.RE
+
+.sp
+.ne 2
+.na
+\fB-M\fR
+.ad
+.sp .6
+.RS 4n
+Display the offset, spacemap, and free space of each metaslab.
 When specified twice, also display information about the maximum contiguous
 free space and the percentage of free space in each space map.  When specified
 three times display every spacemap record.
@@ -380,7 +395,7 @@ transactions.
 .sp
 .ne 2
 .na
-\fB-M \fIinflight I/Os\fR \fR
+\fB-I \fIinflight I/Os\fR \fR
 .ad
 .sp .6
 .RS 4n

usr/src/man/man1m/zpool.1m

@@ -1,7 +1,7 @@
 '\" te
 .\" Copyright (c) 2007, Sun Microsystems, Inc. All Rights Reserved.
 .\" Copyright 2011, Nexenta Systems, Inc. All Rights Reserved.
-.\" Copyright (c) 2012 by Delphix. All rights reserved.
+.\" Copyright (c) 2013 by Delphix. All rights reserved.
 .\" The contents of this file are subject to the terms of the Common Development
 .\" and Distribution License (the "License"). You may not use this file except
 .\" in compliance with the License. You can obtain a copy of the license at
@@ -570,6 +570,15 @@ any space on an EFI labeled vdev which has not been brought online
 (i.e. zpool online -e).  This space occurs when a LUN is dynamically expanded.
 .RE
 
+.sp
+.ne 2
+.na
+\fB\fBfragmentation\fR\fR
+.ad
+.RS 20n
+The amount of fragmentation in the pool.
+.RE
+
 .sp
 .ne 2
 .na
@@ -1648,7 +1657,7 @@ Display numbers in parsable (exact) values.
 .RS 12n
 Comma-separated list of properties to display. See the "Properties" section for
 a list of valid properties. The default list is "name, size, used, available,
-expandsize, capacity, dedupratio, health, altroot"
+fragmentation, expandsize, capacity, dedupratio, health, altroot"
 .RE
 
 .sp
@@ -2035,10 +2044,10 @@ The results from this command are similar to the following:
 .in +2
 .nf
 # \fBzpool list\fR
-     NAME    SIZE  ALLOC   FREE  EXPANDSZ    CAP  DEDUP  HEALTH  ALTROOT
-     rpool  19.9G  8.43G  11.4G         -    42%  1.00x  ONLINE  -
-     tank   61.5G  20.0G  41.5G         -    32%  1.00x  ONLINE  -
-     zion       -      -      -         -      -      -  FAULTED -
+NAME    SIZE  ALLOC   FREE   FRAG  EXPANDSZ    CAP  DEDUP  HEALTH  ALTROOT
+rpool  19.9G  8.43G  11.4G    33%         -    42%  1.00x  ONLINE  -
+tank   61.5G  20.0G  41.5G    48%         -    32%  1.00x  ONLINE  -
+zion       -      -      -      -         -      -      -  FAULTED -
 .fi
 .in -2
 .sp
@@ -2259,20 +2268,20 @@ The command to remove the mirrored log \fBmirror-2\fR is:
 .LP
 The following command dipslays the detailed information for the \fIdata\fR
 pool. This pool is comprised of a single \fIraidz\fR vdev where one of its
-devices increased its capacity by 1GB. In this example, the pool will not
+devices increased its capacity by 10GB. In this example, the pool will not
 be able to utilized this extra capacity until all the devices under the
 \fIraidz\fR vdev have been expanded.
 
 .sp
 .in +2
 .nf
 # \fBzpool list -v data\fR
-   NAME         SIZE  ALLOC   FREE  EXPANDSZ    CAP  DEDUP  HEALTH  ALTROOT
-   data        17.9G   174K  17.9G         -     0%  1.00x  ONLINE  -
-     raidz1    17.9G   174K  17.9G         -
-       c4t2d0      -      -      -        1G
-       c4t3d0      -      -      -         -
-       c4t4d0      -      -      -         - 
+NAME         SIZE  ALLOC   FREE   FRAG  EXPANDSZ    CAP  DEDUP  HEALTH  ALTROOT
+data        23.9G  14.6G  9.30G    48%         -    61%  1.00x  ONLINE  -
+  raidz1    23.9G  14.6G  9.30G    48%         -
+    c1t1d0      -      -      -      -         -
+    c1t2d0      -      -      -      -       10G
+    c1t3d0      -      -      -      -         -
 .fi
 .in -2