Sync with latest upstream PR

cmd/zpool/zpool_main.c

@@ -343,7 +343,7 @@ get_usage(zpool_help_t idx)
 		return (gettext("\treplace [-f] [-o property=value] "
 		    "<pool> <device> [new-device]\n"));
 	case HELP_REMOVE:
-		return (gettext("\tremove <pool> <device> ...\n"));
+		return (gettext("\tremove [-nps] <pool> <device> ...\n"));
 	case HELP_REOPEN:
 		return (gettext("\treopen [-n] <pool>\n"));
 	case HELP_SCRUB:
@@ -790,10 +790,18 @@ zpool_do_remove(int argc, char **argv)
 	zpool_handle_t *zhp = NULL;
 	boolean_t stop = B_FALSE;
 	char c;
+	boolean_t noop = B_FALSE;
+	boolean_t parsable = B_FALSE;
 
 	/* check options */
-	while ((c = getopt(argc, argv, "s")) != -1) {
+	while ((c = getopt(argc, argv, "nps")) != -1) {
 		switch (c) {
+		case 'n':
+			noop = B_TRUE;
+			break;
+		case 'p':
+			parsable = B_TRUE;
+			break;
 		case 's':
 			stop = B_TRUE;
 			break;
@@ -818,6 +826,11 @@ zpool_do_remove(int argc, char **argv)
 	if ((zhp = zpool_open(g_zfs, poolname)) == NULL)
 		return (1);
 
+	if (stop && noop) {
+		(void) fprintf(stderr, gettext("stop request ignored\n"));
+		return (0);
+	}
+
 	if (stop) {
 		if (argc > 1) {
 			(void) fprintf(stderr, gettext("too many arguments\n"));
@@ -832,8 +845,29 @@ zpool_do_remove(int argc, char **argv)
 		}
 
 		for (i = 1; i < argc; i++) {
-			if (zpool_vdev_remove(zhp, argv[i]) != 0)
-				ret = 1;
+			if (noop) {
+				uint64_t size;
+
+				if (zpool_vdev_indirect_size(zhp, argv[i],
+				    &size) != 0) {
+					ret = 1;
+					break;
+				}
+				if (parsable) {
+					(void) printf("%s %llu\n",
+					    argv[i], (unsigned long long)size);
+				} else {
+					char valstr[32];
+					zfs_nicenum(size, valstr,
+					    sizeof (valstr));
+					(void) printf("Memory that will be "
+					    "used after removing %s: %s\n",
+					    argv[i], valstr);
+				}
+			} else {
+				if (zpool_vdev_remove(zhp, argv[i]) != 0)
+					ret = 1;
+			}
 		}
 	}
 	zpool_close(zhp);

include/libzfs.h

@@ -280,6 +280,7 @@ extern int zpool_vdev_attach(zpool_handle_t *, const char *,
 extern int zpool_vdev_detach(zpool_handle_t *, const char *);
 extern int zpool_vdev_remove(zpool_handle_t *, const char *);
 extern int zpool_vdev_remove_cancel(zpool_handle_t *);
+extern int zpool_vdev_indirect_size(zpool_handle_t *, const char *, uint64_t *);
 extern int zpool_vdev_split(zpool_handle_t *, char *, nvlist_t **, nvlist_t *,
     splitflags_t);
 

lib/libzfs/libzfs_pool.c

@@ -22,7 +22,7 @@
 /*
  * Copyright 2015 Nexenta Systems, Inc.  All rights reserved.
  * Copyright (c) 2005, 2010, Oracle and/or its affiliates. All rights reserved.
- * Copyright (c) 2011, 2014 by Delphix. All rights reserved.
+ * Copyright (c) 2011, 2017 by Delphix. All rights reserved.
  * Copyright 2016 Igor Kozhukhov <ikozhukhov@gmail.com>
  * Copyright (c) 2017 Datto Inc.
  * Copyright (c) 2017 Open-E, Inc. All Rights Reserved.
@@ -1411,8 +1411,10 @@ zpool_add(zpool_handle_t *zhp, nvlist_t *nvroot)
 
 		case EINVAL:
 			zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
-			    "Invalid config; a pool with removing/removed "
-			    "vdevs does not support redundant vdevs"));
+			    "invalid config; a pool with removing/removed "
+			    "vdevs does not support adding raidz vdevs "
+			    "or a top level mirror must be a "
+			    "mirror of leaf vdevs only"));
 			(void) zfs_error(hdl, EZFS_BADDEV, msg);
 			break;
 
@@ -2766,7 +2768,7 @@ zpool_vdev_attach(zpool_handle_t *zhp,
 
 	(void) strlcpy(zc.zc_name, zhp->zpool_name, sizeof (zc.zc_name));
 	if ((tgt = zpool_find_vdev(zhp, old_disk, &avail_spare, &l2cache,
-	    &islog)) == 0)
+	    &islog)) == NULL)
 		return (zfs_error(hdl, EZFS_NODEVICE, msg));
 
 	if (avail_spare)
@@ -2921,7 +2923,7 @@ zpool_vdev_detach(zpool_handle_t *zhp, const char *path)
 
 	(void) strlcpy(zc.zc_name, zhp->zpool_name, sizeof (zc.zc_name));
 	if ((tgt = zpool_find_vdev(zhp, path, &avail_spare, &l2cache,
-	    NULL)) == 0)
+	    NULL)) == NULL)
 		return (zfs_error(hdl, EZFS_NODEVICE, msg));
 
 	if (avail_spare)
@@ -3227,7 +3229,7 @@ zpool_vdev_remove(zpool_handle_t *zhp, const char *path)
 
 	(void) strlcpy(zc.zc_name, zhp->zpool_name, sizeof (zc.zc_name));
 	if ((tgt = zpool_find_vdev(zhp, path, &avail_spare, &l2cache,
-	    &islog)) == 0)
+	    &islog)) == NULL)
 		return (zfs_error(hdl, EZFS_NODEVICE, msg));
 
 	version = zpool_get_prop_int(zhp, ZPOOL_PROP_VERSION, NULL);
@@ -3244,7 +3246,7 @@ zpool_vdev_remove(zpool_handle_t *zhp, const char *path)
 		return (zfs_error(hdl, EINVAL, msg));
 	}
 
-	verify(nvlist_lookup_uint64(tgt, ZPOOL_CONFIG_GUID, &zc.zc_guid) == 0);
+	zc.zc_guid = fnvlist_lookup_uint64(tgt, ZPOOL_CONFIG_GUID);
 
 	if (zfs_ioctl(hdl, ZFS_IOC_VDEV_REMOVE, &zc) == 0)
 		return (0);
@@ -3254,7 +3256,7 @@ zpool_vdev_remove(zpool_handle_t *zhp, const char *path)
 	case EINVAL:
 		zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
 		    "invalid config; all top-level vdevs must "
-		    "have the same sector size and not be raidz "));
+		    "have the same sector size and not be raidz."));
 		(void) zfs_error(hdl, EZFS_INVALCONFIG, msg);
 		break;
 
@@ -3290,6 +3292,36 @@ zpool_vdev_remove_cancel(zpool_handle_t *zhp)
 	return (zpool_standard_error(hdl, errno, msg));
 }
 
+int
+zpool_vdev_indirect_size(zpool_handle_t *zhp, const char *path,
+    uint64_t *sizep)
+{
+	char msg[1024];
+	nvlist_t *tgt;
+	boolean_t avail_spare, l2cache, islog;
+	libzfs_handle_t *hdl = zhp->zpool_hdl;
+
+	(void) snprintf(msg, sizeof (msg),
+	    dgettext(TEXT_DOMAIN, "cannot determine indirect size of %s"),
+	    path);
+
+	if ((tgt = zpool_find_vdev(zhp, path, &avail_spare, &l2cache,
+	    &islog)) == NULL)
+		return (zfs_error(hdl, EZFS_NODEVICE, msg));
+
+	if (avail_spare || l2cache || islog) {
+		*sizep = 0;
+		return (0);
+	}
+
+	if (nvlist_lookup_uint64(tgt, ZPOOL_CONFIG_INDIRECT_SIZE, sizep) != 0) {
+		zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
+		    "indirect size not available"));
+		return (zfs_error(hdl, EINVAL, msg));
+	}
+	return (0);
+}
+
 /*
  * Clear the errors for the pool, or the particular device if specified.
  */
@@ -3317,7 +3349,7 @@ zpool_clear(zpool_handle_t *zhp, const char *path, nvlist_t *rewindnvl)
 	(void) strlcpy(zc.zc_name, zhp->zpool_name, sizeof (zc.zc_name));
 	if (path) {
 		if ((tgt = zpool_find_vdev(zhp, path, &avail_spare,
-		    &l2cache, NULL)) == 0)
+		    &l2cache, NULL)) == NULL)
 			return (zfs_error(hdl, EZFS_NODEVICE, msg));
 
 		/*

man/man8/zpool.8

@@ -144,6 +144,7 @@
 .Ar pool
 .Nm
 .Cm remove
+.Op Fl np
 .Ar pool Ar device Ns ...
 .Nm
 .Cm remove
@@ -1754,18 +1755,19 @@ result in partially resilvered devices unless a second scrub is performed.
 .It Xo
 .Nm
 .Cm remove
+.Op Fl np
 .Ar pool Ar device Ns ...
 .Xc
 Removes the specified device from the pool.
 This command currently only supports removing hot spares, cache, log
 devices and mirrored top-level vdevs (mirror of leaf devices); but not raidz.
 .sp
 Removing a top-level vdev reduces the total amount of space in the storage pool.
-The specified device must be evacuated by copying all allocated space from it to
+The specified device will be evacuated by copying all allocated space from it to
 the other devices in the pool.
 In this case, the
 .Nm zpool Cm remove
-command initiates the removal and continues while the evacuation continues in
+command initiates the removal and returns, while the evacuation continues in
 the background.
 The removal progress can be monitored with
 .Nm zpool Cm status.
@@ -1778,6 +1780,19 @@ Non-log devices or data devices that are part of a mirrored configuration can be
 the
 .Nm zpool Cm detach
 command.
+.Bl -tag -width Ds
+.It Fl n
+Do not actually perform the removal ("no-op").
+Instead, print the estimated amount of memory that will be used by the
+mapping table after the removal completes.
+This is nonzero only for top-level vdevs.
+.El
+.Bl -tag -width Ds
+.It Fl p
+Used in conjunction with the
+.Fl p
+flag, displays numbers as parsable (exact) values.
+.El
 .It Xo
 .Nm
 .Cm remove
@@ -2232,7 +2247,7 @@ option as follows:
 # zpool iostat -v pool 5
 .Ed
 .It Sy Example 14 No Removing a Mirrored top-level (Log or Data) Device
-The following commands removes the mirrored log device
+The following commands remove the mirrored log device
 .Sy mirror-2
 and mirrored top-level data device
 .Sy mirror-1 .

module/zfs/metaslab.c

@@ -3899,6 +3899,7 @@ module_param(zfs_metaslab_switch_threshold, int, 0644);
 MODULE_PARM_DESC(zfs_metaslab_switch_threshold,
 	"segment-based metaslab selection maximum buckets before switching");
 
+/* CSTYLED */
 module_param(metaslab_gang_bang, ulong, 0644);
 MODULE_PARM_DESC(metaslab_gang_bang,
 	"blocks larger than this size are forced to be gang blocks");

module/zfs/spa.c

@@ -4843,7 +4843,7 @@ spa_vdev_add(spa_t *spa, nvlist_t *nvroot)
 			}
 			/*
 			 * Need the top level mirror to be
-			 * a mirror of leaf vdevs only.
+			 * a mirror of leaf vdevs only
 			 */
 			if (tvd->vdev_ops == &vdev_mirror_ops) {
 				for (uint64_t cid = 0;

module/zfs/vdev_removal.c

@@ -1618,7 +1618,7 @@ spa_vdev_remove_top_check(vdev_t *vd)
 	spa_t *spa = vd->vdev_spa;
 
 	if (vd != vd->vdev_top)
-		return (SET_ERROR(EINVAL));
+		return (SET_ERROR(ENOTSUP));
 
 	if (!spa_feature_is_enabled(spa, SPA_FEATURE_DEVICE_REMOVAL))
 		return (SET_ERROR(ENOTSUP));

tests/runfiles/linux.run

@@ -617,7 +617,7 @@ tests = ['removal_sanity', 'removal_all_vdev', 'removal_check_space',
     'removal_with_export', 'removal_with_ganging', 'removal_with_remap',
     'removal_with_remove', 'removal_with_scrub', 'removal_with_send',
     'removal_with_send_recv', 'removal_with_snapshot', 'removal_with_write',
-    'removal_with_zdb', 'remove_mirror', 'remove_raidz']
+    'removal_with_zdb', 'remove_mirror', 'remove_mirror_sanity', 'remove_raidz']
 tags = ['functional', 'removal']
 
 [tests/functional/rename_dirs]

tests/zfs-tests/tests/functional/removal/remove_mirror.ksh

@@ -15,7 +15,7 @@
 #
 
 #
-# Copyright (c) 2014, 2016 by Delphix. All rights reserved.
+# Copyright (c) 2014, 2017 by Delphix. All rights reserved.
 #
 
 . $STF_SUITE/include/libtest.shlib
@@ -43,6 +43,6 @@ log_mustnot zpool remove $TESTPOOL $TMPDIR/dsk1
 log_mustnot zpool remove $TESTPOOL $TMPDIR/dsk2
 
 # Attempt to remove the mirror.
-log_must zpool remove $TESTPOOL mirror-1
+log_mustnot zpool remove $TESTPOOL mirror-1
 
-log_pass "Removal will succeed if there is a top level mirror."
+log_pass "Removal will not succeed if there is not enough space."

tests/zfs-tests/tests/functional/removal/remove_mirror_sanity.ksh

@@ -0,0 +1,59 @@
+#! /bin/ksh -p
+#
+# CDDL HEADER START
+#
+# This file and its contents are supplied under the terms of the
+# Common Development and Distribution License ("CDDL"), version 1.0.
+# You may only use this file in accordance with the terms of version
+# 1.0 of the CDDL.
+#
+# A full copy of the text of the CDDL should have accompanied this
+# source.  A copy of the CDDL is also available via the Internet at
+# http://www.illumos.org/license/CDDL.
+#
+# CDDL HEADER END
+#
+
+#
+# Copyright (c) 2017 by Delphix. All rights reserved.
+#
+
+. $STF_SUITE/include/libtest.shlib
+. $STF_SUITE/tests/functional/removal/removal.kshlib
+
+DISK1=$(echo $DISKS | awk '{print $1}')
+DISK2=$(echo $DISKS | awk '{print $2}')
+DISK3=$(echo $DISKS | awk '{print $3}')
+
+DISKS="$DISK1 mirror $DISK2 $DISK3"
+
+log_must default_setup_noexit "$DISKS"
+log_onexit default_cleanup_noexit
+
+WORDS_FILE1="/usr/dict/words"
+WORDS_FILE2="/usr/share/dict/words"
+FILE_CONTENTS="Leeloo Dallas mul-ti-pass."
+
+if [[ -f $WORDS_FILE1 ]]; then
+    log_must cp $WORDS_FILE1 $TESTDIR
+elif [[ -f $WORDS_FILE2 ]]; then
+    log_must cp $WORDS_FILE2 $TESTDIR
+else
+    echo $FILE_CONTENTS  >$TESTDIR/$TESTFILE0
+    log_must [ "x$(cat $TESTDIR/$TESTFILE0)" = "x$FILE_CONTENTS" ]
+fi
+
+log_must zpool remove $TESTPOOL mirror-1
+log_must wait_for_removal $TESTPOOL
+log_mustnot vdevs_in_pool $TESTPOOL mirror-1
+
+if [[ -f $WORDS_FILE1 ]]; then
+    log_must diff $WORDS_FILE1 $TESTDIR/words
+elif [[ -f $WORDS_FILE2 ]]; then
+    log_must diff $WORDS_FILE2 $TESTDIR/words
+else
+    log_must dd if=/$TESTDIR/$TESTFILE0 of=/dev/null
+    log_must [ "x$(cat $TESTDIR/$TESTFILE0)" = "x$FILE_CONTENTS" ]
+fi
+
+log_pass "Removed top-level mirror device not in use after removal."