8414 Implemented zpool scrub pause/resume

illumos/illumos-gate@1702cce751c5cb7ead878d0205a6c90b027e3de8
https://github.com/illumos/illumos-gate/commit/1702cce751c5cb7ead878d0205a6c90b027e3de8

https://www.illumos.org/issues/8414
  This issue tracks the port of scrub pause from ZoL: https://github.com/zfsonlinux/zfs/pull/6167
  Currently, there is no way to pause a scrub. Pausing may be useful when
 the pool is busy with other I/O to preserve bandwidth.

  Description

  This patch adds the ability to pause and resume scrubbing.  This is achieved
  by maintaining a persistent on-disk scrub state.  While the state is 'paused'
  we do not scrub any more blocks.  We do however perform regular scan
  housekeeping such as freeing async destroyed and deadlist blocks while paused.

  If you're testing this change, you probably want to include the patch from #6164

  Motivation and Context

  Scrub pausing can be an I/O intensive operation and people have been asking
  for the ability to pause a scrub for a while. This allows one to preserve scrub
  progress while freeing up bandwidth for other I/O.

  How Has This Been Tested?

  Unit testing and zfs-tests.  to the pool.  This patch will also include the
  patch from https://github.com/zfsonlinux/zfs/ pull/6164 In certain cases
  (dsl_scan_sync() is one), we may end up calling

Reviewed by: George Melikov <mail@gmelikov.ru>
Reviewed by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed by: Brad Lewis <brad.lewis@delphix.com>
Reviewed by: Serapheim Dimitropoulos <serapheim@delphix.com>
Reviewed by: Matt Ahrens <mahrens@delphix.com>
Approved by: Dan McDonald <danmcd@joyent.com>
Author: Alek Pinchuk <apinchuk@datto.com>

3 files changed, 40 insertions, 12 deletions

diff --git a/lib/libzfs/common/libzfs.h b/lib/libzfs/common/libzfs.h
index 5f81aa2048f6..d62c4489da5a 100644
--- a/lib/libzfs/common/libzfs.h
+++ b/lib/libzfs/common/libzfs.h
@@ -27,6 +27,7 @@
  * Copyright (c) 2013 Steven Hartland. All rights reserved.
  * Copyright (c) 2014 Integros [integros.com]
  * Copyright 2016 Nexenta Systems, Inc.
+ * Copyright (c) 2017 Datto Inc.
  */
 
 #ifndef	_LIBZFS_H
@@ -128,6 +129,7 @@ typedef enum zfs_error {
 	EZFS_DIFF,		/* general failure of zfs diff */
 	EZFS_DIFFDATA,		/* bad zfs diff data */
 	EZFS_POOLREADONLY,	/* pool is in read-only mode */
+	EZFS_SCRUB_PAUSED,	/* scrub currently paused */
 	EZFS_UNKNOWN
 } zfs_error_t;
 
@@ -251,7 +253,7 @@ typedef struct splitflags {
 /*
  * Functions to manipulate pool and vdev state
  */
-extern int zpool_scan(zpool_handle_t *, pool_scan_func_t);
+extern int zpool_scan(zpool_handle_t *, pool_scan_func_t, pool_scrub_cmd_t);
 extern int zpool_clear(zpool_handle_t *, const char *, nvlist_t *);
 extern int zpool_reguid(zpool_handle_t *);
 extern int zpool_reopen(zpool_handle_t *);
diff --git a/lib/libzfs/common/libzfs_pool.c b/lib/libzfs/common/libzfs_pool.c
index 9786f2b29957..bf5d5dc081e9 100644
--- a/lib/libzfs/common/libzfs_pool.c
+++ b/lib/libzfs/common/libzfs_pool.c
@@ -25,6 +25,7 @@
  * Copyright (c) 2013, Joyent, Inc. All rights reserved.
  * Copyright 2016 Nexenta Systems, Inc.
  * Copyright 2016 Igor Kozhukhov <ikozhukhov@gmail.com>
+ * Copyright (c) 2017 Datto Inc.
  */
 
 #include <ctype.h>
@@ -1851,22 +1852,39 @@ zpool_import_props(libzfs_handle_t *hdl, nvlist_t *config, const char *newname,
  * Scan the pool.
  */
 int
-zpool_scan(zpool_handle_t *zhp, pool_scan_func_t func)
+zpool_scan(zpool_handle_t *zhp, pool_scan_func_t func, pool_scrub_cmd_t cmd)
 {
 	zfs_cmd_t zc = { 0 };
 	char msg[1024];
+	int err;
 	libzfs_handle_t *hdl = zhp->zpool_hdl;
 
 	(void) strlcpy(zc.zc_name, zhp->zpool_name, sizeof (zc.zc_name));
 	zc.zc_cookie = func;
+	zc.zc_flags = cmd;
+
+	if (zfs_ioctl(hdl, ZFS_IOC_POOL_SCAN, &zc) == 0)
+		return (0);
+
+	err = errno;
 
-	if (zfs_ioctl(hdl, ZFS_IOC_POOL_SCAN, &zc) == 0 ||
-	    (errno == ENOENT && func != POOL_SCAN_NONE))
+	/* ECANCELED on a scrub means we resumed a paused scrub */
+	if (err == ECANCELED && func == POOL_SCAN_SCRUB &&
+	    cmd == POOL_SCRUB_NORMAL)
+		return (0);
+
+	if (err == ENOENT && func != POOL_SCAN_NONE && cmd == POOL_SCRUB_NORMAL)
 		return (0);
 
 	if (func == POOL_SCAN_SCRUB) {
-		(void) snprintf(msg, sizeof (msg),
-		    dgettext(TEXT_DOMAIN, "cannot scrub %s"), zc.zc_name);
+		if (cmd == POOL_SCRUB_PAUSE) {
+			(void) snprintf(msg, sizeof (msg), dgettext(TEXT_DOMAIN,
+			    "cannot pause scrubbing %s"), zc.zc_name);
+		} else {
+			assert(cmd == POOL_SCRUB_NORMAL);
+			(void) snprintf(msg, sizeof (msg), dgettext(TEXT_DOMAIN,
+			    "cannot scrub %s"), zc.zc_name);
+		}
 	} else if (func == POOL_SCAN_NONE) {
 		(void) snprintf(msg, sizeof (msg),
 		    dgettext(TEXT_DOMAIN, "cannot cancel scrubbing %s"),
@@ -1875,7 +1893,7 @@ zpool_scan(zpool_handle_t *zhp, pool_scan_func_t func)
 		assert(!"unexpected result");
 	}
 
-	if (errno == EBUSY) {
+	if (err == EBUSY) {
 		nvlist_t *nvroot;
 		pool_scan_stat_t *ps = NULL;
 		uint_t psc;
@@ -1884,14 +1902,18 @@ zpool_scan(zpool_handle_t *zhp, pool_scan_func_t func)
 		    ZPOOL_CONFIG_VDEV_TREE, &nvroot) == 0);
 		(void) nvlist_lookup_uint64_array(nvroot,
 		    ZPOOL_CONFIG_SCAN_STATS, (uint64_t **)&ps, &psc);
-		if (ps && ps->pss_func == POOL_SCAN_SCRUB)
-			return (zfs_error(hdl, EZFS_SCRUBBING, msg));
-		else
+		if (ps && ps->pss_func == POOL_SCAN_SCRUB) {
+			if (cmd == POOL_SCRUB_PAUSE)
+				return (zfs_error(hdl, EZFS_SCRUB_PAUSED, msg));
+			else
+				return (zfs_error(hdl, EZFS_SCRUBBING, msg));
+		} else {
 			return (zfs_error(hdl, EZFS_RESILVERING, msg));
-	} else if (errno == ENOENT) {
+		}
+	} else if (err == ENOENT) {
 		return (zfs_error(hdl, EZFS_NO_SCRUB, msg));
 	} else {
-		return (zpool_standard_error(hdl, errno, msg));
+		return (zpool_standard_error(hdl, err, msg));
 	}
 }
 
diff --git a/lib/libzfs/common/libzfs_util.c b/lib/libzfs/common/libzfs_util.c
index b8a16a08d454..6910c1d127d4 100644
--- a/lib/libzfs/common/libzfs_util.c
+++ b/lib/libzfs/common/libzfs_util.c
@@ -24,6 +24,7 @@
  * Copyright (c) 2013, Joyent, Inc. All rights reserved.
  * Copyright (c) 2011, 2015 by Delphix. All rights reserved.
  * Copyright 2016 Igor Kozhukhov <ikozhukhov@gmail.com>
+ * Copyright (c) 2017 Datto Inc.
  */
 
 /*
@@ -219,6 +220,9 @@ libzfs_error_description(libzfs_handle_t *hdl)
 	case EZFS_POSTSPLIT_ONLINE:
 		return (dgettext(TEXT_DOMAIN, "disk was split from this pool "
 		    "into a new one"));
+	case EZFS_SCRUB_PAUSED:
+		return (dgettext(TEXT_DOMAIN, "scrub is paused; "
+		    "use 'zpool scrub' to resume"));
 	case EZFS_SCRUBBING:
 		return (dgettext(TEXT_DOMAIN, "currently scrubbing; "
 		    "use 'zpool scrub -s' to cancel current scrub"));