Implemented zpool scrub pause/resume

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.

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.

Reviewed by: Matthew Ahrens <[email protected]>
Reviewed by: Thomas Caputi <[email protected]>
Reviewed-by: Serapheim Dimitropoulos <[email protected]>
Reviewed-by: Brian Behlendorf <[email protected]>
Signed-off-by: Alek Pinchuk <[email protected]>
Closes #6167

2 files changed, 36 insertions, 11 deletions

diff --git a/lib/libzfs/libzfs_pool.c b/lib/libzfs/libzfs_pool.c
index f36c65fda..746e6a8cc 100644
--- a/lib/libzfs/libzfs_pool.c
+++ b/lib/libzfs/libzfs_pool.c
@@ -1898,22 +1898,39 @@ 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"),
@@ -1922,7 +1939,7 @@ 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;
@@ -1931,14 +1948,18 @@ 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/libzfs_util.c b/lib/libzfs/libzfs_util.c
index 1fb7b5ee5..30255d643 100644
--- a/lib/libzfs/libzfs_util.c
+++ b/lib/libzfs/libzfs_util.c
@@ -24,6 +24,7 @@
  * Copyright (c) 2013, Joyent, Inc. All rights reserved.
  * Copyright (c) 2011, 2014 by Delphix. All rights reserved.
  * Copyright 2016 Igor Kozhukhov <[email protected]>
+ * Copyright (c) 2017 Datto Inc.
  */
 
 /*
@@ -246,6 +247,9 @@ 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"));