Multi-modifier protection (MMP)

Add multihost=on|off pool property to control MMP.  When enabled
a new thread writes uberblocks to the last slot in each label, at a
set frequency, to indicate to other hosts the pool is actively imported.
These uberblocks are the last synced uberblock with an updated
timestamp.  Property defaults to off.

During tryimport, find the "best" uberblock (newest txg and timestamp)
repeatedly, checking for change in the found uberblock.  Include the
results of the activity test in the config returned by tryimport.
These results are reported to user in "zpool import".

Allow the user to control the period between MMP writes, and the
duration of the activity test on import, via a new module parameter
zfs_multihost_interval.  The period is specified in milliseconds.  The
activity test duration is calculated from this value, and from the
mmp_delay in the "best" uberblock found initially.

Add a kstat interface to export statistics about Multiple Modifier
Protection (MMP) updates. Include the last synced txg number, the
timestamp, the delay since the last MMP update, the VDEV GUID, the VDEV
label that received the last MMP update, and the VDEV path.  Abbreviated
output below.

$ cat /proc/spl/kstat/zfs/mypool/multihost
31 0 0x01 10 880 105092382393521 105144180101111
txg   timestamp  mmp_delay   vdev_guid   vdev_label vdev_path
20468    261337  250274925   68396651780       3    /dev/sda
20468    261339  252023374   6267402363293     1    /dev/sdc
20468    261340  252000858   6698080955233     1    /dev/sdx
20468    261341  251980635   783892869810      2    /dev/sdy
20468    261342  253385953   8923255792467     3    /dev/sdd
20468    261344  253336622   042125143176      0    /dev/sdab
20468    261345  253310522   1200778101278     2    /dev/sde
20468    261346  253286429   0950576198362     2    /dev/sdt
20468    261347  253261545   96209817917       3    /dev/sds
20468    261349  253238188   8555725937673     3    /dev/sdb

Add a new tunable zfs_multihost_history to specify the number of MMP
updates to store history for. By default it is set to zero meaning that
no MMP statistics are stored.

When using ztest to generate activity, for automated tests of the MMP
function, some test functions interfere with the test.  For example, the
pool is exported to run zdb and then imported again.  Add a new ztest
function, "-M", to alter ztest behavior to prevent this.

Add new tests to verify the new functionality.  Tests provided by
Giuseppe Di Natale.

Reviewed by: Matthew Ahrens <[email protected]>
Reviewed-by: Giuseppe Di Natale <[email protected]>
Reviewed-by: Ned Bass <[email protected]>
Reviewed-by: Andreas Dilger <[email protected]>
Reviewed-by: Brian Behlendorf <[email protected]>
Signed-off-by: Olaf Faaland <[email protected]>
Closes #745
Closes #6279

5 files changed, 161 insertions, 5 deletions

diff --git a/lib/libzfs/libzfs_import.c b/lib/libzfs/libzfs_import.c
index 02264433e..f371d925b 100644
--- a/lib/libzfs/libzfs_import.c
+++ b/lib/libzfs/libzfs_import.c
@@ -2166,6 +2166,80 @@ zpool_search_import(libzfs_handle_t *hdl, importargs_t *import)
 	return (zpool_find_import_impl(hdl, import));
 }
 
+static boolean_t
+pool_match(nvlist_t *cfg, char *tgt)
+{
+	uint64_t v, guid = strtoull(tgt, NULL, 0);
+	char *s;
+
+	if (guid != 0) {
+		if (nvlist_lookup_uint64(cfg, ZPOOL_CONFIG_POOL_GUID, &v) == 0)
+			return (v == guid);
+	} else {
+		if (nvlist_lookup_string(cfg, ZPOOL_CONFIG_POOL_NAME, &s) == 0)
+			return (strcmp(s, tgt) == 0);
+	}
+	return (B_FALSE);
+}
+
+int
+zpool_tryimport(libzfs_handle_t *hdl, char *target, nvlist_t **configp,
+    importargs_t *args)
+{
+	nvlist_t *pools;
+	nvlist_t *match = NULL;
+	nvlist_t *config = NULL;
+	char *name = NULL, *sepp = NULL;
+	char sep = '\0';
+	int count = 0;
+	char *targetdup = strdup(target);
+
+	*configp = NULL;
+
+	if ((sepp = strpbrk(targetdup, "/@")) != NULL) {
+		sep = *sepp;
+		*sepp = '\0';
+	}
+
+	pools = zpool_search_import(hdl, args);
+
+	if (pools != NULL) {
+		nvpair_t *elem = NULL;
+		while ((elem = nvlist_next_nvpair(pools, elem)) != NULL) {
+			VERIFY0(nvpair_value_nvlist(elem, &config));
+			if (pool_match(config, targetdup)) {
+				count++;
+				if (match != NULL) {
+					/* multiple matches found */
+					continue;
+				} else {
+					match = config;
+					name = nvpair_name(elem);
+				}
+			}
+		}
+	}
+
+	if (count == 0) {
+		(void) zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
+		    "no pools found"));
+		free(targetdup);
+		return (ENOENT);
+	}
+
+	if (count > 1) {
+		(void) zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
+		    "%d pools found, use pool GUID\n"), count);
+		free(targetdup);
+		return (EINVAL);
+	}
+
+	*configp = match;
+	free(targetdup);
+
+	return (0);
+}
+
 boolean_t
 find_guid(nvlist_t *nv, uint64_t guid)
 {
diff --git a/lib/libzfs/libzfs_pool.c b/lib/libzfs/libzfs_pool.c
index 746e6a8cc..58d91c8f4 100644
--- a/lib/libzfs/libzfs_pool.c
+++ b/lib/libzfs/libzfs_pool.c
@@ -676,7 +676,14 @@ zpool_valid_proplist(libzfs_handle_t *hdl, const char *poolname,
 				goto error;
 			}
 			break;
-
+		case ZPOOL_PROP_MULTIHOST:
+			if (get_system_hostid() == 0) {
+				zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
+				    "requires a non-zero system hostid"));
+				(void) zfs_error(hdl, EZFS_BADPROP, errbuf);
+				goto error;
+			}
+			break;
 		default:
 			zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
 			    "property '%s'(%d) not defined"), propname, prop);
@@ -1779,6 +1786,7 @@ zpool_import_props(libzfs_handle_t *hdl, nvlist_t *config, const char *newname,
 
 	if (error) {
 		char desc[1024];
+		char aux[256];
 
 		/*
 		 * Dry-run failed, but we print out what success
@@ -1824,6 +1832,47 @@ zpool_import_props(libzfs_handle_t *hdl, nvlist_t *config, const char *newname,
 			(void) zfs_error(hdl, EZFS_BADVERSION, desc);
 			break;
 
+		case EREMOTEIO:
+			if (nv != NULL && nvlist_lookup_nvlist(nv,
+			    ZPOOL_CONFIG_LOAD_INFO, &nvinfo) == 0) {
+				char *hostname = "<unknown>";
+				uint64_t hostid = 0;
+				mmp_state_t mmp_state;
+
+				mmp_state = fnvlist_lookup_uint64(nvinfo,
+				    ZPOOL_CONFIG_MMP_STATE);
+
+				if (nvlist_exists(nvinfo,
+				    ZPOOL_CONFIG_MMP_HOSTNAME))
+					hostname = fnvlist_lookup_string(nvinfo,
+					    ZPOOL_CONFIG_MMP_HOSTNAME);
+
+				if (nvlist_exists(nvinfo,
+				    ZPOOL_CONFIG_MMP_HOSTID))
+					hostid = fnvlist_lookup_uint64(nvinfo,
+					    ZPOOL_CONFIG_MMP_HOSTID);
+
+				if (mmp_state == MMP_STATE_ACTIVE) {
+					(void) snprintf(aux, sizeof (aux),
+					    dgettext(TEXT_DOMAIN, "pool is imp"
+					    "orted on host '%s' (hostid=%lx).\n"
+					    "Export the pool on the other "
+					    "system, then run 'zpool import'."),
+					    hostname, (unsigned long) hostid);
+				} else if (mmp_state == MMP_STATE_NO_HOSTID) {
+					(void) snprintf(aux, sizeof (aux),
+					    dgettext(TEXT_DOMAIN, "pool has "
+					    "the multihost property on and "
+					    "the\nsystem's hostid is not set. "
+					    "Set a unique system hostid with "
+					    "the genhostid(1) command.\n"));
+				}
+
+				(void) zfs_error_aux(hdl, aux);
+			}
+			(void) zfs_error(hdl, EZFS_ACTIVE_POOL, desc);
+			break;
+
 		case EINVAL:
 			(void) zfs_error(hdl, EZFS_INVALCONFIG, desc);
 			break;
@@ -2206,7 +2255,7 @@ zpool_find_vdev(zpool_handle_t *zhp, const char *path, boolean_t *avail_spare,
 }
 
 static int
-vdev_online(nvlist_t *nv)
+vdev_is_online(nvlist_t *nv)
 {
 	uint64_t ival;
 
@@ -2274,7 +2323,7 @@ vdev_get_physpaths(nvlist_t *nv, char *physpath, size_t phypath_size,
 				return (EZFS_INVALCONFIG);
 		}
 
-		if (vdev_online(nv)) {
+		if (vdev_is_online(nv)) {
 			if ((ret = vdev_get_one_physpath(nv, physpath,
 			    phypath_size, rsz)) != 0)
 				return (ret);
diff --git a/lib/libzfs/libzfs_status.c b/lib/libzfs/libzfs_status.c
index d5470f412..05a9afce8 100644
--- a/lib/libzfs/libzfs_status.c
+++ b/lib/libzfs/libzfs_status.c
@@ -64,6 +64,8 @@ static char *zfs_msgid_table[] = {
 	"ZFS-8000-9P",
 	"ZFS-8000-A5",
 	"ZFS-8000-EY",
+	"ZFS-8000-EY",
+	"ZFS-8000-EY",
 	"ZFS-8000-HC",
 	"ZFS-8000-JQ",
 	"ZFS-8000-K4",
@@ -216,6 +218,26 @@ check_status(nvlist_t *config, boolean_t isimport, zpool_errata_t *erratap)
 		return (ZPOOL_STATUS_RESILVERING);
 
 	/*
+	 * The multihost property is set and the pool may be active.
+	 */
+	if (vs->vs_state == VDEV_STATE_CANT_OPEN &&
+	    vs->vs_aux == VDEV_AUX_ACTIVE) {
+		mmp_state_t mmp_state;
+		nvlist_t *nvinfo;
+
+		nvinfo = fnvlist_lookup_nvlist(config, ZPOOL_CONFIG_LOAD_INFO);
+		mmp_state = fnvlist_lookup_uint64(nvinfo,
+		    ZPOOL_CONFIG_MMP_STATE);
+
+		if (mmp_state == MMP_STATE_ACTIVE)
+			return (ZPOOL_STATUS_HOSTID_ACTIVE);
+		else if (mmp_state == MMP_STATE_NO_HOSTID)
+			return (ZPOOL_STATUS_HOSTID_REQUIRED);
+		else
+			return (ZPOOL_STATUS_HOSTID_MISMATCH);
+	}
+
+	/*
 	 * Pool last accessed by another system.
 	 */
 	(void) nvlist_lookup_uint64(config, ZPOOL_CONFIG_HOSTID, &hostid);
@@ -344,8 +366,9 @@ check_status(nvlist_t *config, boolean_t isimport, zpool_errata_t *erratap)
 		if (isimport) {
 			feat = fnvlist_lookup_nvlist(config,
 			    ZPOOL_CONFIG_LOAD_INFO);
-			feat = fnvlist_lookup_nvlist(feat,
-			    ZPOOL_CONFIG_ENABLED_FEAT);
+			if (nvlist_exists(feat, ZPOOL_CONFIG_ENABLED_FEAT))
+				feat = fnvlist_lookup_nvlist(feat,
+				    ZPOOL_CONFIG_ENABLED_FEAT);
 		} else {
 			feat = fnvlist_lookup_nvlist(config,
 			    ZPOOL_CONFIG_FEATURE_STATS);
diff --git a/lib/libzfs/libzfs_util.c b/lib/libzfs/libzfs_util.c
index 30255d643..bc51a76a8 100644
--- a/lib/libzfs/libzfs_util.c
+++ b/lib/libzfs/libzfs_util.c
@@ -261,6 +261,9 @@ libzfs_error_description(libzfs_handle_t *hdl)
 		return (dgettext(TEXT_DOMAIN, "invalid diff data"));
 	case EZFS_POOLREADONLY:
 		return (dgettext(TEXT_DOMAIN, "pool is read-only"));
+	case EZFS_ACTIVE_POOL:
+		return (dgettext(TEXT_DOMAIN, "pool is imported on a "
+		    "different host"));
 	case EZFS_UNKNOWN:
 		return (dgettext(TEXT_DOMAIN, "unknown error"));
 	default:
@@ -423,6 +426,9 @@ zfs_standard_error_fmt(libzfs_handle_t *hdl, int error, const char *fmt, ...)
 		    "pool I/O is currently suspended"));
 		zfs_verror(hdl, EZFS_POOLUNAVAIL, fmt, ap);
 		break;
+	case EREMOTEIO:
+		zfs_verror(hdl, EZFS_ACTIVE_POOL, fmt, ap);
+		break;
 	default:
 		zfs_error_aux(hdl, strerror(error));
 		zfs_verror(hdl, EZFS_UNKNOWN, fmt, ap);
@@ -511,6 +517,9 @@ zpool_standard_error_fmt(libzfs_handle_t *hdl, int error, const char *fmt, ...)
 		    "block size out of range or does not match"));
 		zfs_verror(hdl, EZFS_BADPROP, fmt, ap);
 		break;
+	case EREMOTEIO:
+		zfs_verror(hdl, EZFS_ACTIVE_POOL, fmt, ap);
+		break;
 
 	default:
 		zfs_error_aux(hdl, strerror(error));
diff --git a/lib/libzpool/Makefile.am b/lib/libzpool/Makefile.am
index 1e95f8064..a8c72c98d 100644
--- a/lib/libzpool/Makefile.am
+++ b/lib/libzpool/Makefile.am
@@ -71,6 +71,7 @@ KERNEL_C = \
 	lzjb.c \
 	lz4.c \
 	metaslab.c \
+	mmp.c \
 	multilist.c \
 	pathname.c \
 	range_tree.c \