zpool import progress kstat

When an import requires a long MMP activity check, or when the user
requests pool recovery, the import make take a long time.  The user may
not know why, or be able to tell whether the import is progressing or is
hung.

Add a kstat which lists all imports currently being processed by the
kernel (currently only one at a time is possible, but the kstat allows
for more than one).  The kstat is /proc/spl/kstat/zfs/import_progress.

The kstat contents are as follows:
pool_guid         load_state multihost_secs  max_txg pool_name
16667015954387398 3          15              0       tank3

load_state: the value of spa_load_state
multihost_secs:  seconds until the end of the multihost activity
                 check; if over, or none required, this is 0
max_txg: current spa_load_max_txg, if rewind is occurring

This could be used by outside tools, such as a pacemaker resource agent,
to report import progress, or as a part of manual troubleshooting.  The
zpool import subcommand could also be modified to report this
information.

Reviewed-by: Brian Behlendorf <[email protected]>
Signed-off-by: Olaf Faaland <[email protected]>
Closes #8696 

3 files changed, 242 insertions, 2 deletions

diff --git a/include/sys/spa.h b/include/sys/spa.h
index 343977b30..23434edbc 100644
--- a/include/sys/spa.h
+++ b/include/sys/spa.h
@@ -965,6 +965,14 @@ extern void spa_iostats_trim_add(spa_t *spa, trim_type_t type,
     uint64_t extents_written, uint64_t bytes_written,
     uint64_t extents_skipped, uint64_t bytes_skipped,
     uint64_t extents_failed, uint64_t bytes_failed);
+extern void spa_import_progress_add(spa_t *spa);
+extern void spa_import_progress_remove(uint64_t spa_guid);
+extern int spa_import_progress_set_mmp_check(uint64_t pool_guid,
+    uint64_t mmp_sec_remaining);
+extern int spa_import_progress_set_max_txg(uint64_t pool_guid,
+    uint64_t max_txg);
+extern int spa_import_progress_set_state(uint64_t pool_guid,
+    spa_load_state_t spa_load_state);
 
 /* Pool configuration locks */
 extern int spa_config_tryenter(spa_t *spa, int locks, void *tag, krw_t rw);
diff --git a/module/zfs/spa.c b/module/zfs/spa.c
index 4d26d698e..eb3ff91a0 100644
--- a/module/zfs/spa.c
+++ b/module/zfs/spa.c
@@ -1437,6 +1437,7 @@ spa_unload(spa_t *spa)
 
 	ASSERT(MUTEX_HELD(&spa_namespace_lock));
 
+	spa_import_progress_remove(spa_guid(spa));
 	spa_load_note(spa, "UNLOADING");
 
 	/*
@@ -2375,6 +2376,8 @@ spa_load(spa_t *spa, spa_load_state_t state, spa_import_type_t type)
 	int error;
 
 	spa->spa_load_state = state;
+	(void) spa_import_progress_set_state(spa_guid(spa),
+	    spa_load_state(spa));
 
 	gethrestime(&spa->spa_loaded_ts);
 	error = spa_load_impl(spa, type, &ereport);
@@ -2397,6 +2400,9 @@ spa_load(spa_t *spa, spa_load_state_t state, spa_import_type_t type)
 	spa->spa_load_state = error ? SPA_LOAD_ERROR : SPA_LOAD_NONE;
 	spa->spa_ena = 0;
 
+	(void) spa_import_progress_set_state(spa_guid(spa),
+	    spa_load_state(spa));
+
 	return (error);
 }
 
@@ -2469,6 +2475,7 @@ spa_activity_check_required(spa_t *spa, uberblock_t *ub, nvlist_t *label,
 	 */
 	if (ub->ub_mmp_magic == MMP_MAGIC && ub->ub_mmp_delay == 0)
 		return (B_FALSE);
+
 	/*
 	 * If the tryconfig_ values are nonzero, they are the results of an
 	 * earlier tryimport.  If they all match the uberblock we just found,
@@ -2617,10 +2624,14 @@ spa_activity_check(spa_t *spa, uberblock_t *ub, nvlist_t *config)
 	import_delay = spa_activity_check_duration(spa, ub);
 
 	/* Add a small random factor in case of simultaneous imports (0-25%) */
-	import_expire = gethrtime() + import_delay +
-	    (import_delay * spa_get_random(250) / 1000);
+	import_delay += import_delay * spa_get_random(250) / 1000;
+
+	import_expire = gethrtime() + import_delay;
 
 	while (gethrtime() < import_expire) {
+		(void) spa_import_progress_set_mmp_check(spa_guid(spa),
+		    NSEC2SEC(import_expire - gethrtime()));
+
 		vdev_uberblock_load(rvd, ub, &mmp_label);
 
 		if (txg != ub->ub_txg || timestamp != ub->ub_timestamp ||
@@ -2987,6 +2998,10 @@ spa_ld_select_uberblock(spa_t *spa, spa_import_type_t type)
 		return (spa_vdev_err(rvd, VDEV_AUX_CORRUPT_DATA, ENXIO));
 	}
 
+	if (spa->spa_load_max_txg != UINT64_MAX) {
+		(void) spa_import_progress_set_max_txg(spa_guid(spa),
+		    (u_longlong_t)spa->spa_load_max_txg);
+	}
 	spa_load_note(spa, "using uberblock with txg=%llu",
 	    (u_longlong_t)ub->ub_txg);
 
@@ -3916,6 +3931,8 @@ spa_ld_mos_init(spa_t *spa, spa_import_type_t type)
 	if (error != 0)
 		return (error);
 
+	spa_import_progress_add(spa);
+
 	/*
 	 * Now that we have the vdev tree, try to open each vdev. This involves
 	 * opening the underlying physical device, retrieving its geometry and
@@ -4346,6 +4363,7 @@ spa_load_impl(spa_t *spa, spa_import_type_t type, char **ereport)
 		spa_config_exit(spa, SCL_CONFIG, FTAG);
 	}
 
+	spa_import_progress_remove(spa_guid(spa));
 	spa_load_note(spa, "LOADED");
 
 	return (0);
@@ -4406,6 +4424,7 @@ spa_load_best(spa_t *spa, spa_load_state_t state, uint64_t max_request,
 		 * from previous txgs when spa_load fails.
 		 */
 		ASSERT(spa->spa_import_flags & ZFS_IMPORT_CHECKPOINT);
+		spa_import_progress_remove(spa_guid(spa));
 		return (load_error);
 	}
 
@@ -4417,6 +4436,7 @@ spa_load_best(spa_t *spa, spa_load_state_t state, uint64_t max_request,
 
 	if (rewind_flags & ZPOOL_NEVER_REWIND) {
 		nvlist_free(config);
+		spa_import_progress_remove(spa_guid(spa));
 		return (load_error);
 	}
 
@@ -4459,6 +4479,7 @@ spa_load_best(spa_t *spa, spa_load_state_t state, uint64_t max_request,
 
 	if (state == SPA_LOAD_RECOVER) {
 		ASSERT3P(loadinfo, ==, NULL);
+		spa_import_progress_remove(spa_guid(spa));
 		return (rewind_error);
 	} else {
 		/* Store the rewind info as part of the initial load info */
@@ -4469,6 +4490,7 @@ spa_load_best(spa_t *spa, spa_load_state_t state, uint64_t max_request,
 		fnvlist_free(spa->spa_load_info);
 		spa->spa_load_info = loadinfo;
 
+		spa_import_progress_remove(spa_guid(spa));
 		return (load_error);
 	}
 }
diff --git a/module/zfs/spa_misc.c b/module/zfs/spa_misc.c
index f4497ca1c..e2d1ae3fc 100644
--- a/module/zfs/spa_misc.c
+++ b/module/zfs/spa_misc.c
@@ -2021,6 +2021,214 @@ spa_dirty_data(spa_t *spa)
 
 /*
  * ==========================================================================
+ * SPA Import Progress Routines
+ * ==========================================================================
+ */
+
+typedef struct spa_import_progress {
+	uint64_t		pool_guid;	/* unique id for updates */
+	char			*pool_name;
+	spa_load_state_t	spa_load_state;
+	uint64_t		mmp_sec_remaining;	/* MMP activity check */
+	uint64_t		spa_load_max_txg;	/* rewind txg */
+	procfs_list_node_t	smh_node;
+} spa_import_progress_t;
+
+spa_history_list_t *spa_import_progress_list = NULL;
+
+static int
+spa_import_progress_show_header(struct seq_file *f)
+{
+	seq_printf(f, "%-20s %-14s %-14s %-12s %s\n", "pool_guid",
+	    "load_state", "multihost_secs", "max_txg",
+	    "pool_name");
+	return (0);
+}
+
+static int
+spa_import_progress_show(struct seq_file *f, void *data)
+{
+	spa_import_progress_t *sip = (spa_import_progress_t *)data;
+
+	seq_printf(f, "%-20llu %-14llu %-14llu %-12llu %s\n",
+	    (u_longlong_t)sip->pool_guid, (u_longlong_t)sip->spa_load_state,
+	    (u_longlong_t)sip->mmp_sec_remaining,
+	    (u_longlong_t)sip->spa_load_max_txg,
+	    (sip->pool_name ? sip->pool_name : "-"));
+
+	return (0);
+}
+
+/* Remove oldest elements from list until there are no more than 'size' left */
+static void
+spa_import_progress_truncate(spa_history_list_t *shl, unsigned int size)
+{
+	spa_import_progress_t *sip;
+	while (shl->size > size) {
+		sip = list_remove_head(&shl->procfs_list.pl_list);
+		if (sip->pool_name)
+			spa_strfree(sip->pool_name);
+		kmem_free(sip, sizeof (spa_import_progress_t));
+		shl->size--;
+	}
+
+	IMPLY(size == 0, list_is_empty(&shl->procfs_list.pl_list));
+}
+
+static void
+spa_import_progress_init(void)
+{
+	spa_import_progress_list = kmem_zalloc(sizeof (spa_history_list_t),
+	    KM_SLEEP);
+
+	spa_import_progress_list->size = 0;
+
+	spa_import_progress_list->procfs_list.pl_private =
+	    spa_import_progress_list;
+
+	procfs_list_install("zfs",
+	    "import_progress",
+	    0644,
+	    &spa_import_progress_list->procfs_list,
+	    spa_import_progress_show,
+	    spa_import_progress_show_header,
+	    NULL,
+	    offsetof(spa_import_progress_t, smh_node));
+}
+
+static void
+spa_import_progress_destroy(void)
+{
+	spa_history_list_t *shl = spa_import_progress_list;
+	procfs_list_uninstall(&shl->procfs_list);
+	spa_import_progress_truncate(shl, 0);
+	kmem_free(shl, sizeof (spa_history_list_t));
+	procfs_list_destroy(&shl->procfs_list);
+}
+
+int
+spa_import_progress_set_state(uint64_t pool_guid,
+    spa_load_state_t load_state)
+{
+	spa_history_list_t *shl = spa_import_progress_list;
+	spa_import_progress_t *sip;
+	int error = ENOENT;
+
+	if (shl->size == 0)
+		return (0);
+
+	mutex_enter(&shl->procfs_list.pl_lock);
+	for (sip = list_tail(&shl->procfs_list.pl_list); sip != NULL;
+	    sip = list_prev(&shl->procfs_list.pl_list, sip)) {
+		if (sip->pool_guid == pool_guid) {
+			sip->spa_load_state = load_state;
+			error = 0;
+			break;
+		}
+	}
+	mutex_exit(&shl->procfs_list.pl_lock);
+
+	return (error);
+}
+
+int
+spa_import_progress_set_max_txg(uint64_t pool_guid, uint64_t load_max_txg)
+{
+	spa_history_list_t *shl = spa_import_progress_list;
+	spa_import_progress_t *sip;
+	int error = ENOENT;
+
+	if (shl->size == 0)
+		return (0);
+
+	mutex_enter(&shl->procfs_list.pl_lock);
+	for (sip = list_tail(&shl->procfs_list.pl_list); sip != NULL;
+	    sip = list_prev(&shl->procfs_list.pl_list, sip)) {
+		if (sip->pool_guid == pool_guid) {
+			sip->spa_load_max_txg = load_max_txg;
+			error = 0;
+			break;
+		}
+	}
+	mutex_exit(&shl->procfs_list.pl_lock);
+
+	return (error);
+}
+
+int
+spa_import_progress_set_mmp_check(uint64_t pool_guid,
+    uint64_t mmp_sec_remaining)
+{
+	spa_history_list_t *shl = spa_import_progress_list;
+	spa_import_progress_t *sip;
+	int error = ENOENT;
+
+	if (shl->size == 0)
+		return (0);
+
+	mutex_enter(&shl->procfs_list.pl_lock);
+	for (sip = list_tail(&shl->procfs_list.pl_list); sip != NULL;
+	    sip = list_prev(&shl->procfs_list.pl_list, sip)) {
+		if (sip->pool_guid == pool_guid) {
+			sip->mmp_sec_remaining = mmp_sec_remaining;
+			error = 0;
+			break;
+		}
+	}
+	mutex_exit(&shl->procfs_list.pl_lock);
+
+	return (error);
+}
+
+/*
+ * A new import is in progress, add an entry.
+ */
+void
+spa_import_progress_add(spa_t *spa)
+{
+	spa_history_list_t *shl = spa_import_progress_list;
+	spa_import_progress_t *sip;
+	char *poolname = NULL;
+
+	sip = kmem_zalloc(sizeof (spa_import_progress_t), KM_SLEEP);
+	sip->pool_guid = spa_guid(spa);
+
+	(void) nvlist_lookup_string(spa->spa_config, ZPOOL_CONFIG_POOL_NAME,
+	    &poolname);
+	if (poolname == NULL)
+		poolname = spa_name(spa);
+	sip->pool_name = spa_strdup(poolname);
+	sip->spa_load_state = spa_load_state(spa);
+
+	mutex_enter(&shl->procfs_list.pl_lock);
+	procfs_list_add(&shl->procfs_list, sip);
+	shl->size++;
+	mutex_exit(&shl->procfs_list.pl_lock);
+}
+
+void
+spa_import_progress_remove(uint64_t pool_guid)
+{
+	spa_history_list_t *shl = spa_import_progress_list;
+	spa_import_progress_t *sip;
+
+	mutex_enter(&shl->procfs_list.pl_lock);
+	for (sip = list_tail(&shl->procfs_list.pl_list); sip != NULL;
+	    sip = list_prev(&shl->procfs_list.pl_list, sip)) {
+		if (sip->pool_guid == pool_guid) {
+			if (sip->pool_name)
+				spa_strfree(sip->pool_name);
+			list_remove(&shl->procfs_list.pl_list, sip);
+			shl->size--;
+			kmem_free(sip, sizeof (spa_import_progress_t));
+			break;
+		}
+	}
+	mutex_exit(&shl->procfs_list.pl_lock);
+}
+
+/*
+ * ==========================================================================
  * Initialization and Termination
  * ==========================================================================
  */
@@ -2099,6 +2307,7 @@ spa_init(int mode)
 	l2arc_start();
 	scan_init();
 	qat_init();
+	spa_import_progress_init();
 }
 
 void
@@ -2123,6 +2332,7 @@ spa_fini(void)
 	fm_fini();
 	scan_fini();
 	qat_fini();
+	spa_import_progress_destroy();
 
 	avl_destroy(&spa_namespace_avl);
 	avl_destroy(&spa_spare_avl);