*/
/*
* Copyright (c) 2005, 2010, Oracle and/or its affiliates. All rights reserved.
- * Copyright (c) 2011, 2017 by Delphix. All rights reserved.
+ * Copyright (c) 2011, 2018 by Delphix. All rights reserved.
* Copyright 2015 Nexenta Systems, Inc. All rights reserved.
* Copyright (c) 2014 Spectra Logic Corporation, All rights reserved.
* Copyright 2013 Saso Kiselkov. All rights reserved.
* Copyright (c) 2017 Datto Inc.
+ * Copyright (c) 2017, Intel Corporation.
*/
#include <sys/zfs_context.h>
int spa_mode_global;
#ifdef ZFS_DEBUG
-int zfs_flags = ~(ZFS_DEBUG_DPRINTF | ZFS_DEBUG_SET_ERROR | ZFS_DEBUG_SPA);
+/*
+ * Everything except dprintf, set_error, spa, and indirect_remap is on
+ * by default in debug builds.
+ */
+int zfs_flags = ~(ZFS_DEBUG_DPRINTF | ZFS_DEBUG_SET_ERROR |
+ ZFS_DEBUG_INDIRECT_REMAP);
#else
int zfs_flags = 0;
#endif
* These are the operations that call dsl_pool_adjustedsize() with the netfree
* argument set to TRUE.
*
+ * Operations that are almost guaranteed to free up space in the absence of
+ * a pool checkpoint can use up to three quarters of the slop space
+ * (e.g zfs destroy).
+ *
* A very restricted set of operations are always permitted, regardless of
* the amount of free space. These are the operations that call
- * dsl_sync_task(ZFS_SPACE_CHECK_NONE), e.g. "zfs destroy". If these
- * operations result in a net increase in the amount of space used,
- * it is possible to run the pool completely out of space, causing it to
- * be permanently read-only.
+ * dsl_sync_task(ZFS_SPACE_CHECK_NONE). If these operations result in a net
+ * increase in the amount of space used, it is possible to run the pool
+ * completely out of space, causing it to be permanently read-only.
*
* Note that on very small pools, the slop space will be larger than
* 3.2%, in an effort to have it be at least spa_min_slop (128MB),
*/
int spa_slop_shift = 5;
uint64_t spa_min_slop = 128 * 1024 * 1024;
+int spa_allocators = 4;
+
+
+/*PRINTFLIKE2*/
+void
+spa_load_failed(spa_t *spa, const char *fmt, ...)
+{
+ va_list adx;
+ char buf[256];
+
+ va_start(adx, fmt);
+ (void) vsnprintf(buf, sizeof (buf), fmt, adx);
+ va_end(adx);
+
+ zfs_dbgmsg("spa_load(%s, config %s): FAILED: %s", spa->spa_name,
+ spa->spa_trust_config ? "trusted" : "untrusted", buf);
+}
+
+/*PRINTFLIKE2*/
+void
+spa_load_note(spa_t *spa, const char *fmt, ...)
+{
+ va_list adx;
+ char buf[256];
+
+ va_start(adx, fmt);
+ (void) vsnprintf(buf, sizeof (buf), fmt, adx);
+ va_end(adx);
+
+ zfs_dbgmsg("spa_load(%s, config %s): %s", spa->spa_name,
+ spa->spa_trust_config ? "trusted" : "untrusted", buf);
+}
+
+/*
+ * By default dedup and user data indirects land in the special class
+ */
+int zfs_ddt_data_is_special = B_TRUE;
+int zfs_user_indirect_is_special = B_TRUE;
+
+/*
+ * The percentage of special class final space reserved for metadata only.
+ * Once we allocate 100 - zfs_special_class_metadata_reserve_pct we only
+ * let metadata into the class.
+ */
+int zfs_special_class_metadata_reserve_pct = 25;
/*
* ==========================================================================
(void) refcount_add(&scl->scl_count, tag);
mutex_exit(&scl->scl_lock);
}
- ASSERT(wlocks_held <= locks);
+ ASSERT3U(wlocks_held, <=, locks);
}
void
mutex_init(&spa->spa_suspend_lock, NULL, MUTEX_DEFAULT, NULL);
mutex_init(&spa->spa_vdev_top_lock, NULL, MUTEX_DEFAULT, NULL);
mutex_init(&spa->spa_feat_stats_lock, NULL, MUTEX_DEFAULT, NULL);
- mutex_init(&spa->spa_alloc_lock, NULL, MUTEX_DEFAULT, NULL);
cv_init(&spa->spa_async_cv, NULL, CV_DEFAULT, NULL);
cv_init(&spa->spa_evicting_os_cv, NULL, CV_DEFAULT, NULL);
spa->spa_load_max_txg = UINT64_MAX;
spa->spa_proc = &p0;
spa->spa_proc_state = SPA_PROC_NONE;
+ spa->spa_trust_config = B_TRUE;
spa->spa_deadman_synctime = MSEC2NSEC(zfs_deadman_synctime_ms);
spa->spa_deadman_ziotime = MSEC2NSEC(zfs_deadman_ziotime_ms);
if (altroot)
spa->spa_root = spa_strdup(altroot);
- avl_create(&spa->spa_alloc_tree, zio_bookmark_compare,
- sizeof (zio_t), offsetof(zio_t, io_alloc_node));
+ spa->spa_alloc_count = spa_allocators;
+ spa->spa_alloc_locks = kmem_zalloc(spa->spa_alloc_count *
+ sizeof (kmutex_t), KM_SLEEP);
+ spa->spa_alloc_trees = kmem_zalloc(spa->spa_alloc_count *
+ sizeof (avl_tree_t), KM_SLEEP);
+ for (int i = 0; i < spa->spa_alloc_count; i++) {
+ mutex_init(&spa->spa_alloc_locks[i], NULL, MUTEX_DEFAULT, NULL);
+ avl_create(&spa->spa_alloc_trees[i], zio_bookmark_compare,
+ sizeof (zio_t), offsetof(zio_t, io_alloc_node));
+ }
/*
* Every pool starts with the default cachefile
KM_SLEEP) == 0);
}
- spa->spa_debug = ((zfs_flags & ZFS_DEBUG_SPA) != 0);
-
spa->spa_min_ashift = INT_MAX;
spa->spa_max_ashift = 0;
kmem_free(dp, sizeof (spa_config_dirent_t));
}
- avl_destroy(&spa->spa_alloc_tree);
+ for (int i = 0; i < spa->spa_alloc_count; i++) {
+ avl_destroy(&spa->spa_alloc_trees[i]);
+ mutex_destroy(&spa->spa_alloc_locks[i]);
+ }
+ kmem_free(spa->spa_alloc_locks, spa->spa_alloc_count *
+ sizeof (kmutex_t));
+ kmem_free(spa->spa_alloc_trees, spa->spa_alloc_count *
+ sizeof (avl_tree_t));
+
list_destroy(&spa->spa_config_list);
nvlist_free(spa->spa_label_features);
cv_destroy(&spa->spa_scrub_io_cv);
cv_destroy(&spa->spa_suspend_cv);
- mutex_destroy(&spa->spa_alloc_lock);
mutex_destroy(&spa->spa_async_lock);
mutex_destroy(&spa->spa_errlist_lock);
mutex_destroy(&spa->spa_errlog_lock);
*/
ASSERT(metaslab_class_validate(spa_normal_class(spa)) == 0);
ASSERT(metaslab_class_validate(spa_log_class(spa)) == 0);
+ ASSERT(metaslab_class_validate(spa_special_class(spa)) == 0);
+ ASSERT(metaslab_class_validate(spa_dedup_class(spa)) == 0);
spa_config_exit(spa, SCL_ALL, spa);
* If the config changed, update the config cache.
*/
if (config_changed)
- spa_config_sync(spa, B_FALSE, B_TRUE);
+ spa_write_cachefile(spa, B_FALSE, B_TRUE);
}
/*
*/
if (config_changed) {
mutex_enter(&spa_namespace_lock);
- spa_config_sync(spa, B_FALSE, B_TRUE);
+ spa_write_cachefile(spa, B_FALSE, B_TRUE);
mutex_exit(&spa_namespace_lock);
}
/*
* Sync the updated config cache.
*/
- spa_config_sync(spa, B_FALSE, B_TRUE);
+ spa_write_cachefile(spa, B_FALSE, B_TRUE);
spa_close(spa, FTAG);
char type[256];
char *checksum = NULL;
char *compress = NULL;
- char *crypt_type = NULL;
if (bp != NULL) {
if (BP_GET_TYPE(bp) & DMU_OT_NEWTYPE) {
(void) strlcpy(type, dmu_ot[BP_GET_TYPE(bp)].ot_name,
sizeof (type));
}
- if (BP_IS_ENCRYPTED(bp)) {
- crypt_type = "encrypted";
- } else if (BP_IS_AUTHENTICATED(bp)) {
- crypt_type = "authenticated";
- } else if (BP_HAS_INDIRECT_MAC_CKSUM(bp)) {
- crypt_type = "indirect-MAC";
- } else {
- crypt_type = "unencrypted";
- }
if (!BP_IS_EMBEDDED(bp)) {
checksum =
zio_checksum_table[BP_GET_CHECKSUM(bp)].ci_name;
}
SNPRINTF_BLKPTR(snprintf, ' ', buf, buflen, bp, type, checksum,
- crypt_type, compress);
+ compress);
}
void
return (val);
}
+void
+spa_activate_allocation_classes(spa_t *spa, dmu_tx_t *tx)
+{
+ /*
+ * We bump the feature refcount for each special vdev added to the pool
+ */
+ ASSERT(spa_feature_is_enabled(spa, SPA_FEATURE_ALLOCATION_CLASSES));
+ spa_feature_incr(spa, SPA_FEATURE_ALLOCATION_CLASSES, tx);
+}
+
/*
* ==========================================================================
* Accessor functions
return (spa->spa_is_initializing);
}
+boolean_t
+spa_indirect_vdevs_loaded(spa_t *spa)
+{
+ return (spa->spa_indirect_vdevs_loaded);
+}
+
blkptr_t *
spa_get_rootblkptr(spa_t *spa)
{
return (spa->spa_dspace);
}
+uint64_t
+spa_get_checkpoint_space(spa_t *spa)
+{
+ return (spa->spa_checkpoint_info.sci_dspace);
+}
+
void
spa_update_dspace(spa_t *spa)
{
spa->spa_dspace = metaslab_class_get_dspace(spa_normal_class(spa)) +
ddt_get_dedup_dspace(spa);
+ if (spa->spa_vdev_removal != NULL) {
+ /*
+ * We can't allocate from the removing device, so
+ * subtract its size. This prevents the DMU/DSL from
+ * filling up the (now smaller) pool while we are in the
+ * middle of removing the device.
+ *
+ * Note that the DMU/DSL doesn't actually know or care
+ * how much space is allocated (it does its own tracking
+ * of how much space has been logically used). So it
+ * doesn't matter that the data we are moving may be
+ * allocated twice (on the old device and the new
+ * device).
+ */
+ spa_config_enter(spa, SCL_VDEV, FTAG, RW_READER);
+ vdev_t *vd =
+ vdev_lookup_top(spa, spa->spa_vdev_removal->svr_vdev_id);
+ spa->spa_dspace -= spa_deflate(spa) ?
+ vd->vdev_stat.vs_dspace : vd->vdev_stat.vs_space;
+ spa_config_exit(spa, SCL_VDEV, FTAG);
+ }
}
/*
return (spa->spa_log_class);
}
+metaslab_class_t *
+spa_special_class(spa_t *spa)
+{
+ return (spa->spa_special_class);
+}
+
+metaslab_class_t *
+spa_dedup_class(spa_t *spa)
+{
+ return (spa->spa_dedup_class);
+}
+
+/*
+ * Locate an appropriate allocation class
+ */
+metaslab_class_t *
+spa_preferred_class(spa_t *spa, uint64_t size, dmu_object_type_t objtype,
+ uint_t level, uint_t special_smallblk)
+{
+ if (DMU_OT_IS_ZIL(objtype)) {
+ if (spa->spa_log_class->mc_groups != 0)
+ return (spa_log_class(spa));
+ else
+ return (spa_normal_class(spa));
+ }
+
+ boolean_t has_special_class = spa->spa_special_class->mc_groups != 0;
+
+ if (DMU_OT_IS_DDT(objtype)) {
+ if (spa->spa_dedup_class->mc_groups != 0)
+ return (spa_dedup_class(spa));
+ else if (has_special_class && zfs_ddt_data_is_special)
+ return (spa_special_class(spa));
+ else
+ return (spa_normal_class(spa));
+ }
+
+ /* Indirect blocks for user data can land in special if allowed */
+ if (level > 0 && (DMU_OT_IS_FILE(objtype) || objtype == DMU_OT_ZVOL)) {
+ if (has_special_class && zfs_user_indirect_is_special)
+ return (spa_special_class(spa));
+ else
+ return (spa_normal_class(spa));
+ }
+
+ if (DMU_OT_IS_METADATA(objtype) || level > 0) {
+ if (has_special_class)
+ return (spa_special_class(spa));
+ else
+ return (spa_normal_class(spa));
+ }
+
+ /*
+ * Allow small file blocks in special class in some cases (like
+ * for the dRAID vdev feature). But always leave a reserve of
+ * zfs_special_class_metadata_reserve_pct exclusively for metadata.
+ */
+ if (DMU_OT_IS_FILE(objtype) &&
+ has_special_class && size < special_smallblk) {
+ metaslab_class_t *special = spa_special_class(spa);
+ uint64_t alloc = metaslab_class_get_alloc(special);
+ uint64_t space = metaslab_class_get_space(special);
+ uint64_t limit =
+ (space * (100 - zfs_special_class_metadata_reserve_pct))
+ / 100;
+
+ if (alloc < limit)
+ return (special);
+ }
+
+ return (spa_normal_class(spa));
+}
+
void
spa_evicting_os_register(spa_t *spa, objset_t *os)
{
return (dsize);
}
+uint64_t
+spa_dirty_data(spa_t *spa)
+{
+ return (spa->spa_dsl_pool->dp_dirty_total);
+}
+
/*
* ==========================================================================
* Initialization and Termination
boolean_t
spa_writeable(spa_t *spa)
{
- return (!!(spa->spa_mode & FWRITE));
+ return (!!(spa->spa_mode & FWRITE) && spa->spa_trust_config);
}
/*
boolean_t
spa_has_pending_synctask(spa_t *spa)
{
- return (!txg_all_lists_empty(&spa->spa_dsl_pool->dp_sync_tasks));
+ return (!txg_all_lists_empty(&spa->spa_dsl_pool->dp_sync_tasks) ||
+ !txg_all_lists_empty(&spa->spa_dsl_pool->dp_early_sync_tasks));
}
int
return (0);
}
-boolean_t
-spa_debug_enabled(spa_t *spa)
-{
- return (spa->spa_debug);
-}
-
int
spa_maxblocksize(spa_t *spa)
{
return (SPA_OLD_MAXBLOCKSIZE);
}
+
+/*
+ * Returns the txg that the last device removal completed. No indirect mappings
+ * have been added since this txg.
+ */
+uint64_t
+spa_get_last_removal_txg(spa_t *spa)
+{
+ uint64_t vdevid;
+ uint64_t ret = -1ULL;
+
+ spa_config_enter(spa, SCL_VDEV, FTAG, RW_READER);
+ /*
+ * sr_prev_indirect_vdev is only modified while holding all the
+ * config locks, so it is sufficient to hold SCL_VDEV as reader when
+ * examining it.
+ */
+ vdevid = spa->spa_removing_phys.sr_prev_indirect_vdev;
+
+ while (vdevid != -1ULL) {
+ vdev_t *vd = vdev_lookup_top(spa, vdevid);
+ vdev_indirect_births_t *vib = vd->vdev_indirect_births;
+
+ ASSERT3P(vd->vdev_ops, ==, &vdev_indirect_ops);
+
+ /*
+ * If the removal did not remap any data, we don't care.
+ */
+ if (vdev_indirect_births_count(vib) != 0) {
+ ret = vdev_indirect_births_last_entry_txg(vib);
+ break;
+ }
+
+ vdevid = vd->vdev_indirect_config.vic_prev_indirect_vdev;
+ }
+ spa_config_exit(spa, SCL_VDEV, FTAG);
+
+ IMPLY(ret != -1ULL,
+ spa_feature_is_active(spa, SPA_FEATURE_DEVICE_REMOVAL));
+
+ return (ret);
+}
+
int
spa_maxdnodesize(spa_t *spa)
{
return (myhostid);
}
-#if defined(_KERNEL) && defined(HAVE_SPL)
+boolean_t
+spa_trust_config(spa_t *spa)
+{
+ return (spa->spa_trust_config);
+}
+
+uint64_t
+spa_missing_tvds_allowed(spa_t *spa)
+{
+ return (spa->spa_missing_tvds_allowed);
+}
+
+void
+spa_set_missing_tvds(spa_t *spa, uint64_t missing)
+{
+ spa->spa_missing_tvds = missing;
+}
+
+/*
+ * Return the pool state string ("ONLINE", "DEGRADED", "SUSPENDED", etc).
+ */
+const char *
+spa_state_to_name(spa_t *spa)
+{
+ vdev_state_t state = spa->spa_root_vdev->vdev_state;
+ vdev_aux_t aux = spa->spa_root_vdev->vdev_stat.vs_aux;
+
+ if (spa_suspended(spa) &&
+ (spa_get_failmode(spa) != ZIO_FAILURE_MODE_CONTINUE))
+ return ("SUSPENDED");
+
+ switch (state) {
+ case VDEV_STATE_CLOSED:
+ case VDEV_STATE_OFFLINE:
+ return ("OFFLINE");
+ case VDEV_STATE_REMOVED:
+ return ("REMOVED");
+ case VDEV_STATE_CANT_OPEN:
+ if (aux == VDEV_AUX_CORRUPT_DATA || aux == VDEV_AUX_BAD_LOG)
+ return ("FAULTED");
+ else if (aux == VDEV_AUX_SPLIT_POOL)
+ return ("SPLIT");
+ else
+ return ("UNAVAIL");
+ case VDEV_STATE_FAULTED:
+ return ("FAULTED");
+ case VDEV_STATE_DEGRADED:
+ return ("DEGRADED");
+ case VDEV_STATE_HEALTHY:
+ return ("ONLINE");
+ default:
+ break;
+ }
+
+ return ("UNKNOWN");
+}
+
+boolean_t
+spa_top_vdevs_spacemap_addressable(spa_t *spa)
+{
+ vdev_t *rvd = spa->spa_root_vdev;
+ for (uint64_t c = 0; c < rvd->vdev_children; c++) {
+ if (!vdev_is_spacemap_addressable(rvd->vdev_child[c]))
+ return (B_FALSE);
+ }
+ return (B_TRUE);
+}
+
+boolean_t
+spa_has_checkpoint(spa_t *spa)
+{
+ return (spa->spa_checkpoint_txg != 0);
+}
+
+boolean_t
+spa_importing_readonly_checkpoint(spa_t *spa)
+{
+ return ((spa->spa_import_flags & ZFS_IMPORT_CHECKPOINT) &&
+ spa->spa_mode == FREAD);
+}
+
+uint64_t
+spa_min_claim_txg(spa_t *spa)
+{
+ uint64_t checkpoint_txg = spa->spa_uberblock.ub_checkpoint_txg;
+
+ if (checkpoint_txg != 0)
+ return (checkpoint_txg + 1);
+
+ return (spa->spa_first_txg);
+}
+
+/*
+ * If there is a checkpoint, async destroys may consume more space from
+ * the pool instead of freeing it. In an attempt to save the pool from
+ * getting suspended when it is about to run out of space, we stop
+ * processing async destroys.
+ */
+boolean_t
+spa_suspend_async_destroy(spa_t *spa)
+{
+ dsl_pool_t *dp = spa_get_dsl(spa);
+
+ uint64_t unreserved = dsl_pool_unreserved_space(dp,
+ ZFS_SPACE_CHECK_EXTRA_RESERVED);
+ uint64_t used = dsl_dir_phys(dp->dp_root_dir)->dd_used_bytes;
+ uint64_t avail = (unreserved > used) ? (unreserved - used) : 0;
+
+ if (spa_has_checkpoint(spa) && avail == 0)
+ return (B_TRUE);
+
+ return (B_FALSE);
+}
+
+#if defined(_KERNEL)
#include <linux/mod_compat.h>
strcmp(val, "panic"))
return (SET_ERROR(-EINVAL));
- mutex_enter(&spa_namespace_lock);
- while ((spa = spa_next(spa)) != NULL)
- spa_set_deadman_failmode(spa, val);
- mutex_exit(&spa_namespace_lock);
+ if (spa_mode_global != 0) {
+ mutex_enter(&spa_namespace_lock);
+ while ((spa = spa_next(spa)) != NULL)
+ spa_set_deadman_failmode(spa, val);
+ mutex_exit(&spa_namespace_lock);
+ }
return (param_set_charp(val, kp));
}
+static int
+param_set_deadman_ziotime(const char *val, zfs_kernel_param_t *kp)
+{
+ spa_t *spa = NULL;
+ int error;
+
+ error = param_set_ulong(val, kp);
+ if (error < 0)
+ return (SET_ERROR(error));
+
+ if (spa_mode_global != 0) {
+ mutex_enter(&spa_namespace_lock);
+ while ((spa = spa_next(spa)) != NULL)
+ spa->spa_deadman_ziotime =
+ MSEC2NSEC(zfs_deadman_ziotime_ms);
+ mutex_exit(&spa_namespace_lock);
+ }
+
+ return (0);
+}
+
+static int
+param_set_deadman_synctime(const char *val, zfs_kernel_param_t *kp)
+{
+ spa_t *spa = NULL;
+ int error;
+
+ error = param_set_ulong(val, kp);
+ if (error < 0)
+ return (SET_ERROR(error));
+
+ if (spa_mode_global != 0) {
+ mutex_enter(&spa_namespace_lock);
+ while ((spa = spa_next(spa)) != NULL)
+ spa->spa_deadman_synctime =
+ MSEC2NSEC(zfs_deadman_synctime_ms);
+ mutex_exit(&spa_namespace_lock);
+ }
+
+ return (0);
+}
+
/* Namespace manipulation */
EXPORT_SYMBOL(spa_lookup);
EXPORT_SYMBOL(spa_add);
EXPORT_SYMBOL(spa_deflate);
EXPORT_SYMBOL(spa_normal_class);
EXPORT_SYMBOL(spa_log_class);
+EXPORT_SYMBOL(spa_special_class);
+EXPORT_SYMBOL(spa_preferred_class);
EXPORT_SYMBOL(spa_max_replication);
EXPORT_SYMBOL(spa_prev_software_version);
EXPORT_SYMBOL(spa_get_failmode);
EXPORT_SYMBOL(spa_writeable);
EXPORT_SYMBOL(spa_mode);
EXPORT_SYMBOL(spa_namespace_lock);
+EXPORT_SYMBOL(spa_trust_config);
+EXPORT_SYMBOL(spa_missing_tvds_allowed);
+EXPORT_SYMBOL(spa_set_missing_tvds);
+EXPORT_SYMBOL(spa_state_to_name);
+EXPORT_SYMBOL(spa_importing_readonly_checkpoint);
+EXPORT_SYMBOL(spa_min_claim_txg);
+EXPORT_SYMBOL(spa_suspend_async_destroy);
+EXPORT_SYMBOL(spa_has_checkpoint);
+EXPORT_SYMBOL(spa_top_vdevs_spacemap_addressable);
/* BEGIN CSTYLED */
module_param(zfs_flags, uint, 0644);
MODULE_PARM_DESC(zfs_free_leak_on_eio,
"Set to ignore IO errors during free and permanently leak the space");
-module_param(zfs_deadman_synctime_ms, ulong, 0644);
+module_param_call(zfs_deadman_synctime_ms, param_set_deadman_synctime,
+ param_get_ulong, &zfs_deadman_synctime_ms, 0644);
MODULE_PARM_DESC(zfs_deadman_synctime_ms,
"Pool sync expiration time in milliseconds");
-module_param(zfs_deadman_ziotime_ms, ulong, 0644);
+module_param_call(zfs_deadman_ziotime_ms, param_set_deadman_ziotime,
+ param_get_ulong, &zfs_deadman_ziotime_ms, 0644);
MODULE_PARM_DESC(zfs_deadman_ziotime_ms,
"IO expiration time in milliseconds");
module_param(spa_slop_shift, int, 0644);
MODULE_PARM_DESC(spa_slop_shift, "Reserved free space in pool");
+
+module_param(zfs_ddt_data_is_special, int, 0644);
+MODULE_PARM_DESC(zfs_ddt_data_is_special,
+ "Place DDT data into the special class");
+
+module_param(zfs_user_indirect_is_special, int, 0644);
+MODULE_PARM_DESC(zfs_user_indirect_is_special,
+ "Place user data indirect blocks into the special class");
/* END CSTYLED */
#endif