*/
/*
* 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>
#include <sys/zap.h>
#include <sys/zil.h>
#include <sys/vdev_impl.h>
+#include <sys/vdev_initialize.h>
#include <sys/vdev_file.h>
#include <sys/vdev_raidz.h>
#include <sys/metaslab.h>
* definition they must have an existing reference, and will never need
* to lookup a spa_t by name.
*
- * spa_refcount (per-spa refcount_t protected by mutex)
+ * spa_refcount (per-spa zfs_refcount_t protected by mutex)
*
* This reference count keep track of any active users of the spa_t. The
* spa_t cannot be destroyed or freed while this is non-zero. Internally,
* vdev state is protected by spa_vdev_state_enter() / spa_vdev_state_exit().
* Like spa_vdev_enter/exit, these are convenience wrappers -- the actual
* locking is, always, based on spa_namespace_lock and spa_config_lock[].
- *
- * spa_rename() is also implemented within this file since it requires
- * manipulation of the namespace.
*/
static avl_tree_t spa_namespace_avl;
* Check time in milliseconds. This defines the frequency at which we check
* for hung I/O.
*/
-unsigned long zfs_deadman_checktime_ms = 60000ULL;
+unsigned long zfs_deadman_checktime_ms = 60000ULL;
/*
* By default the deadman is enabled.
* 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->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;
+
/*
* ==========================================================================
* SPA config locking
spa_config_lock_t *scl = &spa->spa_config_lock[i];
mutex_init(&scl->scl_lock, NULL, MUTEX_DEFAULT, NULL);
cv_init(&scl->scl_cv, NULL, CV_DEFAULT, NULL);
- refcount_create_untracked(&scl->scl_count);
+ zfs_refcount_create_untracked(&scl->scl_count);
scl->scl_writer = NULL;
scl->scl_write_wanted = 0;
}
spa_config_lock_t *scl = &spa->spa_config_lock[i];
mutex_destroy(&scl->scl_lock);
cv_destroy(&scl->scl_cv);
- refcount_destroy(&scl->scl_count);
+ zfs_refcount_destroy(&scl->scl_count);
ASSERT(scl->scl_writer == NULL);
ASSERT(scl->scl_write_wanted == 0);
}
}
} else {
ASSERT(scl->scl_writer != curthread);
- if (!refcount_is_zero(&scl->scl_count)) {
+ if (!zfs_refcount_is_zero(&scl->scl_count)) {
mutex_exit(&scl->scl_lock);
spa_config_exit(spa, locks & ((1 << i) - 1),
tag);
}
scl->scl_writer = curthread;
}
- (void) refcount_add(&scl->scl_count, tag);
+ (void) zfs_refcount_add(&scl->scl_count, tag);
mutex_exit(&scl->scl_lock);
}
return (1);
}
} else {
ASSERT(scl->scl_writer != curthread);
- while (!refcount_is_zero(&scl->scl_count)) {
+ while (!zfs_refcount_is_zero(&scl->scl_count)) {
scl->scl_write_wanted++;
cv_wait(&scl->scl_cv, &scl->scl_lock);
scl->scl_write_wanted--;
}
scl->scl_writer = curthread;
}
- (void) refcount_add(&scl->scl_count, tag);
+ (void) zfs_refcount_add(&scl->scl_count, tag);
mutex_exit(&scl->scl_lock);
}
ASSERT3U(wlocks_held, <=, locks);
if (!(locks & (1 << i)))
continue;
mutex_enter(&scl->scl_lock);
- ASSERT(!refcount_is_zero(&scl->scl_count));
- if (refcount_remove(&scl->scl_count, tag) == 0) {
+ ASSERT(!zfs_refcount_is_zero(&scl->scl_count));
+ if (zfs_refcount_remove(&scl->scl_count, tag) == 0) {
ASSERT(scl->scl_writer == NULL ||
scl->scl_writer == curthread);
scl->scl_writer = NULL; /* OK in either case */
spa_config_lock_t *scl = &spa->spa_config_lock[i];
if (!(locks & (1 << i)))
continue;
- if ((rw == RW_READER && !refcount_is_zero(&scl->scl_count)) ||
+ if ((rw == RW_READER &&
+ !zfs_refcount_is_zero(&scl->scl_count)) ||
(rw == RW_WRITER && scl->scl_writer == curthread))
locks_held |= 1 << i;
}
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_deadman_ziotime = MSEC2NSEC(zfs_deadman_ziotime_ms);
spa_set_deadman_failmode(spa, zfs_deadman_failmode);
- refcount_create(&spa->spa_refcount);
+ zfs_refcount_create(&spa->spa_refcount);
spa_config_lock_init(spa);
spa_stats_init(spa);
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
ASSERT(MUTEX_HELD(&spa_namespace_lock));
ASSERT(spa->spa_state == POOL_STATE_UNINITIALIZED);
- ASSERT3U(refcount_count(&spa->spa_refcount), ==, 0);
+ ASSERT3U(zfs_refcount_count(&spa->spa_refcount), ==, 0);
nvlist_free(spa->spa_config_splitting);
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);
nvlist_free(spa->spa_feat_stats);
spa_config_set(spa, NULL);
- refcount_destroy(&spa->spa_refcount);
+ zfs_refcount_destroy(&spa->spa_refcount);
spa_stats_destroy(spa);
spa_config_lock_destroy(spa);
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);
void
spa_open_ref(spa_t *spa, void *tag)
{
- ASSERT(refcount_count(&spa->spa_refcount) >= spa->spa_minref ||
+ ASSERT(zfs_refcount_count(&spa->spa_refcount) >= spa->spa_minref ||
MUTEX_HELD(&spa_namespace_lock));
- (void) refcount_add(&spa->spa_refcount, tag);
+ (void) zfs_refcount_add(&spa->spa_refcount, tag);
}
/*
void
spa_close(spa_t *spa, void *tag)
{
- ASSERT(refcount_count(&spa->spa_refcount) > spa->spa_minref ||
+ ASSERT(zfs_refcount_count(&spa->spa_refcount) > spa->spa_minref ||
MUTEX_HELD(&spa_namespace_lock));
- (void) refcount_remove(&spa->spa_refcount, tag);
+ (void) zfs_refcount_remove(&spa->spa_refcount, tag);
}
/*
void
spa_async_close(spa_t *spa, void *tag)
{
- (void) refcount_remove(&spa->spa_refcount, tag);
+ (void) zfs_refcount_remove(&spa->spa_refcount, tag);
}
/*
{
ASSERT(MUTEX_HELD(&spa_namespace_lock));
- return (refcount_count(&spa->spa_refcount) == spa->spa_minref);
+ return (zfs_refcount_count(&spa->spa_refcount) == spa->spa_minref);
}
/*
*/
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 (vd != NULL) {
ASSERT(!vd->vdev_detached || vd->vdev_dtl_sm == NULL);
+ if (vd->vdev_ops->vdev_op_leaf) {
+ mutex_enter(&vd->vdev_initialize_lock);
+ vdev_initialize_stop(vd, VDEV_INITIALIZE_CANCELED);
+ mutex_exit(&vd->vdev_initialize_lock);
+ }
+
spa_config_enter(spa, SCL_ALL, spa, RW_WRITER);
vdev_free(vd);
spa_config_exit(spa, SCL_ALL, spa);
vdev_config_dirty(spa->spa_root_vdev);
}
-/*
- * Rename a spa_t.
- */
-int
-spa_rename(const char *name, const char *newname)
-{
- spa_t *spa;
- int err;
-
- /*
- * Lookup the spa_t and grab the config lock for writing. We need to
- * actually open the pool so that we can sync out the necessary labels.
- * It's OK to call spa_open() with the namespace lock held because we
- * allow recursive calls for other reasons.
- */
- mutex_enter(&spa_namespace_lock);
- if ((err = spa_open(name, &spa, FTAG)) != 0) {
- mutex_exit(&spa_namespace_lock);
- return (err);
- }
-
- spa_config_enter(spa, SCL_ALL, FTAG, RW_WRITER);
-
- avl_remove(&spa_namespace_avl, spa);
- (void) strlcpy(spa->spa_name, newname, sizeof (spa->spa_name));
- avl_add(&spa_namespace_avl, spa);
-
- /*
- * Sync all labels to disk with the new names by marking the root vdev
- * dirty and waiting for it to sync. It will pick up the new pool name
- * during the sync.
- */
- vdev_config_dirty(spa->spa_root_vdev);
-
- spa_config_exit(spa, SCL_ALL, FTAG);
-
- txg_wait_synced(spa->spa_dsl_pool, 0);
-
- /*
- * Sync the updated config cache.
- */
- spa_write_cachefile(spa, B_FALSE, B_TRUE);
-
- spa_close(spa, FTAG);
-
- mutex_exit(&spa_namespace_lock);
-
- return (0);
-}
-
/*
* Return the spa_t associated with given pool_guid, if it exists. If
* device_guid is non-zero, determine whether the pool exists *and* contains
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_dspace);
}
+uint64_t
+spa_get_checkpoint_space(spa_t *spa)
+{
+ return (spa->spa_checkpoint_info.sci_dspace);
+}
+
void
spa_update_dspace(spa_t *spa)
{
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
#endif
fm_init();
- refcount_init();
+ zfs_refcount_init();
unique_init();
range_tree_init();
metaslab_alloc_trace_init();
metaslab_alloc_trace_fini();
range_tree_fini();
unique_fini();
- refcount_fini();
+ zfs_refcount_fini();
fm_fini();
scan_fini();
qat_fini();
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
spa->spa_missing_tvds = missing;
}
-#if defined(_KERNEL) && defined(HAVE_SPL)
+/*
+ * 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>
return (0);
}
+static int
+param_set_slop_shift(const char *buf, zfs_kernel_param_t *kp)
+{
+ unsigned long val;
+ int error;
+
+ error = kstrtoul(buf, 0, &val);
+ if (error)
+ return (SET_ERROR(error));
+
+ if (val < 1 || val > 31)
+ return (SET_ERROR(-EINVAL));
+
+ error = param_set_int(buf, kp);
+ if (error < 0)
+ return (SET_ERROR(error));
+
+ 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_maxdnodesize);
/* Miscellaneous support routines */
-EXPORT_SYMBOL(spa_rename);
EXPORT_SYMBOL(spa_guid_exists);
EXPORT_SYMBOL(spa_strdup);
EXPORT_SYMBOL(spa_strfree);
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(spa_asize_inflation,
"SPA size estimate multiplication factor");
-module_param(spa_slop_shift, int, 0644);
+module_param_call(spa_slop_shift, param_set_slop_shift, param_get_int,
+ &spa_slop_shift, 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
projects / mirror_zfs.git / blobdiff