*/
/*
* Copyright (c) 2005, 2010, Oracle and/or its affiliates. All rights reserved.
- * Copyright (c) 2011, 2015 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/kstat.h>
#include "zfs_prop.h"
#include <sys/zfeature.h>
+#include "qat.h"
/*
* SPA locking
int spa_mode_global;
#ifdef ZFS_DEBUG
-/* Everything except dprintf and spa is on by default in debug builds */
-int zfs_flags = ~(ZFS_DEBUG_DPRINTF | 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
/*
* Expiration time in milliseconds. This value has two meanings. First it is
* used to determine when the spa_deadman() logic should fire. By default the
- * spa_deadman() will fire if spa_sync() has not completed in 1000 seconds.
+ * spa_deadman() will fire if spa_sync() has not completed in 600 seconds.
* Secondly, the value determines if an I/O is considered "hung". Any I/O that
* has not completed in zfs_deadman_synctime_ms is considered "hung" resulting
- * in a system panic.
+ * in one of three behaviors controlled by zfs_deadman_failmode.
+ */
+unsigned long zfs_deadman_synctime_ms = 600000ULL;
+
+/*
+ * This value controls the maximum amount of time zio_wait() will block for an
+ * outstanding IO. By default this is 300 seconds at which point the "hung"
+ * behavior will be applied as described for zfs_deadman_synctime_ms.
*/
-unsigned long zfs_deadman_synctime_ms = 1000000ULL;
+unsigned long zfs_deadman_ziotime_ms = 300000ULL;
+
+/*
+ * Check time in milliseconds. This defines the frequency at which we check
+ * for hung I/O.
+ */
+unsigned long zfs_deadman_checktime_ms = 60000ULL;
/*
* By default the deadman is enabled.
*/
int zfs_deadman_enabled = 1;
+/*
+ * Controls the behavior of the deadman when it detects a "hung" I/O.
+ * Valid values are zfs_deadman_failmode=<wait|continue|panic>.
+ *
+ * wait - Wait for the "hung" I/O (default)
+ * continue - Attempt to recover from a "hung" I/O
+ * panic - Panic the system
+ */
+char *zfs_deadman_failmode = "wait";
+
/*
* The worst case is single-sector max-parity RAID-Z blocks, in which
* case the space requirement is exactly (VDEV_RAIDZ_MAXPARITY + 1)
* 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),
+ * but we never allow it to be more than half the pool size.
*
* See also the comments in zfs_space_check_t.
*/
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;
/*
* ==========================================================================
static void
spa_config_lock_init(spa_t *spa)
{
- int i;
-
- for (i = 0; i < SCL_LOCKS; i++) {
+ for (int i = 0; i < SCL_LOCKS; i++) {
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);
static void
spa_config_lock_destroy(spa_t *spa)
{
- int i;
-
- for (i = 0; i < SCL_LOCKS; i++) {
+ for (int i = 0; i < SCL_LOCKS; i++) {
spa_config_lock_t *scl = &spa->spa_config_lock[i];
mutex_destroy(&scl->scl_lock);
cv_destroy(&scl->scl_cv);
int
spa_config_tryenter(spa_t *spa, int locks, void *tag, krw_t rw)
{
- int i;
-
- for (i = 0; i < SCL_LOCKS; i++) {
+ for (int i = 0; i < SCL_LOCKS; i++) {
spa_config_lock_t *scl = &spa->spa_config_lock[i];
if (!(locks & (1 << i)))
continue;
spa_config_enter(spa_t *spa, int locks, void *tag, krw_t rw)
{
int wlocks_held = 0;
- int i;
ASSERT3U(SCL_LOCKS, <, sizeof (wlocks_held) * NBBY);
- for (i = 0; i < SCL_LOCKS; i++) {
+ for (int i = 0; i < SCL_LOCKS; i++) {
spa_config_lock_t *scl = &spa->spa_config_lock[i];
if (scl->scl_writer == curthread)
wlocks_held |= (1 << i);
(void) refcount_add(&scl->scl_count, tag);
mutex_exit(&scl->scl_lock);
}
- ASSERT(wlocks_held <= locks);
+ ASSERT3U(wlocks_held, <=, locks);
}
void
spa_config_exit(spa_t *spa, int locks, void *tag)
{
- int i;
-
- for (i = SCL_LOCKS - 1; i >= 0; i--) {
+ for (int i = SCL_LOCKS - 1; i >= 0; i--) {
spa_config_lock_t *scl = &spa->spa_config_lock[i];
if (!(locks & (1 << i)))
continue;
int
spa_config_held(spa_t *spa, int locks, krw_t rw)
{
- int i, locks_held = 0;
+ int locks_held = 0;
- for (i = 0; i < SCL_LOCKS; i++) {
+ for (int i = 0; i < SCL_LOCKS; i++) {
spa_config_lock_t *scl = &spa->spa_config_lock[i];
if (!(locks & (1 << i)))
continue;
{
spa_t *spa = arg;
+ /* Disable the deadman if the pool is suspended. */
+ if (spa_suspended(spa))
+ return;
+
zfs_dbgmsg("slow spa_sync: started %llu seconds ago, calls %llu",
(gethrtime() - spa->spa_sync_starttime) / NANOSEC,
++spa->spa_deadman_calls);
if (zfs_deadman_enabled)
- vdev_deadman(spa->spa_root_vdev);
+ vdev_deadman(spa->spa_root_vdev, FTAG);
spa->spa_deadman_tqid = taskq_dispatch_delay(system_delay_taskq,
spa_deadman, spa, TQ_SLEEP, ddi_get_lbolt() +
- NSEC_TO_TICK(spa->spa_deadman_synctime));
+ MSEC_TO_TICK(zfs_deadman_checktime_ms));
}
/*
{
spa_t *spa;
spa_config_dirent_t *dp;
- int t;
- int i;
ASSERT(MUTEX_HELD(&spa_namespace_lock));
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);
cv_init(&spa->spa_scrub_io_cv, NULL, CV_DEFAULT, NULL);
cv_init(&spa->spa_suspend_cv, NULL, CV_DEFAULT, NULL);
- for (t = 0; t < TXG_SIZE; t++)
+ for (int t = 0; t < TXG_SIZE; t++)
bplist_create(&spa->spa_free_bplist[t]);
(void) strlcpy(spa->spa_name, name, sizeof (spa->spa_name));
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);
+ spa_set_deadman_failmode(spa, zfs_deadman_failmode);
refcount_create(&spa->spa_refcount);
spa_config_lock_init(spa);
if (altroot)
spa->spa_root = spa_strdup(altroot);
- avl_create(&spa->spa_alloc_tree, zio_timestamp_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;
* setting SPA_FEATURE_DISABLED for all entries in the feature
* refcount cache.
*/
- for (i = 0; i < SPA_FEATURES; i++) {
+ for (int i = 0; i < SPA_FEATURES; i++) {
spa->spa_feat_refcount_cache[i] = SPA_FEATURE_DISABLED;
}
spa_remove(spa_t *spa)
{
spa_config_dirent_t *dp;
- int t;
ASSERT(MUTEX_HELD(&spa_namespace_lock));
ASSERT(spa->spa_state == POOL_STATE_UNINITIALIZED);
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);
spa_stats_destroy(spa);
spa_config_lock_destroy(spa);
- for (t = 0; t < TXG_SIZE; t++)
+ for (int t = 0; t < TXG_SIZE; t++)
bplist_destroy(&spa->spa_free_bplist[t]);
zio_checksum_templates_free(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_vdev_config_exit(spa_t *spa, vdev_t *vd, uint64_t txg, int error, char *tag)
{
+ ASSERT(MUTEX_HELD(&spa_namespace_lock));
+
int config_changed = B_FALSE;
- ASSERT(MUTEX_HELD(&spa_namespace_lock));
ASSERT(txg > spa_last_synced_txg(spa));
spa->spa_pending_vdev = NULL;
*/
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);
}
/*
spa_vdev_state_exit(spa_t *spa, vdev_t *vd, int error)
{
boolean_t config_changed = B_FALSE;
+ vdev_t *vdev_top;
+
+ if (vd == NULL || vd == spa->spa_root_vdev) {
+ vdev_top = spa->spa_root_vdev;
+ } else {
+ vdev_top = vd->vdev_top;
+ }
if (vd != NULL || error == 0)
- vdev_dtl_reassess(vd ? vd->vdev_top : spa->spa_root_vdev,
- 0, 0, B_FALSE);
+ vdev_dtl_reassess(vdev_top, 0, 0, B_FALSE);
if (vd != NULL) {
- vdev_state_dirty(vd->vdev_top);
+ if (vd != spa->spa_root_vdev)
+ vdev_state_dirty(vdev_top);
+
config_changed = B_TRUE;
spa->spa_config_generation++;
}
*/
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);
ASSERT(range != 0);
+ if (range == 1)
+ return (0);
+
(void) random_get_pseudo_bytes((void *)&r, sizeof (uint64_t));
return (r % range);
* lowercase hexadecimal numbers that don't overflow.
*/
uint64_t
-strtonum(const char *str, char **nptr)
+zfs_strtonum(const char *str, char **nptr)
{
uint64_t val = 0;
char c;
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_syncing_txg);
}
+/*
+ * Return the last txg where data can be dirtied. The final txgs
+ * will be used to just clear out any deferred frees that remain.
+ */
+uint64_t
+spa_final_dirty_txg(spa_t *spa)
+{
+ return (spa->spa_final_txg - TXG_DEFER_SIZE);
+}
+
pool_state_t
spa_state(spa_t *spa)
{
return (spa->spa_freeze_txg);
}
-/* ARGSUSED */
+/*
+ * Return the inflated asize for a logical write in bytes. This is used by the
+ * DMU to calculate the space a logical write will require on disk.
+ * If lsize is smaller than the largest physical block size allocatable on this
+ * pool we use its value instead, since the write will end up using the whole
+ * block anyway.
+ */
uint64_t
-spa_get_asize(spa_t *spa, uint64_t lsize)
+spa_get_worst_case_asize(spa_t *spa, uint64_t lsize)
{
- return (lsize * spa_asize_inflation);
+ if (lsize == 0)
+ return (0); /* No inflation needed */
+ return (MAX(lsize, 1 << spa->spa_max_ashift) * spa_asize_inflation);
}
/*
* Return the amount of slop space in bytes. It is 1/32 of the pool (3.2%),
- * or at least 32MB.
+ * or at least 128MB, unless that would cause it to be more than half the
+ * pool size.
*
* See the comment above spa_slop_shift for details.
*/
uint64_t
-spa_get_slop_space(spa_t *spa) {
+spa_get_slop_space(spa_t *spa)
+{
uint64_t space = spa_get_dspace(spa);
- return (MAX(space >> spa_slop_shift, SPA_MINDEVSIZE >> 1));
+ return (MAX(space >> spa_slop_shift, MIN(space >> 1, spa_min_slop)));
}
uint64_t
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 the failure mode that has been set to this pool. The default
* behavior will be to block all I/Os when a complete failure occurs.
*/
-uint8_t
+uint64_t
spa_get_failmode(spa_t *spa)
{
return (spa->spa_failmode);
boolean_t
spa_suspended(spa_t *spa)
{
- return (spa->spa_suspended);
+ return (spa->spa_suspended != ZIO_SUSPEND_NONE);
}
uint64_t
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 (spa->spa_deadman_synctime);
}
+uint64_t
+spa_deadman_ziotime(spa_t *spa)
+{
+ return (spa->spa_deadman_ziotime);
+}
+
+uint64_t
+spa_get_deadman_failmode(spa_t *spa)
+{
+ return (spa->spa_deadman_failmode);
+}
+
+void
+spa_set_deadman_failmode(spa_t *spa, const char *failmode)
+{
+ if (strcmp(failmode, "wait") == 0)
+ spa->spa_deadman_failmode = ZIO_FAILURE_MODE_WAIT;
+ else if (strcmp(failmode, "continue") == 0)
+ spa->spa_deadman_failmode = ZIO_FAILURE_MODE_CONTINUE;
+ else if (strcmp(failmode, "panic") == 0)
+ spa->spa_deadman_failmode = ZIO_FAILURE_MODE_PANIC;
+ else
+ spa->spa_deadman_failmode = ZIO_FAILURE_MODE_WAIT;
+}
+
uint64_t
dva_get_dsize_sync(spa_t *spa, const dva_t *dva)
{
bp_get_dsize_sync(spa_t *spa, const blkptr_t *bp)
{
uint64_t dsize = 0;
- int d;
- for (d = 0; d < BP_GET_NDVAS(bp); d++)
+ for (int d = 0; d < BP_GET_NDVAS(bp); d++)
dsize += dva_get_dsize_sync(spa, &bp->blk_dva[d]);
return (dsize);
bp_get_dsize(spa_t *spa, const blkptr_t *bp)
{
uint64_t dsize = 0;
- int d;
spa_config_enter(spa, SCL_VDEV, FTAG, RW_READER);
- for (d = 0; d < BP_GET_NDVAS(bp); d++)
+ for (int d = 0; d < BP_GET_NDVAS(bp); d++)
dsize += dva_get_dsize_sync(spa, &bp->blk_dva[d]);
spa_config_exit(spa, SCL_VDEV, FTAG);
return (dsize);
}
+uint64_t
+spa_dirty_data(spa_t *spa)
+{
+ return (spa->spa_dsl_pool->dp_dirty_total);
+}
+
/*
* ==========================================================================
* Initialization and Termination
dmu_init();
zil_init();
vdev_cache_stat_init();
+ vdev_mirror_stat_init();
vdev_raidz_math_init();
vdev_file_init();
zfs_prop_init();
zpool_feature_init();
spa_config_load();
l2arc_start();
+ scan_init();
+ qat_init();
}
void
vdev_file_fini();
vdev_cache_stat_fini();
+ vdev_mirror_stat_fini();
vdev_raidz_math_fini();
zil_fini();
dmu_fini();
unique_fini();
refcount_fini();
fm_fini();
+ scan_fini();
+ qat_fini();
avl_destroy(&spa_namespace_avl);
avl_destroy(&spa_spare_avl);
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
{
/* data not stored on disk */
spa->spa_scan_pass_start = gethrestime_sec();
+ if (dsl_scan_is_paused_scrub(spa->spa_dsl_pool->dp_scan))
+ spa->spa_scan_pass_scrub_pause = spa->spa_scan_pass_start;
+ else
+ spa->spa_scan_pass_scrub_pause = 0;
+ spa->spa_scan_pass_scrub_spent_paused = 0;
spa->spa_scan_pass_exam = 0;
+ spa->spa_scan_pass_issued = 0;
vdev_scan_stat_init(spa->spa_root_vdev);
}
/* data stored on disk */
ps->pss_func = scn->scn_phys.scn_func;
+ ps->pss_state = scn->scn_phys.scn_state;
ps->pss_start_time = scn->scn_phys.scn_start_time;
ps->pss_end_time = scn->scn_phys.scn_end_time;
ps->pss_to_examine = scn->scn_phys.scn_to_examine;
ps->pss_to_process = scn->scn_phys.scn_to_process;
ps->pss_processed = scn->scn_phys.scn_processed;
ps->pss_errors = scn->scn_phys.scn_errors;
- ps->pss_state = scn->scn_phys.scn_state;
/* data not stored on disk */
- ps->pss_pass_start = spa->spa_scan_pass_start;
ps->pss_pass_exam = spa->spa_scan_pass_exam;
+ ps->pss_pass_start = spa->spa_scan_pass_start;
+ ps->pss_pass_scrub_pause = spa->spa_scan_pass_scrub_pause;
+ ps->pss_pass_scrub_spent_paused = spa->spa_scan_pass_scrub_spent_paused;
+ ps->pss_pass_issued = spa->spa_scan_pass_issued;
+ ps->pss_issued =
+ scn->scn_issued_before_pass + spa->spa_scan_pass_issued;
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 (DNODE_MIN_SIZE);
}
-#if defined(_KERNEL) && defined(HAVE_SPL)
+boolean_t
+spa_multihost(spa_t *spa)
+{
+ return (spa->spa_multihost ? B_TRUE : B_FALSE);
+}
+
+unsigned long
+spa_get_hostid(void)
+{
+ unsigned long myhostid;
+
+#ifdef _KERNEL
+ myhostid = zone_get_hostid(NULL);
+#else /* _KERNEL */
+ /*
+ * We're emulating the system's hostid in userland, so
+ * we can't use zone_get_hostid().
+ */
+ (void) ddi_strtoul(hw_serial, NULL, 10, &myhostid);
+#endif /* _KERNEL */
+
+ return (myhostid);
+}
+
+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>
+
+static int
+param_set_deadman_failmode(const char *val, zfs_kernel_param_t *kp)
+{
+ spa_t *spa = NULL;
+ char *p;
+
+ if (val == NULL)
+ return (SET_ERROR(-EINVAL));
+
+ if ((p = strchr(val, '\n')) != NULL)
+ *p = '\0';
+
+ if (strcmp(val, "wait") != 0 && strcmp(val, "continue") != 0 &&
+ strcmp(val, "panic"))
+ return (SET_ERROR(-EINVAL));
+
+ 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_state);
EXPORT_SYMBOL(spa_load_state);
EXPORT_SYMBOL(spa_freeze_txg);
-EXPORT_SYMBOL(spa_get_asize);
EXPORT_SYMBOL(spa_get_dspace);
EXPORT_SYMBOL(spa_update_dspace);
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_PARM_DESC(zfs_deadman_synctime_ms, "Expiration time in milliseconds");
+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_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(zfs_deadman_checktime_ms, ulong, 0644);
+MODULE_PARM_DESC(zfs_deadman_checktime_ms,
+ "Dead I/O check interval in milliseconds");
module_param(zfs_deadman_enabled, int, 0644);
MODULE_PARM_DESC(zfs_deadman_enabled, "Enable deadman timer");
+module_param_call(zfs_deadman_failmode, param_set_deadman_failmode,
+ param_get_charp, &zfs_deadman_failmode, 0644);
+MODULE_PARM_DESC(zfs_deadman_failmode, "Failmode for deadman timer");
+
module_param(spa_asize_inflation, int, 0644);
MODULE_PARM_DESC(spa_asize_inflation,
"SPA size estimate multiplication factor");
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