/*
* 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 2017 Nexenta Systems, Inc.
* Copyright (c) 2014 Integros [integros.com]
* Copyright 2016 Toomas Soome <tsoome@me.com>
* Copyright 2017 Joyent, Inc.
+ * Copyright (c) 2017, Intel Corporation.
*/
#include <sys/zfs_context.h>
#include <sys/zil.h>
#include <sys/dsl_scan.h>
#include <sys/abd.h>
+#include <sys/vdev_initialize.h>
#include <sys/zvol.h>
#include <sys/zfs_ratelimit.h>
+/* default target for number of metaslabs per top-level vdev */
+int zfs_vdev_default_ms_count = 200;
+
+/* minimum number of metaslabs per top-level vdev */
+int zfs_vdev_min_ms_count = 16;
+
+/* practical upper limit of total metaslabs per top-level vdev */
+int zfs_vdev_ms_count_limit = 1ULL << 17;
+
+/* lower limit for metaslab size (512M) */
+int zfs_vdev_default_ms_shift = 29;
+
+/* upper limit for metaslab size (16G) */
+int zfs_vdev_max_ms_shift = 34;
+
+int vdev_validate_skip = B_FALSE;
+
/*
- * When a vdev is added, it will be divided into approximately (but no
- * more than) this number of metaslabs.
+ * Since the DTL space map of a vdev is not expected to have a lot of
+ * entries, we default its block size to 4K.
*/
-int metaslabs_per_vdev = 200;
+int vdev_dtl_sm_blksz = (1 << 12);
/*
- * Rate limit delay events to this many IO delays per second.
+ * Rate limit slow IO (delay) events to this many per second.
*/
-unsigned int zfs_delays_per_second = 20;
+unsigned int zfs_slow_io_events_per_second = 20;
/*
* Rate limit checksum events after this many checksum errors per second.
*/
-unsigned int zfs_checksums_per_second = 20;
+unsigned int zfs_checksum_events_per_second = 20;
/*
* Ignore errors during scrub/resilver. Allows to work around resilver
*/
int zfs_scan_ignore_errors = 0;
-int vdev_validate_skip = B_FALSE;
+/*
+ * vdev-wide space maps that have lots of entries written to them at
+ * the end of each transaction can benefit from a higher I/O bandwidth
+ * (e.g. vdev_obsolete_sm), thus we default their block size to 128K.
+ */
+int vdev_standard_sm_blksz = (1 << 17);
+
+/*
+ * Tunable parameter for debugging or performance analysis. Setting this
+ * will cause pool corruption on power loss if a volatile out-of-order
+ * write cache is enabled.
+ */
+int zfs_nocacheflush = 0;
/*PRINTFLIKE2*/
void
}
zfs_dbgmsg("%*svdev %u: %s%s, guid: %llu, path: %s, %s", indent,
- "", vd->vdev_id, vd->vdev_ops->vdev_op_type,
+ "", (int)vd->vdev_id, vd->vdev_ops->vdev_op_type,
vd->vdev_islog ? " (log)" : "",
(u_longlong_t)vd->vdev_guid,
vd->vdev_path ? vd->vdev_path : "N/A", state);
return (ops);
}
+/* ARGSUSED */
+void
+vdev_default_xlate(vdev_t *vd, const range_seg_t *in, range_seg_t *res)
+{
+ res->rs_start = in->rs_start;
+ res->rs_end = in->rs_end;
+}
+
+/*
+ * Derive the enumerated alloction bias from string input.
+ * String origin is either the per-vdev zap or zpool(1M).
+ */
+static vdev_alloc_bias_t
+vdev_derive_alloc_bias(const char *bias)
+{
+ vdev_alloc_bias_t alloc_bias = VDEV_BIAS_NONE;
+
+ if (strcmp(bias, VDEV_ALLOC_BIAS_LOG) == 0)
+ alloc_bias = VDEV_BIAS_LOG;
+ else if (strcmp(bias, VDEV_ALLOC_BIAS_SPECIAL) == 0)
+ alloc_bias = VDEV_BIAS_SPECIAL;
+ else if (strcmp(bias, VDEV_ALLOC_BIAS_DEDUP) == 0)
+ alloc_bias = VDEV_BIAS_DEDUP;
+
+ return (alloc_bias);
+}
+
/*
* Default asize function: return the MAX of psize with the asize of
* all children. This is what's used by anything other than RAID-Z.
* and checksum events so that we don't overwhelm ZED with thousands
* of events when a disk is acting up.
*/
- zfs_ratelimit_init(&vd->vdev_delay_rl, &zfs_delays_per_second, 1);
- zfs_ratelimit_init(&vd->vdev_checksum_rl, &zfs_checksums_per_second, 1);
+ zfs_ratelimit_init(&vd->vdev_delay_rl, &zfs_slow_io_events_per_second,
+ 1);
+ zfs_ratelimit_init(&vd->vdev_checksum_rl,
+ &zfs_checksum_events_per_second, 1);
list_link_init(&vd->vdev_config_dirty_node);
list_link_init(&vd->vdev_state_dirty_node);
+ list_link_init(&vd->vdev_initialize_node);
mutex_init(&vd->vdev_dtl_lock, NULL, MUTEX_NOLOCKDEP, NULL);
mutex_init(&vd->vdev_stat_lock, NULL, MUTEX_DEFAULT, NULL);
mutex_init(&vd->vdev_probe_lock, NULL, MUTEX_DEFAULT, NULL);
- mutex_init(&vd->vdev_queue_lock, NULL, MUTEX_DEFAULT, NULL);
mutex_init(&vd->vdev_scan_io_queue_lock, NULL, MUTEX_DEFAULT, NULL);
+ mutex_init(&vd->vdev_initialize_lock, NULL, MUTEX_DEFAULT, NULL);
+ mutex_init(&vd->vdev_initialize_io_lock, NULL, MUTEX_DEFAULT, NULL);
+ cv_init(&vd->vdev_initialize_cv, NULL, CV_DEFAULT, NULL);
+ cv_init(&vd->vdev_initialize_io_cv, NULL, CV_DEFAULT, NULL);
for (int t = 0; t < DTL_TYPES; t++) {
vd->vdev_dtl[t] = range_tree_create(NULL, NULL);
vdev_indirect_config_t *vic;
char *tmp = NULL;
int rc;
+ vdev_alloc_bias_t alloc_bias = VDEV_BIAS_NONE;
+ boolean_t top_level = (parent && !parent->vdev_parent);
ASSERT(spa_config_held(spa, SCL_ALL, RW_WRITER) == SCL_ALL);
}
ASSERT(nparity != -1ULL);
+ /*
+ * If creating a top-level vdev, check for allocation classes input
+ */
+ if (top_level && alloctype == VDEV_ALLOC_ADD) {
+ char *bias;
+
+ if (nvlist_lookup_string(nv, ZPOOL_CONFIG_ALLOCATION_BIAS,
+ &bias) == 0) {
+ alloc_bias = vdev_derive_alloc_bias(bias);
+
+ /* spa_vdev_add() expects feature to be enabled */
+ if (spa->spa_load_state != SPA_LOAD_CREATE &&
+ !spa_feature_is_enabled(spa,
+ SPA_FEATURE_ALLOCATION_CLASSES)) {
+ return (SET_ERROR(ENOTSUP));
+ }
+ }
+ }
+
vd = vdev_alloc_common(spa, id, guid, ops);
vic = &vd->vdev_indirect_config;
vd->vdev_islog = islog;
vd->vdev_nparity = nparity;
+ if (top_level && alloc_bias != VDEV_BIAS_NONE)
+ vd->vdev_alloc_bias = alloc_bias;
if (nvlist_lookup_string(nv, ZPOOL_CONFIG_PATH, &vd->vdev_path) == 0)
vd->vdev_path = spa_strdup(vd->vdev_path);
/*
* If we're a top-level vdev, try to load the allocation parameters.
*/
- if (parent && !parent->vdev_parent &&
+ if (top_level &&
(alloctype == VDEV_ALLOC_LOAD || alloctype == VDEV_ALLOC_SPLIT)) {
(void) nvlist_lookup_uint64(nv, ZPOOL_CONFIG_METASLAB_ARRAY,
&vd->vdev_ms_array);
ASSERT0(vd->vdev_top_zap);
}
- if (parent && !parent->vdev_parent && alloctype != VDEV_ALLOC_ATTACH) {
+ if (top_level && alloctype != VDEV_ALLOC_ATTACH) {
ASSERT(alloctype == VDEV_ALLOC_LOAD ||
alloctype == VDEV_ALLOC_ADD ||
alloctype == VDEV_ALLOC_SPLIT ||
alloctype == VDEV_ALLOC_ROOTPOOL);
- vd->vdev_mg = metaslab_group_create(islog ?
- spa_log_class(spa) : spa_normal_class(spa), vd);
+ /* Note: metaslab_group_create() is now deferred */
}
if (vd->vdev_ops->vdev_op_leaf &&
(void) nvlist_lookup_uint64(nv, ZPOOL_CONFIG_RESILVER_TXG,
&vd->vdev_resilver_txg);
+ if (nvlist_exists(nv, ZPOOL_CONFIG_RESILVER_DEFER))
+ vdev_set_deferred_resilver(spa, vd);
+
/*
* In general, when importing a pool we want to ignore the
* persistent fault state, as the diagnosis made on another
vdev_free(vdev_t *vd)
{
spa_t *spa = vd->vdev_spa;
+ ASSERT3P(vd->vdev_initialize_thread, ==, NULL);
/*
* Scan queues are normally destroyed at the end of a scan. If the
ASSERT(vd->vdev_child == NULL);
ASSERT(vd->vdev_guid_sum == vd->vdev_guid);
+ ASSERT(vd->vdev_initialize_thread == NULL);
/*
* Discard allocation state.
rw_destroy(&vd->vdev_indirect_rwlock);
mutex_destroy(&vd->vdev_obsolete_lock);
- mutex_destroy(&vd->vdev_queue_lock);
mutex_destroy(&vd->vdev_dtl_lock);
mutex_destroy(&vd->vdev_stat_lock);
mutex_destroy(&vd->vdev_probe_lock);
mutex_destroy(&vd->vdev_scan_io_queue_lock);
+ mutex_destroy(&vd->vdev_initialize_lock);
+ mutex_destroy(&vd->vdev_initialize_io_lock);
+ cv_destroy(&vd->vdev_initialize_io_cv);
+ cv_destroy(&vd->vdev_initialize_cv);
zfs_ratelimit_fini(&vd->vdev_delay_rl);
zfs_ratelimit_fini(&vd->vdev_checksum_rl);
if (tvd->vdev_mg != NULL)
tvd->vdev_mg->mg_vd = tvd;
+ tvd->vdev_checkpoint_sm = svd->vdev_checkpoint_sm;
+ svd->vdev_checkpoint_sm = NULL;
+
+ tvd->vdev_alloc_bias = svd->vdev_alloc_bias;
+ svd->vdev_alloc_bias = VDEV_BIAS_NONE;
+
tvd->vdev_stat.vs_alloc = svd->vdev_stat.vs_alloc;
tvd->vdev_stat.vs_space = svd->vdev_stat.vs_space;
tvd->vdev_stat.vs_dspace = svd->vdev_stat.vs_dspace;
vdev_free(mvd);
}
+static void
+vdev_metaslab_group_create(vdev_t *vd)
+{
+ spa_t *spa = vd->vdev_spa;
+
+ /*
+ * metaslab_group_create was delayed until allocation bias was available
+ */
+ if (vd->vdev_mg == NULL) {
+ metaslab_class_t *mc;
+
+ if (vd->vdev_islog && vd->vdev_alloc_bias == VDEV_BIAS_NONE)
+ vd->vdev_alloc_bias = VDEV_BIAS_LOG;
+
+ ASSERT3U(vd->vdev_islog, ==,
+ (vd->vdev_alloc_bias == VDEV_BIAS_LOG));
+
+ switch (vd->vdev_alloc_bias) {
+ case VDEV_BIAS_LOG:
+ mc = spa_log_class(spa);
+ break;
+ case VDEV_BIAS_SPECIAL:
+ mc = spa_special_class(spa);
+ break;
+ case VDEV_BIAS_DEDUP:
+ mc = spa_dedup_class(spa);
+ break;
+ default:
+ mc = spa_normal_class(spa);
+ }
+
+ vd->vdev_mg = metaslab_group_create(mc, vd,
+ spa->spa_alloc_count);
+
+ /*
+ * The spa ashift values currently only reflect the
+ * general vdev classes. Class destination is late
+ * binding so ashift checking had to wait until now
+ */
+ if (vd->vdev_top == vd && vd->vdev_ashift != 0 &&
+ mc == spa_normal_class(spa) && vd->vdev_aux == NULL) {
+ if (vd->vdev_ashift > spa->spa_max_ashift)
+ spa->spa_max_ashift = vd->vdev_ashift;
+ if (vd->vdev_ashift < spa->spa_min_ashift)
+ spa->spa_min_ashift = vd->vdev_ashift;
+ }
+ }
+}
+
int
vdev_metaslab_init(vdev_t *vd, uint64_t txg)
{
uint64_t newc = vd->vdev_asize >> vd->vdev_ms_shift;
metaslab_t **mspp;
int error;
+ boolean_t expanding = (oldc != 0);
ASSERT(txg == 0 || spa_config_held(spa, SCL_ALLOC, RW_WRITER));
mspp = vmem_zalloc(newc * sizeof (*mspp), KM_SLEEP);
- if (oldc != 0) {
+ if (expanding) {
bcopy(vd->vdev_ms, mspp, oldc * sizeof (*mspp));
vmem_free(vd->vdev_ms, oldc * sizeof (*mspp));
}
vd->vdev_ms = mspp;
vd->vdev_ms_count = newc;
-
for (m = oldc; m < newc; m++) {
uint64_t object = 0;
}
}
+#ifndef _KERNEL
+ /*
+ * To accomodate zdb_leak_init() fake indirect
+ * metaslabs, we allocate a metaslab group for
+ * indirect vdevs which normally don't have one.
+ */
+ if (vd->vdev_mg == NULL) {
+ ASSERT0(vdev_is_concrete(vd));
+ vdev_metaslab_group_create(vd);
+ }
+#endif
error = metaslab_init(vd->vdev_mg, m, object, txg,
&(vd->vdev_ms[m]));
if (error != 0) {
* the metaslabs since we want to ensure that no new
* allocations are performed on this device.
*/
- if (oldc == 0 && !vd->vdev_removing)
+ if (!expanding && !vd->vdev_removing) {
metaslab_group_activate(vd->vdev_mg);
+ }
if (txg == 0)
spa_config_exit(spa, SCL_ALLOC, FTAG);
void
vdev_metaslab_fini(vdev_t *vd)
{
+ if (vd->vdev_checkpoint_sm != NULL) {
+ ASSERT(spa_feature_is_active(vd->vdev_spa,
+ SPA_FEATURE_POOL_CHECKPOINT));
+ space_map_close(vd->vdev_checkpoint_sm);
+ /*
+ * Even though we close the space map, we need to set its
+ * pointer to NULL. The reason is that vdev_metaslab_fini()
+ * may be called multiple times for certain operations
+ * (i.e. when destroying a pool) so we need to ensure that
+ * this clause never executes twice. This logic is similar
+ * to the one used for the vdev_ms clause below.
+ */
+ vd->vdev_checkpoint_sm = NULL;
+ }
+
if (vd->vdev_ms != NULL) {
uint64_t count = vd->vdev_ms_count;
/*
* Track the min and max ashift values for normal data devices.
+ *
+ * DJB - TBD these should perhaps be tracked per allocation class
+ * (e.g. spa_min_ashift is used to round up post compression buffers)
*/
if (vd->vdev_top == vd && vd->vdev_ashift != 0 &&
- !vd->vdev_islog && vd->vdev_aux == NULL) {
+ vd->vdev_alloc_bias == VDEV_BIAS_NONE &&
+ vd->vdev_aux == NULL) {
if (vd->vdev_ashift > spa->spa_max_ashift)
spa->spa_max_ashift = vd->vdev_ashift;
if (vd->vdev_ashift < spa->spa_min_ashift)
* since this would just restart the scrub we are already doing.
*/
if (vd->vdev_ops->vdev_op_leaf && !spa->spa_scrub_reopen &&
- vdev_resilver_needed(vd, NULL, NULL))
- spa_async_request(spa, SPA_ASYNC_RESILVER);
+ vdev_resilver_needed(vd, NULL, NULL)) {
+ if (dsl_scan_resilvering(spa->spa_dsl_pool) &&
+ spa_feature_is_enabled(spa, SPA_FEATURE_RESILVER_DEFER))
+ vdev_set_deferred_resilver(spa, vd);
+ else
+ spa_async_request(spa, SPA_ASYNC_RESILVER);
+ }
return (0);
}
void
vdev_metaslab_set_size(vdev_t *vd)
{
+ uint64_t asize = vd->vdev_asize;
+ uint64_t ms_count = asize >> zfs_vdev_default_ms_shift;
+ uint64_t ms_shift;
+
/*
- * Aim for roughly metaslabs_per_vdev (default 200) metaslabs per vdev.
+ * There are two dimensions to the metaslab sizing calculation:
+ * the size of the metaslab and the count of metaslabs per vdev.
+ *
+ * The default values used below are a good balance between memory
+ * usage (larger metaslab size means more memory needed for loaded
+ * metaslabs; more metaslabs means more memory needed for the
+ * metaslab_t structs), metaslab load time (larger metaslabs take
+ * longer to load), and metaslab sync time (more metaslabs means
+ * more time spent syncing all of them).
+ *
+ * In general, we aim for zfs_vdev_default_ms_count (200) metaslabs.
+ * The range of the dimensions are as follows:
+ *
+ * 2^29 <= ms_size <= 2^34
+ * 16 <= ms_count <= 131,072
+ *
+ * On the lower end of vdev sizes, we aim for metaslabs sizes of
+ * at least 512MB (2^29) to minimize fragmentation effects when
+ * testing with smaller devices. However, the count constraint
+ * of at least 16 metaslabs will override this minimum size goal.
+ *
+ * On the upper end of vdev sizes, we aim for a maximum metaslab
+ * size of 16GB. However, we will cap the total count to 2^17
+ * metaslabs to keep our memory footprint in check and let the
+ * metaslab size grow from there if that limit is hit.
+ *
+ * The net effect of applying above constrains is summarized below.
+ *
+ * vdev size metaslab count
+ * --------------|-----------------
+ * < 8GB ~16
+ * 8GB - 100GB one per 512MB
+ * 100GB - 3TB ~200
+ * 3TB - 2PB one per 16GB
+ * > 2PB ~131,072
+ * --------------------------------
+ *
+ * Finally, note that all of the above calculate the initial
+ * number of metaslabs. Expanding a top-level vdev will result
+ * in additional metaslabs being allocated making it possible
+ * to exceed the zfs_vdev_ms_count_limit.
*/
- vd->vdev_ms_shift = highbit64(vd->vdev_asize / metaslabs_per_vdev);
- vd->vdev_ms_shift = MAX(vd->vdev_ms_shift, SPA_MAXBLOCKSHIFT);
+
+ if (ms_count < zfs_vdev_min_ms_count)
+ ms_shift = highbit64(asize / zfs_vdev_min_ms_count);
+ else if (ms_count > zfs_vdev_default_ms_count)
+ ms_shift = highbit64(asize / zfs_vdev_default_ms_count);
+ else
+ ms_shift = zfs_vdev_default_ms_shift;
+
+ if (ms_shift < SPA_MAXBLOCKSHIFT) {
+ ms_shift = SPA_MAXBLOCKSHIFT;
+ } else if (ms_shift > zfs_vdev_max_ms_shift) {
+ ms_shift = zfs_vdev_max_ms_shift;
+ /* cap the total count to constrain memory footprint */
+ if ((asize >> ms_shift) > zfs_vdev_ms_count_limit)
+ ms_shift = highbit64(asize / zfs_vdev_ms_count_limit);
+ }
+
+ vd->vdev_ms_shift = ms_shift;
+ ASSERT3U(vd->vdev_ms_shift, >=, SPA_MAXBLOCKSHIFT);
}
void
return (B_FALSE);
mutex_enter(&vd->vdev_dtl_lock);
- if (range_tree_space(rt) != 0)
+ if (!range_tree_is_empty(rt))
dirty = range_tree_contains(rt, txg, size);
mutex_exit(&vd->vdev_dtl_lock);
boolean_t empty;
mutex_enter(&vd->vdev_dtl_lock);
- empty = (range_tree_space(rt) == 0);
+ empty = range_tree_is_empty(rt);
mutex_exit(&vd->vdev_dtl_lock);
return (empty);
if (vd->vdev_state < VDEV_STATE_DEGRADED)
return (B_FALSE);
+ if (vd->vdev_resilver_deferred)
+ return (B_FALSE);
+
if (vd->vdev_resilver_txg == 0 ||
- range_tree_space(vd->vdev_dtl[DTL_MISSING]) == 0)
+ range_tree_is_empty(vd->vdev_dtl[DTL_MISSING]))
return (B_TRUE);
/*
}
/*
- * Reassess DTLs after a config change or scrub completion.
+ * Reassess DTLs after a config change or scrub completion. If txg == 0 no
+ * write operations will be issued to the pool.
*/
void
vdev_dtl_reassess(vdev_t *vd, uint64_t txg, uint64_t scrub_txg, int scrub_done)
* DTLs then reset its resilvering flag and dirty
* the top level so that we persist the change.
*/
- if (vd->vdev_resilver_txg != 0 &&
- range_tree_space(vd->vdev_dtl[DTL_MISSING]) == 0 &&
- range_tree_space(vd->vdev_dtl[DTL_OUTAGE]) == 0) {
+ if (txg != 0 && vd->vdev_resilver_txg != 0 &&
+ range_tree_is_empty(vd->vdev_dtl[DTL_MISSING]) &&
+ range_tree_is_empty(vd->vdev_dtl[DTL_OUTAGE])) {
vd->vdev_resilver_txg = 0;
vdev_config_dirty(vd->vdev_top);
}
ASSERT(vd->vdev_dtl_sm != NULL);
mutex_enter(&vd->vdev_dtl_lock);
-
- /*
- * Now that we've opened the space_map we need to update
- * the in-core DTL.
- */
- space_map_update(vd->vdev_dtl_sm);
-
error = space_map_load(vd->vdev_dtl_sm,
vd->vdev_dtl[DTL_MISSING], SM_ALLOC);
mutex_exit(&vd->vdev_dtl_lock);
return (error);
}
+static void
+vdev_zap_allocation_data(vdev_t *vd, dmu_tx_t *tx)
+{
+ spa_t *spa = vd->vdev_spa;
+ objset_t *mos = spa->spa_meta_objset;
+ vdev_alloc_bias_t alloc_bias = vd->vdev_alloc_bias;
+ const char *string;
+
+ ASSERT(alloc_bias != VDEV_BIAS_NONE);
+
+ string =
+ (alloc_bias == VDEV_BIAS_LOG) ? VDEV_ALLOC_BIAS_LOG :
+ (alloc_bias == VDEV_BIAS_SPECIAL) ? VDEV_ALLOC_BIAS_SPECIAL :
+ (alloc_bias == VDEV_BIAS_DEDUP) ? VDEV_ALLOC_BIAS_DEDUP : NULL;
+
+ ASSERT(string != NULL);
+ VERIFY0(zap_add(mos, vd->vdev_top_zap, VDEV_TOP_ZAP_ALLOCATION_BIAS,
+ 1, strlen(string) + 1, string, tx));
+
+ if (alloc_bias == VDEV_BIAS_SPECIAL || alloc_bias == VDEV_BIAS_DEDUP) {
+ spa_activate_allocation_classes(spa, tx);
+ }
+}
+
void
vdev_destroy_unlink_zap(vdev_t *vd, uint64_t zapobj, dmu_tx_t *tx)
{
}
if (vd == vd->vdev_top && vd->vdev_top_zap == 0) {
vd->vdev_top_zap = vdev_create_link_zap(vd, tx);
+ if (vd->vdev_alloc_bias != VDEV_BIAS_NONE)
+ vdev_zap_allocation_data(vd, tx);
}
}
+
for (uint64_t i = 0; i < vd->vdev_children; i++) {
vdev_construct_zaps(vd->vdev_child[i], tx);
}
if (vd->vdev_dtl_sm == NULL) {
uint64_t new_object;
- new_object = space_map_alloc(mos, tx);
+ new_object = space_map_alloc(mos, vdev_dtl_sm_blksz, tx);
VERIFY3U(new_object, !=, 0);
VERIFY0(space_map_open(&vd->vdev_dtl_sm, mos, new_object,
range_tree_walk(rt, range_tree_add, rtsync);
mutex_exit(&vd->vdev_dtl_lock);
- space_map_truncate(vd->vdev_dtl_sm, tx);
- space_map_write(vd->vdev_dtl_sm, rtsync, SM_ALLOC, tx);
+ space_map_truncate(vd->vdev_dtl_sm, vdev_dtl_sm_blksz, tx);
+ space_map_write(vd->vdev_dtl_sm, rtsync, SM_ALLOC, SM_NO_VDEVID, tx);
range_tree_vacate(rtsync, NULL, NULL);
range_tree_destroy(rtsync);
}
dmu_tx_commit(tx);
-
- mutex_enter(&vd->vdev_dtl_lock);
- space_map_update(vd->vdev_dtl_sm);
- mutex_exit(&vd->vdev_dtl_lock);
}
/*
if (vd->vdev_children == 0) {
mutex_enter(&vd->vdev_dtl_lock);
- if (range_tree_space(vd->vdev_dtl[DTL_MISSING]) != 0 &&
+ if (!range_tree_is_empty(vd->vdev_dtl[DTL_MISSING]) &&
vdev_writeable(vd)) {
thismin = vdev_dtl_min(vd);
return (needed);
}
+/*
+ * Gets the checkpoint space map object from the vdev's ZAP. On success sm_obj
+ * will contain either the checkpoint spacemap object or zero if none exists.
+ * All other errors are returned to the caller.
+ */
+int
+vdev_checkpoint_sm_object(vdev_t *vd, uint64_t *sm_obj)
+{
+ ASSERT0(spa_config_held(vd->vdev_spa, SCL_ALL, RW_WRITER));
+
+ if (vd->vdev_top_zap == 0) {
+ *sm_obj = 0;
+ return (0);
+ }
+
+ int error = zap_lookup(spa_meta_objset(vd->vdev_spa), vd->vdev_top_zap,
+ VDEV_TOP_ZAP_POOL_CHECKPOINT_SM, sizeof (uint64_t), 1, sm_obj);
+ if (error == ENOENT) {
+ *sm_obj = 0;
+ error = 0;
+ }
+
+ return (error);
+}
+
int
vdev_load(vdev_t *vd)
{
vdev_set_deflate_ratio(vd);
+ /*
+ * On spa_load path, grab the allocation bias from our zap
+ */
+ if (vd == vd->vdev_top && vd->vdev_top_zap != 0) {
+ spa_t *spa = vd->vdev_spa;
+ char bias_str[64];
+
+ if (zap_lookup(spa->spa_meta_objset, vd->vdev_top_zap,
+ VDEV_TOP_ZAP_ALLOCATION_BIAS, 1, sizeof (bias_str),
+ bias_str) == 0) {
+ ASSERT(vd->vdev_alloc_bias == VDEV_BIAS_NONE);
+ vd->vdev_alloc_bias = vdev_derive_alloc_bias(bias_str);
+ }
+ }
+
/*
* If this is a top-level vdev, initialize its metaslabs.
*/
if (vd == vd->vdev_top && vdev_is_concrete(vd)) {
+ vdev_metaslab_group_create(vd);
+
if (vd->vdev_ashift == 0 || vd->vdev_asize == 0) {
vdev_set_state(vd, B_FALSE, VDEV_STATE_CANT_OPEN,
VDEV_AUX_CORRUPT_DATA);
VDEV_AUX_CORRUPT_DATA);
return (error);
}
+
+ uint64_t checkpoint_sm_obj;
+ error = vdev_checkpoint_sm_object(vd, &checkpoint_sm_obj);
+ if (error == 0 && checkpoint_sm_obj != 0) {
+ objset_t *mos = spa_meta_objset(vd->vdev_spa);
+ ASSERT(vd->vdev_asize != 0);
+ ASSERT3P(vd->vdev_checkpoint_sm, ==, NULL);
+
+ if ((error = space_map_open(&vd->vdev_checkpoint_sm,
+ mos, checkpoint_sm_obj, 0, vd->vdev_asize,
+ vd->vdev_ashift))) {
+ vdev_dbgmsg(vd, "vdev_load: space_map_open "
+ "failed for checkpoint spacemap (obj %llu) "
+ "[error=%d]",
+ (u_longlong_t)checkpoint_sm_obj, error);
+ return (error);
+ }
+ ASSERT3P(vd->vdev_checkpoint_sm, !=, NULL);
+
+ /*
+ * Since the checkpoint_sm contains free entries
+ * exclusively we can use space_map_allocated() to
+ * indicate the cumulative checkpointed space that
+ * has been freed.
+ */
+ vd->vdev_stat.vs_checkpoint_space =
+ -space_map_allocated(vd->vdev_checkpoint_sm);
+ vd->vdev_spa->spa_checkpoint_info.sci_dspace +=
+ vd->vdev_stat.vs_checkpoint_space;
+ } else if (error != 0) {
+ vdev_dbgmsg(vd, "vdev_load: failed to retrieve "
+ "checkpoint space map object from vdev ZAP "
+ "[error=%d]", error);
+ return (error);
+ }
}
/*
return (error);
}
- uint64_t obsolete_sm_object = vdev_obsolete_sm_object(vd);
- if (obsolete_sm_object != 0) {
+ uint64_t obsolete_sm_object;
+ error = vdev_obsolete_sm_object(vd, &obsolete_sm_object);
+ if (error == 0 && obsolete_sm_object != 0) {
objset_t *mos = vd->vdev_spa->spa_meta_objset;
ASSERT(vd->vdev_asize != 0);
- ASSERT(vd->vdev_obsolete_sm == NULL);
+ ASSERT3P(vd->vdev_obsolete_sm, ==, NULL);
if ((error = space_map_open(&vd->vdev_obsolete_sm, mos,
obsolete_sm_object, 0, vd->vdev_asize, 0))) {
(u_longlong_t)obsolete_sm_object, error);
return (error);
}
- space_map_update(vd->vdev_obsolete_sm);
+ } else if (error != 0) {
+ vdev_dbgmsg(vd, "vdev_load: failed to retrieve obsolete "
+ "space map object from vdev ZAP [error=%d]", error);
+ return (error);
}
return (0);
}
static void
-vdev_remove_empty(vdev_t *vd, uint64_t txg)
+vdev_remove_empty_log(vdev_t *vd, uint64_t txg)
{
spa_t *spa = vd->vdev_spa;
- dmu_tx_t *tx;
+ ASSERT(vd->vdev_islog);
ASSERT(vd == vd->vdev_top);
ASSERT3U(txg, ==, spa_syncing_txg(spa));
- if (vd->vdev_ms != NULL) {
- metaslab_group_t *mg = vd->vdev_mg;
+ dmu_tx_t *tx = dmu_tx_create_assigned(spa_get_dsl(spa), txg);
- metaslab_group_histogram_verify(mg);
- metaslab_class_histogram_verify(mg->mg_class);
-
- for (int m = 0; m < vd->vdev_ms_count; m++) {
- metaslab_t *msp = vd->vdev_ms[m];
-
- if (msp == NULL || msp->ms_sm == NULL)
- continue;
-
- mutex_enter(&msp->ms_lock);
- /*
- * If the metaslab was not loaded when the vdev
- * was removed then the histogram accounting may
- * not be accurate. Update the histogram information
- * here so that we ensure that the metaslab group
- * and metaslab class are up-to-date.
- */
- metaslab_group_histogram_remove(mg, msp);
-
- VERIFY0(space_map_allocated(msp->ms_sm));
- space_map_close(msp->ms_sm);
- msp->ms_sm = NULL;
- mutex_exit(&msp->ms_lock);
- }
-
- metaslab_group_histogram_verify(mg);
- metaslab_class_histogram_verify(mg->mg_class);
- for (int i = 0; i < RANGE_TREE_HISTOGRAM_SIZE; i++)
- ASSERT0(mg->mg_histogram[i]);
- }
-
- tx = dmu_tx_create_assigned(spa_get_dsl(spa), txg);
vdev_destroy_spacemaps(vd, tx);
-
- if (vd->vdev_islog && vd->vdev_top_zap != 0) {
+ if (vd->vdev_top_zap != 0) {
vdev_destroy_unlink_zap(vd, vd->vdev_top_zap, tx);
vd->vdev_top_zap = 0;
}
+
dmu_tx_commit(tx);
}
ASSERT(vdev_is_concrete(vd));
- while ((msp = txg_list_remove(&vd->vdev_ms_list, TXG_CLEAN(txg))))
+ while ((msp = txg_list_remove(&vd->vdev_ms_list, TXG_CLEAN(txg)))
+ != NULL)
metaslab_sync_done(msp, txg);
if (reassess)
spa_t *spa = vd->vdev_spa;
vdev_t *lvd;
metaslab_t *msp;
- dmu_tx_t *tx;
+ ASSERT3U(txg, ==, spa->spa_syncing_txg);
+ dmu_tx_t *tx = dmu_tx_create_assigned(spa->spa_dsl_pool, txg);
if (range_tree_space(vd->vdev_obsolete_segments) > 0) {
- dmu_tx_t *tx;
-
ASSERT(vd->vdev_removing ||
vd->vdev_ops == &vdev_indirect_ops);
- tx = dmu_tx_create_assigned(spa->spa_dsl_pool, txg);
vdev_indirect_sync_obsolete(vd, tx);
- dmu_tx_commit(tx);
/*
* If the vdev is indirect, it can't have dirty
if (vd->vdev_ops == &vdev_indirect_ops) {
ASSERT(txg_list_empty(&vd->vdev_ms_list, txg));
ASSERT(txg_list_empty(&vd->vdev_dtl_list, txg));
+ dmu_tx_commit(tx);
return;
}
}
!vd->vdev_removing) {
ASSERT(vd == vd->vdev_top);
ASSERT0(vd->vdev_indirect_config.vic_mapping_object);
- tx = dmu_tx_create_assigned(spa->spa_dsl_pool, txg);
vd->vdev_ms_array = dmu_object_alloc(spa->spa_meta_objset,
DMU_OT_OBJECT_ARRAY, 0, DMU_OT_NONE, 0, tx);
ASSERT(vd->vdev_ms_array != 0);
vdev_config_dirty(vd);
- dmu_tx_commit(tx);
}
while ((msp = txg_list_remove(&vd->vdev_ms_list, txg)) != NULL) {
vdev_dtl_sync(lvd, txg);
/*
- * Remove the metadata associated with this vdev once it's empty.
- * Note that this is typically used for log/cache device removal;
- * we don't empty toplevel vdevs when removing them. But if
- * a toplevel happens to be emptied, this is not harmful.
+ * If this is an empty log device being removed, destroy the
+ * metadata associated with it.
*/
- if (vd->vdev_stat.vs_alloc == 0 && vd->vdev_removing) {
- vdev_remove_empty(vd, txg);
- }
+ if (vd->vdev_islog && vd->vdev_stat.vs_alloc == 0 && vd->vdev_removing)
+ vdev_remove_empty_log(vd, txg);
(void) txg_list_add(&spa->spa_vdev_txg_list, vd, TXG_CLEAN(txg));
+ dmu_tx_commit(tx);
}
uint64_t
/* XXX - L2ARC 1.0 does not support expansion */
if (!vd->vdev_aux) {
for (pvd = vd; pvd != rvd; pvd = pvd->vdev_parent)
- pvd->vdev_expanding = !!(flags & ZFS_ONLINE_EXPAND);
+ pvd->vdev_expanding = !!((flags & ZFS_ONLINE_EXPAND) ||
+ spa->spa_autoexpand);
+ vd->vdev_expansion_time = gethrestime_sec();
}
vdev_reopen(tvd);
spa_async_request(spa, SPA_ASYNC_CONFIG_UPDATE);
}
+ /* Restart initializing if necessary */
+ mutex_enter(&vd->vdev_initialize_lock);
+ if (vdev_writeable(vd) &&
+ vd->vdev_initialize_thread == NULL &&
+ vd->vdev_initialize_state == VDEV_INITIALIZE_ACTIVE) {
+ (void) vdev_initialize(vd);
+ }
+ mutex_exit(&vd->vdev_initialize_lock);
+
if (wasoffline ||
(oldstate < VDEV_STATE_DEGRADED &&
vd->vdev_state >= VDEV_STATE_DEGRADED))
error = spa_reset_logs(spa);
+ /*
+ * If the log device was successfully reset but has
+ * checkpointed data, do not offline it.
+ */
+ if (error == 0 &&
+ tvd->vdev_checkpoint_sm != NULL) {
+ ASSERT3U(space_map_allocated(
+ tvd->vdev_checkpoint_sm), !=, 0);
+ error = ZFS_ERR_CHECKPOINT_EXISTS;
+ }
+
spa_vdev_state_enter(spa, SCL_ALLOC);
/*
vd->vdev_stat.vs_read_errors = 0;
vd->vdev_stat.vs_write_errors = 0;
vd->vdev_stat.vs_checksum_errors = 0;
+ vd->vdev_stat.vs_slow_ios = 0;
for (int c = 0; c < vd->vdev_children; c++)
vdev_clear(spa, vd->vdev_child[c]);
if (vd != rvd && vdev_writeable(vd->vdev_top))
vdev_state_dirty(vd->vdev_top);
- if (vd->vdev_aux == NULL && !vdev_is_dead(vd))
- spa_async_request(spa, SPA_ASYNC_RESILVER);
+ if (vd->vdev_aux == NULL && !vdev_is_dead(vd)) {
+ if (dsl_scan_resilvering(spa->spa_dsl_pool) &&
+ spa_feature_is_enabled(spa,
+ SPA_FEATURE_RESILVER_DEFER))
+ vdev_set_deferred_resilver(spa, vd);
+ else
+ spa_async_request(spa, SPA_ASYNC_RESILVER);
+ }
spa_event_notify(spa, vd, NULL, ESC_ZFS_VDEV_CLEAR);
}
}
+boolean_t
+vdev_is_spacemap_addressable(vdev_t *vd)
+{
+ if (spa_feature_is_active(vd->vdev_spa, SPA_FEATURE_SPACEMAP_V2))
+ return (B_TRUE);
+
+ /*
+ * If double-word space map entries are not enabled we assume
+ * 47 bits of the space map entry are dedicated to the entry's
+ * offset (see SM_OFFSET_BITS in space_map.h). We then use that
+ * to calculate the maximum address that can be described by a
+ * space map entry for the given device.
+ */
+ uint64_t shift = vd->vdev_ashift + SM_OFFSET_BITS;
+
+ if (shift >= 63) /* detect potential overflow */
+ return (B_TRUE);
+
+ return (vd->vdev_asize < (1ULL << shift));
+}
+
/*
* Get statistics for the given vdev.
*/
vs->vs_timestamp = gethrtime() - vs->vs_timestamp;
vs->vs_state = vd->vdev_state;
vs->vs_rsize = vdev_get_min_asize(vd);
- if (vd->vdev_ops->vdev_op_leaf)
+ if (vd->vdev_ops->vdev_op_leaf) {
vs->vs_rsize += VDEV_LABEL_START_SIZE +
VDEV_LABEL_END_SIZE;
+ /*
+ * Report intializing progress. Since we don't
+ * have the initializing locks held, this is only
+ * an estimate (although a fairly accurate one).
+ */
+ vs->vs_initialize_bytes_done =
+ vd->vdev_initialize_bytes_done;
+ vs->vs_initialize_bytes_est =
+ vd->vdev_initialize_bytes_est;
+ vs->vs_initialize_state = vd->vdev_initialize_state;
+ vs->vs_initialize_action_time =
+ vd->vdev_initialize_action_time;
+ }
/*
* Report expandable space on top-level, non-auxillary devices
* only. The expandable space is reported in terms of metaslab
vd->vdev_max_asize - vd->vdev_asize,
1ULL << tvd->vdev_ms_shift);
}
- vs->vs_esize = vd->vdev_max_asize - vd->vdev_asize;
if (vd->vdev_aux == NULL && vd == vd->vdev_top &&
vdev_is_concrete(vd)) {
- vs->vs_fragmentation = vd->vdev_mg->mg_fragmentation;
+ vs->vs_fragmentation = (vd->vdev_mg != NULL) ?
+ vd->vdev_mg->mg_fragmentation : 0;
}
+ if (vd->vdev_ops->vdev_op_leaf)
+ vs->vs_resilver_deferred = vd->vdev_resilver_deferred;
}
ASSERT(spa_config_held(vd->vdev_spa, SCL_ALL, RW_READER) != 0);
}
}
+int64_t
+vdev_deflated_space(vdev_t *vd, int64_t space)
+{
+ ASSERT((space & (SPA_MINBLOCKSIZE-1)) == 0);
+ ASSERT(vd->vdev_deflate_ratio != 0 || vd->vdev_isl2cache);
+
+ return ((space >> SPA_MINBLOCKSHIFT) * vd->vdev_deflate_ratio);
+}
+
/*
- * Update the in-core space usage stats for this vdev, its metaslab class,
- * and the root vdev.
+ * Update the in-core space usage stats for this vdev and the root vdev.
*/
void
vdev_space_update(vdev_t *vd, int64_t alloc_delta, int64_t defer_delta,
int64_t space_delta)
{
- int64_t dspace_delta = space_delta;
+ int64_t dspace_delta;
spa_t *spa = vd->vdev_spa;
vdev_t *rvd = spa->spa_root_vdev;
- metaslab_group_t *mg = vd->vdev_mg;
- metaslab_class_t *mc = mg ? mg->mg_class : NULL;
ASSERT(vd == vd->vdev_top);
* because the root vdev's psize-to-asize is simply the max of its
* childrens', thus not accurate enough for us.
*/
- ASSERT((dspace_delta & (SPA_MINBLOCKSIZE-1)) == 0);
- ASSERT(vd->vdev_deflate_ratio != 0 || vd->vdev_isl2cache);
- dspace_delta = (dspace_delta >> SPA_MINBLOCKSHIFT) *
- vd->vdev_deflate_ratio;
+ dspace_delta = vdev_deflated_space(vd, space_delta);
mutex_enter(&vd->vdev_stat_lock);
+ /* ensure we won't underflow */
+ if (alloc_delta < 0) {
+ ASSERT3U(vd->vdev_stat.vs_alloc, >=, -alloc_delta);
+ }
+
vd->vdev_stat.vs_alloc += alloc_delta;
vd->vdev_stat.vs_space += space_delta;
vd->vdev_stat.vs_dspace += dspace_delta;
mutex_exit(&vd->vdev_stat_lock);
- if (mc == spa_normal_class(spa)) {
+ /* every class but log contributes to root space stats */
+ if (vd->vdev_mg != NULL && !vd->vdev_islog) {
+ ASSERT(!vd->vdev_isl2cache);
mutex_enter(&rvd->vdev_stat_lock);
rvd->vdev_stat.vs_alloc += alloc_delta;
rvd->vdev_stat.vs_space += space_delta;
rvd->vdev_stat.vs_dspace += dspace_delta;
mutex_exit(&rvd->vdev_stat_lock);
}
-
- if (mc != NULL) {
- ASSERT(rvd == vd->vdev_parent);
- ASSERT(vd->vdev_ms_count != 0);
-
- metaslab_class_space_update(mc,
- alloc_delta, defer_delta, space_delta, dspace_delta);
- }
+ /* Note: metaslab_class_space_update moved to metaslab_space_update */
}
/*
{
ASSERT(vd->vdev_top == vd);
ASSERT(spa_config_held(vd->vdev_spa, SCL_ALL, RW_WRITER) == SCL_ALL);
+ ASSERT(vdev_is_concrete(vd));
vdev_set_deflate_ratio(vd);
if ((vd->vdev_asize >> vd->vdev_ms_shift) > vd->vdev_ms_count &&
vdev_is_concrete(vd)) {
+ vdev_metaslab_group_create(vd);
VERIFY(vdev_metaslab_init(vd, txg) == 0);
vdev_config_dirty(vd);
}
}
}
-#if defined(_KERNEL) && defined(HAVE_SPL)
+void
+vdev_set_deferred_resilver(spa_t *spa, vdev_t *vd)
+{
+ for (uint64_t i = 0; i < vd->vdev_children; i++)
+ vdev_set_deferred_resilver(spa, vd->vdev_child[i]);
+
+ if (!vd->vdev_ops->vdev_op_leaf || !vdev_writeable(vd) ||
+ range_tree_is_empty(vd->vdev_dtl[DTL_MISSING])) {
+ return;
+ }
+
+ vd->vdev_resilver_deferred = B_TRUE;
+ spa->spa_resilver_deferred = B_TRUE;
+}
+
+#if defined(_KERNEL)
EXPORT_SYMBOL(vdev_fault);
EXPORT_SYMBOL(vdev_degrade);
EXPORT_SYMBOL(vdev_online);
EXPORT_SYMBOL(vdev_offline);
EXPORT_SYMBOL(vdev_clear);
/* BEGIN CSTYLED */
-module_param(metaslabs_per_vdev, int, 0644);
-MODULE_PARM_DESC(metaslabs_per_vdev,
- "Divide added vdev into approximately (but no more than) this number "
- "of metaslabs");
+module_param(zfs_vdev_default_ms_count, int, 0644);
+MODULE_PARM_DESC(zfs_vdev_default_ms_count,
+ "Target number of metaslabs per top-level vdev");
-module_param(zfs_delays_per_second, uint, 0644);
-MODULE_PARM_DESC(zfs_delays_per_second, "Rate limit delay events to this many "
- "IO delays per second");
+module_param(zfs_vdev_min_ms_count, int, 0644);
+MODULE_PARM_DESC(zfs_vdev_min_ms_count,
+ "Minimum number of metaslabs per top-level vdev");
-module_param(zfs_checksums_per_second, uint, 0644);
- MODULE_PARM_DESC(zfs_checksums_per_second, "Rate limit checksum events "
+module_param(zfs_vdev_ms_count_limit, int, 0644);
+MODULE_PARM_DESC(zfs_vdev_ms_count_limit,
+ "Practical upper limit of total metaslabs per top-level vdev");
+
+module_param(zfs_slow_io_events_per_second, uint, 0644);
+MODULE_PARM_DESC(zfs_slow_io_events_per_second,
+ "Rate limit slow IO (delay) events to this many per second");
+
+module_param(zfs_checksum_events_per_second, uint, 0644);
+MODULE_PARM_DESC(zfs_checksum_events_per_second, "Rate limit checksum events "
"to this many checksum errors per second (do not set below zed"
"threshold).");
module_param(vdev_validate_skip, int, 0644);
MODULE_PARM_DESC(vdev_validate_skip,
"Bypass vdev_validate()");
+
+module_param(zfs_nocacheflush, int, 0644);
+MODULE_PARM_DESC(zfs_nocacheflush, "Disable cache flushes");
/* END CSTYLED */
#endif
projects / mirror_zfs.git / blobdiff