/*
* 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/zvol.h>
#include <sys/zfs_ratelimit.h>
+/* target number of metaslabs per top-level vdev */
+int vdev_max_ms_count = 200;
+
+/* minimum number of metaslabs per top-level vdev */
+int vdev_min_ms_count = 16;
+
+/* practical upper limit of total metaslabs per top-level vdev */
+int vdev_ms_count_limit = 1ULL << 17;
+
+/* lower limit for metaslab size (512M) */
+int vdev_default_ms_shift = 29;
+
+/* upper limit for metaslab size (256G) */
+int vdev_max_ms_shift = 38;
+
+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.
*/
int zfs_scan_ignore_errors = 0;
+/*
+ * 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);
+
+/*PRINTFLIKE2*/
+void
+vdev_dbgmsg(vdev_t *vd, const char *fmt, ...)
+{
+ va_list adx;
+ char buf[256];
+
+ va_start(adx, fmt);
+ (void) vsnprintf(buf, sizeof (buf), fmt, adx);
+ va_end(adx);
+
+ if (vd->vdev_path != NULL) {
+ zfs_dbgmsg("%s vdev '%s': %s", vd->vdev_ops->vdev_op_type,
+ vd->vdev_path, buf);
+ } else {
+ zfs_dbgmsg("%s-%llu vdev (guid %llu): %s",
+ vd->vdev_ops->vdev_op_type,
+ (u_longlong_t)vd->vdev_id,
+ (u_longlong_t)vd->vdev_guid, buf);
+ }
+}
+
+void
+vdev_dbgmsg_print_tree(vdev_t *vd, int indent)
+{
+ char state[20];
+
+ if (vd->vdev_ishole || vd->vdev_ops == &vdev_missing_ops) {
+ zfs_dbgmsg("%*svdev %u: %s", indent, "", vd->vdev_id,
+ vd->vdev_ops->vdev_op_type);
+ return;
+ }
+
+ switch (vd->vdev_state) {
+ case VDEV_STATE_UNKNOWN:
+ (void) snprintf(state, sizeof (state), "unknown");
+ break;
+ case VDEV_STATE_CLOSED:
+ (void) snprintf(state, sizeof (state), "closed");
+ break;
+ case VDEV_STATE_OFFLINE:
+ (void) snprintf(state, sizeof (state), "offline");
+ break;
+ case VDEV_STATE_REMOVED:
+ (void) snprintf(state, sizeof (state), "removed");
+ break;
+ case VDEV_STATE_CANT_OPEN:
+ (void) snprintf(state, sizeof (state), "can't open");
+ break;
+ case VDEV_STATE_FAULTED:
+ (void) snprintf(state, sizeof (state), "faulted");
+ break;
+ case VDEV_STATE_DEGRADED:
+ (void) snprintf(state, sizeof (state), "degraded");
+ break;
+ case VDEV_STATE_HEALTHY:
+ (void) snprintf(state, sizeof (state), "healthy");
+ break;
+ default:
+ (void) snprintf(state, sizeof (state), "<state %u>",
+ (uint_t)vd->vdev_state);
+ }
+
+ zfs_dbgmsg("%*svdev %u: %s%s, guid: %llu, path: %s, %s", indent,
+ "", (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);
+
+ for (uint64_t i = 0; i < vd->vdev_children; i++)
+ vdev_dbgmsg_print_tree(vd->vdev_child[i], indent + 2);
+}
+
/*
* Virtual device management.
*/
return (ops);
}
+/*
+ * 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.
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 &&
ZPOOL_CONFIG_AUX_STATE, &aux) == 0 &&
strcmp(aux, "external") == 0)
vd->vdev_label_aux = VDEV_AUX_EXTERNAL;
+ else
+ vd->vdev_faulted = 0ULL;
}
}
}
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;
error = dmu_read(mos, vd->vdev_ms_array,
m * sizeof (uint64_t), sizeof (uint64_t), &object,
DMU_READ_PREFETCH);
- if (error)
+ if (error != 0) {
+ vdev_dbgmsg(vd, "unable to read the metaslab "
+ "array [error=%d]", error);
return (error);
+ }
}
+#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)
+ if (error != 0) {
+ vdev_dbgmsg(vd, "metaslab_init failed [error=%d]",
+ error);
return (error);
+ }
}
if (txg == 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;
zio->io_error = 0;
} else {
ASSERT(zio->io_error != 0);
- zfs_dbgmsg("failed probe on vdev %llu",
- (longlong_t)vd->vdev_id);
+ vdev_dbgmsg(vd, "failed probe");
zfs_ereport_post(FM_EREPORT_ZFS_PROBE_FAILURE,
spa, vd, NULL, NULL, 0, 0);
zio->io_error = SET_ERROR(ENXIO);
vd->vdev_stat.vs_aux != VDEV_AUX_OPEN_FAILED)
vd->vdev_removed = B_FALSE;
- vdev_set_state(vd, B_TRUE, VDEV_STATE_CANT_OPEN,
- vd->vdev_stat.vs_aux);
+ if (vd->vdev_stat.vs_aux == VDEV_AUX_CHILDREN_OFFLINE) {
+ vdev_set_state(vd, B_TRUE, VDEV_STATE_OFFLINE,
+ vd->vdev_stat.vs_aux);
+ } else {
+ vdev_set_state(vd, B_TRUE, VDEV_STATE_CANT_OPEN,
+ vd->vdev_stat.vs_aux);
+ }
return (error);
}
return (error);
}
- if (vd->vdev_top == vd && vd->vdev_ashift != 0 &&
- !vd->vdev_isl2cache && !vd->vdev_islog) {
- 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;
- }
-
/*
* 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)
/*
* Called once the vdevs are all opened, this routine validates the label
- * contents. This needs to be done before vdev_load() so that we don't
+ * contents. This needs to be done before vdev_load() so that we don't
* inadvertently do repair I/Os to the wrong device.
*
- * If 'strict' is false ignore the spa guid check. This is necessary because
- * if the machine crashed during a re-guid the new guid might have been written
- * to all of the vdev labels, but not the cached config. The strict check
- * will be performed when the pool is opened again using the mos config.
- *
* This function will only return failure if one of the vdevs indicates that it
* has since been destroyed or exported. This is only possible if
* /etc/zfs/zpool.cache was readonly at the time. Otherwise, the vdev state
* will be updated but the function will return 0.
*/
int
-vdev_validate(vdev_t *vd, boolean_t strict)
+vdev_validate(vdev_t *vd)
{
spa_t *spa = vd->vdev_spa;
nvlist_t *label;
- uint64_t guid = 0, top_guid;
+ uint64_t guid = 0, aux_guid = 0, top_guid;
uint64_t state;
+ nvlist_t *nvl;
+ uint64_t txg;
- for (int c = 0; c < vd->vdev_children; c++)
- if (vdev_validate(vd->vdev_child[c], strict) != 0)
+ if (vdev_validate_skip)
+ return (0);
+
+ for (uint64_t c = 0; c < vd->vdev_children; c++)
+ if (vdev_validate(vd->vdev_child[c]) != 0)
return (SET_ERROR(EBADF));
/*
* any further validation. Otherwise, label I/O will fail and we will
* overwrite the previous state.
*/
- if (vd->vdev_ops->vdev_op_leaf && vdev_readable(vd)) {
- uint64_t aux_guid = 0;
- nvlist_t *nvl;
- uint64_t txg = spa_last_synced_txg(spa) != 0 ?
- spa_last_synced_txg(spa) : -1ULL;
+ if (!vd->vdev_ops->vdev_op_leaf || !vdev_readable(vd))
+ return (0);
- if ((label = vdev_label_read_config(vd, txg)) == NULL) {
- vdev_set_state(vd, B_FALSE, VDEV_STATE_CANT_OPEN,
- VDEV_AUX_BAD_LABEL);
- return (0);
- }
+ /*
+ * If we are performing an extreme rewind, we allow for a label that
+ * was modified at a point after the current txg.
+ * If config lock is not held do not check for the txg. spa_sync could
+ * be updating the vdev's label before updating spa_last_synced_txg.
+ */
+ if (spa->spa_extreme_rewind || spa_last_synced_txg(spa) == 0 ||
+ spa_config_held(spa, SCL_CONFIG, RW_WRITER) != SCL_CONFIG)
+ txg = UINT64_MAX;
+ else
+ txg = spa_last_synced_txg(spa);
- /*
- * Determine if this vdev has been split off into another
- * pool. If so, then refuse to open it.
- */
- if (nvlist_lookup_uint64(label, ZPOOL_CONFIG_SPLIT_GUID,
- &aux_guid) == 0 && aux_guid == spa_guid(spa)) {
- vdev_set_state(vd, B_FALSE, VDEV_STATE_CANT_OPEN,
- VDEV_AUX_SPLIT_POOL);
- nvlist_free(label);
- return (0);
- }
+ if ((label = vdev_label_read_config(vd, txg)) == NULL) {
+ vdev_set_state(vd, B_TRUE, VDEV_STATE_CANT_OPEN,
+ VDEV_AUX_BAD_LABEL);
+ vdev_dbgmsg(vd, "vdev_validate: failed reading config for "
+ "txg %llu", (u_longlong_t)txg);
+ return (0);
+ }
- if (strict && (nvlist_lookup_uint64(label,
- ZPOOL_CONFIG_POOL_GUID, &guid) != 0 ||
- guid != spa_guid(spa))) {
- vdev_set_state(vd, B_FALSE, VDEV_STATE_CANT_OPEN,
- VDEV_AUX_CORRUPT_DATA);
- nvlist_free(label);
- return (0);
- }
+ /*
+ * Determine if this vdev has been split off into another
+ * pool. If so, then refuse to open it.
+ */
+ if (nvlist_lookup_uint64(label, ZPOOL_CONFIG_SPLIT_GUID,
+ &aux_guid) == 0 && aux_guid == spa_guid(spa)) {
+ vdev_set_state(vd, B_FALSE, VDEV_STATE_CANT_OPEN,
+ VDEV_AUX_SPLIT_POOL);
+ nvlist_free(label);
+ vdev_dbgmsg(vd, "vdev_validate: vdev split into other pool");
+ return (0);
+ }
- if (nvlist_lookup_nvlist(label, ZPOOL_CONFIG_VDEV_TREE, &nvl)
- != 0 || nvlist_lookup_uint64(nvl, ZPOOL_CONFIG_ORIG_GUID,
- &aux_guid) != 0)
- aux_guid = 0;
+ if (nvlist_lookup_uint64(label, ZPOOL_CONFIG_POOL_GUID, &guid) != 0) {
+ vdev_set_state(vd, B_FALSE, VDEV_STATE_CANT_OPEN,
+ VDEV_AUX_CORRUPT_DATA);
+ nvlist_free(label);
+ vdev_dbgmsg(vd, "vdev_validate: '%s' missing from label",
+ ZPOOL_CONFIG_POOL_GUID);
+ return (0);
+ }
- /*
- * If this vdev just became a top-level vdev because its
- * sibling was detached, it will have adopted the parent's
- * vdev guid -- but the label may or may not be on disk yet.
- * Fortunately, either version of the label will have the
- * same top guid, so if we're a top-level vdev, we can
- * safely compare to that instead.
- *
- * If we split this vdev off instead, then we also check the
- * original pool's guid. We don't want to consider the vdev
- * corrupt if it is partway through a split operation.
- */
- if (nvlist_lookup_uint64(label, ZPOOL_CONFIG_GUID,
- &guid) != 0 ||
- nvlist_lookup_uint64(label, ZPOOL_CONFIG_TOP_GUID,
- &top_guid) != 0 ||
- ((vd->vdev_guid != guid && vd->vdev_guid != aux_guid) &&
- (vd->vdev_guid != top_guid || vd != vd->vdev_top))) {
- vdev_set_state(vd, B_FALSE, VDEV_STATE_CANT_OPEN,
- VDEV_AUX_CORRUPT_DATA);
- nvlist_free(label);
- return (0);
+ /*
+ * If config is not trusted then ignore the spa guid check. This is
+ * necessary because if the machine crashed during a re-guid the new
+ * guid might have been written to all of the vdev labels, but not the
+ * cached config. The check will be performed again once we have the
+ * trusted config from the MOS.
+ */
+ if (spa->spa_trust_config && guid != spa_guid(spa)) {
+ vdev_set_state(vd, B_FALSE, VDEV_STATE_CANT_OPEN,
+ VDEV_AUX_CORRUPT_DATA);
+ nvlist_free(label);
+ vdev_dbgmsg(vd, "vdev_validate: vdev label pool_guid doesn't "
+ "match config (%llu != %llu)", (u_longlong_t)guid,
+ (u_longlong_t)spa_guid(spa));
+ return (0);
+ }
+
+ if (nvlist_lookup_nvlist(label, ZPOOL_CONFIG_VDEV_TREE, &nvl)
+ != 0 || nvlist_lookup_uint64(nvl, ZPOOL_CONFIG_ORIG_GUID,
+ &aux_guid) != 0)
+ aux_guid = 0;
+
+ if (nvlist_lookup_uint64(label, ZPOOL_CONFIG_GUID, &guid) != 0) {
+ vdev_set_state(vd, B_FALSE, VDEV_STATE_CANT_OPEN,
+ VDEV_AUX_CORRUPT_DATA);
+ nvlist_free(label);
+ vdev_dbgmsg(vd, "vdev_validate: '%s' missing from label",
+ ZPOOL_CONFIG_GUID);
+ return (0);
+ }
+
+ if (nvlist_lookup_uint64(label, ZPOOL_CONFIG_TOP_GUID, &top_guid)
+ != 0) {
+ vdev_set_state(vd, B_FALSE, VDEV_STATE_CANT_OPEN,
+ VDEV_AUX_CORRUPT_DATA);
+ nvlist_free(label);
+ vdev_dbgmsg(vd, "vdev_validate: '%s' missing from label",
+ ZPOOL_CONFIG_TOP_GUID);
+ return (0);
+ }
+
+ /*
+ * If this vdev just became a top-level vdev because its sibling was
+ * detached, it will have adopted the parent's vdev guid -- but the
+ * label may or may not be on disk yet. Fortunately, either version
+ * of the label will have the same top guid, so if we're a top-level
+ * vdev, we can safely compare to that instead.
+ * However, if the config comes from a cachefile that failed to update
+ * after the detach, a top-level vdev will appear as a non top-level
+ * vdev in the config. Also relax the constraints if we perform an
+ * extreme rewind.
+ *
+ * If we split this vdev off instead, then we also check the
+ * original pool's guid. We don't want to consider the vdev
+ * corrupt if it is partway through a split operation.
+ */
+ if (vd->vdev_guid != guid && vd->vdev_guid != aux_guid) {
+ boolean_t mismatch = B_FALSE;
+ if (spa->spa_trust_config && !spa->spa_extreme_rewind) {
+ if (vd != vd->vdev_top || vd->vdev_guid != top_guid)
+ mismatch = B_TRUE;
+ } else {
+ if (vd->vdev_guid != top_guid &&
+ vd->vdev_top->vdev_guid != guid)
+ mismatch = B_TRUE;
}
- if (nvlist_lookup_uint64(label, ZPOOL_CONFIG_POOL_STATE,
- &state) != 0) {
+ if (mismatch) {
vdev_set_state(vd, B_FALSE, VDEV_STATE_CANT_OPEN,
VDEV_AUX_CORRUPT_DATA);
nvlist_free(label);
+ vdev_dbgmsg(vd, "vdev_validate: config guid "
+ "doesn't match label guid");
+ vdev_dbgmsg(vd, "CONFIG: guid %llu, top_guid %llu",
+ (u_longlong_t)vd->vdev_guid,
+ (u_longlong_t)vd->vdev_top->vdev_guid);
+ vdev_dbgmsg(vd, "LABEL: guid %llu, top_guid %llu, "
+ "aux_guid %llu", (u_longlong_t)guid,
+ (u_longlong_t)top_guid, (u_longlong_t)aux_guid);
return (0);
}
+ }
+ if (nvlist_lookup_uint64(label, ZPOOL_CONFIG_POOL_STATE,
+ &state) != 0) {
+ vdev_set_state(vd, B_FALSE, VDEV_STATE_CANT_OPEN,
+ VDEV_AUX_CORRUPT_DATA);
nvlist_free(label);
+ vdev_dbgmsg(vd, "vdev_validate: '%s' missing from label",
+ ZPOOL_CONFIG_POOL_STATE);
+ return (0);
+ }
- /*
- * If this is a verbatim import, no need to check the
- * state of the pool.
- */
- if (!(spa->spa_import_flags & ZFS_IMPORT_VERBATIM) &&
- spa_load_state(spa) == SPA_LOAD_OPEN &&
- state != POOL_STATE_ACTIVE)
- return (SET_ERROR(EBADF));
+ nvlist_free(label);
- /*
- * If we were able to open and validate a vdev that was
- * previously marked permanently unavailable, clear that state
- * now.
- */
- if (vd->vdev_not_present)
- vd->vdev_not_present = 0;
+ /*
+ * If this is a verbatim import, no need to check the
+ * state of the pool.
+ */
+ if (!(spa->spa_import_flags & ZFS_IMPORT_VERBATIM) &&
+ spa_load_state(spa) == SPA_LOAD_OPEN &&
+ state != POOL_STATE_ACTIVE) {
+ vdev_dbgmsg(vd, "vdev_validate: invalid pool state (%llu) "
+ "for spa %s", (u_longlong_t)state, spa->spa_name);
+ return (SET_ERROR(EBADF));
+ }
+
+ /*
+ * If we were able to open and validate a vdev that was
+ * previously marked permanently unavailable, clear that state
+ * now.
+ */
+ if (vd->vdev_not_present)
+ vd->vdev_not_present = 0;
+
+ return (0);
+}
+
+static void
+vdev_copy_path_impl(vdev_t *svd, vdev_t *dvd)
+{
+ if (svd->vdev_path != NULL && dvd->vdev_path != NULL) {
+ if (strcmp(svd->vdev_path, dvd->vdev_path) != 0) {
+ zfs_dbgmsg("vdev_copy_path: vdev %llu: path changed "
+ "from '%s' to '%s'", (u_longlong_t)dvd->vdev_guid,
+ dvd->vdev_path, svd->vdev_path);
+ spa_strfree(dvd->vdev_path);
+ dvd->vdev_path = spa_strdup(svd->vdev_path);
+ }
+ } else if (svd->vdev_path != NULL) {
+ dvd->vdev_path = spa_strdup(svd->vdev_path);
+ zfs_dbgmsg("vdev_copy_path: vdev %llu: path set to '%s'",
+ (u_longlong_t)dvd->vdev_guid, dvd->vdev_path);
+ }
+}
+
+/*
+ * Recursively copy vdev paths from one vdev to another. Source and destination
+ * vdev trees must have same geometry otherwise return error. Intended to copy
+ * paths from userland config into MOS config.
+ */
+int
+vdev_copy_path_strict(vdev_t *svd, vdev_t *dvd)
+{
+ if ((svd->vdev_ops == &vdev_missing_ops) ||
+ (svd->vdev_ishole && dvd->vdev_ishole) ||
+ (dvd->vdev_ops == &vdev_indirect_ops))
+ return (0);
+
+ if (svd->vdev_ops != dvd->vdev_ops) {
+ vdev_dbgmsg(svd, "vdev_copy_path: vdev type mismatch: %s != %s",
+ svd->vdev_ops->vdev_op_type, dvd->vdev_ops->vdev_op_type);
+ return (SET_ERROR(EINVAL));
+ }
+
+ if (svd->vdev_guid != dvd->vdev_guid) {
+ vdev_dbgmsg(svd, "vdev_copy_path: guids mismatch (%llu != "
+ "%llu)", (u_longlong_t)svd->vdev_guid,
+ (u_longlong_t)dvd->vdev_guid);
+ return (SET_ERROR(EINVAL));
+ }
+
+ if (svd->vdev_children != dvd->vdev_children) {
+ vdev_dbgmsg(svd, "vdev_copy_path: children count mismatch: "
+ "%llu != %llu", (u_longlong_t)svd->vdev_children,
+ (u_longlong_t)dvd->vdev_children);
+ return (SET_ERROR(EINVAL));
+ }
+
+ for (uint64_t i = 0; i < svd->vdev_children; i++) {
+ int error = vdev_copy_path_strict(svd->vdev_child[i],
+ dvd->vdev_child[i]);
+ if (error != 0)
+ return (error);
}
+ if (svd->vdev_ops->vdev_op_leaf)
+ vdev_copy_path_impl(svd, dvd);
+
return (0);
}
+static void
+vdev_copy_path_search(vdev_t *stvd, vdev_t *dvd)
+{
+ ASSERT(stvd->vdev_top == stvd);
+ ASSERT3U(stvd->vdev_id, ==, dvd->vdev_top->vdev_id);
+
+ for (uint64_t i = 0; i < dvd->vdev_children; i++) {
+ vdev_copy_path_search(stvd, dvd->vdev_child[i]);
+ }
+
+ if (!dvd->vdev_ops->vdev_op_leaf || !vdev_is_concrete(dvd))
+ return;
+
+ /*
+ * The idea here is that while a vdev can shift positions within
+ * a top vdev (when replacing, attaching mirror, etc.) it cannot
+ * step outside of it.
+ */
+ vdev_t *vd = vdev_lookup_by_guid(stvd, dvd->vdev_guid);
+
+ if (vd == NULL || vd->vdev_ops != dvd->vdev_ops)
+ return;
+
+ ASSERT(vd->vdev_ops->vdev_op_leaf);
+
+ vdev_copy_path_impl(vd, dvd);
+}
+
+/*
+ * Recursively copy vdev paths from one root vdev to another. Source and
+ * destination vdev trees may differ in geometry. For each destination leaf
+ * vdev, search a vdev with the same guid and top vdev id in the source.
+ * Intended to copy paths from userland config into MOS config.
+ */
+void
+vdev_copy_path_relaxed(vdev_t *srvd, vdev_t *drvd)
+{
+ uint64_t children = MIN(srvd->vdev_children, drvd->vdev_children);
+ ASSERT(srvd->vdev_ops == &vdev_root_ops);
+ ASSERT(drvd->vdev_ops == &vdev_root_ops);
+
+ for (uint64_t i = 0; i < children; i++) {
+ vdev_copy_path_search(srvd->vdev_child[i],
+ drvd->vdev_child[i]);
+ }
+}
+
/*
* Close a virtual device.
*/
!l2arc_vdev_present(vd))
l2arc_add_vdev(spa, vd);
} else {
- (void) vdev_validate(vd, B_TRUE);
+ (void) vdev_validate(vd);
}
/*
void
vdev_metaslab_set_size(vdev_t *vd)
{
+ uint64_t asize = vd->vdev_asize;
+ uint64_t ms_count = asize >> 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.
+ * In general, we aim for vdev_max_ms_count (200) metaslabs. The
+ * range of the dimensions are as follows:
+ *
+ * 2^29 <= ms_size <= 2^38
+ * 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 256GB. However, we will cap the total count to 2^17
+ * metaslabs to keep our memory footprint in check.
+ *
+ * The net effect of applying above constrains is summarized below.
+ *
+ * vdev size metaslab count
+ * -------------|-----------------
+ * < 8GB ~16
+ * 8GB - 100GB one per 512MB
+ * 100GB - 50TB ~200
+ * 50TB - 32PB one per 256GB
+ * > 32PB ~131,072
+ * -------------------------------
*/
- 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 < vdev_min_ms_count)
+ ms_shift = highbit64(asize / vdev_min_ms_count);
+ else if (ms_count > vdev_max_ms_count)
+ ms_shift = highbit64(asize / vdev_max_ms_count);
+ else
+ ms_shift = vdev_default_ms_shift;
+
+ if (ms_shift < SPA_MAXBLOCKSHIFT) {
+ ms_shift = SPA_MAXBLOCKSHIFT;
+ } else if (ms_shift > vdev_max_ms_shift) {
+ ms_shift = vdev_max_ms_shift;
+ /* cap the total count to constrain memory footprint */
+ if ((asize >> ms_shift) > vdev_ms_count_limit)
+ ms_shift = highbit64(asize / 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);
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);
/*
* 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) {
+ 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);
}
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);
* the top level so that we update the config.
*/
if (object != space_map_object(vd->vdev_dtl_sm)) {
- zfs_dbgmsg("txg %llu, spa %s, DTL old object %llu, "
- "new object %llu", txg, spa_name(spa), object,
- space_map_object(vd->vdev_dtl_sm));
+ vdev_dbgmsg(vd, "txg %llu, spa %s, DTL old object %llu, "
+ "new object %llu", (u_longlong_t)txg, spa_name(spa),
+ (u_longlong_t)object,
+ (u_longlong_t)space_map_object(vd->vdev_dtl_sm));
vdev_config_dirty(vd->vdev_top);
}
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.
+ * Returns the spacemap object, or 0 if it wasn't in the ZAP,
+ * the ZAP doesn't exist yet, or the ZAP is damaged.
+ */
+int
+vdev_checkpoint_sm_object(vdev_t *vd)
+{
+ ASSERT0(spa_config_held(vd->vdev_spa, SCL_ALL, RW_WRITER));
+ if (vd->vdev_top_zap == 0) {
+ return (0);
+ }
+
+ uint64_t sm_obj = 0;
+ int err = 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 (err != 0 && err != ENOENT) {
+ vdev_dbgmsg(vd, "vdev_load: vdev_checkpoint_sm_objset "
+ "failed to retrieve checkpoint space map object from "
+ "vdev ZAP [error=%d]", err);
+ ASSERT3S(err, ==, ECKSUM);
+ }
+
+ return (sm_obj);
+}
+
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_dbgmsg(vd, "vdev_load: invalid size. ashift=%llu, "
+ "asize=%llu", (u_longlong_t)vd->vdev_ashift,
+ (u_longlong_t)vd->vdev_asize);
return (SET_ERROR(ENXIO));
} else if ((error = vdev_metaslab_init(vd, 0)) != 0) {
+ vdev_dbgmsg(vd, "vdev_load: metaslab_init failed "
+ "[error=%d]", error);
vdev_set_state(vd, B_FALSE, VDEV_STATE_CANT_OPEN,
VDEV_AUX_CORRUPT_DATA);
return (error);
}
+
+ uint64_t checkpoint_sm_obj = vdev_checkpoint_sm_object(vd);
+ if (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);
+ space_map_update(vd->vdev_checkpoint_sm);
+
+ /*
+ * Since the checkpoint_sm contains free entries
+ * exclusively we can use sm_alloc to indicate the
+ * culmulative checkpointed space that has been freed.
+ */
+ vd->vdev_stat.vs_checkpoint_space =
+ -vd->vdev_checkpoint_sm->sm_alloc;
+ vd->vdev_spa->spa_checkpoint_info.sci_dspace +=
+ vd->vdev_stat.vs_checkpoint_space;
+ }
}
/*
if (vd->vdev_ops->vdev_op_leaf && (error = vdev_dtl_load(vd)) != 0) {
vdev_set_state(vd, B_FALSE, VDEV_STATE_CANT_OPEN,
VDEV_AUX_CORRUPT_DATA);
+ vdev_dbgmsg(vd, "vdev_load: vdev_dtl_load failed "
+ "[error=%d]", error);
return (error);
}
if (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))) {
vdev_set_state(vd, B_FALSE, VDEV_STATE_CANT_OPEN,
VDEV_AUX_CORRUPT_DATA);
+ vdev_dbgmsg(vd, "vdev_load: space_map_open failed for "
+ "obsolete spacemap (obj %llu) [error=%d]",
+ (u_longlong_t)obsolete_sm_object, error);
return (error);
}
space_map_update(vd->vdev_obsolete_sm);
mutex_exit(&msp->ms_lock);
}
+ if (vd->vdev_checkpoint_sm != NULL) {
+ ASSERT(spa_has_checkpoint(spa));
+ space_map_close(vd->vdev_checkpoint_sm);
+ vd->vdev_checkpoint_sm = NULL;
+ }
+
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]);
}
/* 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);
}
vdev_reopen(tvd);
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(tvd->vdev_checkpoint_sm->sm_alloc,
+ !=, 0);
+ error = ZFS_ERR_CHECKPOINT_EXISTS;
+ }
+
spa_vdev_state_enter(spa, SCL_ALLOC);
/*
}
+boolean_t
+vdev_is_spacemap_addressable(vdev_t *vd)
+{
+ /*
+ * Assuming 47 bits of the space map entry dedicated for the entry's
+ * offset (see description in space_map.h), we calculate the maximum
+ * address that can be described by a space map entry for the given
+ * device.
+ */
+ uint64_t shift = vd->vdev_ashift + 47;
+
+ if (shift >= 63) /* detect potential overflow */
+ return (B_TRUE);
+
+ return (vd->vdev_asize < (1ULL << shift));
+}
+
/*
* Get statistics for the given vdev.
*/
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;
}
}
}
}
+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);
vd->vdev_stat.vs_alloc += alloc_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) {
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 */
}
/*
vdev_propagate_state(vd->vdev_parent);
}
+boolean_t
+vdev_children_are_offline(vdev_t *vd)
+{
+ ASSERT(!vd->vdev_ops->vdev_op_leaf);
+
+ for (uint64_t i = 0; i < vd->vdev_children; i++) {
+ if (vd->vdev_child[i]->vdev_state != VDEV_STATE_OFFLINE)
+ return (B_FALSE);
+ }
+
+ return (B_TRUE);
+}
+
/*
* Check the vdev configuration to ensure that it's capable of supporting
* a root pool. We do not support partial configuration.
}
}
-/*
- * Load the state from the original vdev tree (ovd) which
- * we've retrieved from the MOS config object. If the original
- * vdev was offline or faulted then we transfer that state to the
- * device in the current vdev tree (nvd).
- */
-void
-vdev_load_log_state(vdev_t *nvd, vdev_t *ovd)
-{
- ASSERT(nvd->vdev_top->vdev_islog);
- ASSERT(spa_config_held(nvd->vdev_spa,
- SCL_STATE_ALL, RW_WRITER) == SCL_STATE_ALL);
- ASSERT3U(nvd->vdev_guid, ==, ovd->vdev_guid);
-
- for (int c = 0; c < nvd->vdev_children; c++)
- vdev_load_log_state(nvd->vdev_child[c], ovd->vdev_child[c]);
-
- if (nvd->vdev_ops->vdev_op_leaf) {
- /*
- * Restore the persistent vdev state
- */
- nvd->vdev_offline = ovd->vdev_offline;
- nvd->vdev_faulted = ovd->vdev_faulted;
- nvd->vdev_degraded = ovd->vdev_degraded;
- nvd->vdev_removed = ovd->vdev_removed;
- }
-}
-
/*
* Determine if a log device has valid content. If the vdev was
* removed or faulted in the MOS config then we know that
{
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)
+#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(vdev_max_ms_count, int, 0644);
+MODULE_PARM_DESC(vdev_max_ms_count,
+ "Target number of metaslabs per top-level vdev");
+
+module_param(vdev_min_ms_count, int, 0644);
+MODULE_PARM_DESC(vdev_min_ms_count,
+ "Minimum number of metaslabs per top-level vdev");
+
+module_param(vdev_ms_count_limit, int, 0644);
+MODULE_PARM_DESC(vdev_ms_count_limit,
+ "Practical upper limit of total 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 "
module_param(zfs_scan_ignore_errors, int, 0644);
MODULE_PARM_DESC(zfs_scan_ignore_errors,
"Ignore errors during resilver/scrub");
+
+module_param(vdev_validate_skip, int, 0644);
+MODULE_PARM_DESC(vdev_validate_skip,
+ "Bypass vdev_validate()");
/* END CSTYLED */
#endif