/*
* Copyright (c) 2005, 2010, Oracle and/or its affiliates. All rights reserved.
- * Copyright (c) 2012, 2015 by Delphix. All rights reserved.
+ * Copyright (c) 2012, 2018 by Delphix. All rights reserved.
+ * Copyright (c) 2012, 2016 by Delphix. All rights reserved.
+ * Copyright (c) 2017, Intel Corporation.
*/
/*
* 1. Uniquely identify this device as part of a ZFS pool and confirm its
* identity within the pool.
*
- * 2. Verify that all the devices given in a configuration are present
+ * 2. Verify that all the devices given in a configuration are present
* within the pool.
*
- * 3. Determine the uberblock for the pool.
+ * 3. Determine the uberblock for the pool.
*
- * 4. In case of an import operation, determine the configuration of the
+ * 4. In case of an import operation, determine the configuration of the
* toplevel vdev of which it is a part.
*
- * 5. If an import operation cannot find all the devices in the pool,
+ * 5. If an import operation cannot find all the devices in the pool,
* provide enough information to the administrator to determine which
* devices are missing.
*
* In order to identify which labels are valid, the labels are written in the
* following manner:
*
- * 1. For each vdev, update 'L1' to the new label
- * 2. Update the uberblock
- * 3. For each vdev, update 'L2' to the new label
+ * 1. For each vdev, update 'L1' to the new label
+ * 2. Update the uberblock
+ * 3. For each vdev, update 'L2' to the new label
*
* Given arbitrary failure, we can determine the correct label to use based on
* the transaction group. If we fail after updating L1 but before updating the
*
* The nvlist describing the pool and vdev contains the following elements:
*
- * version ZFS on-disk version
- * name Pool name
- * state Pool state
- * txg Transaction group in which this label was written
- * pool_guid Unique identifier for this pool
- * vdev_tree An nvlist describing vdev tree.
+ * version ZFS on-disk version
+ * name Pool name
+ * state Pool state
+ * txg Transaction group in which this label was written
+ * pool_guid Unique identifier for this pool
+ * vdev_tree An nvlist describing vdev tree.
* features_for_read
* An nvlist of the features necessary for reading the MOS.
*
* Each leaf device label also contains the following:
*
- * top_guid Unique ID for top-level vdev in which this is contained
- * guid Unique ID for the leaf vdev
+ * top_guid Unique ID for top-level vdev in which this is contained
+ * guid Unique ID for the leaf vdev
*
* The 'vs' configuration follows the format described in 'spa_config.c'.
*/
#include <sys/vdev_impl.h>
#include <sys/uberblock_impl.h>
#include <sys/metaslab.h>
+#include <sys/metaslab_impl.h>
#include <sys/zio.h>
#include <sys/dsl_scan.h>
#include <sys/abd.h>
fnvlist_add_uint64_array(nv, ZPOOL_CONFIG_VDEV_STATS,
(uint64_t *)vs, sizeof (*vs) / sizeof (uint64_t));
- kmem_free(vs, sizeof (*vs));
-
/*
* Add extended stats into a special extended stats nvlist. This keeps
* all the extended stats nicely grouped together. The extended stats
vsx->vsx_agg_histo[ZIO_PRIORITY_SCRUB],
ARRAY_SIZE(vsx->vsx_agg_histo[ZIO_PRIORITY_SCRUB]));
+ /* IO delays */
+ fnvlist_add_uint64(nvx, ZPOOL_CONFIG_VDEV_SLOW_IOS, vs->vs_slow_ios);
+
/* Add extended stats nvlist to main nvlist */
fnvlist_add_nvlist(nv, ZPOOL_CONFIG_VDEV_STATS_EX, nvx);
fnvlist_free(nvx);
+ kmem_free(vs, sizeof (*vs));
kmem_free(vsx, sizeof (*vsx));
}
+static void
+root_vdev_actions_getprogress(vdev_t *vd, nvlist_t *nvl)
+{
+ spa_t *spa = vd->vdev_spa;
+
+ if (vd != spa->spa_root_vdev)
+ return;
+
+ /* provide either current or previous scan information */
+ pool_scan_stat_t ps;
+ if (spa_scan_get_stats(spa, &ps) == 0) {
+ fnvlist_add_uint64_array(nvl,
+ ZPOOL_CONFIG_SCAN_STATS, (uint64_t *)&ps,
+ sizeof (pool_scan_stat_t) / sizeof (uint64_t));
+ }
+
+ pool_removal_stat_t prs;
+ if (spa_removal_get_stats(spa, &prs) == 0) {
+ fnvlist_add_uint64_array(nvl,
+ ZPOOL_CONFIG_REMOVAL_STATS, (uint64_t *)&prs,
+ sizeof (prs) / sizeof (uint64_t));
+ }
+
+ pool_checkpoint_stat_t pcs;
+ if (spa_checkpoint_get_stats(spa, &pcs) == 0) {
+ fnvlist_add_uint64_array(nvl,
+ ZPOOL_CONFIG_CHECKPOINT_STATS, (uint64_t *)&pcs,
+ sizeof (pcs) / sizeof (uint64_t));
+ }
+}
+
/*
* Generate the nvlist representing this vdev's config.
*/
vdev_config_flag_t flags)
{
nvlist_t *nv = NULL;
+ vdev_indirect_config_t *vic = &vd->vdev_indirect_config;
+
nv = fnvlist_alloc();
fnvlist_add_string(nv, ZPOOL_CONFIG_TYPE, vd->vdev_ops->vdev_op_type);
fnvlist_add_uint64(nv, ZPOOL_CONFIG_WHOLE_DISK,
vd->vdev_wholedisk);
- if (vd->vdev_not_present)
+ if (vd->vdev_not_present && !(flags & VDEV_CONFIG_MISSING))
fnvlist_add_uint64(nv, ZPOOL_CONFIG_NOT_PRESENT, 1);
if (vd->vdev_isspare)
fnvlist_add_uint64(nv, ZPOOL_CONFIG_ASIZE,
vd->vdev_asize);
fnvlist_add_uint64(nv, ZPOOL_CONFIG_IS_LOG, vd->vdev_islog);
- if (vd->vdev_removing)
+ if (vd->vdev_removing) {
fnvlist_add_uint64(nv, ZPOOL_CONFIG_REMOVING,
vd->vdev_removing);
+ }
+
+ /* zpool command expects alloc class data */
+ if (getstats && vd->vdev_alloc_bias != VDEV_BIAS_NONE) {
+ const char *bias = NULL;
+
+ switch (vd->vdev_alloc_bias) {
+ case VDEV_BIAS_LOG:
+ bias = VDEV_ALLOC_BIAS_LOG;
+ break;
+ case VDEV_BIAS_SPECIAL:
+ bias = VDEV_ALLOC_BIAS_SPECIAL;
+ break;
+ case VDEV_BIAS_DEDUP:
+ bias = VDEV_ALLOC_BIAS_DEDUP;
+ break;
+ default:
+ ASSERT3U(vd->vdev_alloc_bias, ==,
+ VDEV_BIAS_NONE);
+ }
+ fnvlist_add_string(nv, ZPOOL_CONFIG_ALLOCATION_BIAS,
+ bias);
+ }
}
if (vd->vdev_dtl_sm != NULL) {
space_map_object(vd->vdev_dtl_sm));
}
+ if (vic->vic_mapping_object != 0) {
+ fnvlist_add_uint64(nv, ZPOOL_CONFIG_INDIRECT_OBJECT,
+ vic->vic_mapping_object);
+ }
+
+ if (vic->vic_births_object != 0) {
+ fnvlist_add_uint64(nv, ZPOOL_CONFIG_INDIRECT_BIRTHS,
+ vic->vic_births_object);
+ }
+
+ if (vic->vic_prev_indirect_vdev != UINT64_MAX) {
+ fnvlist_add_uint64(nv, ZPOOL_CONFIG_PREV_INDIRECT_VDEV,
+ vic->vic_prev_indirect_vdev);
+ }
+
if (vd->vdev_crtxg)
fnvlist_add_uint64(nv, ZPOOL_CONFIG_CREATE_TXG, vd->vdev_crtxg);
+ if (vd->vdev_expansion_time)
+ fnvlist_add_uint64(nv, ZPOOL_CONFIG_EXPANSION_TIME,
+ vd->vdev_expansion_time);
+
if (flags & VDEV_CONFIG_MOS) {
if (vd->vdev_leaf_zap != 0) {
ASSERT(vd->vdev_ops->vdev_op_leaf);
fnvlist_add_uint64(nv, ZPOOL_CONFIG_VDEV_TOP_ZAP,
vd->vdev_top_zap);
}
+
+ if (vd->vdev_resilver_deferred) {
+ ASSERT(vd->vdev_ops->vdev_op_leaf);
+ ASSERT(spa->spa_resilver_deferred);
+ fnvlist_add_boolean(nv, ZPOOL_CONFIG_RESILVER_DEFER);
+ }
}
if (getstats) {
- pool_scan_stat_t ps;
-
vdev_config_generate_stats(vd, nv);
- /* provide either current or previous scan information */
- if (spa_scan_get_stats(spa, &ps) == 0) {
- fnvlist_add_uint64_array(nv,
- ZPOOL_CONFIG_SCAN_STATS, (uint64_t *)&ps,
- sizeof (pool_scan_stat_t) / sizeof (uint64_t));
+ root_vdev_actions_getprogress(vd, nv);
+
+ /*
+ * Note: this can be called from open context
+ * (spa_get_stats()), so we need the rwlock to prevent
+ * the mapping from being changed by condensing.
+ */
+ rw_enter(&vd->vdev_indirect_rwlock, RW_READER);
+ if (vd->vdev_indirect_mapping != NULL) {
+ ASSERT(vd->vdev_indirect_births != NULL);
+ vdev_indirect_mapping_t *vim =
+ vd->vdev_indirect_mapping;
+ fnvlist_add_uint64(nv, ZPOOL_CONFIG_INDIRECT_SIZE,
+ vdev_indirect_mapping_size(vim));
+ }
+ rw_exit(&vd->vdev_indirect_rwlock);
+ if (vd->vdev_mg != NULL &&
+ vd->vdev_mg->mg_fragmentation != ZFS_FRAG_INVALID) {
+ /*
+ * Compute approximately how much memory would be used
+ * for the indirect mapping if this device were to
+ * be removed.
+ *
+ * Note: If the frag metric is invalid, then not
+ * enough metaslabs have been converted to have
+ * histograms.
+ */
+ uint64_t seg_count = 0;
+ uint64_t to_alloc = vd->vdev_stat.vs_alloc;
+
+ /*
+ * There are the same number of allocated segments
+ * as free segments, so we will have at least one
+ * entry per free segment. However, small free
+ * segments (smaller than vdev_removal_max_span)
+ * will be combined with adjacent allocated segments
+ * as a single mapping.
+ */
+ for (int i = 0; i < RANGE_TREE_HISTOGRAM_SIZE; i++) {
+ if (1ULL << (i + 1) < vdev_removal_max_span) {
+ to_alloc +=
+ vd->vdev_mg->mg_histogram[i] <<
+ (i + 1);
+ } else {
+ seg_count +=
+ vd->vdev_mg->mg_histogram[i];
+ }
+ }
+
+ /*
+ * The maximum length of a mapping is
+ * zfs_remove_max_segment, so we need at least one entry
+ * per zfs_remove_max_segment of allocated data.
+ */
+ seg_count += to_alloc / zfs_remove_max_segment;
+
+ fnvlist_add_uint64(nv, ZPOOL_CONFIG_INDIRECT_SIZE,
+ seg_count *
+ sizeof (vdev_indirect_mapping_entry_phys_t));
}
}
for (c = 0, idx = 0; c < rvd->vdev_children; c++) {
vdev_t *tvd = rvd->vdev_child[c];
- if (tvd->vdev_ishole)
+ if (tvd->vdev_ishole) {
array[idx++] = c;
+ }
}
if (idx) {
abd_t *vp_abd;
zio_t *zio;
uint64_t best_txg = 0;
+ uint64_t label_txg = 0;
int error = 0;
int flags = ZIO_FLAG_CONFIG_WRITER | ZIO_FLAG_CANFAIL |
ZIO_FLAG_SPECULATIVE;
if (zio_wait(zio) == 0 &&
nvlist_unpack(vp->vp_nvlist, sizeof (vp->vp_nvlist),
&label, 0) == 0) {
- uint64_t label_txg = 0;
-
/*
* Auxiliary vdevs won't have txg values in their
* labels and newly added vdevs may not have been
goto retry;
}
+ /*
+ * We found a valid label but it didn't pass txg restrictions.
+ */
+ if (config == NULL && label_txg != 0) {
+ vdev_dbgmsg(vd, "label discarded as txg is too large "
+ "(%llu > %llu)", (u_longlong_t)label_txg,
+ (u_longlong_t)txg);
+ }
+
abd_free(vp_abd);
return (config);
* Search all labels on this vdev to find the configuration that
* matches the txg for our uberblock.
*/
- if (cb.ubl_vd != NULL)
+ if (cb.ubl_vd != NULL) {
+ vdev_dbgmsg(cb.ubl_vd, "best uberblock found for spa %s. "
+ "txg %llu", spa->spa_name, (u_longlong_t)ub->ub_txg);
+
*config = vdev_label_read_config(cb.ubl_vd, ub->ub_txg);
+ if (*config == NULL && spa->spa_extreme_rewind) {
+ vdev_dbgmsg(cb.ubl_vd, "failed to read label config. "
+ "Trying again without txg restrictions.");
+ *config = vdev_label_read_config(cb.ubl_vd, UINT64_MAX);
+ }
+ if (*config == NULL) {
+ vdev_dbgmsg(cb.ubl_vd, "failed to read label config");
+ }
+ }
spa_config_exit(spa, SCL_ALL, FTAG);
}
* Write the uberblock to all labels of all leaves of the specified vdev.
*/
static void
-vdev_uberblock_sync(zio_t *zio, uberblock_t *ub, vdev_t *vd, int flags)
+vdev_uberblock_sync(zio_t *zio, uint64_t *good_writes,
+ uberblock_t *ub, vdev_t *vd, int flags)
{
- for (int c = 0; c < vd->vdev_children; c++)
- vdev_uberblock_sync(zio, ub, vd->vdev_child[c], flags);
+ for (uint64_t c = 0; c < vd->vdev_children; c++) {
+ vdev_uberblock_sync(zio, good_writes,
+ ub, vd->vdev_child[c], flags);
+ }
if (!vd->vdev_ops->vdev_op_leaf)
return;
for (int l = 0; l < VDEV_LABELS; l++)
vdev_label_write(zio, vd, l, ub_abd,
VDEV_UBERBLOCK_OFFSET(vd, n), VDEV_UBERBLOCK_SIZE(vd),
- vdev_uberblock_sync_done, zio->io_private,
+ vdev_uberblock_sync_done, good_writes,
flags | ZIO_FLAG_DONT_PROPAGATE);
abd_free(ub_abd);
zio_t *zio;
uint64_t good_writes = 0;
- zio = zio_root(spa, NULL, &good_writes, flags);
+ zio = zio_root(spa, NULL, NULL, flags);
for (int v = 0; v < svdcount; v++)
- vdev_uberblock_sync(zio, ub, svd[v], flags);
+ vdev_uberblock_sync(zio, &good_writes, ub, svd[v], flags);
(void) zio_wait(zio);
*/
zio = zio_root(spa, NULL, NULL, flags);
- for (int v = 0; v < svdcount; v++)
- zio_flush(zio, svd[v]);
+ for (int v = 0; v < svdcount; v++) {
+ if (vdev_writeable(svd[v])) {
+ zio_flush(zio, svd[v]);
+ }
+ }
(void) zio_wait(zio);
* Write all even or odd labels to all leaves of the specified vdev.
*/
static void
-vdev_label_sync(zio_t *zio, vdev_t *vd, int l, uint64_t txg, int flags)
+vdev_label_sync(zio_t *zio, uint64_t *good_writes,
+ vdev_t *vd, int l, uint64_t txg, int flags)
{
nvlist_t *label;
vdev_phys_t *vp;
char *buf;
size_t buflen;
- for (int c = 0; c < vd->vdev_children; c++)
- vdev_label_sync(zio, vd->vdev_child[c], l, txg, flags);
+ for (int c = 0; c < vd->vdev_children; c++) {
+ vdev_label_sync(zio, good_writes,
+ vd->vdev_child[c], l, txg, flags);
+ }
if (!vd->vdev_ops->vdev_op_leaf)
return;
vdev_label_write(zio, vd, l, vp_abd,
offsetof(vdev_label_t, vl_vdev_phys),
sizeof (vdev_phys_t),
- vdev_label_sync_done, zio->io_private,
+ vdev_label_sync_done, good_writes,
flags | ZIO_FLAG_DONT_PROPAGATE);
}
}
(vd->vdev_islog || vd->vdev_aux != NULL) ?
vdev_label_sync_ignore_done : vdev_label_sync_top_done,
good_writes, flags);
- vdev_label_sync(vio, vd, l, txg, flags);
+ vdev_label_sync(vio, good_writes, vd, l, txg, flags);
zio_nowait(vio);
}
{
spa_t *spa = svd[0]->vdev_spa;
uberblock_t *ub = &spa->spa_uberblock;
- vdev_t *vd;
- zio_t *zio;
int error = 0;
int flags = ZIO_FLAG_CONFIG_WRITER | ZIO_FLAG_CANFAIL;
+ ASSERT(svdcount != 0);
retry:
/*
* Normally, we don't want to try too hard to write every label and
* written in this txg will be committed to stable storage
* before any uberblock that references them.
*/
- zio = zio_root(spa, NULL, NULL, flags);
+ zio_t *zio = zio_root(spa, NULL, NULL, flags);
- for (vd = txg_list_head(&spa->spa_vdev_txg_list, TXG_CLEAN(txg)); vd;
+ for (vdev_t *vd =
+ txg_list_head(&spa->spa_vdev_txg_list, TXG_CLEAN(txg)); vd != NULL;
vd = txg_list_next(&spa->spa_vdev_txg_list, vd, TXG_CLEAN(txg)))
zio_flush(zio, vd);
* the new labels to disk to ensure that all even-label updates
* are committed to stable storage before the uberblock update.
*/
- if ((error = vdev_label_sync_list(spa, 0, txg, flags)) != 0)
+ if ((error = vdev_label_sync_list(spa, 0, txg, flags)) != 0) {
+ if ((flags & ZIO_FLAG_TRYHARD) != 0) {
+ zfs_dbgmsg("vdev_label_sync_list() returned error %d "
+ "for pool '%s' when syncing out the even labels "
+ "of dirty vdevs", error, spa_name(spa));
+ }
goto retry;
+ }
/*
* Sync the uberblocks to all vdevs in svd[].
* been successfully committed) will be valid with respect
* to the new uberblocks.
*/
- if ((error = vdev_uberblock_sync_list(svd, svdcount, ub, flags)) != 0)
+ if ((error = vdev_uberblock_sync_list(svd, svdcount, ub, flags)) != 0) {
+ if ((flags & ZIO_FLAG_TRYHARD) != 0) {
+ zfs_dbgmsg("vdev_uberblock_sync_list() returned error "
+ "%d for pool '%s'", error, spa_name(spa));
+ }
goto retry;
-
+ }
if (spa_multihost(spa))
mmp_update_uberblock(spa, ub);
* to disk to ensure that all odd-label updates are committed to
* stable storage before the next transaction group begins.
*/
- if ((error = vdev_label_sync_list(spa, 1, txg, flags)) != 0)
+ if ((error = vdev_label_sync_list(spa, 1, txg, flags)) != 0) {
+ if ((flags & ZIO_FLAG_TRYHARD) != 0) {
+ zfs_dbgmsg("vdev_label_sync_list() returned error %d "
+ "for pool '%s' when syncing out the odd labels of "
+ "dirty vdevs", error, spa_name(spa));
+ }
goto retry;
+ }
return (0);
}