/*
* Copyright (c) 2005, 2010, Oracle and/or its affiliates. All rights reserved.
* Copyright 2011 Nexenta Systems, Inc. All rights reserved.
- * Copyright (c) 2011, 2014 by Delphix. All rights reserved.
+ * Copyright (c) 2011, 2015 by Delphix. All rights reserved.
*/
#include <sys/zfs_context.h>
return (NULL);
}
+static int
+vdev_count_leaves_impl(vdev_t *vd)
+{
+ int n = 0;
+ int c;
+
+ if (vd->vdev_ops->vdev_op_leaf)
+ return (1);
+
+ for (c = 0; c < vd->vdev_children; c++)
+ n += vdev_count_leaves_impl(vd->vdev_child[c]);
+
+ return (n);
+}
+
+int
+vdev_count_leaves(spa_t *spa)
+{
+ return (vdev_count_leaves_impl(spa->spa_root_vdev));
+}
+
void
vdev_add_child(vdev_t *pvd, vdev_t *cvd)
{
list_link_init(&vd->vdev_config_dirty_node);
list_link_init(&vd->vdev_state_dirty_node);
- mutex_init(&vd->vdev_dtl_lock, NULL, MUTEX_DEFAULT, NULL);
+ 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);
for (t = 0; t < DTL_TYPES; t++) {
&vd->vdev_asize);
(void) nvlist_lookup_uint64(nv, ZPOOL_CONFIG_REMOVING,
&vd->vdev_removing);
+ (void) nvlist_lookup_uint64(nv, ZPOOL_CONFIG_VDEV_TOP_ZAP,
+ &vd->vdev_top_zap);
+ } else {
+ ASSERT0(vd->vdev_top_zap);
}
if (parent && !parent->vdev_parent && alloctype != VDEV_ALLOC_ATTACH) {
spa_log_class(spa) : spa_normal_class(spa), vd);
}
+ if (vd->vdev_ops->vdev_op_leaf &&
+ (alloctype == VDEV_ALLOC_LOAD || alloctype == VDEV_ALLOC_SPLIT)) {
+ (void) nvlist_lookup_uint64(nv,
+ ZPOOL_CONFIG_VDEV_LEAF_ZAP, &vd->vdev_leaf_zap);
+ } else {
+ ASSERT0(vd->vdev_leaf_zap);
+ }
+
/*
* If we're a leaf vdev, try to load the DTL object and other state.
*/
+
if (vd->vdev_ops->vdev_op_leaf &&
(alloctype == VDEV_ALLOC_LOAD || alloctype == VDEV_ALLOC_L2CACHE ||
alloctype == VDEV_ALLOC_ROOTPOOL)) {
tvd->vdev_ms_array = svd->vdev_ms_array;
tvd->vdev_ms_shift = svd->vdev_ms_shift;
tvd->vdev_ms_count = svd->vdev_ms_count;
+ tvd->vdev_top_zap = svd->vdev_top_zap;
svd->vdev_ms_array = 0;
svd->vdev_ms_shift = 0;
svd->vdev_ms_count = 0;
+ svd->vdev_top_zap = 0;
if (tvd->vdev_mg)
ASSERT3P(tvd->vdev_mg, ==, svd->vdev_mg);
/*
* Compute the raidz-deflation ratio. Note, we hard-code
- * in 128k (1 << 17) because it is the current "typical" blocksize.
- * Even if SPA_MAXBLOCKSIZE changes, this algorithm must never change,
- * or we will inconsistently account for existing bp's.
+ * in 128k (1 << 17) because it is the "typical" blocksize.
+ * Even though SPA_MAXBLOCKSIZE changed, this algorithm can not change,
+ * otherwise it would inconsistently account for existing bp's.
*/
vd->vdev_deflate_ratio = (1 << 17) /
(vdev_psize_to_asize(vd, 1 << 17) >> SPA_MINBLOCKSHIFT);
vd->vdev_open_thread = curthread;
vd->vdev_open_error = vdev_open(vd);
vd->vdev_open_thread = NULL;
+ vd->vdev_parent->vdev_nonrot &= vd->vdev_nonrot;
}
static boolean_t
int children = vd->vdev_children;
int c;
+ vd->vdev_nonrot = B_TRUE;
+
/*
* in order to handle pools on top of zvols, do the opens
* in a single thread so that the same thread holds the
* spa_namespace_lock
*/
if (vdev_uses_zvols(vd)) {
- for (c = 0; c < children; c++)
+ for (c = 0; c < children; c++) {
vd->vdev_child[c]->vdev_open_error =
vdev_open(vd->vdev_child[c]);
+ vd->vdev_nonrot &= vd->vdev_child[c]->vdev_nonrot;
+ }
return;
}
tq = taskq_create("vdev_open", children, minclsyspri,
TQ_SLEEP) != 0);
taskq_destroy(tq);
+
+ for (c = 0; c < children; c++)
+ vd->vdev_nonrot &= vd->vdev_child[c]->vdev_nonrot;
}
/*
return (error);
}
+ /*
+ * Track the min and max ashift values for normal data devices.
+ */
+ if (vd->vdev_top == vd && vd->vdev_ashift != 0 &&
+ !vd->vdev_islog && 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;
+ }
+
/*
* If a leaf vdev has a DTL, and seems healthy, then kick off a
* resilver. But don't do this if we are doing a reopen for a scrub,
return (error);
}
+void
+vdev_destroy_unlink_zap(vdev_t *vd, uint64_t zapobj, dmu_tx_t *tx)
+{
+ spa_t *spa = vd->vdev_spa;
+
+ VERIFY0(zap_destroy(spa->spa_meta_objset, zapobj, tx));
+ VERIFY0(zap_remove_int(spa->spa_meta_objset, spa->spa_all_vdev_zaps,
+ zapobj, tx));
+}
+
+uint64_t
+vdev_create_link_zap(vdev_t *vd, dmu_tx_t *tx)
+{
+ spa_t *spa = vd->vdev_spa;
+ uint64_t zap = zap_create(spa->spa_meta_objset, DMU_OTN_ZAP_METADATA,
+ DMU_OT_NONE, 0, tx);
+
+ ASSERT(zap != 0);
+ VERIFY0(zap_add_int(spa->spa_meta_objset, spa->spa_all_vdev_zaps,
+ zap, tx));
+
+ return (zap);
+}
+
+void
+vdev_construct_zaps(vdev_t *vd, dmu_tx_t *tx)
+{
+ uint64_t i;
+
+ if (vd->vdev_ops != &vdev_hole_ops &&
+ vd->vdev_ops != &vdev_missing_ops &&
+ vd->vdev_ops != &vdev_root_ops &&
+ !vd->vdev_top->vdev_removing) {
+ if (vd->vdev_ops->vdev_op_leaf && vd->vdev_leaf_zap == 0) {
+ vd->vdev_leaf_zap = vdev_create_link_zap(vd, tx);
+ }
+ if (vd == vd->vdev_top && vd->vdev_top_zap == 0) {
+ vd->vdev_top_zap = vdev_create_link_zap(vd, tx);
+ }
+ }
+ for (i = 0; i < vd->vdev_children; i++) {
+ vdev_construct_zaps(vd->vdev_child[i], tx);
+ }
+}
+
void
vdev_dtl_sync(vdev_t *vd, uint64_t txg)
{
space_map_close(vd->vdev_dtl_sm);
vd->vdev_dtl_sm = NULL;
mutex_exit(&vd->vdev_dtl_lock);
+
+ /*
+ * We only destroy the leaf ZAP for detached leaves or for
+ * removed log devices. Removed data devices handle leaf ZAP
+ * cleanup later, once cancellation is no longer possible.
+ */
+ if (vd->vdev_leaf_zap != 0 && (vd->vdev_detached ||
+ vd->vdev_top->vdev_islog)) {
+ vdev_destroy_unlink_zap(vd, vd->vdev_leaf_zap, tx);
+ vd->vdev_leaf_zap = 0;
+ }
+
dmu_tx_commit(tx);
return;
}
int m, i;
tx = dmu_tx_create_assigned(spa_get_dsl(spa), txg);
+ ASSERT(vd == vd->vdev_top);
+ ASSERT3U(txg, ==, spa_syncing_txg(spa));
if (vd->vdev_ms != NULL) {
metaslab_group_t *mg = vd->vdev_mg;
(void) dmu_object_free(mos, vd->vdev_ms_array, tx);
vd->vdev_ms_array = 0;
}
+
+ if (vd->vdev_islog && vd->vdev_top_zap != 0) {
+ vdev_destroy_unlink_zap(vd, vd->vdev_top_zap, tx);
+ vd->vdev_top_zap = 0;
+ }
dmu_tx_commit(tx);
}
return (B_TRUE);
}
+static void
+vdev_get_child_stat(vdev_t *cvd, vdev_stat_t *vs, vdev_stat_t *cvs)
+{
+ int t;
+ for (t = 0; t < ZIO_TYPES; t++) {
+ vs->vs_ops[t] += cvs->vs_ops[t];
+ vs->vs_bytes[t] += cvs->vs_bytes[t];
+ }
+
+ cvs->vs_scan_removing = cvd->vdev_removing;
+}
+
/*
- * Get statistics for the given vdev.
+ * Get extended stats
*/
-void
-vdev_get_stats(vdev_t *vd, vdev_stat_t *vs)
+static void
+vdev_get_child_stat_ex(vdev_t *cvd, vdev_stat_ex_t *vsx, vdev_stat_ex_t *cvsx)
{
- spa_t *spa = vd->vdev_spa;
- vdev_t *rvd = spa->spa_root_vdev;
- int c, t;
+ int t, b;
+ for (t = 0; t < ZIO_TYPES; t++) {
+ for (b = 0; b < ARRAY_SIZE(vsx->vsx_disk_histo[0]); b++)
+ vsx->vsx_disk_histo[t][b] += cvsx->vsx_disk_histo[t][b];
- ASSERT(spa_config_held(spa, SCL_ALL, RW_READER) != 0);
+ for (b = 0; b < ARRAY_SIZE(vsx->vsx_total_histo[0]); b++) {
+ vsx->vsx_total_histo[t][b] +=
+ cvsx->vsx_total_histo[t][b];
+ }
+ }
- mutex_enter(&vd->vdev_stat_lock);
- bcopy(&vd->vdev_stat, vs, sizeof (*vs));
- 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)
- vs->vs_rsize += VDEV_LABEL_START_SIZE + VDEV_LABEL_END_SIZE;
- vs->vs_esize = vd->vdev_max_asize - vd->vdev_asize;
- if (vd->vdev_aux == NULL && vd == vd->vdev_top && !vd->vdev_ishole) {
- vs->vs_fragmentation = vd->vdev_mg->mg_fragmentation;
+ for (t = 0; t < ZIO_PRIORITY_NUM_QUEUEABLE; t++) {
+ for (b = 0; b < ARRAY_SIZE(vsx->vsx_queue_histo[0]); b++) {
+ vsx->vsx_queue_histo[t][b] +=
+ cvsx->vsx_queue_histo[t][b];
+ }
+ vsx->vsx_active_queue[t] += cvsx->vsx_active_queue[t];
+ vsx->vsx_pend_queue[t] += cvsx->vsx_pend_queue[t];
+
+ for (b = 0; b < ARRAY_SIZE(vsx->vsx_ind_histo[0]); b++)
+ vsx->vsx_ind_histo[t][b] += cvsx->vsx_ind_histo[t][b];
+
+ for (b = 0; b < ARRAY_SIZE(vsx->vsx_agg_histo[0]); b++)
+ vsx->vsx_agg_histo[t][b] += cvsx->vsx_agg_histo[t][b];
}
+}
+
+/*
+ * Get statistics for the given vdev.
+ */
+static void
+vdev_get_stats_ex_impl(vdev_t *vd, vdev_stat_t *vs, vdev_stat_ex_t *vsx)
+{
+ int c, t;
/*
* If we're getting stats on the root vdev, aggregate the I/O counts
* over all top-level vdevs (i.e. the direct children of the root).
*/
- if (vd == rvd) {
- for (c = 0; c < rvd->vdev_children; c++) {
- vdev_t *cvd = rvd->vdev_child[c];
+ if (!vd->vdev_ops->vdev_op_leaf) {
+ if (vs) {
+ memset(vs->vs_ops, 0, sizeof (vs->vs_ops));
+ memset(vs->vs_bytes, 0, sizeof (vs->vs_bytes));
+ }
+ if (vsx)
+ memset(vsx, 0, sizeof (*vsx));
+
+ for (c = 0; c < vd->vdev_children; c++) {
+ vdev_t *cvd = vd->vdev_child[c];
vdev_stat_t *cvs = &cvd->vdev_stat;
+ vdev_stat_ex_t *cvsx = &cvd->vdev_stat_ex;
- for (t = 0; t < ZIO_TYPES; t++) {
- vs->vs_ops[t] += cvs->vs_ops[t];
- vs->vs_bytes[t] += cvs->vs_bytes[t];
- }
- cvs->vs_scan_removing = cvd->vdev_removing;
+ vdev_get_stats_ex_impl(cvd, cvs, cvsx);
+ if (vs)
+ vdev_get_child_stat(cvd, vs, cvs);
+ if (vsx)
+ vdev_get_child_stat_ex(cvd, vsx, cvsx);
+
+ }
+ } else {
+ /*
+ * We're a leaf. Just copy our ZIO active queue stats in. The
+ * other leaf stats are updated in vdev_stat_update().
+ */
+ if (!vsx)
+ return;
+
+ memcpy(vsx, &vd->vdev_stat_ex, sizeof (vd->vdev_stat_ex));
+
+ for (t = 0; t < ARRAY_SIZE(vd->vdev_queue.vq_class); t++) {
+ vsx->vsx_active_queue[t] =
+ vd->vdev_queue.vq_class[t].vqc_active;
+ vsx->vsx_pend_queue[t] = avl_numnodes(
+ &vd->vdev_queue.vq_class[t].vqc_queued_tree);
+ }
+ }
+}
+
+void
+vdev_get_stats_ex(vdev_t *vd, vdev_stat_t *vs, vdev_stat_ex_t *vsx)
+{
+ mutex_enter(&vd->vdev_stat_lock);
+ if (vs) {
+ bcopy(&vd->vdev_stat, vs, sizeof (*vs));
+ 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)
+ vs->vs_rsize += VDEV_LABEL_START_SIZE +
+ VDEV_LABEL_END_SIZE;
+ vs->vs_esize = vd->vdev_max_asize - vd->vdev_asize;
+ if (vd->vdev_aux == NULL && vd == vd->vdev_top &&
+ !vd->vdev_ishole) {
+ vs->vs_fragmentation = vd->vdev_mg->mg_fragmentation;
}
}
+
+ ASSERT(spa_config_held(vd->vdev_spa, SCL_ALL, RW_READER) != 0);
+ vdev_get_stats_ex_impl(vd, vs, vsx);
mutex_exit(&vd->vdev_stat_lock);
}
+void
+vdev_get_stats(vdev_t *vd, vdev_stat_t *vs)
+{
+ return (vdev_get_stats_ex(vd, vs, NULL));
+}
+
void
vdev_clear_stats(vdev_t *vd)
{
vdev_t *pvd;
uint64_t txg = zio->io_txg;
vdev_stat_t *vs = &vd->vdev_stat;
+ vdev_stat_ex_t *vsx = &vd->vdev_stat_ex;
zio_type_t type = zio->io_type;
int flags = zio->io_flags;
vs->vs_self_healed += psize;
}
- vs->vs_ops[type]++;
- vs->vs_bytes[type] += psize;
+ /*
+ * The bytes/ops/histograms are recorded at the leaf level and
+ * aggregated into the higher level vdevs in vdev_get_stats().
+ */
+ if (vd->vdev_ops->vdev_op_leaf) {
+
+ vs->vs_ops[type]++;
+ vs->vs_bytes[type] += psize;
+
+ if (flags & ZIO_FLAG_DELEGATED) {
+ vsx->vsx_agg_histo[zio->io_priority]
+ [RQ_HISTO(zio->io_size)]++;
+ } else {
+ vsx->vsx_ind_histo[zio->io_priority]
+ [RQ_HISTO(zio->io_size)]++;
+ }
+
+ if (zio->io_delta && zio->io_delay) {
+ vsx->vsx_queue_histo[zio->io_priority]
+ [L_HISTO(zio->io_delta - zio->io_delay)]++;
+ vsx->vsx_disk_histo[type]
+ [L_HISTO(zio->io_delay)]++;
+ vsx->vsx_total_histo[type]
+ [L_HISTO(zio->io_delta)]++;
+ }
+ }
mutex_exit(&vd->vdev_stat_lock);
return;
projects / mirror_zfs.git / blobdiff