Print this page
5056 ZFS deadlock on db_mtx and dn_holds
Reviewed by: Will Andrews <willa@spectralogic.com>
Reviewed by: Matt Ahrens <mahrens@delphix.com>
Reviewed by: George Wilson <george.wilson@delphix.com>
Approved by: Dan McDonald <danmcd@omniti.com>
@@ -21,10 +21,11 @@
/*
* Copyright (c) 2005, 2010, Oracle and/or its affiliates. All rights reserved.
* Copyright (c) 2011, 2014 by Delphix. All rights reserved.
* Copyright (c) 2014, Joyent, Inc. All rights reserved.
* Copyright (c) 2014 RackTop Systems.
+ * Copyright (c) 2014 Spectra Logic Corporation, All rights reserved.
*/
#include <sys/dmu_objset.h>
#include <sys/dsl_dataset.h>
#include <sys/dsl_dir.h>
@@ -69,11 +70,10 @@
}
#define DS_REF_MAX (1ULL << 62)
extern inline dsl_dataset_phys_t *dsl_dataset_phys(dsl_dataset_t *ds);
-extern inline boolean_t dsl_dataset_is_snapshot(dsl_dataset_t *ds);
/*
* Figure out how much of this delta should be propogated to the dsl_dir
* layer. If there's a refreservation, that space has already been
* partially accounted for in our ancestors.
@@ -153,11 +153,11 @@
-used, -compressed, -uncompressed);
return (used);
}
ASSERT3P(tx->tx_pool, ==, ds->ds_dir->dd_pool);
- ASSERT(!dsl_dataset_is_snapshot(ds));
+ ASSERT(!ds->ds_is_snapshot);
dmu_buf_will_dirty(ds->ds_dbuf, tx);
if (bp->blk_birth > dsl_dataset_phys(ds)->ds_prev_snap_txg) {
int64_t delta;
@@ -251,18 +251,19 @@
ddt_prefetch(dsl_dataset_get_spa(ds), bp);
return (B_TRUE);
}
-/* ARGSUSED */
static void
-dsl_dataset_evict(dmu_buf_t *db, void *dsv)
+dsl_dataset_evict(void *dbu)
{
- dsl_dataset_t *ds = dsv;
+ dsl_dataset_t *ds = dbu;
ASSERT(ds->ds_owner == NULL);
+ ds->ds_dbuf = NULL;
+
unique_remove(ds->ds_fsid_guid);
if (ds->ds_objset != NULL)
dmu_objset_evict(ds->ds_objset);
@@ -270,14 +271,14 @@
dsl_dataset_rele(ds->ds_prev, ds);
ds->ds_prev = NULL;
}
bplist_destroy(&ds->ds_pending_deadlist);
- if (dsl_dataset_phys(ds)->ds_deadlist_obj != 0)
+ if (ds->ds_deadlist.dl_os != NULL)
dsl_deadlist_close(&ds->ds_deadlist);
if (ds->ds_dir)
- dsl_dir_rele(ds->ds_dir, ds);
+ dsl_dir_async_rele(ds->ds_dir, ds);
ASSERT(!list_link_active(&ds->ds_synced_link));
mutex_destroy(&ds->ds_lock);
mutex_destroy(&ds->ds_opening_lock);
@@ -387,10 +388,11 @@
dsl_dataset_t *winner = NULL;
ds = kmem_zalloc(sizeof (dsl_dataset_t), KM_SLEEP);
ds->ds_dbuf = dbuf;
ds->ds_object = dsobj;
+ ds->ds_is_snapshot = dsl_dataset_phys(ds)->ds_num_children != 0;
mutex_init(&ds->ds_lock, NULL, MUTEX_DEFAULT, NULL);
mutex_init(&ds->ds_opening_lock, NULL, MUTEX_DEFAULT, NULL);
mutex_init(&ds->ds_sendstream_lock, NULL, MUTEX_DEFAULT, NULL);
refcount_create(&ds->ds_longholds);
@@ -425,11 +427,11 @@
kmem_free(ds, sizeof (dsl_dataset_t));
dmu_buf_rele(dbuf, tag);
return (err);
}
- if (!dsl_dataset_is_snapshot(ds)) {
+ if (!ds->ds_is_snapshot) {
ds->ds_snapname[0] = '\0';
if (dsl_dataset_phys(ds)->ds_prev_snap_obj != 0) {
err = dsl_dataset_hold_obj(dp,
dsl_dataset_phys(ds)->ds_prev_snap_obj,
ds, &ds->ds_prev);
@@ -452,11 +454,11 @@
dsl_dataset_phys(ds)->ds_userrefs_obj,
&ds->ds_userrefs);
}
}
- if (err == 0 && !dsl_dataset_is_snapshot(ds)) {
+ if (err == 0 && !ds->ds_is_snapshot) {
err = dsl_prop_get_int_ds(ds,
zfs_prop_to_name(ZFS_PROP_REFRESERVATION),
&ds->ds_reserved);
if (err == 0) {
err = dsl_prop_get_int_ds(ds,
@@ -465,12 +467,15 @@
}
} else {
ds->ds_reserved = ds->ds_quota = 0;
}
- if (err != 0 || (winner = dmu_buf_set_user_ie(dbuf, ds,
- dsl_dataset_evict)) != NULL) {
+ dmu_buf_init_user(&ds->ds_dbu, dsl_dataset_evict, &ds->ds_dbuf);
+ if (err == 0)
+ winner = dmu_buf_set_user_ie(dbuf, &ds->ds_dbu);
+
+ if (err != 0 || winner != NULL) {
bplist_destroy(&ds->ds_pending_deadlist);
dsl_deadlist_close(&ds->ds_deadlist);
if (ds->ds_prev)
dsl_dataset_rele(ds->ds_prev, ds);
dsl_dir_rele(ds->ds_dir, ds);
@@ -846,11 +851,11 @@
dsl_dataset_recalc_head_uniq(dsl_dataset_t *ds)
{
uint64_t mrs_used;
uint64_t dlused, dlcomp, dluncomp;
- ASSERT(!dsl_dataset_is_snapshot(ds));
+ ASSERT(!ds->ds_is_snapshot);
if (dsl_dataset_phys(ds)->ds_prev_snap_obj != 0)
mrs_used = dsl_dataset_phys(ds->ds_prev)->ds_referenced_bytes;
else
mrs_used = 0;
@@ -1589,11 +1594,11 @@
dsl_prop_nvlist_add_uint64(nv, ZFS_PROP_REFRATIO, ratio);
dsl_prop_nvlist_add_uint64(nv, ZFS_PROP_LOGICALREFERENCED,
dsl_dataset_phys(ds)->ds_uncompressed_bytes);
- if (dsl_dataset_is_snapshot(ds)) {
+ if (ds->ds_is_snapshot) {
dsl_prop_nvlist_add_uint64(nv, ZFS_PROP_COMPRESSRATIO, ratio);
dsl_prop_nvlist_add_uint64(nv, ZFS_PROP_USED,
dsl_dataset_phys(ds)->ds_unique_bytes);
get_clones_stat(ds, nv);
} else {
@@ -1657,11 +1662,11 @@
stat->dds_creation_txg = dsl_dataset_phys(ds)->ds_creation_txg;
stat->dds_inconsistent =
dsl_dataset_phys(ds)->ds_flags & DS_FLAG_INCONSISTENT;
stat->dds_guid = dsl_dataset_phys(ds)->ds_guid;
stat->dds_origin[0] = '\0';
- if (dsl_dataset_is_snapshot(ds)) {
+ if (ds->ds_is_snapshot) {
stat->dds_is_snapshot = B_TRUE;
stat->dds_num_clones =
dsl_dataset_phys(ds)->ds_num_children - 1;
} else {
stat->dds_is_snapshot = B_FALSE;
@@ -1917,11 +1922,11 @@
error = dsl_dataset_hold(dp, ddra->ddra_fsname, FTAG, &ds);
if (error != 0)
return (error);
/* must not be a snapshot */
- if (dsl_dataset_is_snapshot(ds)) {
+ if (ds->ds_is_snapshot) {
dsl_dataset_rele(ds, FTAG);
return (SET_ERROR(EINVAL));
}
/* must have a most recent snapshot */
@@ -2489,11 +2494,11 @@
&ddpa->ddpa_clone);
if (error != 0)
return (error);
dd = ddpa->ddpa_clone->ds_dir;
- if (dsl_dataset_is_snapshot(ddpa->ddpa_clone) ||
+ if (ddpa->ddpa_clone->ds_is_snapshot ||
!dsl_dir_is_clone(dd)) {
dsl_dataset_rele(ddpa->ddpa_clone, tag);
return (SET_ERROR(EINVAL));
}
@@ -2581,12 +2586,12 @@
dsl_dataset_t *origin_head, boolean_t force, void *owner, dmu_tx_t *tx)
{
int64_t unused_refres_delta;
/* they should both be heads */
- if (dsl_dataset_is_snapshot(clone) ||
- dsl_dataset_is_snapshot(origin_head))
+ if (clone->ds_is_snapshot ||
+ origin_head->ds_is_snapshot)
return (SET_ERROR(EINVAL));
/* if we are not forcing, the branch point should be just before them */
if (!force && clone->ds_prev != origin_head->ds_prev)
return (SET_ERROR(EINVAL));
@@ -2861,11 +2866,11 @@
error = dsl_dataset_hold(dp, ddsqra->ddsqra_name, FTAG, &ds);
if (error != 0)
return (error);
- if (dsl_dataset_is_snapshot(ds)) {
+ if (ds->ds_is_snapshot) {
dsl_dataset_rele(ds, FTAG);
return (SET_ERROR(EINVAL));
}
error = dsl_prop_predict(ds->ds_dir,
@@ -2944,11 +2949,11 @@
error = dsl_dataset_hold(dp, ddsqra->ddsqra_name, FTAG, &ds);
if (error != 0)
return (error);
- if (dsl_dataset_is_snapshot(ds)) {
+ if (ds->ds_is_snapshot) {
dsl_dataset_rele(ds, FTAG);
return (SET_ERROR(EINVAL));
}
error = dsl_prop_predict(ds->ds_dir,
@@ -3158,12 +3163,12 @@
{
int err = 0;
uint64_t snapobj;
dsl_pool_t *dp = firstsnap->ds_dir->dd_pool;
- ASSERT(dsl_dataset_is_snapshot(firstsnap));
- ASSERT(dsl_dataset_is_snapshot(lastsnap));
+ ASSERT(firstsnap->ds_is_snapshot);
+ ASSERT(lastsnap->ds_is_snapshot);
/*
* Check that the snapshots are in the same dsl_dir, and firstsnap
* is before lastsnap.
*/
@@ -3284,16 +3289,16 @@
dsl_pool_t *dp = later->ds_dir->dd_pool;
int error;
boolean_t ret;
ASSERT(dsl_pool_config_held(dp));
- ASSERT(dsl_dataset_is_snapshot(earlier) || earlier_txg != 0);
+ ASSERT(earlier->ds_is_snapshot || earlier_txg != 0);
if (earlier_txg == 0)
earlier_txg = dsl_dataset_phys(earlier)->ds_creation_txg;
- if (dsl_dataset_is_snapshot(later) &&
+ if (later->ds_is_snapshot &&
earlier_txg >= dsl_dataset_phys(later)->ds_creation_txg)
return (B_FALSE);
if (later->ds_dir == earlier->ds_dir)
return (B_TRUE);