*/
/*
* Copyright (c) 2005, 2010, Oracle and/or its affiliates. All rights reserved.
+ * Copyright (c) 2012 by Delphix. All rights reserved.
+ * Copyright 2011 Nexenta Systems, Inc. All rights reserved.
*/
#include <sys/zfs_context.h>
#include <sys/dsl_pool.h>
#include <sys/dsl_dir.h>
#include <sys/dsl_prop.h>
+#include <sys/fm/util.h>
#include <sys/dsl_scan.h>
#include <sys/fs/zfs.h>
#include <sys/metaslab_impl.h>
#include <sys/arc.h>
#include <sys/ddt.h>
#include "zfs_prop.h"
+#include "zfeature_common.h"
/*
* SPA locking
* Like spa_vdev_enter/exit, these are convenience wrappers -- the actual
* locking is, always, based on spa_namespace_lock and spa_config_lock[].
*
- * spa_rename() is also implemented within this file since is requires
+ * spa_rename() is also implemented within this file since it requires
* manipulation of the namespace.
*/
kmem_cache_t *spa_buffer_pool;
int spa_mode_global;
-#ifdef ZFS_DEBUG
-/* Everything except dprintf is on by default in debug builds */
-int zfs_flags = ~ZFS_DEBUG_DPRINTF;
-#else
-int zfs_flags = 0;
-#endif
+/*
+ * Expiration time in units of zfs_txg_synctime_ms. This value has two
+ * meanings. First it is used to determine when the spa_deadman logic
+ * should fire. By default the spa_deadman will fire if spa_sync has
+ * not completed in 1000 * zfs_txg_synctime_ms (i.e. 1000 seconds).
+ * Secondly, the value determines if an I/O is considered "hung".
+ * Any I/O that has not completed in zfs_deadman_synctime is considered
+ * "hung" resulting in a zevent being posted.
+ * 1000 zfs_txg_synctime_ms (i.e. 1000 seconds).
+ */
+unsigned long zfs_deadman_synctime = 1000ULL;
/*
- * zfs_recover can be set to nonzero to attempt to recover from
- * otherwise-fatal errors, typically caused by on-disk corruption. When
- * set, calls to zfs_panic_recover() will turn into warning messages.
+ * By default the deadman is enabled.
*/
-int zfs_recover = 0;
+int zfs_deadman_enabled = 1;
/*
static void
spa_config_lock_init(spa_t *spa)
{
- for (int i = 0; i < SCL_LOCKS; i++) {
+ int i;
+
+ for (i = 0; i < SCL_LOCKS; i++) {
spa_config_lock_t *scl = &spa->spa_config_lock[i];
mutex_init(&scl->scl_lock, NULL, MUTEX_DEFAULT, NULL);
cv_init(&scl->scl_cv, NULL, CV_DEFAULT, NULL);
static void
spa_config_lock_destroy(spa_t *spa)
{
- for (int i = 0; i < SCL_LOCKS; i++) {
+ int i;
+
+ for (i = 0; i < SCL_LOCKS; i++) {
spa_config_lock_t *scl = &spa->spa_config_lock[i];
mutex_destroy(&scl->scl_lock);
cv_destroy(&scl->scl_cv);
int
spa_config_tryenter(spa_t *spa, int locks, void *tag, krw_t rw)
{
- for (int i = 0; i < SCL_LOCKS; i++) {
+ int i;
+
+ for (i = 0; i < SCL_LOCKS; i++) {
spa_config_lock_t *scl = &spa->spa_config_lock[i];
if (!(locks & (1 << i)))
continue;
spa_config_enter(spa_t *spa, int locks, void *tag, krw_t rw)
{
int wlocks_held = 0;
+ int i;
- for (int i = 0; i < SCL_LOCKS; i++) {
+ for (i = 0; i < SCL_LOCKS; i++) {
spa_config_lock_t *scl = &spa->spa_config_lock[i];
if (scl->scl_writer == curthread)
wlocks_held |= (1 << i);
void
spa_config_exit(spa_t *spa, int locks, void *tag)
{
- for (int i = SCL_LOCKS - 1; i >= 0; i--) {
+ int i;
+
+ for (i = SCL_LOCKS - 1; i >= 0; i--) {
spa_config_lock_t *scl = &spa->spa_config_lock[i];
if (!(locks & (1 << i)))
continue;
int
spa_config_held(spa_t *spa, int locks, krw_t rw)
{
- int locks_held = 0;
+ int i, locks_held = 0;
- for (int i = 0; i < SCL_LOCKS; i++) {
+ for (i = 0; i < SCL_LOCKS; i++) {
spa_config_lock_t *scl = &spa->spa_config_lock[i];
if (!(locks & (1 << i)))
continue;
static spa_t search; /* spa_t is large; don't allocate on stack */
spa_t *spa;
avl_index_t where;
- char c;
+ char c = 0;
char *cp;
ASSERT(MUTEX_HELD(&spa_namespace_lock));
}
/*
+ * Fires when spa_sync has not completed within zfs_deadman_synctime_ms.
+ * If the zfs_deadman_enabled flag is set then it inspects all vdev queues
+ * looking for potentially hung I/Os.
+ */
+void
+spa_deadman(void *arg)
+{
+ spa_t *spa = arg;
+
+ zfs_dbgmsg("slow spa_sync: started %llu seconds ago, calls %llu",
+ (gethrtime() - spa->spa_sync_starttime) / NANOSEC,
+ ++spa->spa_deadman_calls);
+ if (zfs_deadman_enabled)
+ vdev_deadman(spa->spa_root_vdev);
+
+ spa->spa_deadman_tqid = taskq_dispatch_delay(system_taskq,
+ spa_deadman, spa, TQ_SLEEP, ddi_get_lbolt() +
+ NSEC_TO_TICK(spa->spa_deadman_synctime));
+}
+
+/*
* Create an uninitialized spa_t with the given name. Requires
* spa_namespace_lock. The caller must ensure that the spa_t doesn't already
* exist by calling spa_lookup() first.
{
spa_t *spa;
spa_config_dirent_t *dp;
+ int t;
ASSERT(MUTEX_HELD(&spa_namespace_lock));
- spa = kmem_zalloc(sizeof (spa_t), KM_SLEEP);
+ spa = kmem_zalloc(sizeof (spa_t), KM_PUSHPAGE | KM_NODEBUG);
mutex_init(&spa->spa_async_lock, NULL, MUTEX_DEFAULT, NULL);
mutex_init(&spa->spa_errlist_lock, NULL, MUTEX_DEFAULT, NULL);
cv_init(&spa->spa_scrub_io_cv, NULL, CV_DEFAULT, NULL);
cv_init(&spa->spa_suspend_cv, NULL, CV_DEFAULT, NULL);
- for (int t = 0; t < TXG_SIZE; t++)
+ for (t = 0; t < TXG_SIZE; t++)
bplist_create(&spa->spa_free_bplist[t]);
(void) strlcpy(spa->spa_name, name, sizeof (spa->spa_name));
spa->spa_proc = &p0;
spa->spa_proc_state = SPA_PROC_NONE;
+ spa->spa_deadman_synctime = zfs_deadman_synctime *
+ zfs_txg_synctime_ms * MICROSEC;
+
refcount_create(&spa->spa_refcount);
spa_config_lock_init(spa);
list_create(&spa->spa_config_list, sizeof (spa_config_dirent_t),
offsetof(spa_config_dirent_t, scd_link));
- dp = kmem_zalloc(sizeof (spa_config_dirent_t), KM_SLEEP);
+ dp = kmem_zalloc(sizeof (spa_config_dirent_t), KM_PUSHPAGE);
dp->scd_path = altroot ? NULL : spa_strdup(spa_config_path);
list_insert_head(&spa->spa_config_list, dp);
- if (config != NULL)
+ VERIFY(nvlist_alloc(&spa->spa_load_info, NV_UNIQUE_NAME,
+ KM_PUSHPAGE) == 0);
+
+ if (config != NULL) {
+ nvlist_t *features;
+
+ if (nvlist_lookup_nvlist(config, ZPOOL_CONFIG_FEATURES_FOR_READ,
+ &features) == 0) {
+ VERIFY(nvlist_dup(features, &spa->spa_label_features,
+ 0) == 0);
+ }
+
VERIFY(nvlist_dup(config, &spa->spa_config, 0) == 0);
+ }
+
+ if (spa->spa_label_features == NULL) {
+ VERIFY(nvlist_alloc(&spa->spa_label_features, NV_UNIQUE_NAME,
+ KM_SLEEP) == 0);
+ }
return (spa);
}
spa_remove(spa_t *spa)
{
spa_config_dirent_t *dp;
+ int t;
ASSERT(MUTEX_HELD(&spa_namespace_lock));
ASSERT(spa->spa_state == POOL_STATE_UNINITIALIZED);
list_destroy(&spa->spa_config_list);
+ nvlist_free(spa->spa_label_features);
+ nvlist_free(spa->spa_load_info);
spa_config_set(spa, NULL);
refcount_destroy(&spa->spa_refcount);
spa_config_lock_destroy(spa);
- for (int t = 0; t < TXG_SIZE; t++)
+ for (t = 0; t < TXG_SIZE; t++)
bplist_destroy(&spa->spa_free_bplist[t]);
cv_destroy(&spa->spa_async_cv);
if ((aux = avl_find(avl, &search, &where)) != NULL) {
aux->aux_count++;
} else {
- aux = kmem_zalloc(sizeof (spa_aux_t), KM_SLEEP);
+ aux = kmem_zalloc(sizeof (spa_aux_t), KM_PUSHPAGE);
aux->aux_guid = vd->vdev_guid;
aux->aux_count = 1;
avl_insert(avl, aux, where);
void
spa_vdev_config_exit(spa_t *spa, vdev_t *vd, uint64_t txg, int error, char *tag)
{
- ASSERT(MUTEX_HELD(&spa_namespace_lock));
-
int config_changed = B_FALSE;
+ ASSERT(MUTEX_HELD(&spa_namespace_lock));
ASSERT(txg > spa_last_synced_txg(spa));
spa->spa_pending_vdev = NULL;
*/
vdev_dtl_reassess(spa->spa_root_vdev, 0, 0, B_FALSE);
- /*
- * If the config changed, notify the scrub that it must restart.
- * This will initiate a resilver if needed.
- */
if (error == 0 && !list_is_empty(&spa->spa_config_dirty_list)) {
config_changed = B_TRUE;
spa->spa_config_generation++;
* ==========================================================================
*/
+void
+spa_activate_mos_feature(spa_t *spa, const char *feature)
+{
+ (void) nvlist_add_boolean(spa->spa_label_features, feature);
+ vdev_config_dirty(spa->spa_root_vdev);
+}
+
+void
+spa_deactivate_mos_feature(spa_t *spa, const char *feature)
+{
+ (void) nvlist_remove_all(spa->spa_label_features, feature);
+ vdev_config_dirty(spa->spa_root_vdev);
+}
+
/*
* Rename a spa_t.
*/
}
/*
- * Determine whether a pool with given pool_guid exists. If device_guid is
- * non-zero, determine whether the pool exists *and* contains a device with the
- * specified device_guid.
+ * Return the spa_t associated with given pool_guid, if it exists. If
+ * device_guid is non-zero, determine whether the pool exists *and* contains
+ * a device with the specified device_guid.
*/
-boolean_t
-spa_guid_exists(uint64_t pool_guid, uint64_t device_guid)
+spa_t *
+spa_by_guid(uint64_t pool_guid, uint64_t device_guid)
{
spa_t *spa;
avl_tree_t *t = &spa_namespace_avl;
}
}
- return (spa != NULL);
+ return (spa);
+}
+
+/*
+ * Determine whether a pool with the given pool_guid exists.
+ */
+boolean_t
+spa_guid_exists(uint64_t pool_guid, uint64_t device_guid)
+{
+ return (spa_by_guid(pool_guid, device_guid) != NULL);
}
char *
char *new;
len = strlen(s);
- new = kmem_alloc(len + 1, KM_SLEEP);
+ new = kmem_alloc(len + 1, KM_PUSHPAGE);
bcopy(s, new, len);
new[len] = '\0';
void
sprintf_blkptr(char *buf, const blkptr_t *bp)
{
- char *type = NULL;
+ char type[256];
char *checksum = NULL;
char *compress = NULL;
if (bp != NULL) {
- type = dmu_ot[BP_GET_TYPE(bp)].ot_name;
+ if (BP_GET_TYPE(bp) & DMU_OT_NEWTYPE) {
+ dmu_object_byteswap_t bswap =
+ DMU_OT_BYTESWAP(BP_GET_TYPE(bp));
+ (void) snprintf(type, sizeof (type), "bswap %s %s",
+ DMU_OT_IS_METADATA(BP_GET_TYPE(bp)) ?
+ "metadata" : "data",
+ dmu_ot_byteswap[bswap].ob_name);
+ } else {
+ (void) strlcpy(type, dmu_ot[BP_GET_TYPE(bp)].ot_name,
+ sizeof (type));
+ }
checksum = zio_checksum_table[BP_GET_CHECKSUM(bp)].ci_name;
compress = zio_compress_table[BP_GET_COMPRESS(bp)].ci_name;
}
txg_wait_synced(spa_get_dsl(spa), freeze_txg);
}
-void
-zfs_panic_recover(const char *fmt, ...)
-{
- va_list adx;
-
- va_start(adx, fmt);
- vcmn_err(zfs_recover ? CE_WARN : CE_PANIC, fmt, adx);
- va_end(adx);
-}
-
/*
* This is a stripped-down version of strtoull, suitable only for converting
* lowercase hexidecimal numbers that don't overflow.
return (spa->spa_dsl_pool);
}
+boolean_t
+spa_is_initializing(spa_t *spa)
+{
+ return (spa->spa_is_initializing);
+}
+
blkptr_t *
spa_get_rootblkptr(spa_t *spa)
{
uint64_t
spa_guid(spa_t *spa)
{
+ dsl_pool_t *dp = spa_get_dsl(spa);
+ uint64_t guid;
+
/*
* If we fail to parse the config during spa_load(), we can go through
* the error path (which posts an ereport) and end up here with no root
- * vdev. We stash the original pool guid in 'spa_load_guid' to handle
+ * vdev. We stash the original pool guid in 'spa_config_guid' to handle
* this case.
*/
- if (spa->spa_root_vdev != NULL)
+ if (spa->spa_root_vdev == NULL)
+ return (spa->spa_config_guid);
+
+ guid = spa->spa_last_synced_guid != 0 ?
+ spa->spa_last_synced_guid : spa->spa_root_vdev->vdev_guid;
+
+ /*
+ * Return the most recently synced out guid unless we're
+ * in syncing context.
+ */
+ if (dp && dsl_pool_sync_context(dp))
return (spa->spa_root_vdev->vdev_guid);
else
- return (spa->spa_load_guid);
+ return (guid);
+}
+
+uint64_t
+spa_load_guid(spa_t *spa)
+{
+ /*
+ * This is a GUID that exists solely as a reference for the
+ * purposes of the arc. It is generated at load time, and
+ * is never written to persistent storage.
+ */
+ return (spa->spa_load_guid);
}
uint64_t
}
uint64_t
+spa_deadman_synctime(spa_t *spa)
+{
+ return (spa->spa_deadman_synctime);
+}
+
+uint64_t
dva_get_dsize_sync(spa_t *spa, const dva_t *dva)
{
uint64_t asize = DVA_GET_ASIZE(dva);
bp_get_dsize_sync(spa_t *spa, const blkptr_t *bp)
{
uint64_t dsize = 0;
+ int d;
- for (int d = 0; d < SPA_DVAS_PER_BP; d++)
+ for (d = 0; d < SPA_DVAS_PER_BP; d++)
dsize += dva_get_dsize_sync(spa, &bp->blk_dva[d]);
return (dsize);
bp_get_dsize(spa_t *spa, const blkptr_t *bp)
{
uint64_t dsize = 0;
+ int d;
spa_config_enter(spa, SCL_VDEV, FTAG, RW_READER);
- for (int d = 0; d < SPA_DVAS_PER_BP; d++)
+ for (d = 0; d < SPA_DVAS_PER_BP; d++)
dsize += dva_get_dsize_sync(spa, &bp->blk_dva[d]);
spa_config_exit(spa, SCL_VDEV, FTAG);
return (0);
}
-int
-spa_busy(void)
-{
- return (spa_active_count);
-}
-
void
-spa_boot_init()
+spa_boot_init(void)
{
spa_config_load();
}
spa_mode_global = mode;
+ fm_init();
refcount_init();
unique_init();
zio_init();
vdev_cache_stat_init();
zfs_prop_init();
zpool_prop_init();
+ zpool_feature_init();
spa_config_load();
l2arc_start();
}
zio_fini();
unique_fini();
refcount_fini();
+ fm_fini();
avl_destroy(&spa_namespace_avl);
avl_destroy(&spa_spare_avl);
return (0);
}
+
+boolean_t
+spa_debug_enabled(spa_t *spa)
+{
+ return (spa->spa_debug);
+}
+
+#if defined(_KERNEL) && defined(HAVE_SPL)
+/* Namespace manipulation */
+EXPORT_SYMBOL(spa_lookup);
+EXPORT_SYMBOL(spa_add);
+EXPORT_SYMBOL(spa_remove);
+EXPORT_SYMBOL(spa_next);
+
+/* Refcount functions */
+EXPORT_SYMBOL(spa_open_ref);
+EXPORT_SYMBOL(spa_close);
+EXPORT_SYMBOL(spa_refcount_zero);
+
+/* Pool configuration lock */
+EXPORT_SYMBOL(spa_config_tryenter);
+EXPORT_SYMBOL(spa_config_enter);
+EXPORT_SYMBOL(spa_config_exit);
+EXPORT_SYMBOL(spa_config_held);
+
+/* Pool vdev add/remove lock */
+EXPORT_SYMBOL(spa_vdev_enter);
+EXPORT_SYMBOL(spa_vdev_exit);
+
+/* Pool vdev state change lock */
+EXPORT_SYMBOL(spa_vdev_state_enter);
+EXPORT_SYMBOL(spa_vdev_state_exit);
+
+/* Accessor functions */
+EXPORT_SYMBOL(spa_shutting_down);
+EXPORT_SYMBOL(spa_get_dsl);
+EXPORT_SYMBOL(spa_get_rootblkptr);
+EXPORT_SYMBOL(spa_set_rootblkptr);
+EXPORT_SYMBOL(spa_altroot);
+EXPORT_SYMBOL(spa_sync_pass);
+EXPORT_SYMBOL(spa_name);
+EXPORT_SYMBOL(spa_guid);
+EXPORT_SYMBOL(spa_last_synced_txg);
+EXPORT_SYMBOL(spa_first_txg);
+EXPORT_SYMBOL(spa_syncing_txg);
+EXPORT_SYMBOL(spa_version);
+EXPORT_SYMBOL(spa_state);
+EXPORT_SYMBOL(spa_load_state);
+EXPORT_SYMBOL(spa_freeze_txg);
+EXPORT_SYMBOL(spa_get_asize);
+EXPORT_SYMBOL(spa_get_dspace);
+EXPORT_SYMBOL(spa_update_dspace);
+EXPORT_SYMBOL(spa_deflate);
+EXPORT_SYMBOL(spa_normal_class);
+EXPORT_SYMBOL(spa_log_class);
+EXPORT_SYMBOL(spa_max_replication);
+EXPORT_SYMBOL(spa_prev_software_version);
+EXPORT_SYMBOL(spa_get_failmode);
+EXPORT_SYMBOL(spa_suspended);
+EXPORT_SYMBOL(spa_bootfs);
+EXPORT_SYMBOL(spa_delegation);
+EXPORT_SYMBOL(spa_meta_objset);
+
+/* Miscellaneous support routines */
+EXPORT_SYMBOL(spa_rename);
+EXPORT_SYMBOL(spa_guid_exists);
+EXPORT_SYMBOL(spa_strdup);
+EXPORT_SYMBOL(spa_strfree);
+EXPORT_SYMBOL(spa_get_random);
+EXPORT_SYMBOL(spa_generate_guid);
+EXPORT_SYMBOL(sprintf_blkptr);
+EXPORT_SYMBOL(spa_freeze);
+EXPORT_SYMBOL(spa_upgrade);
+EXPORT_SYMBOL(spa_evict_all);
+EXPORT_SYMBOL(spa_lookup_by_guid);
+EXPORT_SYMBOL(spa_has_spare);
+EXPORT_SYMBOL(dva_get_dsize_sync);
+EXPORT_SYMBOL(bp_get_dsize_sync);
+EXPORT_SYMBOL(bp_get_dsize);
+EXPORT_SYMBOL(spa_has_slogs);
+EXPORT_SYMBOL(spa_is_root);
+EXPORT_SYMBOL(spa_writeable);
+EXPORT_SYMBOL(spa_mode);
+
+EXPORT_SYMBOL(spa_namespace_lock);
+
+module_param(zfs_deadman_synctime, ulong, 0644);
+MODULE_PARM_DESC(zfs_deadman_synctime,"Expire in units of zfs_txg_synctime_ms");
+
+module_param(zfs_deadman_enabled, int, 0644);
+MODULE_PARM_DESC(zfs_deadman_enabled, "Enable deadman timer");
+#endif
git://git.camperquake.de / zfs.git / blobdiff