c/mirror_zfs
1
0
Fork 0
mirror of https://git.proxmox.com/git/mirror_zfs.git synced 2026-05-25 11:47:43 +03:00
Code Issues Packages Projects Releases Wiki Activity

Illumos #4101, #4102, #4103, #4105, #4106

Browse Source 
4101 metaslab_debug should allow for fine-grained control
4102 space_maps should store more information about themselves
4103 space map object blocksize should be increased
4105 removing a mirrored log device results in a leaked object
4106 asynchronously load metaslab
Reviewed by: Matthew Ahrens <mahrens@delphix.com>
Reviewed by: Adam Leventhal <ahl@delphix.com>
Reviewed by: Sebastien Roy <seb@delphix.com>
Approved by: Garrett D'Amore <garrett@damore.org>

Prior to this patch, space_maps were preferred solely based on the
amount of free space left in each. Unfortunately, this heuristic didn't
contain any information about the make-up of that free space, which
meant we could keep preferring and loading a highly fragmented space map
that wouldn't actually have enough contiguous space to satisfy the
allocation; then unloading that space_map and repeating the process.

This change modifies the space_map's to store additional information
about the contiguous space in the space_map, so that we can use this
information to make a better decision about which space_map to load.
This requires reallocating all space_map objects to increase their
bonus buffer size sizes enough to fit the new metadata.

The above feature can be enabled via a new feature flag introduced by
this change: com.delphix:spacemap_histogram

In addition to the above, this patch allows the space_map block size to
be increase. Currently the block size is set to be 4K in size, which has
certain implications including the following:

    * 4K sector devices will not see any compression benefit
    * large space_maps require more metadata on-disk
    * large space_maps require more time to load (typically random reads)

Now the space_map block size can adjust as needed up to the maximum size
set via the space_map_max_blksz variable.

A bug was fixed which resulted in potentially leaking an object when
removing a mirrored log device. The previous logic for vdev_remove() did
not deal with removing top-level vdevs that are interior vdevs (i.e.
mirror) correctly. The problem would occur when removing a mirrored log
device, and result in the DTL space map object being leaked; because
top-level vdevs don't have DTL space map objects associated with them.

References:
  https://www.illumos.org/issues/4101
  https://www.illumos.org/issues/4102
  https://www.illumos.org/issues/4103
  https://www.illumos.org/issues/4105
  https://www.illumos.org/issues/4106
  https://github.com/illumos/illumos-gate/commit/0713e23

Porting notes:

A handful of kmem_alloc() calls were converted to kmem_zalloc(). Also,
the KM_PUSHPAGE and TQ_PUSHPAGE flags were used as necessary.

Ported-by: Tim Chase <tim@chase2k.com>
Signed-off-by: Prakash Surya <surya1@llnl.gov>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes #2488
This commit is contained in:
George Wilson
2013-10-01 13:25:53 -08:00
committed by Brian Behlendorf
parent 1be627f5c2
commit 93cf20764a
24 changed files with 2481 additions and 1414 deletions
Download Patch File Download Diff File Expand all files Collapse all files
module/zfs/spa.c
+24 -21
View File
@@ -1259,6 +1259,15 @@ spa_unload(spa_t *spa)
bpobj_close(&spa->spa_deferred_bpobj);
spa_config_enter(spa, SCL_ALL, FTAG, RW_WRITER);
/*
* Close all vdevs.
*/
if (spa->spa_root_vdev)
vdev_free(spa->spa_root_vdev);
ASSERT(spa->spa_root_vdev == NULL);
/*
* Close the dsl pool.
*/
@@ -1270,20 +1279,12 @@ spa_unload(spa_t *spa)
ddt_unload(spa);
spa_config_enter(spa, SCL_ALL, FTAG, RW_WRITER);
/*
* Drop and purge level 2 cache
*/
spa_l2cache_drop(spa);
/*
* Close all vdevs.
*/
if (spa->spa_root_vdev)
vdev_free(spa->spa_root_vdev);
ASSERT(spa->spa_root_vdev == NULL);
for (i = 0; i < spa->spa_spares.sav_count; i++)
vdev_free(spa->spa_spares.sav_vdevs[i]);
if (spa->spa_spares.sav_vdevs) {
@@ -4568,7 +4569,9 @@ spa_vdev_attach(spa_t *spa, uint64_t guid, nvlist_t *nvroot, int replacing)
vdev_dirty(tvd, VDD_DTL, newvd, txg);
/*
* Restart the resilver
* Schedule the resilver to restart in the future. We do this to
* ensure that dmu_sync-ed blocks have been stitched into the
* respective datasets.
*/
dsl_resilver_restart(spa->spa_dsl_pool, dtl_max_txg);
@@ -5193,7 +5196,7 @@ spa_vdev_remove_evacuate(spa_t *spa, vdev_t *vd)
ASSERT0(vd->vdev_stat.vs_alloc);
txg = spa_vdev_config_enter(spa);
vd->vdev_removing = B_TRUE;
vdev_dirty(vd, 0, NULL, txg);
vdev_dirty_leaves(vd, VDD_DTL, txg);
vdev_config_dirty(vd);
spa_vdev_config_exit(spa, NULL, txg, 0, FTAG);
@@ -5965,7 +5968,7 @@ spa_sync_props(void *arg, dmu_tx_t *tx)
ASSERT(zpool_prop_feature(nvpair_name(elem)));
fname = strchr(nvpair_name(elem), '@') + 1;
VERIFY3U(0, ==, zfeature_lookup_name(fname, &feature));
VERIFY0(zfeature_lookup_name(fname, &feature));
spa_feature_enable(spa, feature, tx);
spa_history_log_internal(spa, "set", tx,
@@ -5973,7 +5976,7 @@ spa_sync_props(void *arg, dmu_tx_t *tx)
break;
case ZPOOL_PROP_VERSION:
VERIFY(nvpair_value_uint64(elem, &intval) == 0);
intval = fnvpair_value_uint64(elem);
/*
* The version is synced seperatly before other
* properties and should be correct by now.
@@ -5997,7 +6000,7 @@ spa_sync_props(void *arg, dmu_tx_t *tx)
*/
break;
case ZPOOL_PROP_COMMENT:
VERIFY(nvpair_value_string(elem, &strval) == 0);
strval = fnvpair_value_string(elem);
if (spa->spa_comment != NULL)
spa_strfree(spa->spa_comment);
spa->spa_comment = spa_strdup(strval);
@@ -6029,23 +6032,23 @@ spa_sync_props(void *arg, dmu_tx_t *tx)
if (nvpair_type(elem) == DATA_TYPE_STRING) {
ASSERT(proptype == PROP_TYPE_STRING);
VERIFY(nvpair_value_string(elem, &strval) == 0);
VERIFY(zap_update(mos,
strval = fnvpair_value_string(elem);
VERIFY0(zap_update(mos,
spa->spa_pool_props_object, propname,
1, strlen(strval) + 1, strval, tx) == 0);
1, strlen(strval) + 1, strval, tx));
spa_history_log_internal(spa, "set", tx,
"%s=%s", nvpair_name(elem), strval);
} else if (nvpair_type(elem) == DATA_TYPE_UINT64) {
VERIFY(nvpair_value_uint64(elem, &intval) == 0);
intval = fnvpair_value_uint64(elem);
if (proptype == PROP_TYPE_INDEX) {
const char *unused;
VERIFY(zpool_prop_index_to_string(
prop, intval, &unused) == 0);
VERIFY0(zpool_prop_index_to_string(
prop, intval, &unused));
}
VERIFY(zap_update(mos,
VERIFY0(zap_update(mos,
spa->spa_pool_props_object, propname,
8, 1, &intval, tx) == 0);
8, 1, &intval, tx));
spa_history_log_internal(spa, "set", tx,
"%s=%lld", nvpair_name(elem), intval);
} else {