c/mirror_zfs
1
0
Fork 0
mirror of https://git.proxmox.com/git/mirror_zfs.git synced 2026-05-27 04:32:16 +03:00
Code Issues Packages Projects Releases Wiki Activity

OpenZFS 9166 - zfs storage pool checkpoint

Browse Source 
Details about the motivation of this feature and its usage can
be found in this blogpost:

    https://sdimitro.github.io/post/zpool-checkpoint/

A lightning talk of this feature can be found here:
https://www.youtube.com/watch?v=fPQA8K40jAM

Implementation details can be found in big block comment of
spa_checkpoint.c

Side-changes that are relevant to this commit but not explained
elsewhere:

* renames members of "struct metaslab trees to be shorter without
  losing meaning

* space_map_{alloc,truncate}() accept a block size as a
  parameter. The reason is that in the current state all space
  maps that we allocate through the DMU use a global tunable
  (space_map_blksz) which defauls to 4KB. This is ok for metaslab
  space maps in terms of bandwirdth since they are scattered all
  over the disk. But for other space maps this default is probably
  not what we want. Examples are device removal's vdev_obsolete_sm
  or vdev_chedkpoint_sm from this review. Both of these have a
  1:1 relationship with each vdev and could benefit from a bigger
  block size.

Porting notes:

* The part of dsl_scan_sync() which handles async destroys has
  been moved into the new dsl_process_async_destroys() function.

* Remove "VERIFY(!(flags & FWRITE))" in "kernel.c" so zhack can write
  to block device backed pools.

* ZTS:
  * Fix get_txg() in zpool_sync_001_pos due to "checkpoint_txg".

  * Don't use large dd block sizes on /dev/urandom under Linux in
    checkpoint_capacity.

  * Adopt Delphix-OS's setting of 4 (spa_asize_inflation =
    SPA_DVAS_PER_BP + 1) for the checkpoint_capacity test to speed
    its attempts to fill the pool

  * Create the base and nested pools with sync=disabled to speed up
    the "setup" phase.

  * Clear labels in test pool between checkpoint tests to avoid
    duplicate pool issues.

  * The import_rewind_device_replaced test has been marked as "known
    to fail" for the reasons listed in its DISCLAIMER.

  * New module parameters:

      zfs_spa_discard_memory_limit,
      zfs_remove_max_bytes_pause (not documented - debugging only)
      vdev_max_ms_count (formerly metaslabs_per_vdev)
      vdev_min_ms_count

Authored by: Serapheim Dimitropoulos <serapheim.dimitro@delphix.com>
Reviewed by: Matthew Ahrens <mahrens@delphix.com>
Reviewed by: John Kennedy <john.kennedy@delphix.com>
Reviewed by: Dan Kimmel <dan.kimmel@delphix.com>
Reviewed by: Brian Behlendorf <behlendorf1@llnl.gov>
Approved by: Richard Lowe <richlowe@richlowe.net>
Ported-by: Tim Chase <tim@chase2k.com>
Signed-off-by: Tim Chase <tim@chase2k.com>

OpenZFS-issue: https://illumos.org/issues/9166
OpenZFS-commit: https://github.com/openzfs/openzfs/commit/7159fdb8
Closes #7570
This commit is contained in:
Serapheim Dimitropoulos
2016-12-16 14:11:29 -08:00
committed by Brian Behlendorf
parent 88eaf610d9
commit d2734cce68
115 changed files with 5956 additions and 817 deletions
Download Patch File Download Diff File Expand all files Collapse all files
cmd/ztest/ztest.c
+104 -9
View File
@@ -345,6 +345,7 @@ ztest_func_t ztest_reguid;
ztest_func_t ztest_spa_upgrade;
ztest_func_t ztest_device_removal;
ztest_func_t ztest_remap_blocks;
ztest_func_t ztest_spa_checkpoint_create_discard;
ztest_func_t ztest_fletcher;
ztest_func_t ztest_fletcher_incr;
ztest_func_t ztest_verify_dnode_bt;
@@ -397,6 +398,7 @@ ztest_info_t ztest_info[] = {
ZTI_INIT(ztest_vdev_aux_add_remove, 1, &ztest_opts.zo_vdevtime),
ZTI_INIT(ztest_device_removal, 1, &zopt_sometimes),
ZTI_INIT(ztest_remap_blocks, 1, &zopt_sometimes),
ZTI_INIT(ztest_spa_checkpoint_create_discard, 1, &zopt_rarely),
ZTI_INIT(ztest_fletcher, 1, &zopt_rarely),
ZTI_INIT(ztest_fletcher_incr, 1, &zopt_rarely),
ZTI_INIT(ztest_verify_dnode_bt, 1, &zopt_sometimes),
@@ -446,6 +448,7 @@ static ztest_ds_t *ztest_ds;
static kmutex_t ztest_vdev_lock;
static boolean_t ztest_device_removal_active = B_FALSE;
static kmutex_t ztest_checkpoint_lock;
/*
* The ztest_name_lock protects the pool and dataset namespace used by
@@ -2864,6 +2867,62 @@ ztest_spa_upgrade(ztest_ds_t *zd, uint64_t id)
mutex_exit(&ztest_vdev_lock);
}
static void
ztest_spa_checkpoint(spa_t *spa)
{
ASSERT(MUTEX_HELD(&ztest_checkpoint_lock));
int error = spa_checkpoint(spa->spa_name);
switch (error) {
case 0:
case ZFS_ERR_DEVRM_IN_PROGRESS:
case ZFS_ERR_DISCARDING_CHECKPOINT:
case ZFS_ERR_CHECKPOINT_EXISTS:
break;
case ENOSPC:
ztest_record_enospc(FTAG);
break;
default:
fatal(0, "spa_checkpoint(%s) = %d", spa->spa_name, error);
}
}
static void
ztest_spa_discard_checkpoint(spa_t *spa)
{
ASSERT(MUTEX_HELD(&ztest_checkpoint_lock));
int error = spa_checkpoint_discard(spa->spa_name);
switch (error) {
case 0:
case ZFS_ERR_DISCARDING_CHECKPOINT:
case ZFS_ERR_NO_CHECKPOINT:
break;
default:
fatal(0, "spa_discard_checkpoint(%s) = %d",
spa->spa_name, error);
}
}
/* ARGSUSED */
void
ztest_spa_checkpoint_create_discard(ztest_ds_t *zd, uint64_t id)
{
spa_t *spa = ztest_spa;
mutex_enter(&ztest_checkpoint_lock);
if (ztest_random(2) == 0) {
ztest_spa_checkpoint(spa);
} else {
ztest_spa_discard_checkpoint(spa);
}
mutex_exit(&ztest_checkpoint_lock);
}
static vdev_t *
vdev_lookup_by_path(vdev_t *vd, const char *path)
{
@@ -2953,6 +3012,8 @@ ztest_vdev_add_remove(ztest_ds_t *zd, uint64_t id)
case EEXIST: /* Generic zil_reset() error */
case EBUSY: /* Replay required */
case EACCES: /* Crypto key not loaded */
case ZFS_ERR_CHECKPOINT_EXISTS:
case ZFS_ERR_DISCARDING_CHECKPOINT:
break;
default:
fatal(0, "spa_vdev_remove() = %d", error);
@@ -2971,10 +3032,15 @@ ztest_vdev_add_remove(ztest_ds_t *zd, uint64_t id)
error = spa_vdev_add(spa, nvroot);
nvlist_free(nvroot);
if (error == ENOSPC)
switch (error) {
case 0:
break;
case ENOSPC:
ztest_record_enospc("spa_vdev_add");
else if (error != 0)
break;
default:
fatal(0, "spa_vdev_add() = %d", error);
}
}
mutex_exit(&ztest_vdev_lock);
@@ -3048,8 +3114,13 @@ ztest_vdev_aux_add_remove(ztest_ds_t *zd, uint64_t id)
nvlist_t *nvroot = make_vdev_root(NULL, aux, NULL,
(ztest_opts.zo_vdev_size * 5) / 4, 0, 0, 0, 0, 1);
error = spa_vdev_add(spa, nvroot);
if (error != 0)
switch (error) {
case 0:
break;
default:
fatal(0, "spa_vdev_add(%p) = %d", nvroot, error);
}
nvlist_free(nvroot);
} else {
/*
@@ -3061,8 +3132,16 @@ ztest_vdev_aux_add_remove(ztest_ds_t *zd, uint64_t id)
(void) vdev_online(spa, guid, 0, NULL);
error = spa_vdev_remove(spa, guid, B_FALSE);
if (error != 0 && error != EBUSY)
switch (error) {
case 0:
case EBUSY:
case ZFS_ERR_CHECKPOINT_EXISTS:
case ZFS_ERR_DISCARDING_CHECKPOINT:
break;
default:
fatal(0, "spa_vdev_remove(%llu) = %d", guid, error);
}
}
mutex_exit(&ztest_vdev_lock);
@@ -3166,7 +3245,6 @@ ztest_split_pool(ztest_ds_t *zd, uint64_t id)
--zs->zs_mirrors;
}
mutex_exit(&ztest_vdev_lock);
}
/*
@@ -3271,7 +3349,8 @@ ztest_vdev_attach_detach(ztest_ds_t *zd, uint64_t id)
spa_config_exit(spa, SCL_ALL, FTAG);
error = spa_vdev_detach(spa, oldguid, pguid, B_FALSE);
if (error != 0 && error != ENODEV && error != EBUSY &&
error != ENOTSUP)
error != ENOTSUP && error != ZFS_ERR_CHECKPOINT_EXISTS &&
error != ZFS_ERR_DISCARDING_CHECKPOINT)
fatal(0, "detach (%s) returned %d", oldpath, error);
goto out;
}
@@ -3362,6 +3441,10 @@ ztest_vdev_attach_detach(ztest_ds_t *zd, uint64_t id)
if (error == EOVERFLOW || error == EBUSY)
expected_error = error;
if (error == ZFS_ERR_CHECKPOINT_EXISTS ||
error == ZFS_ERR_DISCARDING_CHECKPOINT)
expected_error = error;
/* XXX workaround 6690467 */
if (error != expected_error && expected_error != EBUSY) {
fatal(0, "attach (%s %llu, %s %llu, %d) "
@@ -3556,6 +3639,7 @@ ztest_vdev_LUN_growth(ztest_ds_t *zd, uint64_t id)
uint64_t top;
uint64_t old_class_space, new_class_space, old_ms_count, new_ms_count;
mutex_enter(&ztest_checkpoint_lock);
mutex_enter(&ztest_vdev_lock);
spa_config_enter(spa, SCL_STATE, spa, RW_READER);
@@ -3566,8 +3650,9 @@ ztest_vdev_LUN_growth(ztest_ds_t *zd, uint64_t id)
* when the device removal completes).
*/
if (ztest_device_removal_active) {
spa_config_exit(spa, SCL_STATE, FTAG);
spa_config_exit(spa, SCL_STATE, spa);
mutex_exit(&ztest_vdev_lock);
mutex_exit(&ztest_checkpoint_lock);
return;
}
@@ -3597,6 +3682,7 @@ ztest_vdev_LUN_growth(ztest_ds_t *zd, uint64_t id)
psize == 0 || psize >= 4 * ztest_opts.zo_vdev_size) {
spa_config_exit(spa, SCL_STATE, spa);
mutex_exit(&ztest_vdev_lock);
mutex_exit(&ztest_checkpoint_lock);
return;
}
ASSERT(psize > 0);
@@ -3622,6 +3708,7 @@ ztest_vdev_LUN_growth(ztest_ds_t *zd, uint64_t id)
}
spa_config_exit(spa, SCL_STATE, spa);
mutex_exit(&ztest_vdev_lock);
mutex_exit(&ztest_checkpoint_lock);
return;
}
@@ -3656,6 +3743,7 @@ ztest_vdev_LUN_growth(ztest_ds_t *zd, uint64_t id)
}
spa_config_exit(spa, SCL_STATE, spa);
mutex_exit(&ztest_vdev_lock);
mutex_exit(&ztest_checkpoint_lock);
return;
}
@@ -3686,6 +3774,7 @@ ztest_vdev_LUN_growth(ztest_ds_t *zd, uint64_t id)
spa_config_exit(spa, SCL_STATE, spa);
mutex_exit(&ztest_vdev_lock);
mutex_exit(&ztest_checkpoint_lock);
}
/*
@@ -5722,7 +5811,7 @@ ztest_fault_inject(ztest_ds_t *zd, uint64_t id)
*/
fd = open(pathrand, O_RDWR);
if (fd == -1) /* we hit a gap in the device namespace */
if (fd == -1) /* we hit a gap in the device namespace */
goto out;
fsize = lseek(fd, 0, SEEK_END);
@@ -6645,6 +6734,7 @@ ztest_run(ztest_shared_t *zs)
* Initialize parent/child shared state.
*/
mutex_init(&ztest_vdev_lock, NULL, MUTEX_DEFAULT, NULL);
mutex_init(&ztest_checkpoint_lock, NULL, MUTEX_DEFAULT, NULL);
VERIFY0(pthread_rwlock_init(&ztest_name_lock, NULL));
zs->zs_thread_start = gethrtime();
@@ -6696,7 +6786,7 @@ ztest_run(ztest_shared_t *zs)
spa->spa_deadman_failmode = ZIO_FAILURE_MODE_PANIC;
/*
* Verify that we can safely inquire about about any object,
* Verify that we can safely inquire about any object,
* whether it's allocated or not. To make it interesting,
* we probe a 5-wide window around each power of two.
* This hits all edge cases, including zero and the max.
@@ -6804,6 +6894,7 @@ ztest_run(ztest_shared_t *zs)
mutex_destroy(&zcl.zcl_callbacks_lock);
(void) pthread_rwlock_destroy(&ztest_name_lock);
mutex_destroy(&ztest_vdev_lock);
mutex_destroy(&ztest_checkpoint_lock);
}
static void
@@ -6953,6 +7044,7 @@ ztest_import(ztest_shared_t *zs)
int error;
mutex_init(&ztest_vdev_lock, NULL, MUTEX_DEFAULT, NULL);
mutex_init(&ztest_checkpoint_lock, NULL, MUTEX_DEFAULT, NULL);
VERIFY0(pthread_rwlock_init(&ztest_name_lock, NULL));
kernel_init(FREAD | FWRITE);
@@ -6984,6 +7076,7 @@ ztest_import(ztest_shared_t *zs)
(void) pthread_rwlock_destroy(&ztest_name_lock);
mutex_destroy(&ztest_vdev_lock);
mutex_destroy(&ztest_checkpoint_lock);
}
/*
@@ -6998,6 +7091,7 @@ ztest_init(ztest_shared_t *zs)
int i;
mutex_init(&ztest_vdev_lock, NULL, MUTEX_DEFAULT, NULL);
mutex_init(&ztest_checkpoint_lock, NULL, MUTEX_DEFAULT, NULL);
VERIFY0(pthread_rwlock_init(&ztest_name_lock, NULL));
kernel_init(FREAD | FWRITE);
@@ -7049,6 +7143,7 @@ ztest_init(ztest_shared_t *zs)
(void) pthread_rwlock_destroy(&ztest_name_lock);
mutex_destroy(&ztest_vdev_lock);
mutex_destroy(&ztest_checkpoint_lock);
}
static void