mirror of
https://git.proxmox.com/git/mirror_zfs.git
synced 2024-12-27 03:19:35 +03:00
37f6845c6f
When iterating through children physical ashifts for vdev, prefer ones above the maximum logical ashift, that we can actually use, but within the administrator defined maximum. When selecting top-level vdev ashift, do not set it to the defined maximum in case physical ashift is even higher, but just ignore one. Using the maximum does not prevent misaligned writes, but reduces space efficiency. Since ZFS tries to write data sequentially and aggregates the writes, in many cases large misanigned writes may be not as bad as the space penalty otherwise. Allow internal physical ashifts for vdevs higher than SHIFT_MAX. May be one day allocator or aggregation could benefit from that. Reduce zfs_vdev_max_auto_ashift default from 16 (64KB) to 14 (16KB), so that ZFS may still use bigger ashifts up to SHIFT_MAX (64KB), but only if it really has to or explicitly told to, but not as an "optimization". There are some read-intensive NVMe SSDs that report Preferred Write Alignment of 64KB, and attempt to build RAIDZ2 of those leads to a space inefficiency that can't be justified. Instead these changes make ZFS fall back to logical ashift of 12 (4KB) by default and only warn user that it may be suboptimal for performance. Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Reviewed-by: Ryan Moeller <ryan@iXsystems.com> Signed-off-by: Alexander Motin <mav@FreeBSD.org> Sponsored by: iXsystems, Inc. Closes #13798
102 lines
6.0 KiB
INI
102 lines
6.0 KiB
INI
# This file exports variables for each tunable used in the test suite.
|
|
#
|
|
# Different platforms use different names for most tunables. To avoid littering
|
|
# the tests with conditional logic for deciding how to set each tunable, the
|
|
# logic is instead consolidated to this one file.
|
|
#
|
|
# Any use of tunables in tests must use a name defined here. New entries
|
|
# should be added to the table as needed. Please keep the table sorted
|
|
# alphabetically for ease of maintenance.
|
|
#
|
|
# Platform-specific tunables should still use a NAME from this table for
|
|
# consistency. Enter UNSUPPORTED in the column for platforms on which the
|
|
# tunable is not implemented.
|
|
|
|
UNAME=$(uname)
|
|
|
|
# NAME FreeBSD tunable Linux tunable
|
|
cat <<%%%% |
|
|
ADMIN_SNAPSHOT UNSUPPORTED zfs_admin_snapshot
|
|
ALLOW_REDACTED_DATASET_MOUNT allow_redacted_dataset_mount zfs_allow_redacted_dataset_mount
|
|
ARC_MAX arc.max zfs_arc_max
|
|
ARC_MIN arc.min zfs_arc_min
|
|
ASYNC_BLOCK_MAX_BLOCKS async_block_max_blocks zfs_async_block_max_blocks
|
|
CHECKSUM_EVENTS_PER_SECOND checksum_events_per_second zfs_checksum_events_per_second
|
|
COMMIT_TIMEOUT_PCT commit_timeout_pct zfs_commit_timeout_pct
|
|
COMPRESSED_ARC_ENABLED compressed_arc_enabled zfs_compressed_arc_enabled
|
|
CONDENSE_INDIRECT_COMMIT_ENTRY_DELAY_MS condense.indirect_commit_entry_delay_ms zfs_condense_indirect_commit_entry_delay_ms
|
|
CONDENSE_INDIRECT_OBSOLETE_PCT condense.indirect_obsolete_pct zfs_condense_indirect_obsolete_pct
|
|
CONDENSE_MIN_MAPPING_BYTES condense.min_mapping_bytes zfs_condense_min_mapping_bytes
|
|
DBUF_CACHE_SHIFT dbuf.cache_shift dbuf_cache_shift
|
|
DEADMAN_CHECKTIME_MS deadman.checktime_ms zfs_deadman_checktime_ms
|
|
DEADMAN_FAILMODE deadman.failmode zfs_deadman_failmode
|
|
DEADMAN_SYNCTIME_MS deadman.synctime_ms zfs_deadman_synctime_ms
|
|
DEADMAN_ZIOTIME_MS deadman.ziotime_ms zfs_deadman_ziotime_ms
|
|
DISABLE_IVSET_GUID_CHECK disable_ivset_guid_check zfs_disable_ivset_guid_check
|
|
DMU_OFFSET_NEXT_SYNC dmu_offset_next_sync zfs_dmu_offset_next_sync
|
|
INITIALIZE_CHUNK_SIZE initialize_chunk_size zfs_initialize_chunk_size
|
|
INITIALIZE_VALUE initialize_value zfs_initialize_value
|
|
KEEP_LOG_SPACEMAPS_AT_EXPORT keep_log_spacemaps_at_export zfs_keep_log_spacemaps_at_export
|
|
LUA_MAX_MEMLIMIT lua.max_memlimit zfs_lua_max_memlimit
|
|
L2ARC_MFUONLY l2arc.mfuonly l2arc_mfuonly
|
|
L2ARC_NOPREFETCH l2arc.noprefetch l2arc_noprefetch
|
|
L2ARC_REBUILD_BLOCKS_MIN_L2SIZE l2arc.rebuild_blocks_min_l2size l2arc_rebuild_blocks_min_l2size
|
|
L2ARC_REBUILD_ENABLED l2arc.rebuild_enabled l2arc_rebuild_enabled
|
|
L2ARC_TRIM_AHEAD l2arc.trim_ahead l2arc_trim_ahead
|
|
L2ARC_WRITE_BOOST l2arc.write_boost l2arc_write_boost
|
|
L2ARC_WRITE_MAX l2arc.write_max l2arc_write_max
|
|
LIVELIST_CONDENSE_NEW_ALLOC livelist.condense.new_alloc zfs_livelist_condense_new_alloc
|
|
LIVELIST_CONDENSE_SYNC_CANCEL livelist.condense.sync_cancel zfs_livelist_condense_sync_cancel
|
|
LIVELIST_CONDENSE_SYNC_PAUSE livelist.condense.sync_pause zfs_livelist_condense_sync_pause
|
|
LIVELIST_CONDENSE_ZTHR_CANCEL livelist.condense.zthr_cancel zfs_livelist_condense_zthr_cancel
|
|
LIVELIST_CONDENSE_ZTHR_PAUSE livelist.condense.zthr_pause zfs_livelist_condense_zthr_pause
|
|
LIVELIST_MAX_ENTRIES livelist.max_entries zfs_livelist_max_entries
|
|
LIVELIST_MIN_PERCENT_SHARED livelist.min_percent_shared zfs_livelist_min_percent_shared
|
|
MAX_DATASET_NESTING max_dataset_nesting zfs_max_dataset_nesting
|
|
MAX_MISSING_TVDS max_missing_tvds zfs_max_missing_tvds
|
|
METASLAB_DEBUG_LOAD metaslab.debug_load metaslab_debug_load
|
|
METASLAB_FORCE_GANGING metaslab.force_ganging metaslab_force_ganging
|
|
MULTIHOST_FAIL_INTERVALS multihost.fail_intervals zfs_multihost_fail_intervals
|
|
MULTIHOST_HISTORY multihost.history zfs_multihost_history
|
|
MULTIHOST_IMPORT_INTERVALS multihost.import_intervals zfs_multihost_import_intervals
|
|
MULTIHOST_INTERVAL multihost.interval zfs_multihost_interval
|
|
OVERRIDE_ESTIMATE_RECORDSIZE send.override_estimate_recordsize zfs_override_estimate_recordsize
|
|
PREFETCH_DISABLE prefetch.disable zfs_prefetch_disable
|
|
REBUILD_SCRUB_ENABLED rebuild_scrub_enabled zfs_rebuild_scrub_enabled
|
|
REMOVAL_SUSPEND_PROGRESS removal_suspend_progress zfs_removal_suspend_progress
|
|
REMOVE_MAX_SEGMENT remove_max_segment zfs_remove_max_segment
|
|
RESILVER_MIN_TIME_MS resilver_min_time_ms zfs_resilver_min_time_ms
|
|
SCAN_LEGACY scan_legacy zfs_scan_legacy
|
|
SCAN_SUSPEND_PROGRESS scan_suspend_progress zfs_scan_suspend_progress
|
|
SCAN_VDEV_LIMIT scan_vdev_limit zfs_scan_vdev_limit
|
|
SEND_HOLES_WITHOUT_BIRTH_TIME send_holes_without_birth_time send_holes_without_birth_time
|
|
SLOW_IO_EVENTS_PER_SECOND slow_io_events_per_second zfs_slow_io_events_per_second
|
|
SPA_ASIZE_INFLATION spa.asize_inflation spa_asize_inflation
|
|
SPA_DISCARD_MEMORY_LIMIT spa.discard_memory_limit zfs_spa_discard_memory_limit
|
|
SPA_LOAD_VERIFY_DATA spa.load_verify_data spa_load_verify_data
|
|
SPA_LOAD_VERIFY_METADATA spa.load_verify_metadata spa_load_verify_metadata
|
|
TRIM_EXTENT_BYTES_MIN trim.extent_bytes_min zfs_trim_extent_bytes_min
|
|
TRIM_METASLAB_SKIP trim.metaslab_skip zfs_trim_metaslab_skip
|
|
TRIM_TXG_BATCH trim.txg_batch zfs_trim_txg_batch
|
|
TXG_HISTORY txg.history zfs_txg_history
|
|
TXG_TIMEOUT txg.timeout zfs_txg_timeout
|
|
UNLINK_SUSPEND_PROGRESS UNSUPPORTED zfs_unlink_suspend_progress
|
|
VDEV_FILE_LOGICAL_ASHIFT vdev.file.logical_ashift vdev_file_logical_ashift
|
|
VDEV_FILE_PHYSICAL_ASHIFT vdev.file.physical_ashift vdev_file_physical_ashift
|
|
VDEV_MAX_AUTO_ASHIFT vdev.max_auto_ashift zfs_vdev_max_auto_ashift
|
|
VDEV_MIN_MS_COUNT vdev.min_ms_count zfs_vdev_min_ms_count
|
|
VDEV_VALIDATE_SKIP vdev.validate_skip vdev_validate_skip
|
|
VOL_INHIBIT_DEV UNSUPPORTED zvol_inhibit_dev
|
|
VOL_MODE vol.mode zvol_volmode
|
|
VOL_RECURSIVE vol.recursive UNSUPPORTED
|
|
VOL_USE_BLK_MQ UNSUPPORTED zvol_use_blk_mq
|
|
XATTR_COMPAT xattr_compat zfs_xattr_compat
|
|
ZEVENT_LEN_MAX zevent.len_max zfs_zevent_len_max
|
|
ZEVENT_RETAIN_MAX zevent.retain_max zfs_zevent_retain_max
|
|
ZIO_SLOW_IO_MS zio.slow_io_ms zio_slow_io_ms
|
|
ZIL_SAXATTR zil_saxattr zfs_zil_saxattr
|
|
%%%%
|
|
while read name FreeBSD Linux; do
|
|
eval "export ${name}=\$${UNAME}"
|
|
done
|