Archive-Team
/
zfs
2
0
Fork 0
Code Issues Pull Requests Packages Projects Releases 103 Wiki Activity

Fix incorrect use of unit prefix names in man pages 

Reviewed-by: George Melikov <mail@gmelikov.ru>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Damian Szuberski <szuberskidamian@gmail.com>
Signed-off-by: WHR <msl0000023508@gmail.com>
Closes #13363
This commit is contained in:
WHR 2022-05-03 20:07:04 +08:00 committed by Brian Behlendorf
parent c55b293287
commit a894ae75b8
8 changed files with 109 additions and 109 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

172
man/man4/zfs.4
View File

@ -70,7 +70,7 @@ to a log2 fraction of the target ARC size.
dnode slots allocated in a single operation as a power of 2. dnode slots allocated in a single operation as a power of 2.
The default value minimizes lock contention for the bulk operation performed. The default value minimizes lock contention for the bulk operation performed.
. .
.It Sy dmu_prefetch_max Ns = Ns Sy 134217728 Ns B Po 128MB Pc Pq int .It Sy dmu_prefetch_max Ns = Ns Sy 134217728 Ns B Po 128 MiB Pc Pq int
Limit the amount we can prefetch with one call to this amount in bytes. Limit the amount we can prefetch with one call to this amount in bytes.
This helps to limit the amount of memory that can be used by prefetching. This helps to limit the amount of memory that can be used by prefetching.
. .
@ -164,7 +164,7 @@ If set to
.Sy 100 .Sy 100
we TRIM twice the space required to accommodate upcoming writes. we TRIM twice the space required to accommodate upcoming writes.
A minimum of A minimum of
.Sy 64MB .Sy 64 MiB
will be trimmed. will be trimmed.
It also enables TRIM of the whole L2ARC device upon creation It also enables TRIM of the whole L2ARC device upon creation
or addition to an existing pool or if the header of the device is or addition to an existing pool or if the header of the device is
@ -194,12 +194,12 @@ to enable caching/reading prefetches to/from L2ARC.
.It Sy l2arc_norw Ns = Ns Sy 0 Ns | Ns 1 Pq int .It Sy l2arc_norw Ns = Ns Sy 0 Ns | Ns 1 Pq int
No reads during writes. No reads during writes.
. .
.It Sy l2arc_write_boost Ns = Ns Sy 8388608 Ns B Po 8MB Pc Pq ulong .It Sy l2arc_write_boost Ns = Ns Sy 8388608 Ns B Po 8 MiB Pc Pq ulong
Cold L2ARC devices will have Cold L2ARC devices will have
.Sy l2arc_write_max .Sy l2arc_write_max
increased by this amount while they remain cold. increased by this amount while they remain cold.
. .
.It Sy l2arc_write_max Ns = Ns Sy 8388608 Ns B Po 8MB Pc Pq ulong .It Sy l2arc_write_max Ns = Ns Sy 8388608 Ns B Po 8 MiB Pc Pq ulong
Max write bytes per interval. Max write bytes per interval.
. .
.It Sy l2arc_rebuild_enabled Ns = Ns Sy 1 Ns | Ns 0 Pq int .It Sy l2arc_rebuild_enabled Ns = Ns Sy 1 Ns | Ns 0 Pq int
@ -209,16 +209,16 @@ or attaching an L2ARC device (e.g. the L2ARC device is slow
in reading stored log metadata, or the metadata in reading stored log metadata, or the metadata
has become somehow fragmented/unusable). has become somehow fragmented/unusable).
. .
.It Sy l2arc_rebuild_blocks_min_l2size Ns = Ns Sy 1073741824 Ns B Po 1GB Pc Pq ulong .It Sy l2arc_rebuild_blocks_min_l2size Ns = Ns Sy 1073741824 Ns B Po 1 GiB Pc Pq ulong
Mininum size of an L2ARC device required in order to write log blocks in it. Mininum size of an L2ARC device required in order to write log blocks in it.
The log blocks are used upon importing the pool to rebuild the persistent L2ARC. The log blocks are used upon importing the pool to rebuild the persistent L2ARC.
.Pp .Pp
For L2ARC devices less than 1GB, the amount of data For L2ARC devices less than 1 GiB, the amount of data
.Fn l2arc_evict .Fn l2arc_evict
evicts is significant compared to the amount of restored L2ARC data. evicts is significant compared to the amount of restored L2ARC data.
In this case, do not write log blocks in L2ARC in order not to waste space. In this case, do not write log blocks in L2ARC in order not to waste space.
. .
.It Sy metaslab_aliquot Ns = Ns Sy 1048576 Ns B Po 1MB Pc Pq ulong .It Sy metaslab_aliquot Ns = Ns Sy 1048576 Ns B Po 1 MiB Pc Pq ulong
Metaslab granularity, in bytes. Metaslab granularity, in bytes.
This is roughly similar to what would be referred to as the "stripe size" This is roughly similar to what would be referred to as the "stripe size"
in traditional RAID arrays. in traditional RAID arrays.
@ -229,15 +229,15 @@ before moving on to the next top-level vdev.
Enable metaslab group biasing based on their vdevs' over- or under-utilization Enable metaslab group biasing based on their vdevs' over- or under-utilization
relative to the pool. relative to the pool.
. .
.It Sy metaslab_force_ganging Ns = Ns Sy 16777217 Ns B Ns B Po 16MB + 1B Pc Pq ulong .It Sy metaslab_force_ganging Ns = Ns Sy 16777217 Ns B Po 16 MiB + 1 B Pc Pq ulong
Make some blocks above a certain size be gang blocks. Make some blocks above a certain size be gang blocks.
This option is used by the test suite to facilitate testing. This option is used by the test suite to facilitate testing.
. .
.It Sy zfs_history_output_max Ns = Ns Sy 1048576 Ns B Ns B Po 1MB Pc Pq int .It Sy zfs_history_output_max Ns = Ns Sy 1048576 Ns B Po 1 MiB Pc Pq int
When attempting to log an output nvlist of an ioctl in the on-disk history, When attempting to log an output nvlist of an ioctl in the on-disk history,
the output will not be stored if it is larger than this size (in bytes). the output will not be stored if it is larger than this size (in bytes).
This must be less than This must be less than
.Sy DMU_MAX_ACCESS Pq 64MB . .Sy DMU_MAX_ACCESS Pq 64 MiB .
This applies primarily to This applies primarily to
.Fn zfs_ioc_channel_program Pq cf. Xr zfs-program 8 . .Fn zfs_ioc_channel_program Pq cf. Xr zfs-program 8 .
. .
@ -261,7 +261,7 @@ Prevent metaslabs from being unloaded.
.It Sy metaslab_fragmentation_factor_enabled Ns = Ns Sy 1 Ns | Ns 0 Pq int .It Sy metaslab_fragmentation_factor_enabled Ns = Ns Sy 1 Ns | Ns 0 Pq int
Enable use of the fragmentation metric in computing metaslab weights. Enable use of the fragmentation metric in computing metaslab weights.
. .
.It Sy metaslab_df_max_search Ns = Ns Sy 16777216 Ns B Po 16MB Pc Pq int .It Sy metaslab_df_max_search Ns = Ns Sy 16777216 Ns B Po 16 MiB Pc Pq int
Maximum distance to search forward from the last offset. Maximum distance to search forward from the last offset.
Without this limit, fragmented pools can see Without this limit, fragmented pools can see
.Em >100`000 .Em >100`000
@ -270,7 +270,7 @@ iterations and
becomes the performance limiting factor on high-performance storage. becomes the performance limiting factor on high-performance storage.
.Pp .Pp
With the default setting of With the default setting of
.Sy 16MB , .Sy 16 MiB ,
we typically see less than we typically see less than
.Em 500 .Em 500
iterations, even with very fragmented iterations, even with very fragmented
@ -279,7 +279,7 @@ pools.
The maximum number of iterations possible is The maximum number of iterations possible is
.Sy metaslab_df_max_search / 2^(ashift+1) . .Sy metaslab_df_max_search / 2^(ashift+1) .
With the default setting of With the default setting of
.Sy 16MB .Sy 16 MiB
this is this is
.Em 16*1024 Pq with Sy ashift Ns = Ns Sy 9 .Em 16*1024 Pq with Sy ashift Ns = Ns Sy 9
or or
@ -293,7 +293,7 @@ this tunable controls which segment is used.
If set, we will use the largest free segment. If set, we will use the largest free segment.
If unset, we will use a segment of at least the requested size. If unset, we will use a segment of at least the requested size.
. .
.It Sy zfs_metaslab_max_size_cache_sec Ns = Ns Sy 3600 Ns s Po 1h Pc Pq ulong .It Sy zfs_metaslab_max_size_cache_sec Ns = Ns Sy 3600 Ns s Po 1 hour Pc Pq ulong
When we unload a metaslab, we cache the size of the largest free chunk. When we unload a metaslab, we cache the size of the largest free chunk.
We use that cached size to determine whether or not to load a metaslab We use that cached size to determine whether or not to load a metaslab
for a given allocation. for a given allocation.
@ -344,7 +344,7 @@ and the allocation can't actually be satisfied
.It Sy zfs_vdev_default_ms_count Ns = Ns Sy 200 Pq int .It Sy zfs_vdev_default_ms_count Ns = Ns Sy 200 Pq int
When a vdev is added, target this number of metaslabs per top-level vdev. When a vdev is added, target this number of metaslabs per top-level vdev.
. .
.It Sy zfs_vdev_default_ms_shift Ns = Ns Sy 29 Po 512MB Pc Pq int .It Sy zfs_vdev_default_ms_shift Ns = Ns Sy 29 Po 512 MiB Pc Pq int
Default limit for metaslab size. Default limit for metaslab size.
. .
.It Sy zfs_vdev_max_auto_ashift Ns = Ns Sy ASHIFT_MAX Po 16 Pc Pq ulong .It Sy zfs_vdev_max_auto_ashift Ns = Ns Sy ASHIFT_MAX Po 16 Pc Pq ulong
@ -380,7 +380,7 @@ Note that both this many TXGs and
.Sy metaslab_unload_delay_ms .Sy metaslab_unload_delay_ms
milliseconds must pass before unloading will occur. milliseconds must pass before unloading will occur.
. .
.It Sy metaslab_unload_delay_ms Ns = Ns Sy 600000 Ns ms Po 10min Pc Pq int .It Sy metaslab_unload_delay_ms Ns = Ns Sy 600000 Ns ms Po 10 min Pc Pq int
After a metaslab is used, we keep it loaded for this many milliseconds, After a metaslab is used, we keep it loaded for this many milliseconds,
to attempt to reduce unnecessary reloading. to attempt to reduce unnecessary reloading.
Note, that both this many milliseconds and Note, that both this many milliseconds and
@ -461,7 +461,7 @@ new format when enabling the
feature. feature.
The default is to convert all log entries. The default is to convert all log entries.
. .
.It Sy vdev_removal_max_span Ns = Ns Sy 32768 Ns B Po 32kB Pc Pq int .It Sy vdev_removal_max_span Ns = Ns Sy 32768 Ns B Po 32 KiB Pc Pq int
During top-level vdev removal, chunks of data are copied from the vdev During top-level vdev removal, chunks of data are copied from the vdev
which may include free space in order to trade bandwidth for IOPS. which may include free space in order to trade bandwidth for IOPS.
This parameter determines the maximum span of free space, in bytes, This parameter determines the maximum span of free space, in bytes,
@ -472,10 +472,10 @@ The default value here was chosen to align with
which is a similar concept when doing which is a similar concept when doing
regular reads (but there's no reason it has to be the same). regular reads (but there's no reason it has to be the same).
. .
.It Sy vdev_file_logical_ashift Ns = Ns Sy 9 Po 512B Pc Pq ulong .It Sy vdev_file_logical_ashift Ns = Ns Sy 9 Po 512 B Pc Pq ulong
Logical ashift for file-based devices. Logical ashift for file-based devices.
. .
.It Sy vdev_file_physical_ashift Ns = Ns Sy 9 Po 512B Pc Pq ulong .It Sy vdev_file_physical_ashift Ns = Ns Sy 9 Po 512 B Pc Pq ulong
Physical ashift for file-based devices. Physical ashift for file-based devices.
. .
.It Sy zap_iterate_prefetch Ns = Ns Sy 1 Ns | Ns 0 Pq int .It Sy zap_iterate_prefetch Ns = Ns Sy 1 Ns | Ns 0 Pq int
@ -484,13 +484,13 @@ prefetch the entire object (all leaf blocks).
However, this is limited by However, this is limited by
.Sy dmu_prefetch_max . .Sy dmu_prefetch_max .
. .
.It Sy zfetch_array_rd_sz Ns = Ns Sy 1048576 Ns B Po 1MB Pc Pq ulong .It Sy zfetch_array_rd_sz Ns = Ns Sy 1048576 Ns B Po 1 MiB Pc Pq ulong
If prefetching is enabled, disable prefetching for reads larger than this size. If prefetching is enabled, disable prefetching for reads larger than this size.
. .
.It Sy zfetch_max_distance Ns = Ns Sy 8388608 Ns B Po 8MB Pc Pq uint .It Sy zfetch_max_distance Ns = Ns Sy 8388608 Ns B Po 8 MiB Pc Pq uint
Max bytes to prefetch per stream. Max bytes to prefetch per stream.
. .
.It Sy zfetch_max_idistance Ns = Ns Sy 67108864 Ns B Po 64MB Pc Pq uint .It Sy zfetch_max_idistance Ns = Ns Sy 67108864 Ns B Po 64 MiB Pc Pq uint
Max bytes to prefetch indirects for per stream. Max bytes to prefetch indirects for per stream.
. .
.It Sy zfetch_max_streams Ns = Ns Sy 8 Pq uint .It Sy zfetch_max_streams Ns = Ns Sy 8 Pq uint
@ -513,7 +513,7 @@ The value of
.Sy MAX_ORDER .Sy MAX_ORDER
depends on kernel configuration. depends on kernel configuration.
. .
.It Sy zfs_abd_scatter_min_size Ns = Ns Sy 1536 Ns B Po 1.5kB Pc Pq uint .It Sy zfs_abd_scatter_min_size Ns = Ns Sy 1536 Ns B Po 1.5 KiB Pc Pq uint
This is the minimum allocation size that will use scatter (page-based) ABDs. This is the minimum allocation size that will use scatter (page-based) ABDs.
Smaller allocations will use linear ABDs. Smaller allocations will use linear ABDs.
. .
@ -545,10 +545,10 @@ Percentage of ARC dnodes to try to scan in response to demand for non-metadata
when the number of bytes consumed by dnodes exceeds when the number of bytes consumed by dnodes exceeds
.Sy zfs_arc_dnode_limit . .Sy zfs_arc_dnode_limit .
. .
.It Sy zfs_arc_average_blocksize Ns = Ns Sy 8192 Ns B Po 8kB Pc Pq int .It Sy zfs_arc_average_blocksize Ns = Ns Sy 8192 Ns B Po 8 KiB Pc Pq int
The ARC's buffer hash table is sized based on the assumption of an average The ARC's buffer hash table is sized based on the assumption of an average
block size of this value. block size of this value.
This works out to roughly 1MB of hash table per 1GB of physical memory This works out to roughly 1 MiB of hash table per 1 GiB of physical memory
with 8-byte pointers. with 8-byte pointers.
For configurations with a known larger average block size, For configurations with a known larger average block size,
this value can be increased to reduce the memory footprint. this value can be increased to reduce the memory footprint.
@ -559,9 +559,9 @@ When
.Fn arc_get_data_impl .Fn arc_get_data_impl
waits for this percent of the requested amount of data to be evicted. waits for this percent of the requested amount of data to be evicted.
For example, by default, for every For example, by default, for every
.Em 2kB .Em 2 KiB
that's evicted, that's evicted,
.Em 1kB .Em 1 KiB
of it may be "reused" by a new allocation. of it may be "reused" by a new allocation.
Since this is above Since this is above
.Sy 100 Ns % , .Sy 100 Ns % ,
@ -602,12 +602,12 @@ Under Linux, half of system memory will be used as the limit.
Under Under
.Fx , .Fx ,
the larger of the larger of
.Sy all_system_memory No \- Sy 1GB .Sy all_system_memory No \- Sy 1 GiB
and and
.Sy 5/8 No \(mu Sy all_system_memory .Sy 5/8 No \(mu Sy all_system_memory
will be used as the limit. will be used as the limit.
This value must be at least This value must be at least
.Sy 67108864 Ns B Pq 64MB . .Sy 67108864 Ns B Pq 64 MiB .
.Pp .Pp
This value can be changed dynamically, with some caveats. This value can be changed dynamically, with some caveats.
It cannot be set back to It cannot be set back to
@ -675,7 +675,7 @@ to evict the required number of metadata buffers.
Min size of ARC in bytes. Min size of ARC in bytes.
.No If set to Sy 0 , arc_c_min .No If set to Sy 0 , arc_c_min
will default to consuming the larger of will default to consuming the larger of
.Sy 32MB .Sy 32 MiB
and and
.Sy all_system_memory No / Sy 32 . .Sy all_system_memory No / Sy 32 .
. .
@ -716,7 +716,7 @@ If
equivalent to a quarter of the user-wired memory limit under equivalent to a quarter of the user-wired memory limit under
.Fx .Fx
and to and to
.Sy 134217728 Ns B Pq 128MB .Sy 134217728 Ns B Pq 128 MiB
under Linux. under Linux.
. .
.It Sy zfs_multilist_num_sublists Ns = Ns Sy 0 Pq int .It Sy zfs_multilist_num_sublists Ns = Ns Sy 0 Pq int
@ -794,10 +794,10 @@ Note that in practice, the kernel's shrinker can ask us to evict
up to about four times this for one allocation attempt. up to about four times this for one allocation attempt.
.Pp .Pp
The default limit of The default limit of
.Sy 10000 Pq in practice, Em 160MB No per allocation attempt with 4kB pages .Sy 10000 Pq in practice, Em 160 MiB No per allocation attempt with 4 KiB pages
limits the amount of time spent attempting to reclaim ARC memory to limits the amount of time spent attempting to reclaim ARC memory to
less than 100ms per allocation attempt, less than 100 ms per allocation attempt,
even with a small average compressed block size of ~8kB. even with a small average compressed block size of ~8 KiB.
.Pp .Pp
The parameter can be set to 0 (zero) to disable the limit, The parameter can be set to 0 (zero) to disable the limit,
and only applies on Linux. and only applies on Linux.
@ -805,7 +805,7 @@ and only applies on Linux.
.It Sy zfs_arc_sys_free Ns = Ns Sy 0 Ns B Pq ulong .It Sy zfs_arc_sys_free Ns = Ns Sy 0 Ns B Pq ulong
The target number of bytes the ARC should leave as free memory on the system. The target number of bytes the ARC should leave as free memory on the system.
If zero, equivalent to the bigger of If zero, equivalent to the bigger of
.Sy 512kB No and Sy all_system_memory/64 . .Sy 512 KiB No and Sy all_system_memory/64 .
. .
.It Sy zfs_autoimport_disable Ns = Ns Sy 1 Ns | Ns 0 Pq int .It Sy zfs_autoimport_disable Ns = Ns Sy 1 Ns | Ns 0 Pq int
Disable pool import at module load by ignoring the cache file Disable pool import at module load by ignoring the cache file
@ -846,12 +846,12 @@ bytes of memory and if the obsolete space map object uses more than
bytes on-disk. bytes on-disk.
The condensing process is an attempt to save memory by removing obsolete mappings. The condensing process is an attempt to save memory by removing obsolete mappings.
. .
.It Sy zfs_condense_max_obsolete_bytes Ns = Ns Sy 1073741824 Ns B Po 1GB Pc Pq ulong .It Sy zfs_condense_max_obsolete_bytes Ns = Ns Sy 1073741824 Ns B Po 1 GiB Pc Pq ulong
Only attempt to condense indirect vdev mappings if the on-disk size Only attempt to condense indirect vdev mappings if the on-disk size
of the obsolete space map object is greater than this number of bytes of the obsolete space map object is greater than this number of bytes
.Pq see Sy zfs_condense_indirect_vdevs_enable . .Pq see Sy zfs_condense_indirect_vdevs_enable .
. .
.It Sy zfs_condense_min_mapping_bytes Ns = Ns Sy 131072 Ns B Po 128kB Pc Pq ulong .It Sy zfs_condense_min_mapping_bytes Ns = Ns Sy 131072 Ns B Po 128 KiB Pc Pq ulong
Minimum size vdev mapping to attempt to condense Minimum size vdev mapping to attempt to condense
.Pq see Sy zfs_condense_indirect_vdevs_enable . .Pq see Sy zfs_condense_indirect_vdevs_enable .
. .
@ -867,7 +867,7 @@ to the file clears the log.
This setting does not influence debug prints due to This setting does not influence debug prints due to
.Sy zfs_flags . .Sy zfs_flags .
. .
.It Sy zfs_dbgmsg_maxsize Ns = Ns Sy 4194304 Ns B Po 4MB Pc Pq int .It Sy zfs_dbgmsg_maxsize Ns = Ns Sy 4194304 Ns B Po 4 MiB Pc Pq int
Maximum size of the internal ZFS debug log. Maximum size of the internal ZFS debug log.
. .
.It Sy zfs_dbuf_state_index Ns = Ns Sy 0 Pq int .It Sy zfs_dbuf_state_index Ns = Ns Sy 0 Pq int
@ -907,21 +907,21 @@ This can be used to facilitate automatic fail-over
to a properly configured fail-over partner. to a properly configured fail-over partner.
.El .El
. .
.It Sy zfs_deadman_checktime_ms Ns = Ns Sy 60000 Ns ms Po 1min Pc Pq int .It Sy zfs_deadman_checktime_ms Ns = Ns Sy 60000 Ns ms Po 1 min Pc Pq int
Check time in milliseconds. Check time in milliseconds.
This defines the frequency at which we check for hung I/O requests This defines the frequency at which we check for hung I/O requests
and potentially invoke the and potentially invoke the
.Sy zfs_deadman_failmode .Sy zfs_deadman_failmode
behavior. behavior.
. .
.It Sy zfs_deadman_synctime_ms Ns = Ns Sy 600000 Ns ms Po 10min Pc Pq ulong .It Sy zfs_deadman_synctime_ms Ns = Ns Sy 600000 Ns ms Po 10 min Pc Pq ulong
Interval in milliseconds after which the deadman is triggered and also Interval in milliseconds after which the deadman is triggered and also
the interval after which a pool sync operation is considered to be "hung". the interval after which a pool sync operation is considered to be "hung".
Once this limit is exceeded the deadman will be invoked every Once this limit is exceeded the deadman will be invoked every
.Sy zfs_deadman_checktime_ms .Sy zfs_deadman_checktime_ms
milliseconds until the pool sync completes. milliseconds until the pool sync completes.
. .
.It Sy zfs_deadman_ziotime_ms Ns = Ns Sy 300000 Ns ms Po 5min Pc Pq ulong .It Sy zfs_deadman_ziotime_ms Ns = Ns Sy 300000 Ns ms Po 5 min Pc Pq ulong
Interval in milliseconds after which the deadman is triggered and an Interval in milliseconds after which the deadman is triggered and an
individual I/O operation is considered to be "hung". individual I/O operation is considered to be "hung".
As long as the operation remains "hung", As long as the operation remains "hung",
@ -974,7 +974,7 @@ same object.
Rate limit delay and deadman zevents (which report slow I/O operations) to this many per Rate limit delay and deadman zevents (which report slow I/O operations) to this many per
second. second.
. .
.It Sy zfs_unflushed_max_mem_amt Ns = Ns Sy 1073741824 Ns B Po 1GB Pc Pq ulong .It Sy zfs_unflushed_max_mem_amt Ns = Ns Sy 1073741824 Ns B Po 1 GiB Pc Pq ulong
Upper-bound limit for unflushed metadata changes to be held by the Upper-bound limit for unflushed metadata changes to be held by the
log spacemap in memory, in bytes. log spacemap in memory, in bytes.
. .
@ -988,10 +988,10 @@ The default value means that the space in all the log spacemaps
can add up to no more than can add up to no more than
.Sy 131072 .Sy 131072
blocks (which means blocks (which means
.Em 16GB .Em 16 GiB
of logical space before compression and ditto blocks, of logical space before compression and ditto blocks,
assuming that blocksize is assuming that blocksize is
.Em 128kB ) . .Em 128 KiB ) .
.Pp .Pp
This tunable is important because it involves a trade-off between import This tunable is important because it involves a trade-off between import
time after an unclean export and the frequency of flushing metaslabs. time after an unclean export and the frequency of flushing metaslabs.
@ -1395,7 +1395,7 @@ Similar to
.Sy zfs_free_min_time_ms , .Sy zfs_free_min_time_ms ,
but for cleanup of old indirection records for removed vdevs. but for cleanup of old indirection records for removed vdevs.
. .
.It Sy zfs_immediate_write_sz Ns = Ns Sy 32768 Ns B Po 32kB Pc Pq long .It Sy zfs_immediate_write_sz Ns = Ns Sy 32768 Ns B Po 32 KiB Pc Pq long
Largest data block to write to the ZIL. Largest data block to write to the ZIL.
Larger blocks will be treated as if the dataset being written to had the Larger blocks will be treated as if the dataset being written to had the
.Sy logbias Ns = Ns Sy throughput .Sy logbias Ns = Ns Sy throughput
@ -1405,7 +1405,7 @@ property set.
Pattern written to vdev free space by Pattern written to vdev free space by
.Xr zpool-initialize 8 . .Xr zpool-initialize 8 .
. .
.It Sy zfs_initialize_chunk_size Ns = Ns Sy 1048576 Ns B Po 1MB Pc Pq ulong .It Sy zfs_initialize_chunk_size Ns = Ns Sy 1048576 Ns B Po 1 MiB Pc Pq ulong
Size of writes used by Size of writes used by
.Xr zpool-initialize 8 . .Xr zpool-initialize 8 .
This option is used by the test suite. This option is used by the test suite.
@ -1453,7 +1453,7 @@ This option is used by the test suite to trigger race conditions.
The maximum execution time limit that can be set for a ZFS channel program, The maximum execution time limit that can be set for a ZFS channel program,
specified as a number of Lua instructions. specified as a number of Lua instructions.
. .
.It Sy zfs_lua_max_memlimit Ns = Ns Sy 104857600 Po 100MB Pc Pq ulong .It Sy zfs_lua_max_memlimit Ns = Ns Sy 104857600 Po 100 MiB Pc Pq ulong
The maximum memory limit that can be set for a ZFS channel program, specified The maximum memory limit that can be set for a ZFS channel program, specified
in bytes. in bytes.
. .
@ -1469,9 +1469,9 @@ feature uses to estimate incoming log blocks.
.It Sy zfs_max_logsm_summary_length Ns = Ns Sy 10 Pq ulong .It Sy zfs_max_logsm_summary_length Ns = Ns Sy 10 Pq ulong
Maximum number of rows allowed in the summary of the spacemap log. Maximum number of rows allowed in the summary of the spacemap log.
. .
.It Sy zfs_max_recordsize Ns = Ns Sy 16777216 Po 16MB Pc Pq int .It Sy zfs_max_recordsize Ns = Ns Sy 16777216 Po 16 MiB Pc Pq int
We currently support block sizes from We currently support block sizes from
.Em 512B No to Em 16MB . .Em 512 Po 512 B Pc No to Em 16777216 Po 16 MiB Pc .
The benefits of larger blocks, and thus larger I/O, The benefits of larger blocks, and thus larger I/O,
need to be weighed against the cost of COWing a giant block to modify one byte. need to be weighed against the cost of COWing a giant block to modify one byte.
Additionally, very large blocks can have an impact on I/O latency, Additionally, very large blocks can have an impact on I/O latency,
@ -1535,7 +1535,7 @@ into the special allocation class.
Historical statistics for this many latest multihost updates will be available in Historical statistics for this many latest multihost updates will be available in
.Pa /proc/spl/kstat/zfs/ Ns Ao Ar pool Ac Ns Pa /multihost . .Pa /proc/spl/kstat/zfs/ Ns Ao Ar pool Ac Ns Pa /multihost .
. .
.It Sy zfs_multihost_interval Ns = Ns Sy 1000 Ns ms Po 1s Pc Pq ulong .It Sy zfs_multihost_interval Ns = Ns Sy 1000 Ns ms Po 1 s Pc Pq ulong
Used to control the frequency of multihost writes which are performed when the Used to control the frequency of multihost writes which are performed when the
.Sy multihost .Sy multihost
pool property is on. pool property is on.
@ -1568,7 +1568,7 @@ delay found in the best uberblock indicates actual multihost updates happened
at longer intervals than at longer intervals than
.Sy zfs_multihost_interval . .Sy zfs_multihost_interval .
A minimum of A minimum of
.Em 100ms .Em 100 ms
is enforced. is enforced.
.Pp .Pp
.Sy 0 No is equivalent to Sy 1 . .Sy 0 No is equivalent to Sy 1 .
@ -1617,7 +1617,7 @@ When enabled forces ZFS to sync data when
flags are used allowing holes in a file to be accurately reported. flags are used allowing holes in a file to be accurately reported.
When disabled holes will not be reported in recently dirtied files. When disabled holes will not be reported in recently dirtied files.
. .
.It Sy zfs_pd_bytes_max Ns = Ns Sy 52428800 Ns B Po 50MB Pc Pq int .It Sy zfs_pd_bytes_max Ns = Ns Sy 52428800 Ns B Po 50 MiB Pc Pq int
The number of bytes which should be prefetched during a pool traversal, like The number of bytes which should be prefetched during a pool traversal, like
.Nm zfs Cm send .Nm zfs Cm send
or other data crawling operations. or other data crawling operations.
@ -1656,7 +1656,7 @@ Disable QAT hardware acceleration for AES-GCM encryption.
May be unset after the ZFS modules have been loaded to initialize the QAT May be unset after the ZFS modules have been loaded to initialize the QAT
hardware as long as support is compiled in and the QAT driver is present. hardware as long as support is compiled in and the QAT driver is present.
. .
.It Sy zfs_vnops_read_chunk_size Ns = Ns Sy 1048576 Ns B Po 1MB Pc Pq long .It Sy zfs_vnops_read_chunk_size Ns = Ns Sy 1048576 Ns B Po 1 MiB Pc Pq long
Bytes to read per chunk. Bytes to read per chunk.
. .
.It Sy zfs_read_history Ns = Ns Sy 0 Pq int .It Sy zfs_read_history Ns = Ns Sy 0 Pq int
@ -1666,7 +1666,7 @@ Historical statistics for this many latest reads will be available in
.It Sy zfs_read_history_hits Ns = Ns Sy 0 Ns | Ns 1 Pq int .It Sy zfs_read_history_hits Ns = Ns Sy 0 Ns | Ns 1 Pq int
Include cache hits in read history Include cache hits in read history
. .
.It Sy zfs_rebuild_max_segment Ns = Ns Sy 1048576 Ns B Po 1MB Pc Pq ulong .It Sy zfs_rebuild_max_segment Ns = Ns Sy 1048576 Ns B Po 1 MiB Pc Pq ulong
Maximum read segment size to issue when sequentially resilvering a Maximum read segment size to issue when sequentially resilvering a
top-level vdev. top-level vdev.
. .
@ -1676,7 +1676,7 @@ completes in order to verify the checksums of all blocks which have been
resilvered. resilvered.
This is enabled by default and strongly recommended. This is enabled by default and strongly recommended.
. .
.It Sy zfs_rebuild_vdev_limit Ns = Ns Sy 33554432 Ns B Po 32MB Pc Pq ulong .It Sy zfs_rebuild_vdev_limit Ns = Ns Sy 33554432 Ns B Po 32 MiB Pc Pq ulong
Maximum amount of I/O that can be concurrently issued for a sequential Maximum amount of I/O that can be concurrently issued for a sequential
resilver per leaf device, given in bytes. resilver per leaf device, given in bytes.
. .
@ -1708,7 +1708,7 @@ pool cannot be returned to a healthy state prior to removing the device.
This is used by the test suite so that it can ensure that certain actions This is used by the test suite so that it can ensure that certain actions
happen while in the middle of a removal. happen while in the middle of a removal.
. .
.It Sy zfs_remove_max_segment Ns = Ns Sy 16777216 Ns B Po 16MB Pc Pq int .It Sy zfs_remove_max_segment Ns = Ns Sy 16777216 Ns B Po 16 MiB Pc Pq int
The largest contiguous segment that we will attempt to allocate when removing The largest contiguous segment that we will attempt to allocate when removing
a device. a device.
If there is a performance problem with attempting to allocate large blocks, If there is a performance problem with attempting to allocate large blocks,
@ -1721,7 +1721,7 @@ Ignore the
feature, causing an operation that would start a resilver to feature, causing an operation that would start a resilver to
immediately restart the one in progress. immediately restart the one in progress.
. .
.It Sy zfs_resilver_min_time_ms Ns = Ns Sy 3000 Ns ms Po 3s Pc Pq int .It Sy zfs_resilver_min_time_ms Ns = Ns Sy 3000 Ns ms Po 3 s Pc Pq int
Resilvers are processed by the sync thread. Resilvers are processed by the sync thread.
While resilvering, it will spend at least this much time While resilvering, it will spend at least this much time
working on a resilver between TXG flushes. working on a resilver between TXG flushes.
@ -1732,12 +1732,12 @@ even if there were unrepairable errors.
Intended to be used during pool repair or recovery to Intended to be used during pool repair or recovery to
stop resilvering when the pool is next imported. stop resilvering when the pool is next imported.
. .
.It Sy zfs_scrub_min_time_ms Ns = Ns Sy 1000 Ns ms Po 1s Pc Pq int .It Sy zfs_scrub_min_time_ms Ns = Ns Sy 1000 Ns ms Po 1 s Pc Pq int
Scrubs are processed by the sync thread. Scrubs are processed by the sync thread.
While scrubbing, it will spend at least this much time While scrubbing, it will spend at least this much time
working on a scrub between TXG flushes. working on a scrub between TXG flushes.
. .
.It Sy zfs_scan_checkpoint_intval Ns = Ns Sy 7200 Ns s Po 2h Pc Pq int .It Sy zfs_scan_checkpoint_intval Ns = Ns Sy 7200 Ns s Po 2 hour Pc Pq int
To preserve progress across reboots, the sequential scan algorithm periodically To preserve progress across reboots, the sequential scan algorithm periodically
needs to stop metadata scanning and issue all the verification I/O to disk. needs to stop metadata scanning and issue all the verification I/O to disk.
The frequency of this flushing is determined by this tunable. The frequency of this flushing is determined by this tunable.
@ -1774,7 +1774,7 @@ Otherwise indicates that the legacy algorithm will be used,
where I/O is initiated as soon as it is discovered. where I/O is initiated as soon as it is discovered.
Unsetting will not affect scrubs or resilvers that are already in progress. Unsetting will not affect scrubs or resilvers that are already in progress.
. .
.It Sy zfs_scan_max_ext_gap Ns = Ns Sy 2097152 Ns B Po 2MB Pc Pq int .It Sy zfs_scan_max_ext_gap Ns = Ns Sy 2097152 Ns B Po 2 MiB Pc Pq int
Sets the largest gap in bytes between scrub/resilver I/O operations Sets the largest gap in bytes between scrub/resilver I/O operations
that will still be considered sequential for sorting purposes. that will still be considered sequential for sorting purposes.
Changing this value will not Changing this value will not
@ -1803,7 +1803,7 @@ When disabled, the memory limit may be exceeded by fast disks.
Freezes a scrub/resilver in progress without actually pausing it. Freezes a scrub/resilver in progress without actually pausing it.
Intended for testing/debugging. Intended for testing/debugging.
. .
.It Sy zfs_scan_vdev_limit Ns = Ns Sy 4194304 Ns B Po 4MB Pc Pq int .It Sy zfs_scan_vdev_limit Ns = Ns Sy 4194304 Ns B Po 4 MiB Pc Pq int
Maximum amount of data that can be concurrently issued at once for scrubs and Maximum amount of data that can be concurrently issued at once for scrubs and
resilvers per leaf device, given in bytes. resilvers per leaf device, given in bytes.
. .
@ -1823,7 +1823,7 @@ The fill fraction of the
internal queues. internal queues.
The fill fraction controls the timing with which internal threads are woken up. The fill fraction controls the timing with which internal threads are woken up.
. .
.It Sy zfs_send_no_prefetch_queue_length Ns = Ns Sy 1048576 Ns B Po 1MB Pc Pq int .It Sy zfs_send_no_prefetch_queue_length Ns = Ns Sy 1048576 Ns B Po 1 MiB Pc Pq int
The maximum number of bytes allowed in The maximum number of bytes allowed in
.Nm zfs Cm send Ns 's .Nm zfs Cm send Ns 's
internal queues. internal queues.
@ -1834,7 +1834,7 @@ The fill fraction of the
prefetch queue. prefetch queue.
The fill fraction controls the timing with which internal threads are woken up. The fill fraction controls the timing with which internal threads are woken up.
. .
.It Sy zfs_send_queue_length Ns = Ns Sy 16777216 Ns B Po 16MB Pc Pq int .It Sy zfs_send_queue_length Ns = Ns Sy 16777216 Ns B Po 16 MiB Pc Pq int
The maximum number of bytes allowed that will be prefetched by The maximum number of bytes allowed that will be prefetched by
.Nm zfs Cm send . .Nm zfs Cm send .
This value must be at least twice the maximum block size in use. This value must be at least twice the maximum block size in use.
@ -1845,20 +1845,20 @@ The fill fraction of the
queue. queue.
The fill fraction controls the timing with which internal threads are woken up. The fill fraction controls the timing with which internal threads are woken up.
. .
.It Sy zfs_recv_queue_length Ns = Ns Sy 16777216 Ns B Po 16MB Pc Pq int .It Sy zfs_recv_queue_length Ns = Ns Sy 16777216 Ns B Po 16 MiB Pc Pq int
The maximum number of bytes allowed in the The maximum number of bytes allowed in the
.Nm zfs Cm receive .Nm zfs Cm receive
queue. queue.
This value must be at least twice the maximum block size in use. This value must be at least twice the maximum block size in use.
. .
.It Sy zfs_recv_write_batch_size Ns = Ns Sy 1048576 Ns B Po 1MB Pc Pq int .It Sy zfs_recv_write_batch_size Ns = Ns Sy 1048576 Ns B Po 1 MiB Pc Pq int
The maximum amount of data, in bytes, that The maximum amount of data, in bytes, that
.Nm zfs Cm receive .Nm zfs Cm receive
will write in one DMU transaction. will write in one DMU transaction.
This is the uncompressed size, even when receiving a compressed send stream. This is the uncompressed size, even when receiving a compressed send stream.
This setting will not reduce the write size below a single block. This setting will not reduce the write size below a single block.
Capped at a maximum of Capped at a maximum of
.Sy 32MB . .Sy 32 MiB .
. .
.It Sy zfs_override_estimate_recordsize Ns = Ns Sy 0 Ns | Ns 1 Pq ulong .It Sy zfs_override_estimate_recordsize Ns = Ns Sy 0 Ns | Ns 1 Pq ulong
Setting this variable overrides the default logic for estimating block Setting this variable overrides the default logic for estimating block
@ -1873,7 +1873,7 @@ and you require accurate zfs send size estimates.
Flushing of data to disk is done in passes. Flushing of data to disk is done in passes.
Defer frees starting in this pass. Defer frees starting in this pass.
. .
.It Sy zfs_spa_discard_memory_limit Ns = Ns Sy 16777216 Ns B Po 16MB Pc Pq int .It Sy zfs_spa_discard_memory_limit Ns = Ns Sy 16777216 Ns B Po 16 MiB Pc Pq int
Maximum memory used for prefetching a checkpoint's space map on each Maximum memory used for prefetching a checkpoint's space map on each
vdev while discarding the checkpoint. vdev while discarding the checkpoint.
. .
@ -1895,11 +1895,11 @@ the average number of sync passes; because when we turn compression off,
many blocks' size will change, and thus we have to re-allocate many blocks' size will change, and thus we have to re-allocate
(not overwrite) them. (not overwrite) them.
It also increases the number of It also increases the number of
.Em 128kB .Em 128 KiB
allocations (e.g. for indirect blocks and spacemaps) allocations (e.g. for indirect blocks and spacemaps)
because these will not be compressed. because these will not be compressed.
The The
.Em 128kB .Em 128 KiB
allocations are especially detrimental to performance allocations are especially detrimental to performance
on highly fragmented systems, which may have very few free segments of this size, on highly fragmented systems, which may have very few free segments of this size,
and may need to load new metaslabs to satisfy these allocations. and may need to load new metaslabs to satisfy these allocations.
@ -1914,11 +1914,11 @@ The default value of
.Sy 75% .Sy 75%
will create a maximum of one thread per CPU. will create a maximum of one thread per CPU.
. .
.It Sy zfs_trim_extent_bytes_max Ns = Ns Sy 134217728 Ns B Po 128MB Pc Pq uint .It Sy zfs_trim_extent_bytes_max Ns = Ns Sy 134217728 Ns B Po 128 MiB Pc Pq uint
Maximum size of TRIM command. Maximum size of TRIM command.
Larger ranges will be split into chunks no larger than this value before issuing. Larger ranges will be split into chunks no larger than this value before issuing.
. .
.It Sy zfs_trim_extent_bytes_min Ns = Ns Sy 32768 Ns B Po 32kB Pc Pq uint .It Sy zfs_trim_extent_bytes_min Ns = Ns Sy 32768 Ns B Po 32 KiB Pc Pq uint
Minimum size of TRIM commands. Minimum size of TRIM commands.
TRIM ranges smaller than this will be skipped, TRIM ranges smaller than this will be skipped,
unless they're part of a larger range which was chunked. unless they're part of a larger range which was chunked.
@ -1966,20 +1966,20 @@ This is normally not helpful because the extents to be trimmed
will have been already been aggregated by the metaslab. will have been already been aggregated by the metaslab.
This option is provided for debugging and performance analysis. This option is provided for debugging and performance analysis.
. .
.It Sy zfs_vdev_aggregation_limit Ns = Ns Sy 1048576 Ns B Po 1MB Pc Pq int .It Sy zfs_vdev_aggregation_limit Ns = Ns Sy 1048576 Ns B Po 1 MiB Pc Pq int
Max vdev I/O aggregation size. Max vdev I/O aggregation size.
. .
.It Sy zfs_vdev_aggregation_limit_non_rotating Ns = Ns Sy 131072 Ns B Po 128kB Pc Pq int .It Sy zfs_vdev_aggregation_limit_non_rotating Ns = Ns Sy 131072 Ns B Po 128 KiB Pc Pq int
Max vdev I/O aggregation size for non-rotating media. Max vdev I/O aggregation size for non-rotating media.
. .
.It Sy zfs_vdev_cache_bshift Ns = Ns Sy 16 Po 64kB Pc Pq int .It Sy zfs_vdev_cache_bshift Ns = Ns Sy 16 Po 64 KiB Pc Pq int
Shift size to inflate reads to. Shift size to inflate reads to.
. .
.It Sy zfs_vdev_cache_max Ns = Ns Sy 16384 Ns B Po 16kB Pc Pq int .It Sy zfs_vdev_cache_max Ns = Ns Sy 16384 Ns B Po 16 KiB Pc Pq int
Inflate reads smaller than this value to meet the Inflate reads smaller than this value to meet the
.Sy zfs_vdev_cache_bshift .Sy zfs_vdev_cache_bshift
size size
.Pq default Sy 64kB . .Pq default Sy 64 KiB .
. .
.It Sy zfs_vdev_cache_size Ns = Ns Sy 0 Pq int .It Sy zfs_vdev_cache_size Ns = Ns Sy 0 Pq int
Total size of the per-disk cache in bytes. Total size of the per-disk cache in bytes.
@ -2001,7 +2001,7 @@ lacks locality as defined by
Operations within this that are not immediately following the previous operation Operations within this that are not immediately following the previous operation
are incremented by half. are incremented by half.
. .
.It Sy zfs_vdev_mirror_rotating_seek_offset Ns = Ns Sy 1048576 Ns B Po 1MB Pc Pq int .It Sy zfs_vdev_mirror_rotating_seek_offset Ns = Ns Sy 1048576 Ns B Po 1 MiB Pc Pq int
The maximum distance for the last queued I/O operation in which The maximum distance for the last queued I/O operation in which
the balancing algorithm considers an operation to have locality. the balancing algorithm considers an operation to have locality.
.No See Sx ZFS I/O SCHEDULER . .No See Sx ZFS I/O SCHEDULER .
@ -2019,11 +2019,11 @@ locality as defined by the
Operations within this that are not immediately following the previous operation Operations within this that are not immediately following the previous operation
are incremented by half. are incremented by half.
. .
.It Sy zfs_vdev_read_gap_limit Ns = Ns Sy 32768 Ns B Po 32kB Pc Pq int .It Sy zfs_vdev_read_gap_limit Ns = Ns Sy 32768 Ns B Po 32 KiB Pc Pq int
Aggregate read I/O operations if the on-disk gap between them is within this Aggregate read I/O operations if the on-disk gap between them is within this
threshold. threshold.
. .
.It Sy zfs_vdev_write_gap_limit Ns = Ns Sy 4096 Ns B Po 4kB Pc Pq int .It Sy zfs_vdev_write_gap_limit Ns = Ns Sy 4096 Ns B Po 4 KiB Pc Pq int
Aggregate write I/O operations if the on-disk gap between them is within this Aggregate write I/O operations if the on-disk gap between them is within this
threshold. threshold.
. .
@ -2071,7 +2071,7 @@ Setting this to
.Sy 0 .Sy 0
disables duplicate detection. disables duplicate detection.
. .
.It Sy zfs_zevent_retain_expire_secs Ns = Ns Sy 900 Ns s Po 15min Pc Pq int .It Sy zfs_zevent_retain_expire_secs Ns = Ns Sy 900 Ns s Po 15 min Pc Pq int
Lifespan for a recent ereport that was retained for duplicate checking. Lifespan for a recent ereport that was retained for duplicate checking.
. .
.It Sy zfs_zil_clean_taskq_maxalloc Ns = Ns Sy 1048576 Pq int .It Sy zfs_zil_clean_taskq_maxalloc Ns = Ns Sy 1048576 Pq int
@ -2090,10 +2090,10 @@ The default value of
.Sy 100% .Sy 100%
will create a maximum of one thread per cpu. will create a maximum of one thread per cpu.
. .
.It Sy zil_maxblocksize Ns = Ns Sy 131072 Ns B Po 128kB Pc Pq int .It Sy zil_maxblocksize Ns = Ns Sy 131072 Ns B Po 128 KiB Pc Pq int
This sets the maximum block size used by the ZIL. This sets the maximum block size used by the ZIL.
On very fragmented pools, lowering this On very fragmented pools, lowering this
.Pq typically to Sy 36kB .Pq typically to Sy 36 KiB
can improve performance. can improve performance.
. .
.It Sy zil_nocacheflush Ns = Ns Sy 0 Ns | Ns 1 Pq int .It Sy zil_nocacheflush Ns = Ns Sy 0 Ns | Ns 1 Pq int
@ -2106,7 +2106,7 @@ if a volatile out-of-order write cache is enabled.
Disable intent logging replay. Disable intent logging replay.
Can be disabled for recovery from corrupted ZIL. Can be disabled for recovery from corrupted ZIL.
. .
.It Sy zil_slog_bulk Ns = Ns Sy 786432 Ns B Po 768kB Pc Pq ulong .It Sy zil_slog_bulk Ns = Ns Sy 786432 Ns B Po 768 KiB Pc Pq ulong
Limit SLOG write size per commit executed with synchronous priority. Limit SLOG write size per commit executed with synchronous priority.
Any writes above that will be executed with lower (asynchronous) priority Any writes above that will be executed with lower (asynchronous) priority
to limit potential SLOG device abuse by single active ZIL writer. to limit potential SLOG device abuse by single active ZIL writer.
@ -2138,7 +2138,7 @@ diagnostic information for hang conditions which don't involve a mutex
or other locking primitive: typically conditions in which a thread in or other locking primitive: typically conditions in which a thread in
the zio pipeline is looping indefinitely. the zio pipeline is looping indefinitely.
. .
.It Sy zio_slow_io_ms Ns = Ns Sy 30000 Ns ms Po 30s Pc Pq int .It Sy zio_slow_io_ms Ns = Ns Sy 30000 Ns ms Po 30 s Pc Pq int
When an I/O operation takes more than this much time to complete, When an I/O operation takes more than this much time to complete,
it's marked as slow. it's marked as slow.
Each slow operation causes a delay zevent. Each slow operation causes a delay zevent.
@ -2214,7 +2214,7 @@ many blocks, where block size is determined by the
.Sy volblocksize .Sy volblocksize
property of a zvol. property of a zvol.
. .
.It Sy zvol_prefetch_bytes Ns = Ns Sy 131072 Ns B Po 128kB Pc Pq uint .It Sy zvol_prefetch_bytes Ns = Ns Sy 131072 Ns B Po 128 KiB Pc Pq uint
When adding a zvol to the system, prefetch this many bytes When adding a zvol to the system, prefetch this many bytes
from the start and end of the volume. from the start and end of the volume.
Prefetching these regions of the volume is desirable, Prefetching these regions of the volume is desirable,
@ -2406,7 +2406,7 @@ delay
Note, that since the delay is added to the outstanding time remaining on the Note, that since the delay is added to the outstanding time remaining on the
most recent transaction it's effectively the inverse of IOPS. most recent transaction it's effectively the inverse of IOPS.
Here, the midpoint of Here, the midpoint of
.Em 500us .Em 500 us
translates to translates to
.Em 2000 IOPS . .Em 2000 IOPS .
The shape of the curve The shape of the curve

10
man/man7/zfsprops.7
View File

@ -904,7 +904,7 @@ after compression, otherwise the compression will not be considered worthwhile
and the block saved uncompressed. and the block saved uncompressed.
Note that when the logical block is less than Note that when the logical block is less than
8 times the disk sector size this effectively reduces the necessary compression 8 times the disk sector size this effectively reduces the necessary compression
ratio; for example, 8kB blocks on disks with 4kB disk sectors must compress to 1/2 ratio; for example, 8 KiB blocks on disks with 4 KiB disk sectors must compress to 1/2
or less of their original size. or less of their original size.
.It Xo .It Xo
.Sy context Ns = Ns Sy none Ns | Ns .Sy context Ns = Ns Sy none Ns | Ns
@ -1199,7 +1199,7 @@ blocks into the special allocation class.
Blocks smaller than or equal to this Blocks smaller than or equal to this
value will be assigned to the special allocation class while greater blocks value will be assigned to the special allocation class while greater blocks
will be assigned to the regular class. will be assigned to the regular class.
Valid values are zero or a power of two from 512B up to 1M. Valid values are zero or a power of two from 512 up to 1048576 (1 MiB).
The default size is 0 which means no small file blocks The default size is 0 which means no small file blocks
will be allocated in the special class. will be allocated in the special class.
.Pp .Pp
@ -1426,13 +1426,13 @@ Use of this property for general purpose file systems is strongly discouraged,
and may adversely affect performance. and may adversely affect performance.
.Pp .Pp
The size specified must be a power of two greater than or equal to The size specified must be a power of two greater than or equal to
.Ar 512B .Ar 512 B
and less than or equal to and less than or equal to
.Ar 128kB . .Ar 128 KiB .
If the If the
.Sy large_blocks .Sy large_blocks
feature is enabled on the pool, the size may be up to feature is enabled on the pool, the size may be up to
.Ar 1MB . .Ar 1 MiB .
See See
.Xr zpool-features 7 .Xr zpool-features 7
for details on ZFS feature flags. for details on ZFS feature flags.

16
man/man7/zpool-features.7
View File

@ -157,7 +157,7 @@ separated by whitespace and/or commas.
Only features present in all files are enabled. Only features present in all files are enabled.
.Pp .Pp
Simple sanity checks are applied to the files: Simple sanity checks are applied to the files:
they must be between 1B and 16kB in size, and must end with a newline character. they must be between 1 B and 16 KiB in size, and must end with a newline character.
.Pp .Pp
The requested features are applied when a pool is created using The requested features are applied when a pool is created using
.Nm zpool Cm create Fl o Sy compatibility Ns = Ns Ar … .Nm zpool Cm create Fl o Sy compatibility Ns = Ns Ar …
@ -446,7 +446,7 @@ or smaller can take advantage of this feature.
When this feature is enabled, the contents of highly-compressible blocks are When this feature is enabled, the contents of highly-compressible blocks are
stored in the block "pointer" itself (a misnomer in this case, as it contains stored in the block "pointer" itself (a misnomer in this case, as it contains
the compressed data, rather than a pointer to its location on disk). the compressed data, rather than a pointer to its location on disk).
Thus the space of the block (one sector, typically 512B or 4kB) is saved, Thus the space of the block (one sector, typically 512 B or 4 KiB) is saved,
and no additional I/O is needed to read and write the data block. and no additional I/O is needed to read and write the data block.
. .
\*[instant-never] \*[instant-never]
@ -565,29 +565,29 @@ already exist on the receiving side.
\*[instant-never] \*[instant-never]
. .
.feature org.open-zfs large_blocks no extensible_dataset .feature org.open-zfs large_blocks no extensible_dataset
This feature allows the record size on a dataset to be set larger than 128kB. This feature allows the record size on a dataset to be set larger than 128 KiB.
.Pp .Pp
This feature becomes This feature becomes
.Sy active .Sy active
once a dataset contains a file with a block size larger than 128kB, once a dataset contains a file with a block size larger than 128 KiB,
and will return to being and will return to being
.Sy enabled .Sy enabled
once all filesystems that have ever had their recordsize larger than 128kB once all filesystems that have ever had their recordsize larger than 128 KiB
are destroyed. are destroyed.
. .
.feature org.zfsonlinux large_dnode no extensible_dataset .feature org.zfsonlinux large_dnode no extensible_dataset
This feature allows the size of dnodes in a dataset to be set larger than 512B. This feature allows the size of dnodes in a dataset to be set larger than 512 B.
. .
This feature becomes This feature becomes
.Sy active .Sy active
once a dataset contains an object with a dnode larger than 512B, once a dataset contains an object with a dnode larger than 512 B,
which occurs as a result of setting the which occurs as a result of setting the
.Sy dnodesize .Sy dnodesize
dataset property to a value other than dataset property to a value other than
.Sy legacy . .Sy legacy .
The feature will return to being The feature will return to being
.Sy enabled .Sy enabled
once all filesystems that have ever contained a dnode larger than 512B once all filesystems that have ever contained a dnode larger than 512 B
are destroyed. are destroyed.
Large dnodes allow more data to be stored in the bonus buffer, Large dnodes allow more data to be stored in the bonus buffer,
thus potentially improving performance by avoiding the use of spill blocks. thus potentially improving performance by avoiding the use of spill blocks.

6
man/man7/zpoolconcepts.7
View File

@ -107,7 +107,7 @@ Unlike raidz, dRAID uses a fixed stripe width (padding as necessary with
zeros) to allow fully sequential resilvering. zeros) to allow fully sequential resilvering.
This fixed stripe width significantly effects both usable capacity and IOPS. This fixed stripe width significantly effects both usable capacity and IOPS.
For example, with the default For example, with the default
.Em D=8 No and Em 4kB No disk sectors the minimum allocation size is Em 32kB . .Em D=8 No and Em 4 KiB No disk sectors the minimum allocation size is Em 32 KiB .
If using compression, this relatively large allocation size can reduce the If using compression, this relatively large allocation size can reduce the
effective compression ratio. effective compression ratio.
When using ZFS volumes and dRAID, the default of the When using ZFS volumes and dRAID, the default of the
@ -422,13 +422,13 @@ asynchronously when importing the pool in L2ARC (persistent L2ARC).
This can be disabled by setting This can be disabled by setting
.Sy l2arc_rebuild_enabled Ns = Ns Sy 0 . .Sy l2arc_rebuild_enabled Ns = Ns Sy 0 .
For cache devices smaller than For cache devices smaller than
.Em 1GB , .Em 1 GiB ,
we do not write the metadata structures we do not write the metadata structures
required for rebuilding the L2ARC in order not to waste space. required for rebuilding the L2ARC in order not to waste space.
This can be changed with This can be changed with
.Sy l2arc_rebuild_blocks_min_l2size . .Sy l2arc_rebuild_blocks_min_l2size .
The cache device header The cache device header
.Pq Em 512B .Pq Em 512 B
is updated even if no metadata structures are written. is updated even if no metadata structures are written.
Setting Setting
.Sy l2arc_headroom Ns = Ns Sy 0 .Sy l2arc_headroom Ns = Ns Sy 0

2
man/man8/zfs-program.8
View File

@ -73,7 +73,7 @@ The default limit is 10 million instructions, and it can be set to a maximum of
Memory limit, in bytes. Memory limit, in bytes.
If a channel program attempts to allocate more memory than the given limit, it If a channel program attempts to allocate more memory than the given limit, it
will be stopped and an error returned. will be stopped and an error returned.
The default memory limit is 10 MB, and can be set to a maximum of 100 MB. The default memory limit is 10 MiB, and can be set to a maximum of 100 MiB.
.El .El
.Pp .Pp
All remaining argument strings will be passed directly to the Lua script as All remaining argument strings will be passed directly to the Lua script as

8
man/man8/zfs-send.8
View File

@ -102,12 +102,12 @@ The incremental source may be specified as with the
.Fl i .Fl i
option. option.
.It Fl L , -large-block .It Fl L , -large-block
Generate a stream which may contain blocks larger than 128KB. Generate a stream which may contain blocks larger than 128 KiB.
This flag has no effect if the This flag has no effect if the
.Sy large_blocks .Sy large_blocks
pool feature is disabled, or if the pool feature is disabled, or if the
.Sy recordsize .Sy recordsize
property of this filesystem has never been set above 128KB. property of this filesystem has never been set above 128 KiB.
The receiving system must have the The receiving system must have the
.Sy large_blocks .Sy large_blocks
pool feature enabled as well. pool feature enabled as well.
@ -317,12 +317,12 @@ Deduplicated send is no longer supported.
This flag is accepted for backwards compatibility, but a regular, This flag is accepted for backwards compatibility, but a regular,
non-deduplicated stream will be generated. non-deduplicated stream will be generated.
.It Fl L , -large-block .It Fl L , -large-block
Generate a stream which may contain blocks larger than 128KB. Generate a stream which may contain blocks larger than 128 KiB.
This flag has no effect if the This flag has no effect if the
.Sy large_blocks .Sy large_blocks
pool feature is disabled, or if the pool feature is disabled, or if the
.Sy recordsize .Sy recordsize
property of this filesystem has never been set above 128KB. property of this filesystem has never been set above 128 KiB.
The receiving system must have the The receiving system must have the
.Sy large_blocks .Sy large_blocks
pool feature enabled as well. pool feature enabled as well.

2
man/man8/zpool-list.8
View File

@ -128,7 +128,7 @@ zion - - - - - - - FAULTED -
The following command displays the detailed information for the pool The following command displays the detailed information for the pool
.Ar data . .Ar data .
This pool is comprised of a single raidz vdev where one of its devices This pool is comprised of a single raidz vdev where one of its devices
increased its capacity by 10GB. increased its capacity by 10 GiB.
In this example, the pool will not be able to utilize this extra capacity until In this example, the pool will not be able to utilize this extra capacity until
all the devices under the raidz vdev have been expanded. all the devices under the raidz vdev have been expanded.
.Bd -literal -compact -offset Ds .Bd -literal -compact -offset Ds

2
man/man8/zpool.8
View File

@ -395,7 +395,7 @@ The command to remove the mirrored data
The following command displays the detailed information for the pool The following command displays the detailed information for the pool
.Ar data . .Ar data .
This pool is comprised of a single raidz vdev where one of its devices This pool is comprised of a single raidz vdev where one of its devices
increased its capacity by 10GB. increased its capacity by 10 GiB.
In this example, the pool will not be able to utilize this extra capacity until In this example, the pool will not be able to utilize this extra capacity until
all the devices under the raidz vdev have been expanded. all the devices under the raidz vdev have been expanded.
.Bd -literal -compact -offset Ds .Bd -literal -compact -offset Ds