zfs-module-parameters(5) ZFS module parameters

DESCRIPTION

Description of the different parameters to the ZFS module.

Module parameters

l2arc_feed_again (int)

Turbo L2ARC warmup

Use 1 for yes (default) and 0 to disable.

l2arc_feed_min_ms (ulong)

Min feed interval in milliseconds

Default value: 200.

l2arc_feed_secs (ulong)

Seconds between L2ARC writing

Default value: 1.

l2arc_headroom (ulong)

Number of max device writes to precache

Default value: 2.

l2arc_headroom_boost (ulong)

Compressed l2arc_headroom multiplier

Default value: 200.

l2arc_nocompress (int)

Skip compressing L2ARC buffers

Use 1 for yes and 0 for no (default).

l2arc_noprefetch (int)

Skip caching prefetched buffers

Use 1 for yes (default) and 0 to disable.

l2arc_norw (int)

No reads during writes

Use 1 for yes and 0 for no (default).

l2arc_write_boost (ulong)

Extra write bytes during device warmup

Default value: 8,388,608.

l2arc_write_max (ulong)

Max write bytes per interval

Default value: 8,388,608.

metaslab_aliquot (ulong)

Metaslab granularity, in bytes. This is roughly similar to what would be referred to as the "stripe size" in traditional RAID arrays. In normal operation, ZFS will try to write this amount of data to a top-level vdev before moving on to the next one.

Default value: 524,288.

metaslab_bias_enabled (int)

Enable metaslab group biasing based on its vdev's over- or under-utilization relative to the pool.

Use 1 for yes (default) and 0 for no.

metaslab_debug_load (int)

Load all metaslabs during pool import.

Use 1 for yes and 0 for no (default).

metaslab_debug_unload (int)

Prevent metaslabs from being unloaded.

Use 1 for yes and 0 for no (default).

metaslab_fragmentation_factor_enabled (int)

Enable use of the fragmentation metric in computing metaslab weights.

Use 1 for yes (default) and 0 for no.

metaslabs_per_vdev (int)

When a vdev is added, it will be divided into approximately (but no more than) this number of metaslabs.

Default value: 200.

metaslab_preload_enabled (int)

Enable metaslab group preloading.

Use 1 for yes (default) and 0 for no.

metaslab_lba_weighting_enabled (int)

Give more weight to metaslabs with lower LBAs, assuming they have greater bandwidth as is typically the case on a modern constant angular velocity disk drive.

Use 1 for yes (default) and 0 for no.

spa_config_path (charp)

SPA config file

Default value: /etc/zfs/zpool.cache.

spa_asize_inflation (int)

Multiplication factor used to estimate actual disk consumption from the size of data being written. The default value is a worst case estimate, but lower values may be valid for a given pool depending on its configuration. Pool administrators who understand the factors involved may wish to specify a more realistic inflation factor, particularly if they operate close to quota or capacity limits.

Default value: 24

spa_load_verify_data (int)

Whether to traverse data blocks during an "extreme rewind" (-X) import. Use 0 to disable and 1 to enable.

An extreme rewind import normally performs a full traversal of all blocks in the pool for verification. If this parameter is set to 0, the traversal skips non-metadata blocks. It can be toggled once the import has started to stop or start the traversal of non-metadata blocks.

Default value: 1

spa_load_verify_metadata (int)

Whether to traverse blocks during an "extreme rewind" (-X) pool import. Use 0 to disable and 1 to enable.

An extreme rewind import normally performs a full traversal of all blocks in the pool for verification. If this parameter is set to 1, the traversal is not performed. It can be toggled once the import has started to stop or start the traversal.

Default value: 1

spa_load_verify_maxinflight (int)

Maximum concurrent I/Os during the traversal performed during an "extreme rewind" (-X) pool import.

Default value: 10000

spa_slop_shift (int)

Normally, we don't allow the last 3.2% (1/(2^spa_slop_shift)) of space in the pool to be consumed. This ensures that we don't run the pool completely out of space, due to unaccounted changes (e.g. to the MOS). It also limits the worst-case time to allocate space. If we have less than this amount of free space, most ZPL operations (e.g. write, create) will return ENOSPC.

Default value: 5

zfetch_array_rd_sz (ulong)

If prefetching is enabled, disable prefetching for reads larger than this size.

Default value: 1,048,576.

zfetch_block_cap (uint)

Max number of blocks to prefetch at a time

Default value: 256.

zfetch_max_streams (uint)

Max number of streams per zfetch (prefetch streams per file).

Default value: 8.

zfetch_min_sec_reap (uint)

Min time before an active prefetch stream can be reclaimed

Default value: 2.

zfs_arc_average_blocksize (int)

The ARC's buffer hash table is sized based on the assumption of an average block size of zfs_arc_average_blocksize (default 8K). This works out to roughly 1MB of hash table per 1GB of physical memory with 8-byte pointers. For configurations with a known larger average block size this value can be increased to reduce the memory footprint.

Default value: 8192.

zfs_arc_evict_batch_limit (int)

Number ARC headers to evict per sub-list before proceeding to another sub-list. This batch-style operation prevents entire sub-lists from being evicted at once but comes at a cost of additional unlocking and locking.

Default value: 10.

zfs_arc_grow_retry (int)

Seconds before growing arc size

Default value: 5.

zfs_arc_lotsfree_percent (int)

Throttle I/O when free system memory drops below this percentage of total system memory. Setting this value to 0 will disable the throttle.

Default value: 10.

zfs_arc_max (ulong)

Max arc size

Default value: 0.

zfs_arc_meta_limit (ulong)

The maximum allowed size in bytes that meta data buffers are allowed to consume in the ARC. When this limit is reached meta data buffers will be reclaimed even if the overall arc_c_max has not been reached. This value defaults to 0 which indicates that 3/4 of the ARC may be used for meta data.

Default value: 0.

zfs_arc_meta_min (ulong)

The minimum allowed size in bytes that meta data buffers may consume in the ARC. This value defaults to 0 which disables a floor on the amount of the ARC devoted meta data.

Default value: 0.

zfs_arc_meta_prune (int)

The number of dentries and inodes to be scanned looking for entries which can be dropped. This may be required when the ARC reaches the zfs_arc_meta_limit because dentries and inodes can pin buffers in the ARC. Increasing this value will cause to dentry and inode caches to be pruned more aggressively. Setting this value to 0 will disable pruning the inode and dentry caches.

Default value: 10,000.

zfs_arc_meta_adjust_restarts (ulong)

The number of restart passes to make while scanning the ARC attempting the free buffers in order to stay below the zfs_arc_meta_limit. This value should not need to be tuned but is available to facilitate performance analysis.

Default value: 4096.

zfs_arc_min (ulong)

Min arc size

Default value: 100.

zfs_arc_min_prefetch_lifespan (int)

Min life of prefetch block

Default value: 100.

zfs_arc_num_sublists_per_state (int)

To allow more fine-grained locking, each ARC state contains a series of lists for both data and meta data objects. Locking is performed at the level of these "sub-lists". This parameters controls the number of sub-lists per ARC state.

Default value: 1 or the number of on-online CPUs, whichever is greater

zfs_arc_overflow_shift (int)

The ARC size is considered to be overflowing if it exceeds the current ARC target size (arc_c) by a threshold determined by this parameter. The threshold is calculated as a fraction of arc_c using the formula "arc_c >> zfs_arc_overflow_shift".

The default value of 8 causes the ARC to be considered to be overflowing if it exceeds the target size by 1/256th (0.3%) of the target size.

When the ARC is overflowing, new buffer allocations are stalled until the reclaim thread catches up and the overflow condition no longer exists.

Default value: 8.

zfs_arc_p_min_shift (int)

arc_c shift to calc min/max arc_p

Default value: 4.

zfs_arc_p_aggressive_disable (int)

Disable aggressive arc_p growth

Use 1 for yes (default) and 0 to disable.

zfs_arc_p_dampener_disable (int)

Disable arc_p adapt dampener

Use 1 for yes (default) and 0 to disable.

zfs_arc_shrink_shift (int)

log2(fraction of arc to reclaim)

Default value: 5.

zfs_arc_sys_free (ulong)

The target number of bytes the ARC should leave as free memory on the system. Defaults to the larger of 1/64 of physical memory or 512K. Setting this option to a non-zero value will override the default.

Default value: 0.

zfs_autoimport_disable (int)

Disable pool import at module load by ignoring the cache file (typically /etc/zfs/zpool.cache).

Use 1 for yes (default) and 0 for no.

zfs_dbgmsg_enable (int)

Internally ZFS keeps a small log to facilitate debugging. By default the log is disabled, to enable it set this option to 1. The contents of the log can be accessed by reading the /proc/spl/kstat/zfs/dbgmsg file. Writing 0 to this proc file clears the log.

Default value: 0.

zfs_dbgmsg_maxsize (int)

The maximum size in bytes of the internal ZFS debug log.

Default value: 4M.

zfs_dbuf_state_index (int)

Calculate arc header index

Default value: 0.

zfs_deadman_enabled (int)

Enable deadman timer

Use 1 for yes (default) and 0 to disable.

zfs_deadman_synctime_ms (ulong)

Expiration time in milliseconds. 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 seconds. Secondly, the value determines if an I/O is considered "hung". Any I/O that has not completed in zfs_deadman_synctime_ms is considered "hung" resulting in a zevent being logged.

Default value: 1,000,000.

zfs_dedup_prefetch (int)

Enable prefetching dedup-ed blks

Use 1 for yes and 0 to disable (default).

zfs_delay_min_dirty_percent (int)

Start to delay each transaction once there is this amount of dirty data, expressed as a percentage of zfs_dirty_data_max. This value should be >= zfs_vdev_async_write_active_max_dirty_percent. See the section "ZFS TRANSACTION DELAY".

Default value: 60.

zfs_delay_scale (int)

This controls how quickly the transaction delay approaches infinity. Larger values cause longer delays for a given amount of dirty data.

For the smoothest delay, this value should be about 1 billion divided by the maximum number of operations per second. This will smoothly handle between 10x and 1/10th this number.

See the section "ZFS TRANSACTION DELAY".

Note: zfs_delay_scale * zfs_dirty_data_max must be < 2^64.

Default value: 500,000.

zfs_dirty_data_max (int)

Determines the dirty space limit in bytes. Once this limit is exceeded, new writes are halted until space frees up. This parameter takes precedence over zfs_dirty_data_max_percent. See the section "ZFS TRANSACTION DELAY".

Default value: 10 percent of all memory, capped at zfs_dirty_data_max_max.

zfs_dirty_data_max_max (int)

Maximum allowable value of zfs_dirty_data_max, expressed in bytes. This limit is only enforced at module load time, and will be ignored if zfs_dirty_data_max is later changed. This parameter takes precedence over zfs_dirty_data_max_max_percent. See the section "ZFS TRANSACTION DELAY".

Default value: 25% of physical RAM.

zfs_dirty_data_max_max_percent (int)

Maximum allowable value of zfs_dirty_data_max, expressed as a percentage of physical RAM. This limit is only enforced at module load time, and will be ignored if zfs_dirty_data_max is later changed. The parameter zfs_dirty_data_max_max takes precedence over this one. See the section "ZFS TRANSACTION DELAY".

Default value: 25

zfs_dirty_data_max_percent (int)

Determines the dirty space limit, expressed as a percentage of all memory. Once this limit is exceeded, new writes are halted until space frees up. The parameter zfs_dirty_data_max takes precedence over this one. See the section "ZFS TRANSACTION DELAY".

Default value: 10%, subject to zfs_dirty_data_max_max.

zfs_dirty_data_sync (int)

Start syncing out a transaction group if there is at least this much dirty data.

Default value: 67,108,864.

zfs_free_max_blocks (ulong)

Maximum number of blocks freed in a single txg.

Default value: 100,000.

zfs_vdev_async_read_max_active (int)

Maxium asynchronous read I/Os active to each device. See the section "ZFS I/O SCHEDULER".

Default value: 3.

zfs_vdev_async_read_min_active (int)

Minimum asynchronous read I/Os active to each device. See the section "ZFS I/O SCHEDULER".

Default value: 1.

zfs_vdev_async_write_active_max_dirty_percent (int)

When the pool has more than zfs_vdev_async_write_active_max_dirty_percent dirty data, use zfs_vdev_async_write_max_active to limit active async writes. If the dirty data is between min and max, the active I/O limit is linearly interpolated. See the section "ZFS I/O SCHEDULER".

Default value: 60.

zfs_vdev_async_write_active_min_dirty_percent (int)

When the pool has less than zfs_vdev_async_write_active_min_dirty_percent dirty data, use zfs_vdev_async_write_min_active to limit active async writes. If the dirty data is between min and max, the active I/O limit is linearly interpolated. See the section "ZFS I/O SCHEDULER".

Default value: 30.

zfs_vdev_async_write_max_active (int)

Maxium asynchronous write I/Os active to each device. See the section "ZFS I/O SCHEDULER".

Default value: 10.

zfs_vdev_async_write_min_active (int)

Minimum asynchronous write I/Os active to each device. See the section "ZFS I/O SCHEDULER".

Default value: 1.

zfs_vdev_max_active (int)

The maximum number of I/Os active to each device. Ideally, this will be >= the sum of each queue's max_active. It must be at least the sum of each queue's min_active. See the section "ZFS I/O SCHEDULER".

Default value: 1,000.

zfs_vdev_scrub_max_active (int)

Maxium scrub I/Os active to each device. See the section "ZFS I/O SCHEDULER".

Default value: 2.

zfs_vdev_scrub_min_active (int)

Minimum scrub I/Os active to each device. See the section "ZFS I/O SCHEDULER".

Default value: 1.

zfs_vdev_sync_read_max_active (int)

Maxium synchronous read I/Os active to each device. See the section "ZFS I/O SCHEDULER".

Default value: 10.

zfs_vdev_sync_read_min_active (int)

Minimum synchronous read I/Os active to each device. See the section "ZFS I/O SCHEDULER".

Default value: 10.

zfs_vdev_sync_write_max_active (int)

Maxium synchronous write I/Os active to each device. See the section "ZFS I/O SCHEDULER".

Default value: 10.

zfs_vdev_sync_write_min_active (int)

Minimum synchronous write I/Os active to each device. See the section "ZFS I/O SCHEDULER".

Default value: 10.

zfs_disable_dup_eviction (int)

Disable duplicate buffer eviction

Use 1 for yes and 0 for no (default).

zfs_expire_snapshot (int)

Seconds to expire .zfs/snapshot

Default value: 300.

zfs_admin_snapshot (int)

Allow the creation, removal, or renaming of entries in the .zfs/snapshot directory to cause the creation, destruction, or renaming of snapshots. When enabled this functionality works both locally and over NFS exports which have the 'no_root_squash' option set. This functionality is disabled by default.

Use 1 for yes and 0 for no (default).

zfs_flags (int)

Set additional debugging flags. The following flags may be bitwise-or'd together.

ValueSymbolic Name
Description

1ZFS_DEBUG_DPRINTF
Enable dprintf entries in the debug log.

2ZFS_DEBUG_DBUF_VERIFY *
Enable extra dbuf verifications.

4ZFS_DEBUG_DNODE_VERIFY *
Enable extra dnode verifications.

8ZFS_DEBUG_SNAPNAMES
Enable snapshot name verification.

16ZFS_DEBUG_MODIFY
Check for illegally modified ARC buffers.

32ZFS_DEBUG_SPA
Enable spa_dbgmsg entries in the debug log.

64ZFS_DEBUG_ZIO_FREE
Enable verification of block frees.

128ZFS_DEBUG_HISTOGRAM_VERIFY
Enable extra spacemap histogram verifications.

* Requires debug build.

Default value: 0.

zfs_free_leak_on_eio (int)

If destroy encounters an EIO while reading metadata (e.g. indirect blocks), space referenced by the missing metadata can not be freed. Normally this causes the background destroy to become "stalled", as it is unable to make forward progress. While in this stalled state, all remaining space to free from the error-encountering filesystem is "temporarily leaked". Set this flag to cause it to ignore the EIO, permanently leak the space from indirect blocks that can not be read, and continue to free everything else that it can.

The default, "stalling" behavior is useful if the storage partially fails (i.e. some but not all i/os fail), and then later recovers. In this case, we will be able to continue pool operations while it is partially failed, and when it recovers, we can continue to free the space, with no leaks. However, note that this case is actually fairly rare.

Typically pools either (a) fail completely (but perhaps temporarily, e.g. a top-level vdev going offline), or (b) have localized, permanent errors (e.g. disk returns the wrong data due to bit flip or firmware bug). In case (a), this setting does not matter because the pool will be suspended and the sync thread will not be able to make forward progress regardless. In case (b), because the error is permanent, the best we can do is leak the minimum amount of space, which is what setting this flag will do. Therefore, it is reasonable for this flag to normally be set, but we chose the more conservative approach of not setting it, so that there is no possibility of leaking space in the "partial temporary" failure case.

Default value: 0.

zfs_free_min_time_ms (int)

Min millisecs to free per txg

Default value: 1,000.

zfs_immediate_write_sz (long)

Largest data block to write to zil

Default value: 32,768.

zfs_max_recordsize (int)

We currently support block sizes from 512 bytes to 16MB. The benefits of larger blocks, and thus larger IO, 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, and also potentially on the memory allocator. Therefore, we do not allow the recordsize to be set larger than zfs_max_recordsize (default 1MB). Larger blocks can be created by changing this tunable, and pools with larger blocks can always be imported and used, regardless of this setting.

Default value: 1,048,576.

zfs_mdcomp_disable (int)

Disable meta data compression

Use 1 for yes and 0 for no (default).

zfs_metaslab_fragmentation_threshold (int)

Allow metaslabs to keep their active state as long as their fragmentation percentage is less than or equal to this value. An active metaslab that exceeds this threshold will no longer keep its active status allowing better metaslabs to be selected.

Default value: 70.

zfs_mg_fragmentation_threshold (int)

Metaslab groups are considered eligible for allocations if their fragmenation metric (measured as a percentage) is less than or equal to this value. If a metaslab group exceeds this threshold then it will be skipped unless all metaslab groups within the metaslab class have also crossed this threshold.

Default value: 85.

zfs_mg_noalloc_threshold (int)

Defines a threshold at which metaslab groups should be eligible for allocations. The value is expressed as a percentage of free space beyond which a metaslab group is always eligible for allocations. If a metaslab group's free space is less than or equal to the the threshold, the allocator will avoid allocating to that group unless all groups in the pool have reached the threshold. Once all groups have reached the threshold, all groups are allowed to accept allocations. The default value of 0 disables the feature and causes all metaslab groups to be eligible for allocations.

This parameter allows to deal with pools having heavily imbalanced vdevs such as would be the case when a new vdev has been added. Setting the threshold to a non-zero percentage will stop allocations from being made to vdevs that aren't filled to the specified percentage and allow lesser filled vdevs to acquire more allocations than they otherwise would under the old zfs_mg_alloc_failures facility.

Default value: 0.

zfs_no_scrub_io (int)

Set for no scrub I/O

Use 1 for yes and 0 for no (default).

zfs_no_scrub_prefetch (int)

Set for no scrub prefetching

Use 1 for yes and 0 for no (default).

zfs_nocacheflush (int)

Disable cache flushes

Use 1 for yes and 0 for no (default).

zfs_nopwrite_enabled (int)

Enable NOP writes

Use 1 for yes (default) and 0 to disable.

zfs_pd_bytes_max (int)

The number of bytes which should be prefetched.

Default value: 52,428,800.

zfs_prefetch_disable (int)

Disable all ZFS prefetching

Use 1 for yes and 0 for no (default).

zfs_read_chunk_size (long)

Bytes to read per chunk

Default value: 1,048,576.

zfs_read_history (int)

Historic statistics for the last N reads

Default value: 0.

zfs_read_history_hits (int)

Include cache hits in read history

Use 1 for yes and 0 for no (default).

zfs_recover (int)

Set to attempt to recover from fatal errors. This should only be used as a last resort, as it typically results in leaked space, or worse.

Use 1 for yes and 0 for no (default).

zfs_resilver_delay (int)

Number of ticks to delay prior to issuing a resilver I/O operation when a non-resilver or non-scrub I/O operation has occurred within the past zfs_scan_idle ticks.

Default value: 2.

zfs_resilver_min_time_ms (int)

Min millisecs to resilver per txg

Default value: 3,000.

zfs_scan_idle (int)

Idle window in clock ticks. During a scrub or a resilver, if a non-scrub or non-resilver I/O operation has occurred during this window, the next scrub or resilver operation is delayed by, respectively zfs_scrub_delay or zfs_resilver_delay ticks.

Default value: 50.

zfs_scan_min_time_ms (int)

Min millisecs to scrub per txg

Default value: 1,000.

zfs_scrub_delay (int)

Number of ticks to delay prior to issuing a scrub I/O operation when a non-scrub or non-resilver I/O operation has occurred within the past zfs_scan_idle ticks.

Default value: 4.

zfs_send_corrupt_data (int)

Allow to send corrupt data (ignore read/checksum errors when sending data)

Use 1 for yes and 0 for no (default).

zfs_sync_pass_deferred_free (int)

Defer frees starting in this pass

Default value: 2.

zfs_sync_pass_dont_compress (int)

Don't compress starting in this pass

Default value: 5.

zfs_sync_pass_rewrite (int)

Rewrite new bps starting in this pass

Default value: 2.

zfs_top_maxinflight (int)

Max I/Os per top-level vdev during scrub or resilver operations.

Default value: 32.

zfs_txg_history (int)

Historic statistics for the last N txgs

Default value: 0.

zfs_txg_timeout (int)

Max seconds worth of delta per txg

Default value: 5.

zfs_vdev_aggregation_limit (int)

Max vdev I/O aggregation size

Default value: 131,072.

zfs_vdev_cache_bshift (int)

Shift size to inflate reads too

Default value: 16.

zfs_vdev_cache_max (int)

Inflate reads small than max

zfs_vdev_cache_size (int)

Total size of the per-disk cache

Default value: 0.

zfs_vdev_mirror_switch_us (int)

Switch mirrors every N usecs

Default value: 10,000.

zfs_vdev_read_gap_limit (int)

Aggregate read I/O over gap

Default value: 32,768.

zfs_vdev_scheduler (charp)

I/O scheduler

Default value: noop.

zfs_vdev_write_gap_limit (int)

Aggregate write I/O over gap

Default value: 4,096.

zfs_zevent_cols (int)

Max event column width

Default value: 80.

zfs_zevent_console (int)

Log events to the console

Use 1 for yes and 0 for no (default).

zfs_zevent_len_max (int)

Max event queue length

Default value: 0.

zil_replay_disable (int)

Disable intent logging replay

Use 1 for yes and 0 for no (default).

zil_slog_limit (ulong)

Max commit bytes to separate log device

Default value: 1,048,576.

zio_delay_max (int)

Max zio millisec delay before posting event

Default value: 30,000.

zio_requeue_io_start_cut_in_line (int)

Prioritize requeued I/O

Default value: 0.

zio_taskq_batch_pct (uint)

Percentage of online CPUs (or CPU cores, etc) which will run a worker thread for IO. These workers are responsible for IO work such as compression and checksum calculations. Fractional number of CPUs will be rounded down.

The default value of 75 was chosen to avoid using all CPUs which can result in latency issues and inconsistent application performance, especially when high compression is enabled.

Default value: 75.

zvol_inhibit_dev (uint)

Do not create zvol device nodes

Use 1 for yes and 0 for no (default).

zvol_major (uint)

Major number for zvol device

Default value: 230.

zvol_max_discard_blocks (ulong)

Max number of blocks to discard at once

Default value: 16,384.

zvol_prefetch_bytes (uint)

When adding a zvol to the system prefetch zvol_prefetch_bytes from the start and end of the volume. Prefetching these regions of the volume is desirable because they are likely to be accessed immediately by blkid(8) or by the kernel scanning for a partition table.

Default value: 131,072.

ZFS I/O SCHEDULER

ZFS issues I/O operations to leaf vdevs to satisfy and complete I/Os. The I/O scheduler determines when and in what order those operations are issued. The I/O scheduler divides operations into five I/O classes prioritized in the following order: sync read, sync write, async read, async write, and scrub/resilver. Each queue defines the minimum and maximum number of concurrent operations that may be issued to the device. In addition, the device has an aggregate maximum, zfs_vdev_max_active. Note that the sum of the per-queue minimums must not exceed the aggregate maximum. If the sum of the per-queue maximums exceeds the aggregate maximum, then the number of active I/Os may reach zfs_vdev_max_active, in which case no further I/Os will be issued regardless of whether all per-queue minimums have been met.

For many physical devices, throughput increases with the number of concurrent operations, but latency typically suffers. Further, physical devices typically have a limit at which more concurrent operations have no effect on throughput or can actually cause it to decrease.

The scheduler selects the next operation to issue by first looking for an I/O class whose minimum has not been satisfied. Once all are satisfied and the aggregate maximum has not been hit, the scheduler looks for classes whose maximum has not been satisfied. Iteration through the I/O classes is done in the order specified above. No further operations are issued if the aggregate maximum number of concurrent operations has been hit or if there are no operations queued for an I/O class that has not hit its maximum. Every time an I/O is queued or an operation completes, the I/O scheduler looks for new operations to issue.

In general, smaller max_active's will lead to lower latency of synchronous operations. Larger max_active's may lead to higher overall throughput, depending on underlying storage.

The ratio of the queues' max_actives determines the balance of performance between reads, writes, and scrubs. E.g., increasing zfs_vdev_scrub_max_active will cause the scrub or resilver to complete more quickly, but reads and writes to have higher latency and lower throughput.

All I/O classes have a fixed maximum number of outstanding operations except for the async write class. Asynchronous writes represent the data that is committed to stable storage during the syncing stage for transaction groups. Transaction groups enter the syncing state periodically so the number of queued async writes will quickly burst up and then bleed down to zero. Rather than servicing them as quickly as possible, the I/O scheduler changes the maximum number of active async write I/Os according to the amount of dirty data in the pool. Since both throughput and latency typically increase with the number of concurrent operations issued to physical devices, reducing the burstiness in the number of concurrent operations also stabilizes the response time of operations from other -- and in particular synchronous -- queues. In broad strokes, the I/O scheduler will issue more concurrent operations from the async write queue as there's more dirty data in the pool.

Async Writes

The number of concurrent operations issued for the async write I/O class follows a piece-wise linear function defined by a few adjustable points.

       |              o---------| <-- zfs_vdev_async_write_max_active
  ^    |             /^         |
  |    |            / |         |
active |           /  |         |
 I/O   |          /   |         |
count  |         /    |         |
       |        /     |         |
       |-------o      |         | <-- zfs_vdev_async_write_min_active
      0|_______^______|_________|
       0%      |      |       100% of zfs_dirty_data_max
               |      |
               |      `-- zfs_vdev_async_write_active_max_dirty_percent
               `--------- zfs_vdev_async_write_active_min_dirty_percent
Until the amount of dirty data exceeds a minimum percentage of the dirty data allowed in the pool, the I/O scheduler will limit the number of concurrent operations to the minimum. As that threshold is crossed, the number of concurrent operations issued increases linearly to the maximum at the specified maximum percentage of the dirty data allowed in the pool.

Ideally, the amount of dirty data on a busy pool will stay in the sloped part of the function between zfs_vdev_async_write_active_min_dirty_percent and zfs_vdev_async_write_active_max_dirty_percent. If it exceeds the maximum percentage, this indicates that the rate of incoming data is greater than the rate that the backend storage can handle. In this case, we must further throttle incoming writes, as described in the next section.

ZFS TRANSACTION DELAY

We delay transactions when we've determined that the backend storage isn't able to accommodate the rate of incoming writes.

If there is already a transaction waiting, we delay relative to when that transaction will finish waiting. This way the calculated delay time is independent of the number of threads concurrently executing transactions.

If we are the only waiter, wait relative to when the transaction started, rather than the current time. This credits the transaction for "time already served", e.g. reading indirect blocks.

The minimum time for a transaction to take is calculated as:

    min_time = zfs_delay_scale * (dirty - min) / (max - dirty)
    min_time is then capped at 100 milliseconds.

The delay has two degrees of freedom that can be adjusted via tunables. The percentage of dirty data at which we start to delay is defined by zfs_delay_min_dirty_percent. This should typically be at or above zfs_vdev_async_write_active_max_dirty_percent so that we only start to delay after writing at full speed has failed to keep up with the incoming write rate. The scale of the curve is defined by zfs_delay_scale. Roughly speaking, this variable determines the amount of delay at the midpoint of the curve.

delay
 10ms +-------------------------------------------------------------*+
      |                                                             *|
  9ms +                                                             *+
      |                                                             *|
  8ms +                                                             *+
      |                                                            * |
  7ms +                                                            * +
      |                                                            * |
  6ms +                                                            * +
      |                                                            * |
  5ms +                                                           *  +
      |                                                           *  |
  4ms +                                                           *  +
      |                                                           *  |
  3ms +                                                          *   +
      |                                                          *   |
  2ms +                                              (midpoint) *    +
      |                                                  |    **     |
  1ms +                                                  v ***       +
      |             zfs_delay_scale ---------->     ********         |
    0 +-------------------------------------*********----------------+
      0%                    <- zfs_dirty_data_max ->               100%

Note that since the delay is added to the outstanding time remaining on the most recent transaction, the delay is effectively the inverse of IOPS. Here the midpoint of 500us translates to 2000 IOPS. The shape of the curve was chosen such that small changes in the amount of accumulated dirty data in the first 3/4 of the curve yield relatively small differences in the amount of delay.

The effects can be easier to understand when the amount of delay is represented on a log scale:

delay
100ms +-------------------------------------------------------------++
      +                                                              +
      |                                                              |
      +                                                             *+
 10ms +                                                             *+
      +                                                           ** +
      |                                              (midpoint)  **  |
      +                                                  |     **    +
  1ms +                                                  v ****      +
      +             zfs_delay_scale ---------->        *****         +
      |                                             ****             |
      +                                          ****                +
100us +                                        **                    +
      +                                       *                      +
      |                                      *                       |
      +                                     *                        +
 10us +                                     *                        +
      +                                                              +
      |                                                              |
      +                                                              +
      +--------------------------------------------------------------+
      0%                    <- zfs_dirty_data_max ->               100%

Note here that only as the amount of dirty data approaches its limit does the delay start to increase rapidly. The goal of a properly tuned system should be to keep the amount of dirty data out of that range by first ensuring that the appropriate limits are set for the I/O scheduler to reach optimal throughput on the backend storage, and then by changing the value of zfs_delay_scale to increase the steepness of the curve.