]>
Commit | Line | Data |
---|---|---|
29714574 TF |
1 | '\" te |
2 | .\" Copyright (c) 2013 by Turbo Fredriksson <turbo@bayour.com>. All rights reserved. | |
d4a72f23 | 3 | .\" Copyright (c) 2017 Datto Inc. |
29714574 TF |
4 | .\" The contents of this file are subject to the terms of the Common Development |
5 | .\" and Distribution License (the "License"). You may not use this file except | |
6 | .\" in compliance with the License. You can obtain a copy of the license at | |
7 | .\" usr/src/OPENSOLARIS.LICENSE or http://www.opensolaris.org/os/licensing. | |
8 | .\" | |
9 | .\" See the License for the specific language governing permissions and | |
10 | .\" limitations under the License. When distributing Covered Code, include this | |
11 | .\" CDDL HEADER in each file and include the License file at | |
12 | .\" usr/src/OPENSOLARIS.LICENSE. If applicable, add the following below this | |
13 | .\" CDDL HEADER, with the fields enclosed by brackets "[]" replaced with your | |
14 | .\" own identifying information: | |
15 | .\" Portions Copyright [yyyy] [name of copyright owner] | |
d4a72f23 | 16 | .TH ZFS-MODULE-PARAMETERS 5 "Oct 28, 2017" |
29714574 TF |
17 | .SH NAME |
18 | zfs\-module\-parameters \- ZFS module parameters | |
19 | .SH DESCRIPTION | |
20 | .sp | |
21 | .LP | |
22 | Description of the different parameters to the ZFS module. | |
23 | ||
24 | .SS "Module parameters" | |
25 | .sp | |
26 | .LP | |
27 | ||
6d836e6f RE |
28 | .sp |
29 | .ne 2 | |
30 | .na | |
31 | \fBignore_hole_birth\fR (int) | |
32 | .ad | |
33 | .RS 12n | |
34 | When set, the hole_birth optimization will not be used, and all holes will | |
35 | always be sent on zfs send. Useful if you suspect your datasets are affected | |
36 | by a bug in hole_birth. | |
37 | .sp | |
9ea9e0b9 | 38 | Use \fB1\fR for on (default) and \fB0\fR for off. |
6d836e6f RE |
39 | .RE |
40 | ||
29714574 TF |
41 | .sp |
42 | .ne 2 | |
43 | .na | |
44 | \fBl2arc_feed_again\fR (int) | |
45 | .ad | |
46 | .RS 12n | |
83426735 D |
47 | Turbo L2ARC warm-up. When the L2ARC is cold the fill interval will be set as |
48 | fast as possible. | |
29714574 TF |
49 | .sp |
50 | Use \fB1\fR for yes (default) and \fB0\fR to disable. | |
51 | .RE | |
52 | ||
53 | .sp | |
54 | .ne 2 | |
55 | .na | |
56 | \fBl2arc_feed_min_ms\fR (ulong) | |
57 | .ad | |
58 | .RS 12n | |
83426735 D |
59 | Min feed interval in milliseconds. Requires \fBl2arc_feed_again=1\fR and only |
60 | applicable in related situations. | |
29714574 TF |
61 | .sp |
62 | Default value: \fB200\fR. | |
63 | .RE | |
64 | ||
65 | .sp | |
66 | .ne 2 | |
67 | .na | |
68 | \fBl2arc_feed_secs\fR (ulong) | |
69 | .ad | |
70 | .RS 12n | |
71 | Seconds between L2ARC writing | |
72 | .sp | |
73 | Default value: \fB1\fR. | |
74 | .RE | |
75 | ||
76 | .sp | |
77 | .ne 2 | |
78 | .na | |
79 | \fBl2arc_headroom\fR (ulong) | |
80 | .ad | |
81 | .RS 12n | |
83426735 D |
82 | How far through the ARC lists to search for L2ARC cacheable content, expressed |
83 | as a multiplier of \fBl2arc_write_max\fR | |
29714574 TF |
84 | .sp |
85 | Default value: \fB2\fR. | |
86 | .RE | |
87 | ||
88 | .sp | |
89 | .ne 2 | |
90 | .na | |
91 | \fBl2arc_headroom_boost\fR (ulong) | |
92 | .ad | |
93 | .RS 12n | |
83426735 D |
94 | Scales \fBl2arc_headroom\fR by this percentage when L2ARC contents are being |
95 | successfully compressed before writing. A value of 100 disables this feature. | |
29714574 TF |
96 | .sp |
97 | Default value: \fB200\fR. | |
98 | .RE | |
99 | ||
100 | .sp | |
101 | .ne 2 | |
102 | .na | |
103 | \fBl2arc_nocompress\fR (int) | |
104 | .ad | |
105 | .RS 12n | |
106 | Skip compressing L2ARC buffers | |
107 | .sp | |
108 | Use \fB1\fR for yes and \fB0\fR for no (default). | |
109 | .RE | |
110 | ||
111 | .sp | |
112 | .ne 2 | |
113 | .na | |
114 | \fBl2arc_noprefetch\fR (int) | |
115 | .ad | |
116 | .RS 12n | |
83426735 D |
117 | Do not write buffers to L2ARC if they were prefetched but not used by |
118 | applications | |
29714574 TF |
119 | .sp |
120 | Use \fB1\fR for yes (default) and \fB0\fR to disable. | |
121 | .RE | |
122 | ||
123 | .sp | |
124 | .ne 2 | |
125 | .na | |
126 | \fBl2arc_norw\fR (int) | |
127 | .ad | |
128 | .RS 12n | |
129 | No reads during writes | |
130 | .sp | |
131 | Use \fB1\fR for yes and \fB0\fR for no (default). | |
132 | .RE | |
133 | ||
134 | .sp | |
135 | .ne 2 | |
136 | .na | |
137 | \fBl2arc_write_boost\fR (ulong) | |
138 | .ad | |
139 | .RS 12n | |
603a1784 | 140 | Cold L2ARC devices will have \fBl2arc_write_max\fR increased by this amount |
83426735 | 141 | while they remain cold. |
29714574 TF |
142 | .sp |
143 | Default value: \fB8,388,608\fR. | |
144 | .RE | |
145 | ||
146 | .sp | |
147 | .ne 2 | |
148 | .na | |
149 | \fBl2arc_write_max\fR (ulong) | |
150 | .ad | |
151 | .RS 12n | |
152 | Max write bytes per interval | |
153 | .sp | |
154 | Default value: \fB8,388,608\fR. | |
155 | .RE | |
156 | ||
99b14de4 ED |
157 | .sp |
158 | .ne 2 | |
159 | .na | |
160 | \fBmetaslab_aliquot\fR (ulong) | |
161 | .ad | |
162 | .RS 12n | |
163 | Metaslab granularity, in bytes. This is roughly similar to what would be | |
164 | referred to as the "stripe size" in traditional RAID arrays. In normal | |
165 | operation, ZFS will try to write this amount of data to a top-level vdev | |
166 | before moving on to the next one. | |
167 | .sp | |
168 | Default value: \fB524,288\fR. | |
169 | .RE | |
170 | ||
f3a7f661 GW |
171 | .sp |
172 | .ne 2 | |
173 | .na | |
174 | \fBmetaslab_bias_enabled\fR (int) | |
175 | .ad | |
176 | .RS 12n | |
177 | Enable metaslab group biasing based on its vdev's over- or under-utilization | |
178 | relative to the pool. | |
179 | .sp | |
180 | Use \fB1\fR for yes (default) and \fB0\fR for no. | |
181 | .RE | |
182 | ||
4e21fd06 DB |
183 | .sp |
184 | .ne 2 | |
185 | .na | |
186 | \fBzfs_metaslab_segment_weight_enabled\fR (int) | |
187 | .ad | |
188 | .RS 12n | |
189 | Enable/disable segment-based metaslab selection. | |
190 | .sp | |
191 | Use \fB1\fR for yes (default) and \fB0\fR for no. | |
192 | .RE | |
193 | ||
194 | .sp | |
195 | .ne 2 | |
196 | .na | |
197 | \fBzfs_metaslab_switch_threshold\fR (int) | |
198 | .ad | |
199 | .RS 12n | |
200 | When using segment-based metaslab selection, continue allocating | |
321204be | 201 | from the active metaslab until \fBzfs_metaslab_switch_threshold\fR |
4e21fd06 DB |
202 | worth of buckets have been exhausted. |
203 | .sp | |
204 | Default value: \fB2\fR. | |
205 | .RE | |
206 | ||
29714574 TF |
207 | .sp |
208 | .ne 2 | |
209 | .na | |
aa7d06a9 | 210 | \fBmetaslab_debug_load\fR (int) |
29714574 TF |
211 | .ad |
212 | .RS 12n | |
aa7d06a9 GW |
213 | Load all metaslabs during pool import. |
214 | .sp | |
215 | Use \fB1\fR for yes and \fB0\fR for no (default). | |
216 | .RE | |
217 | ||
218 | .sp | |
219 | .ne 2 | |
220 | .na | |
221 | \fBmetaslab_debug_unload\fR (int) | |
222 | .ad | |
223 | .RS 12n | |
224 | Prevent metaslabs from being unloaded. | |
29714574 TF |
225 | .sp |
226 | Use \fB1\fR for yes and \fB0\fR for no (default). | |
227 | .RE | |
228 | ||
f3a7f661 GW |
229 | .sp |
230 | .ne 2 | |
231 | .na | |
232 | \fBmetaslab_fragmentation_factor_enabled\fR (int) | |
233 | .ad | |
234 | .RS 12n | |
235 | Enable use of the fragmentation metric in computing metaslab weights. | |
236 | .sp | |
237 | Use \fB1\fR for yes (default) and \fB0\fR for no. | |
238 | .RE | |
239 | ||
b8bcca18 MA |
240 | .sp |
241 | .ne 2 | |
242 | .na | |
243 | \fBmetaslabs_per_vdev\fR (int) | |
244 | .ad | |
245 | .RS 12n | |
246 | When a vdev is added, it will be divided into approximately (but no more than) this number of metaslabs. | |
247 | .sp | |
248 | Default value: \fB200\fR. | |
249 | .RE | |
250 | ||
f3a7f661 GW |
251 | .sp |
252 | .ne 2 | |
253 | .na | |
254 | \fBmetaslab_preload_enabled\fR (int) | |
255 | .ad | |
256 | .RS 12n | |
257 | Enable metaslab group preloading. | |
258 | .sp | |
259 | Use \fB1\fR for yes (default) and \fB0\fR for no. | |
260 | .RE | |
261 | ||
262 | .sp | |
263 | .ne 2 | |
264 | .na | |
265 | \fBmetaslab_lba_weighting_enabled\fR (int) | |
266 | .ad | |
267 | .RS 12n | |
268 | Give more weight to metaslabs with lower LBAs, assuming they have | |
269 | greater bandwidth as is typically the case on a modern constant | |
270 | angular velocity disk drive. | |
271 | .sp | |
272 | Use \fB1\fR for yes (default) and \fB0\fR for no. | |
273 | .RE | |
274 | ||
29714574 TF |
275 | .sp |
276 | .ne 2 | |
277 | .na | |
278 | \fBspa_config_path\fR (charp) | |
279 | .ad | |
280 | .RS 12n | |
281 | SPA config file | |
282 | .sp | |
283 | Default value: \fB/etc/zfs/zpool.cache\fR. | |
284 | .RE | |
285 | ||
e8b96c60 MA |
286 | .sp |
287 | .ne 2 | |
288 | .na | |
289 | \fBspa_asize_inflation\fR (int) | |
290 | .ad | |
291 | .RS 12n | |
292 | Multiplication factor used to estimate actual disk consumption from the | |
293 | size of data being written. The default value is a worst case estimate, | |
294 | but lower values may be valid for a given pool depending on its | |
295 | configuration. Pool administrators who understand the factors involved | |
296 | may wish to specify a more realistic inflation factor, particularly if | |
297 | they operate close to quota or capacity limits. | |
298 | .sp | |
83426735 | 299 | Default value: \fB24\fR. |
e8b96c60 MA |
300 | .RE |
301 | ||
dea377c0 MA |
302 | .sp |
303 | .ne 2 | |
304 | .na | |
305 | \fBspa_load_verify_data\fR (int) | |
306 | .ad | |
307 | .RS 12n | |
308 | Whether to traverse data blocks during an "extreme rewind" (\fB-X\fR) | |
309 | import. Use 0 to disable and 1 to enable. | |
310 | ||
311 | An extreme rewind import normally performs a full traversal of all | |
312 | blocks in the pool for verification. If this parameter is set to 0, | |
313 | the traversal skips non-metadata blocks. It can be toggled once the | |
314 | import has started to stop or start the traversal of non-metadata blocks. | |
315 | .sp | |
83426735 | 316 | Default value: \fB1\fR. |
dea377c0 MA |
317 | .RE |
318 | ||
319 | .sp | |
320 | .ne 2 | |
321 | .na | |
322 | \fBspa_load_verify_metadata\fR (int) | |
323 | .ad | |
324 | .RS 12n | |
325 | Whether to traverse blocks during an "extreme rewind" (\fB-X\fR) | |
326 | pool import. Use 0 to disable and 1 to enable. | |
327 | ||
328 | An extreme rewind import normally performs a full traversal of all | |
1c012083 | 329 | blocks in the pool for verification. If this parameter is set to 0, |
dea377c0 MA |
330 | the traversal is not performed. It can be toggled once the import has |
331 | started to stop or start the traversal. | |
332 | .sp | |
83426735 | 333 | Default value: \fB1\fR. |
dea377c0 MA |
334 | .RE |
335 | ||
336 | .sp | |
337 | .ne 2 | |
338 | .na | |
339 | \fBspa_load_verify_maxinflight\fR (int) | |
340 | .ad | |
341 | .RS 12n | |
342 | Maximum concurrent I/Os during the traversal performed during an "extreme | |
343 | rewind" (\fB-X\fR) pool import. | |
344 | .sp | |
83426735 | 345 | Default value: \fB10000\fR. |
dea377c0 MA |
346 | .RE |
347 | ||
6cde6435 BB |
348 | .sp |
349 | .ne 2 | |
350 | .na | |
351 | \fBspa_slop_shift\fR (int) | |
352 | .ad | |
353 | .RS 12n | |
354 | Normally, we don't allow the last 3.2% (1/(2^spa_slop_shift)) of space | |
355 | in the pool to be consumed. This ensures that we don't run the pool | |
356 | completely out of space, due to unaccounted changes (e.g. to the MOS). | |
357 | It also limits the worst-case time to allocate space. If we have | |
358 | less than this amount of free space, most ZPL operations (e.g. write, | |
359 | create) will return ENOSPC. | |
360 | .sp | |
83426735 | 361 | Default value: \fB5\fR. |
6cde6435 BB |
362 | .RE |
363 | ||
29714574 TF |
364 | .sp |
365 | .ne 2 | |
366 | .na | |
367 | \fBzfetch_array_rd_sz\fR (ulong) | |
368 | .ad | |
369 | .RS 12n | |
27b293be | 370 | If prefetching is enabled, disable prefetching for reads larger than this size. |
29714574 TF |
371 | .sp |
372 | Default value: \fB1,048,576\fR. | |
373 | .RE | |
374 | ||
375 | .sp | |
376 | .ne 2 | |
377 | .na | |
7f60329a | 378 | \fBzfetch_max_distance\fR (uint) |
29714574 TF |
379 | .ad |
380 | .RS 12n | |
7f60329a | 381 | Max bytes to prefetch per stream (default 8MB). |
29714574 | 382 | .sp |
7f60329a | 383 | Default value: \fB8,388,608\fR. |
29714574 TF |
384 | .RE |
385 | ||
386 | .sp | |
387 | .ne 2 | |
388 | .na | |
389 | \fBzfetch_max_streams\fR (uint) | |
390 | .ad | |
391 | .RS 12n | |
27b293be | 392 | Max number of streams per zfetch (prefetch streams per file). |
29714574 TF |
393 | .sp |
394 | Default value: \fB8\fR. | |
395 | .RE | |
396 | ||
397 | .sp | |
398 | .ne 2 | |
399 | .na | |
400 | \fBzfetch_min_sec_reap\fR (uint) | |
401 | .ad | |
402 | .RS 12n | |
27b293be | 403 | Min time before an active prefetch stream can be reclaimed |
29714574 TF |
404 | .sp |
405 | Default value: \fB2\fR. | |
406 | .RE | |
407 | ||
25458cbe TC |
408 | .sp |
409 | .ne 2 | |
410 | .na | |
411 | \fBzfs_arc_dnode_limit\fR (ulong) | |
412 | .ad | |
413 | .RS 12n | |
414 | When the number of bytes consumed by dnodes in the ARC exceeds this number of | |
9907cc1c | 415 | bytes, try to unpin some of it in response to demand for non-metadata. This |
627791f3 | 416 | value acts as a ceiling to the amount of dnode metadata, and defaults to 0 which |
9907cc1c G |
417 | indicates that a percent which is based on \fBzfs_arc_dnode_limit_percent\fR of |
418 | the ARC meta buffers that may be used for dnodes. | |
25458cbe TC |
419 | |
420 | See also \fBzfs_arc_meta_prune\fR which serves a similar purpose but is used | |
421 | when the amount of metadata in the ARC exceeds \fBzfs_arc_meta_limit\fR rather | |
422 | than in response to overall demand for non-metadata. | |
423 | ||
424 | .sp | |
9907cc1c G |
425 | Default value: \fB0\fR. |
426 | .RE | |
427 | ||
428 | .sp | |
429 | .ne 2 | |
430 | .na | |
431 | \fBzfs_arc_dnode_limit_percent\fR (ulong) | |
432 | .ad | |
433 | .RS 12n | |
434 | Percentage that can be consumed by dnodes of ARC meta buffers. | |
435 | .sp | |
436 | See also \fBzfs_arc_dnode_limit\fR which serves a similar purpose but has a | |
437 | higher priority if set to nonzero value. | |
438 | .sp | |
439 | Default value: \fB10\fR. | |
25458cbe TC |
440 | .RE |
441 | ||
442 | .sp | |
443 | .ne 2 | |
444 | .na | |
445 | \fBzfs_arc_dnode_reduce_percent\fR (ulong) | |
446 | .ad | |
447 | .RS 12n | |
448 | Percentage of ARC dnodes to try to scan in response to demand for non-metadata | |
6146e17e | 449 | when the number of bytes consumed by dnodes exceeds \fBzfs_arc_dnode_limit\fR. |
25458cbe TC |
450 | |
451 | .sp | |
452 | Default value: \fB10% of the number of dnodes in the ARC\fR. | |
453 | .RE | |
454 | ||
49ddb315 MA |
455 | .sp |
456 | .ne 2 | |
457 | .na | |
458 | \fBzfs_arc_average_blocksize\fR (int) | |
459 | .ad | |
460 | .RS 12n | |
461 | The ARC's buffer hash table is sized based on the assumption of an average | |
462 | block size of \fBzfs_arc_average_blocksize\fR (default 8K). This works out | |
463 | to roughly 1MB of hash table per 1GB of physical memory with 8-byte pointers. | |
464 | For configurations with a known larger average block size this value can be | |
465 | increased to reduce the memory footprint. | |
466 | ||
467 | .sp | |
468 | Default value: \fB8192\fR. | |
469 | .RE | |
470 | ||
ca0bf58d PS |
471 | .sp |
472 | .ne 2 | |
473 | .na | |
474 | \fBzfs_arc_evict_batch_limit\fR (int) | |
475 | .ad | |
476 | .RS 12n | |
8f343973 | 477 | Number ARC headers to evict per sub-list before proceeding to another sub-list. |
ca0bf58d PS |
478 | This batch-style operation prevents entire sub-lists from being evicted at once |
479 | but comes at a cost of additional unlocking and locking. | |
480 | .sp | |
481 | Default value: \fB10\fR. | |
482 | .RE | |
483 | ||
29714574 TF |
484 | .sp |
485 | .ne 2 | |
486 | .na | |
487 | \fBzfs_arc_grow_retry\fR (int) | |
488 | .ad | |
489 | .RS 12n | |
ca85d690 | 490 | If set to a non zero value, it will replace the arc_grow_retry value with this value. |
d4a72f23 | 491 | The arc_grow_retry value (default 5) is the number of seconds the ARC will wait before |
ca85d690 | 492 | trying to resume growth after a memory pressure event. |
29714574 | 493 | .sp |
ca85d690 | 494 | Default value: \fB0\fR. |
29714574 TF |
495 | .RE |
496 | ||
497 | .sp | |
498 | .ne 2 | |
499 | .na | |
7e8bddd0 | 500 | \fBzfs_arc_lotsfree_percent\fR (int) |
29714574 TF |
501 | .ad |
502 | .RS 12n | |
7e8bddd0 BB |
503 | Throttle I/O when free system memory drops below this percentage of total |
504 | system memory. Setting this value to 0 will disable the throttle. | |
29714574 | 505 | .sp |
7e8bddd0 | 506 | Default value: \fB10\fR. |
29714574 TF |
507 | .RE |
508 | ||
509 | .sp | |
510 | .ne 2 | |
511 | .na | |
7e8bddd0 | 512 | \fBzfs_arc_max\fR (ulong) |
29714574 TF |
513 | .ad |
514 | .RS 12n | |
83426735 D |
515 | Max arc size of ARC in bytes. If set to 0 then it will consume 1/2 of system |
516 | RAM. This value must be at least 67108864 (64 megabytes). | |
517 | .sp | |
518 | This value can be changed dynamically with some caveats. It cannot be set back | |
519 | to 0 while running and reducing it below the current ARC size will not cause | |
520 | the ARC to shrink without memory pressure to induce shrinking. | |
29714574 | 521 | .sp |
7e8bddd0 | 522 | Default value: \fB0\fR. |
29714574 TF |
523 | .RE |
524 | ||
ca85d690 | 525 | .sp |
526 | .ne 2 | |
527 | .na | |
528 | \fBzfs_arc_meta_adjust_restarts\fR (ulong) | |
529 | .ad | |
530 | .RS 12n | |
531 | The number of restart passes to make while scanning the ARC attempting | |
532 | the free buffers in order to stay below the \fBzfs_arc_meta_limit\fR. | |
533 | This value should not need to be tuned but is available to facilitate | |
534 | performance analysis. | |
535 | .sp | |
536 | Default value: \fB4096\fR. | |
537 | .RE | |
538 | ||
29714574 TF |
539 | .sp |
540 | .ne 2 | |
541 | .na | |
542 | \fBzfs_arc_meta_limit\fR (ulong) | |
543 | .ad | |
544 | .RS 12n | |
2cbb06b5 BB |
545 | The maximum allowed size in bytes that meta data buffers are allowed to |
546 | consume in the ARC. When this limit is reached meta data buffers will | |
547 | be reclaimed even if the overall arc_c_max has not been reached. This | |
9907cc1c G |
548 | value defaults to 0 which indicates that a percent which is based on |
549 | \fBzfs_arc_meta_limit_percent\fR of the ARC may be used for meta data. | |
29714574 | 550 | .sp |
83426735 | 551 | This value my be changed dynamically except that it cannot be set back to 0 |
9907cc1c | 552 | for a specific percent of the ARC; it must be set to an explicit value. |
83426735 | 553 | .sp |
29714574 TF |
554 | Default value: \fB0\fR. |
555 | .RE | |
556 | ||
9907cc1c G |
557 | .sp |
558 | .ne 2 | |
559 | .na | |
560 | \fBzfs_arc_meta_limit_percent\fR (ulong) | |
561 | .ad | |
562 | .RS 12n | |
563 | Percentage of ARC buffers that can be used for meta data. | |
564 | ||
565 | See also \fBzfs_arc_meta_limit\fR which serves a similar purpose but has a | |
566 | higher priority if set to nonzero value. | |
567 | ||
568 | .sp | |
569 | Default value: \fB75\fR. | |
570 | .RE | |
571 | ||
ca0bf58d PS |
572 | .sp |
573 | .ne 2 | |
574 | .na | |
575 | \fBzfs_arc_meta_min\fR (ulong) | |
576 | .ad | |
577 | .RS 12n | |
578 | The minimum allowed size in bytes that meta data buffers may consume in | |
579 | the ARC. This value defaults to 0 which disables a floor on the amount | |
580 | of the ARC devoted meta data. | |
581 | .sp | |
582 | Default value: \fB0\fR. | |
583 | .RE | |
584 | ||
29714574 TF |
585 | .sp |
586 | .ne 2 | |
587 | .na | |
588 | \fBzfs_arc_meta_prune\fR (int) | |
589 | .ad | |
590 | .RS 12n | |
2cbb06b5 BB |
591 | The number of dentries and inodes to be scanned looking for entries |
592 | which can be dropped. This may be required when the ARC reaches the | |
593 | \fBzfs_arc_meta_limit\fR because dentries and inodes can pin buffers | |
594 | in the ARC. Increasing this value will cause to dentry and inode caches | |
595 | to be pruned more aggressively. Setting this value to 0 will disable | |
596 | pruning the inode and dentry caches. | |
29714574 | 597 | .sp |
2cbb06b5 | 598 | Default value: \fB10,000\fR. |
29714574 TF |
599 | .RE |
600 | ||
bc888666 BB |
601 | .sp |
602 | .ne 2 | |
603 | .na | |
ca85d690 | 604 | \fBzfs_arc_meta_strategy\fR (int) |
bc888666 BB |
605 | .ad |
606 | .RS 12n | |
ca85d690 | 607 | Define the strategy for ARC meta data buffer eviction (meta reclaim strategy). |
608 | A value of 0 (META_ONLY) will evict only the ARC meta data buffers. | |
d4a72f23 | 609 | A value of 1 (BALANCED) indicates that additional data buffers may be evicted if |
ca85d690 | 610 | that is required to in order to evict the required number of meta data buffers. |
bc888666 | 611 | .sp |
ca85d690 | 612 | Default value: \fB1\fR. |
bc888666 BB |
613 | .RE |
614 | ||
29714574 TF |
615 | .sp |
616 | .ne 2 | |
617 | .na | |
618 | \fBzfs_arc_min\fR (ulong) | |
619 | .ad | |
620 | .RS 12n | |
ca85d690 | 621 | Min arc size of ARC in bytes. If set to 0 then arc_c_min will default to |
622 | consuming the larger of 32M or 1/32 of total system memory. | |
29714574 | 623 | .sp |
ca85d690 | 624 | Default value: \fB0\fR. |
29714574 TF |
625 | .RE |
626 | ||
627 | .sp | |
628 | .ne 2 | |
629 | .na | |
d4a72f23 | 630 | \fBzfs_arc_min_prefetch_ms\fR (int) |
29714574 TF |
631 | .ad |
632 | .RS 12n | |
d4a72f23 TC |
633 | Minimum time prefetched blocks are locked in the ARC, specified in ms. |
634 | A value of \fB0\fR will default to 1 second. | |
635 | .sp | |
636 | Default value: \fB0\fR. | |
637 | .RE | |
638 | ||
639 | .sp | |
640 | .ne 2 | |
641 | .na | |
642 | \fBzfs_arc_min_prescient_prefetch_ms\fR (int) | |
643 | .ad | |
644 | .RS 12n | |
645 | Minimum time "prescient prefetched" blocks are locked in the ARC, specified | |
646 | in ms. These blocks are meant to be prefetched fairly aggresively ahead of | |
647 | the code that may use them. A value of \fB0\fR will default to 6 seconds. | |
29714574 | 648 | .sp |
83426735 | 649 | Default value: \fB0\fR. |
29714574 TF |
650 | .RE |
651 | ||
ca0bf58d PS |
652 | .sp |
653 | .ne 2 | |
654 | .na | |
c30e58c4 | 655 | \fBzfs_multilist_num_sublists\fR (int) |
ca0bf58d PS |
656 | .ad |
657 | .RS 12n | |
658 | To allow more fine-grained locking, each ARC state contains a series | |
659 | of lists for both data and meta data objects. Locking is performed at | |
660 | the level of these "sub-lists". This parameters controls the number of | |
c30e58c4 MA |
661 | sub-lists per ARC state, and also applies to other uses of the |
662 | multilist data structure. | |
ca0bf58d | 663 | .sp |
c30e58c4 | 664 | Default value: \fB4\fR or the number of online CPUs, whichever is greater |
ca0bf58d PS |
665 | .RE |
666 | ||
667 | .sp | |
668 | .ne 2 | |
669 | .na | |
670 | \fBzfs_arc_overflow_shift\fR (int) | |
671 | .ad | |
672 | .RS 12n | |
673 | The ARC size is considered to be overflowing if it exceeds the current | |
674 | ARC target size (arc_c) by a threshold determined by this parameter. | |
675 | The threshold is calculated as a fraction of arc_c using the formula | |
676 | "arc_c >> \fBzfs_arc_overflow_shift\fR". | |
677 | ||
678 | The default value of 8 causes the ARC to be considered to be overflowing | |
679 | if it exceeds the target size by 1/256th (0.3%) of the target size. | |
680 | ||
681 | When the ARC is overflowing, new buffer allocations are stalled until | |
682 | the reclaim thread catches up and the overflow condition no longer exists. | |
683 | .sp | |
684 | Default value: \fB8\fR. | |
685 | .RE | |
686 | ||
728d6ae9 BB |
687 | .sp |
688 | .ne 2 | |
689 | .na | |
690 | ||
691 | \fBzfs_arc_p_min_shift\fR (int) | |
692 | .ad | |
693 | .RS 12n | |
ca85d690 | 694 | If set to a non zero value, this will update arc_p_min_shift (default 4) |
695 | with the new value. | |
d4a72f23 | 696 | arc_p_min_shift is used to shift of arc_c for calculating both min and max |
ca85d690 | 697 | max arc_p |
728d6ae9 | 698 | .sp |
ca85d690 | 699 | Default value: \fB0\fR. |
728d6ae9 BB |
700 | .RE |
701 | ||
89c8cac4 PS |
702 | .sp |
703 | .ne 2 | |
704 | .na | |
705 | \fBzfs_arc_p_aggressive_disable\fR (int) | |
706 | .ad | |
707 | .RS 12n | |
708 | Disable aggressive arc_p growth | |
709 | .sp | |
710 | Use \fB1\fR for yes (default) and \fB0\fR to disable. | |
711 | .RE | |
712 | ||
62422785 PS |
713 | .sp |
714 | .ne 2 | |
715 | .na | |
716 | \fBzfs_arc_p_dampener_disable\fR (int) | |
717 | .ad | |
718 | .RS 12n | |
719 | Disable arc_p adapt dampener | |
720 | .sp | |
721 | Use \fB1\fR for yes (default) and \fB0\fR to disable. | |
722 | .RE | |
723 | ||
29714574 TF |
724 | .sp |
725 | .ne 2 | |
726 | .na | |
727 | \fBzfs_arc_shrink_shift\fR (int) | |
728 | .ad | |
729 | .RS 12n | |
ca85d690 | 730 | If set to a non zero value, this will update arc_shrink_shift (default 7) |
731 | with the new value. | |
29714574 | 732 | .sp |
ca85d690 | 733 | Default value: \fB0\fR. |
29714574 TF |
734 | .RE |
735 | ||
03b60eee DB |
736 | .sp |
737 | .ne 2 | |
738 | .na | |
739 | \fBzfs_arc_pc_percent\fR (uint) | |
740 | .ad | |
741 | .RS 12n | |
742 | Percent of pagecache to reclaim arc to | |
743 | ||
744 | This tunable allows ZFS arc to play more nicely with the kernel's LRU | |
745 | pagecache. It can guarantee that the arc size won't collapse under scanning | |
746 | pressure on the pagecache, yet still allows arc to be reclaimed down to | |
747 | zfs_arc_min if necessary. This value is specified as percent of pagecache | |
748 | size (as measured by NR_FILE_PAGES) where that percent may exceed 100. This | |
749 | only operates during memory pressure/reclaim. | |
750 | .sp | |
751 | Default value: \fB0\fR (disabled). | |
752 | .RE | |
753 | ||
11f552fa BB |
754 | .sp |
755 | .ne 2 | |
756 | .na | |
757 | \fBzfs_arc_sys_free\fR (ulong) | |
758 | .ad | |
759 | .RS 12n | |
760 | The target number of bytes the ARC should leave as free memory on the system. | |
761 | Defaults to the larger of 1/64 of physical memory or 512K. Setting this | |
762 | option to a non-zero value will override the default. | |
763 | .sp | |
764 | Default value: \fB0\fR. | |
765 | .RE | |
766 | ||
29714574 TF |
767 | .sp |
768 | .ne 2 | |
769 | .na | |
770 | \fBzfs_autoimport_disable\fR (int) | |
771 | .ad | |
772 | .RS 12n | |
27b293be | 773 | Disable pool import at module load by ignoring the cache file (typically \fB/etc/zfs/zpool.cache\fR). |
29714574 | 774 | .sp |
70081096 | 775 | Use \fB1\fR for yes (default) and \fB0\fR for no. |
29714574 TF |
776 | .RE |
777 | ||
2fe61a7e PS |
778 | .sp |
779 | .ne 2 | |
780 | .na | |
781 | \fBzfs_commit_timeout_pct\fR (int) | |
782 | .ad | |
783 | .RS 12n | |
784 | This controls the amount of time that a ZIL block (lwb) will remain "open" | |
785 | when it isn't "full", and it has a thread waiting for it to be committed to | |
786 | stable storage. The timeout is scaled based on a percentage of the last lwb | |
787 | latency to avoid significantly impacting the latency of each individual | |
788 | transaction record (itx). | |
789 | .sp | |
790 | Default value: \fB5\fR. | |
791 | .RE | |
792 | ||
3b36f831 BB |
793 | .sp |
794 | .ne 2 | |
795 | .na | |
796 | \fBzfs_dbgmsg_enable\fR (int) | |
797 | .ad | |
798 | .RS 12n | |
799 | Internally ZFS keeps a small log to facilitate debugging. By default the log | |
800 | is disabled, to enable it set this option to 1. The contents of the log can | |
801 | be accessed by reading the /proc/spl/kstat/zfs/dbgmsg file. Writing 0 to | |
802 | this proc file clears the log. | |
803 | .sp | |
804 | Default value: \fB0\fR. | |
805 | .RE | |
806 | ||
807 | .sp | |
808 | .ne 2 | |
809 | .na | |
810 | \fBzfs_dbgmsg_maxsize\fR (int) | |
811 | .ad | |
812 | .RS 12n | |
813 | The maximum size in bytes of the internal ZFS debug log. | |
814 | .sp | |
815 | Default value: \fB4M\fR. | |
816 | .RE | |
817 | ||
29714574 TF |
818 | .sp |
819 | .ne 2 | |
820 | .na | |
821 | \fBzfs_dbuf_state_index\fR (int) | |
822 | .ad | |
823 | .RS 12n | |
83426735 D |
824 | This feature is currently unused. It is normally used for controlling what |
825 | reporting is available under /proc/spl/kstat/zfs. | |
29714574 TF |
826 | .sp |
827 | Default value: \fB0\fR. | |
828 | .RE | |
829 | ||
830 | .sp | |
831 | .ne 2 | |
832 | .na | |
833 | \fBzfs_deadman_enabled\fR (int) | |
834 | .ad | |
835 | .RS 12n | |
b81a3ddc TC |
836 | When a pool sync operation takes longer than \fBzfs_deadman_synctime_ms\fR |
837 | milliseconds, a "slow spa_sync" message is logged to the debug log | |
838 | (see \fBzfs_dbgmsg_enable\fR). If \fBzfs_deadman_enabled\fR is set, | |
839 | all pending IO operations are also checked and if any haven't completed | |
840 | within \fBzfs_deadman_synctime_ms\fR milliseconds, a "SLOW IO" message | |
841 | is logged to the debug log and a "delay" system event with the details of | |
842 | the hung IO is posted. | |
29714574 | 843 | .sp |
b81a3ddc TC |
844 | Use \fB1\fR (default) to enable the slow IO check and \fB0\fR to disable. |
845 | .RE | |
846 | ||
847 | .sp | |
848 | .ne 2 | |
849 | .na | |
850 | \fBzfs_deadman_checktime_ms\fR (int) | |
851 | .ad | |
852 | .RS 12n | |
853 | Once a pool sync operation has taken longer than | |
854 | \fBzfs_deadman_synctime_ms\fR milliseconds, continue to check for slow | |
855 | operations every \fBzfs_deadman_checktime_ms\fR milliseconds. | |
856 | .sp | |
857 | Default value: \fB5,000\fR. | |
29714574 TF |
858 | .RE |
859 | ||
860 | .sp | |
861 | .ne 2 | |
862 | .na | |
e8b96c60 | 863 | \fBzfs_deadman_synctime_ms\fR (ulong) |
29714574 TF |
864 | .ad |
865 | .RS 12n | |
b81a3ddc TC |
866 | Interval in milliseconds after which the deadman is triggered and also |
867 | the interval after which an IO operation is considered to be "hung" | |
868 | if \fBzfs_deadman_enabled\fR is set. | |
869 | ||
870 | See \fBzfs_deadman_enabled\fR. | |
29714574 | 871 | .sp |
e8b96c60 | 872 | Default value: \fB1,000,000\fR. |
29714574 TF |
873 | .RE |
874 | ||
875 | .sp | |
876 | .ne 2 | |
877 | .na | |
878 | \fBzfs_dedup_prefetch\fR (int) | |
879 | .ad | |
880 | .RS 12n | |
881 | Enable prefetching dedup-ed blks | |
882 | .sp | |
0dfc7324 | 883 | Use \fB1\fR for yes and \fB0\fR to disable (default). |
29714574 TF |
884 | .RE |
885 | ||
e8b96c60 MA |
886 | .sp |
887 | .ne 2 | |
888 | .na | |
889 | \fBzfs_delay_min_dirty_percent\fR (int) | |
890 | .ad | |
891 | .RS 12n | |
892 | Start to delay each transaction once there is this amount of dirty data, | |
893 | expressed as a percentage of \fBzfs_dirty_data_max\fR. | |
894 | This value should be >= zfs_vdev_async_write_active_max_dirty_percent. | |
895 | See the section "ZFS TRANSACTION DELAY". | |
896 | .sp | |
897 | Default value: \fB60\fR. | |
898 | .RE | |
899 | ||
900 | .sp | |
901 | .ne 2 | |
902 | .na | |
903 | \fBzfs_delay_scale\fR (int) | |
904 | .ad | |
905 | .RS 12n | |
906 | This controls how quickly the transaction delay approaches infinity. | |
907 | Larger values cause longer delays for a given amount of dirty data. | |
908 | .sp | |
909 | For the smoothest delay, this value should be about 1 billion divided | |
910 | by the maximum number of operations per second. This will smoothly | |
911 | handle between 10x and 1/10th this number. | |
912 | .sp | |
913 | See the section "ZFS TRANSACTION DELAY". | |
914 | .sp | |
915 | Note: \fBzfs_delay_scale\fR * \fBzfs_dirty_data_max\fR must be < 2^64. | |
916 | .sp | |
917 | Default value: \fB500,000\fR. | |
918 | .RE | |
919 | ||
a966c564 K |
920 | .sp |
921 | .ne 2 | |
922 | .na | |
923 | \fBzfs_delete_blocks\fR (ulong) | |
924 | .ad | |
925 | .RS 12n | |
926 | This is the used to define a large file for the purposes of delete. Files | |
927 | containing more than \fBzfs_delete_blocks\fR will be deleted asynchronously | |
928 | while smaller files are deleted synchronously. Decreasing this value will | |
929 | reduce the time spent in an unlink(2) system call at the expense of a longer | |
930 | delay before the freed space is available. | |
931 | .sp | |
932 | Default value: \fB20,480\fR. | |
933 | .RE | |
934 | ||
e8b96c60 MA |
935 | .sp |
936 | .ne 2 | |
937 | .na | |
938 | \fBzfs_dirty_data_max\fR (int) | |
939 | .ad | |
940 | .RS 12n | |
941 | Determines the dirty space limit in bytes. Once this limit is exceeded, new | |
942 | writes are halted until space frees up. This parameter takes precedence | |
943 | over \fBzfs_dirty_data_max_percent\fR. | |
944 | See the section "ZFS TRANSACTION DELAY". | |
945 | .sp | |
946 | Default value: 10 percent of all memory, capped at \fBzfs_dirty_data_max_max\fR. | |
947 | .RE | |
948 | ||
949 | .sp | |
950 | .ne 2 | |
951 | .na | |
952 | \fBzfs_dirty_data_max_max\fR (int) | |
953 | .ad | |
954 | .RS 12n | |
955 | Maximum allowable value of \fBzfs_dirty_data_max\fR, expressed in bytes. | |
956 | This limit is only enforced at module load time, and will be ignored if | |
957 | \fBzfs_dirty_data_max\fR is later changed. This parameter takes | |
958 | precedence over \fBzfs_dirty_data_max_max_percent\fR. See the section | |
959 | "ZFS TRANSACTION DELAY". | |
960 | .sp | |
961 | Default value: 25% of physical RAM. | |
962 | .RE | |
963 | ||
964 | .sp | |
965 | .ne 2 | |
966 | .na | |
967 | \fBzfs_dirty_data_max_max_percent\fR (int) | |
968 | .ad | |
969 | .RS 12n | |
970 | Maximum allowable value of \fBzfs_dirty_data_max\fR, expressed as a | |
971 | percentage of physical RAM. This limit is only enforced at module load | |
972 | time, and will be ignored if \fBzfs_dirty_data_max\fR is later changed. | |
973 | The parameter \fBzfs_dirty_data_max_max\fR takes precedence over this | |
974 | one. See the section "ZFS TRANSACTION DELAY". | |
975 | .sp | |
9ef3906a | 976 | Default value: \fB25\fR. |
e8b96c60 MA |
977 | .RE |
978 | ||
979 | .sp | |
980 | .ne 2 | |
981 | .na | |
982 | \fBzfs_dirty_data_max_percent\fR (int) | |
983 | .ad | |
984 | .RS 12n | |
985 | Determines the dirty space limit, expressed as a percentage of all | |
986 | memory. Once this limit is exceeded, new writes are halted until space frees | |
987 | up. The parameter \fBzfs_dirty_data_max\fR takes precedence over this | |
988 | one. See the section "ZFS TRANSACTION DELAY". | |
989 | .sp | |
990 | Default value: 10%, subject to \fBzfs_dirty_data_max_max\fR. | |
991 | .RE | |
992 | ||
993 | .sp | |
994 | .ne 2 | |
995 | .na | |
996 | \fBzfs_dirty_data_sync\fR (int) | |
997 | .ad | |
998 | .RS 12n | |
999 | Start syncing out a transaction group if there is at least this much dirty data. | |
1000 | .sp | |
1001 | Default value: \fB67,108,864\fR. | |
1002 | .RE | |
1003 | ||
1eeb4562 JX |
1004 | .sp |
1005 | .ne 2 | |
1006 | .na | |
1007 | \fBzfs_fletcher_4_impl\fR (string) | |
1008 | .ad | |
1009 | .RS 12n | |
1010 | Select a fletcher 4 implementation. | |
1011 | .sp | |
35a76a03 | 1012 | Supported selectors are: \fBfastest\fR, \fBscalar\fR, \fBsse2\fR, \fBssse3\fR, |
24cdeaf1 | 1013 | \fBavx2\fR, \fBavx512f\fR, and \fBaarch64_neon\fR. |
70b258fc GN |
1014 | All of the selectors except \fBfastest\fR and \fBscalar\fR require instruction |
1015 | set extensions to be available and will only appear if ZFS detects that they are | |
1016 | present at runtime. If multiple implementations of fletcher 4 are available, | |
1017 | the \fBfastest\fR will be chosen using a micro benchmark. Selecting \fBscalar\fR | |
1018 | results in the original, CPU based calculation, being used. Selecting any option | |
1019 | other than \fBfastest\fR and \fBscalar\fR results in vector instructions from | |
1020 | the respective CPU instruction set being used. | |
1eeb4562 JX |
1021 | .sp |
1022 | Default value: \fBfastest\fR. | |
1023 | .RE | |
1024 | ||
ba5ad9a4 GW |
1025 | .sp |
1026 | .ne 2 | |
1027 | .na | |
1028 | \fBzfs_free_bpobj_enabled\fR (int) | |
1029 | .ad | |
1030 | .RS 12n | |
1031 | Enable/disable the processing of the free_bpobj object. | |
1032 | .sp | |
1033 | Default value: \fB1\fR. | |
1034 | .RE | |
1035 | ||
36283ca2 MG |
1036 | .sp |
1037 | .ne 2 | |
1038 | .na | |
1039 | \fBzfs_free_max_blocks\fR (ulong) | |
1040 | .ad | |
1041 | .RS 12n | |
1042 | Maximum number of blocks freed in a single txg. | |
1043 | .sp | |
1044 | Default value: \fB100,000\fR. | |
1045 | .RE | |
1046 | ||
e8b96c60 MA |
1047 | .sp |
1048 | .ne 2 | |
1049 | .na | |
1050 | \fBzfs_vdev_async_read_max_active\fR (int) | |
1051 | .ad | |
1052 | .RS 12n | |
83426735 | 1053 | Maximum asynchronous read I/Os active to each device. |
e8b96c60 MA |
1054 | See the section "ZFS I/O SCHEDULER". |
1055 | .sp | |
1056 | Default value: \fB3\fR. | |
1057 | .RE | |
1058 | ||
1059 | .sp | |
1060 | .ne 2 | |
1061 | .na | |
1062 | \fBzfs_vdev_async_read_min_active\fR (int) | |
1063 | .ad | |
1064 | .RS 12n | |
1065 | Minimum asynchronous read I/Os active to each device. | |
1066 | See the section "ZFS I/O SCHEDULER". | |
1067 | .sp | |
1068 | Default value: \fB1\fR. | |
1069 | .RE | |
1070 | ||
1071 | .sp | |
1072 | .ne 2 | |
1073 | .na | |
1074 | \fBzfs_vdev_async_write_active_max_dirty_percent\fR (int) | |
1075 | .ad | |
1076 | .RS 12n | |
1077 | When the pool has more than | |
1078 | \fBzfs_vdev_async_write_active_max_dirty_percent\fR dirty data, use | |
1079 | \fBzfs_vdev_async_write_max_active\fR to limit active async writes. If | |
1080 | the dirty data is between min and max, the active I/O limit is linearly | |
1081 | interpolated. See the section "ZFS I/O SCHEDULER". | |
1082 | .sp | |
1083 | Default value: \fB60\fR. | |
1084 | .RE | |
1085 | ||
1086 | .sp | |
1087 | .ne 2 | |
1088 | .na | |
1089 | \fBzfs_vdev_async_write_active_min_dirty_percent\fR (int) | |
1090 | .ad | |
1091 | .RS 12n | |
1092 | When the pool has less than | |
1093 | \fBzfs_vdev_async_write_active_min_dirty_percent\fR dirty data, use | |
1094 | \fBzfs_vdev_async_write_min_active\fR to limit active async writes. If | |
1095 | the dirty data is between min and max, the active I/O limit is linearly | |
1096 | interpolated. See the section "ZFS I/O SCHEDULER". | |
1097 | .sp | |
1098 | Default value: \fB30\fR. | |
1099 | .RE | |
1100 | ||
1101 | .sp | |
1102 | .ne 2 | |
1103 | .na | |
1104 | \fBzfs_vdev_async_write_max_active\fR (int) | |
1105 | .ad | |
1106 | .RS 12n | |
83426735 | 1107 | Maximum asynchronous write I/Os active to each device. |
e8b96c60 MA |
1108 | See the section "ZFS I/O SCHEDULER". |
1109 | .sp | |
1110 | Default value: \fB10\fR. | |
1111 | .RE | |
1112 | ||
1113 | .sp | |
1114 | .ne 2 | |
1115 | .na | |
1116 | \fBzfs_vdev_async_write_min_active\fR (int) | |
1117 | .ad | |
1118 | .RS 12n | |
1119 | Minimum asynchronous write I/Os active to each device. | |
1120 | See the section "ZFS I/O SCHEDULER". | |
1121 | .sp | |
06226b59 D |
1122 | Lower values are associated with better latency on rotational media but poorer |
1123 | resilver performance. The default value of 2 was chosen as a compromise. A | |
1124 | value of 3 has been shown to improve resilver performance further at a cost of | |
1125 | further increasing latency. | |
1126 | .sp | |
1127 | Default value: \fB2\fR. | |
e8b96c60 MA |
1128 | .RE |
1129 | ||
1130 | .sp | |
1131 | .ne 2 | |
1132 | .na | |
1133 | \fBzfs_vdev_max_active\fR (int) | |
1134 | .ad | |
1135 | .RS 12n | |
1136 | The maximum number of I/Os active to each device. Ideally, this will be >= | |
1137 | the sum of each queue's max_active. It must be at least the sum of each | |
1138 | queue's min_active. See the section "ZFS I/O SCHEDULER". | |
1139 | .sp | |
1140 | Default value: \fB1,000\fR. | |
1141 | .RE | |
1142 | ||
1143 | .sp | |
1144 | .ne 2 | |
1145 | .na | |
1146 | \fBzfs_vdev_scrub_max_active\fR (int) | |
1147 | .ad | |
1148 | .RS 12n | |
83426735 | 1149 | Maximum scrub I/Os active to each device. |
e8b96c60 MA |
1150 | See the section "ZFS I/O SCHEDULER". |
1151 | .sp | |
1152 | Default value: \fB2\fR. | |
1153 | .RE | |
1154 | ||
1155 | .sp | |
1156 | .ne 2 | |
1157 | .na | |
1158 | \fBzfs_vdev_scrub_min_active\fR (int) | |
1159 | .ad | |
1160 | .RS 12n | |
1161 | Minimum scrub I/Os active to each device. | |
1162 | See the section "ZFS I/O SCHEDULER". | |
1163 | .sp | |
1164 | Default value: \fB1\fR. | |
1165 | .RE | |
1166 | ||
1167 | .sp | |
1168 | .ne 2 | |
1169 | .na | |
1170 | \fBzfs_vdev_sync_read_max_active\fR (int) | |
1171 | .ad | |
1172 | .RS 12n | |
83426735 | 1173 | Maximum synchronous read I/Os active to each device. |
e8b96c60 MA |
1174 | See the section "ZFS I/O SCHEDULER". |
1175 | .sp | |
1176 | Default value: \fB10\fR. | |
1177 | .RE | |
1178 | ||
1179 | .sp | |
1180 | .ne 2 | |
1181 | .na | |
1182 | \fBzfs_vdev_sync_read_min_active\fR (int) | |
1183 | .ad | |
1184 | .RS 12n | |
1185 | Minimum synchronous read I/Os active to each device. | |
1186 | See the section "ZFS I/O SCHEDULER". | |
1187 | .sp | |
1188 | Default value: \fB10\fR. | |
1189 | .RE | |
1190 | ||
1191 | .sp | |
1192 | .ne 2 | |
1193 | .na | |
1194 | \fBzfs_vdev_sync_write_max_active\fR (int) | |
1195 | .ad | |
1196 | .RS 12n | |
83426735 | 1197 | Maximum synchronous write I/Os active to each device. |
e8b96c60 MA |
1198 | See the section "ZFS I/O SCHEDULER". |
1199 | .sp | |
1200 | Default value: \fB10\fR. | |
1201 | .RE | |
1202 | ||
1203 | .sp | |
1204 | .ne 2 | |
1205 | .na | |
1206 | \fBzfs_vdev_sync_write_min_active\fR (int) | |
1207 | .ad | |
1208 | .RS 12n | |
1209 | Minimum synchronous write I/Os active to each device. | |
1210 | See the section "ZFS I/O SCHEDULER". | |
1211 | .sp | |
1212 | Default value: \fB10\fR. | |
1213 | .RE | |
1214 | ||
3dfb57a3 DB |
1215 | .sp |
1216 | .ne 2 | |
1217 | .na | |
1218 | \fBzfs_vdev_queue_depth_pct\fR (int) | |
1219 | .ad | |
1220 | .RS 12n | |
e815485f TC |
1221 | Maximum number of queued allocations per top-level vdev expressed as |
1222 | a percentage of \fBzfs_vdev_async_write_max_active\fR which allows the | |
1223 | system to detect devices that are more capable of handling allocations | |
1224 | and to allocate more blocks to those devices. It allows for dynamic | |
1225 | allocation distribution when devices are imbalanced as fuller devices | |
1226 | will tend to be slower than empty devices. | |
1227 | ||
1228 | See also \fBzio_dva_throttle_enabled\fR. | |
3dfb57a3 DB |
1229 | .sp |
1230 | Default value: \fB1000\fR. | |
1231 | .RE | |
1232 | ||
29714574 TF |
1233 | .sp |
1234 | .ne 2 | |
1235 | .na | |
1236 | \fBzfs_disable_dup_eviction\fR (int) | |
1237 | .ad | |
1238 | .RS 12n | |
1239 | Disable duplicate buffer eviction | |
1240 | .sp | |
1241 | Use \fB1\fR for yes and \fB0\fR for no (default). | |
1242 | .RE | |
1243 | ||
1244 | .sp | |
1245 | .ne 2 | |
1246 | .na | |
1247 | \fBzfs_expire_snapshot\fR (int) | |
1248 | .ad | |
1249 | .RS 12n | |
1250 | Seconds to expire .zfs/snapshot | |
1251 | .sp | |
1252 | Default value: \fB300\fR. | |
1253 | .RE | |
1254 | ||
0500e835 BB |
1255 | .sp |
1256 | .ne 2 | |
1257 | .na | |
1258 | \fBzfs_admin_snapshot\fR (int) | |
1259 | .ad | |
1260 | .RS 12n | |
1261 | Allow the creation, removal, or renaming of entries in the .zfs/snapshot | |
1262 | directory to cause the creation, destruction, or renaming of snapshots. | |
1263 | When enabled this functionality works both locally and over NFS exports | |
1264 | which have the 'no_root_squash' option set. This functionality is disabled | |
1265 | by default. | |
1266 | .sp | |
1267 | Use \fB1\fR for yes and \fB0\fR for no (default). | |
1268 | .RE | |
1269 | ||
29714574 TF |
1270 | .sp |
1271 | .ne 2 | |
1272 | .na | |
1273 | \fBzfs_flags\fR (int) | |
1274 | .ad | |
1275 | .RS 12n | |
33b6dbbc NB |
1276 | Set additional debugging flags. The following flags may be bitwise-or'd |
1277 | together. | |
1278 | .sp | |
1279 | .TS | |
1280 | box; | |
1281 | rB lB | |
1282 | lB lB | |
1283 | r l. | |
1284 | Value Symbolic Name | |
1285 | Description | |
1286 | _ | |
1287 | 1 ZFS_DEBUG_DPRINTF | |
1288 | Enable dprintf entries in the debug log. | |
1289 | _ | |
1290 | 2 ZFS_DEBUG_DBUF_VERIFY * | |
1291 | Enable extra dbuf verifications. | |
1292 | _ | |
1293 | 4 ZFS_DEBUG_DNODE_VERIFY * | |
1294 | Enable extra dnode verifications. | |
1295 | _ | |
1296 | 8 ZFS_DEBUG_SNAPNAMES | |
1297 | Enable snapshot name verification. | |
1298 | _ | |
1299 | 16 ZFS_DEBUG_MODIFY | |
1300 | Check for illegally modified ARC buffers. | |
1301 | _ | |
1302 | 32 ZFS_DEBUG_SPA | |
1303 | Enable spa_dbgmsg entries in the debug log. | |
1304 | _ | |
1305 | 64 ZFS_DEBUG_ZIO_FREE | |
1306 | Enable verification of block frees. | |
1307 | _ | |
1308 | 128 ZFS_DEBUG_HISTOGRAM_VERIFY | |
1309 | Enable extra spacemap histogram verifications. | |
8740cf4a NB |
1310 | _ |
1311 | 256 ZFS_DEBUG_METASLAB_VERIFY | |
1312 | Verify space accounting on disk matches in-core range_trees. | |
1313 | _ | |
1314 | 512 ZFS_DEBUG_SET_ERROR | |
1315 | Enable SET_ERROR and dprintf entries in the debug log. | |
33b6dbbc NB |
1316 | .TE |
1317 | .sp | |
1318 | * Requires debug build. | |
29714574 | 1319 | .sp |
33b6dbbc | 1320 | Default value: \fB0\fR. |
29714574 TF |
1321 | .RE |
1322 | ||
fbeddd60 MA |
1323 | .sp |
1324 | .ne 2 | |
1325 | .na | |
1326 | \fBzfs_free_leak_on_eio\fR (int) | |
1327 | .ad | |
1328 | .RS 12n | |
1329 | If destroy encounters an EIO while reading metadata (e.g. indirect | |
1330 | blocks), space referenced by the missing metadata can not be freed. | |
1331 | Normally this causes the background destroy to become "stalled", as | |
1332 | it is unable to make forward progress. While in this stalled state, | |
1333 | all remaining space to free from the error-encountering filesystem is | |
1334 | "temporarily leaked". Set this flag to cause it to ignore the EIO, | |
1335 | permanently leak the space from indirect blocks that can not be read, | |
1336 | and continue to free everything else that it can. | |
1337 | ||
1338 | The default, "stalling" behavior is useful if the storage partially | |
1339 | fails (i.e. some but not all i/os fail), and then later recovers. In | |
1340 | this case, we will be able to continue pool operations while it is | |
1341 | partially failed, and when it recovers, we can continue to free the | |
1342 | space, with no leaks. However, note that this case is actually | |
1343 | fairly rare. | |
1344 | ||
1345 | Typically pools either (a) fail completely (but perhaps temporarily, | |
1346 | e.g. a top-level vdev going offline), or (b) have localized, | |
1347 | permanent errors (e.g. disk returns the wrong data due to bit flip or | |
1348 | firmware bug). In case (a), this setting does not matter because the | |
1349 | pool will be suspended and the sync thread will not be able to make | |
1350 | forward progress regardless. In case (b), because the error is | |
1351 | permanent, the best we can do is leak the minimum amount of space, | |
1352 | which is what setting this flag will do. Therefore, it is reasonable | |
1353 | for this flag to normally be set, but we chose the more conservative | |
1354 | approach of not setting it, so that there is no possibility of | |
1355 | leaking space in the "partial temporary" failure case. | |
1356 | .sp | |
1357 | Default value: \fB0\fR. | |
1358 | .RE | |
1359 | ||
29714574 TF |
1360 | .sp |
1361 | .ne 2 | |
1362 | .na | |
1363 | \fBzfs_free_min_time_ms\fR (int) | |
1364 | .ad | |
1365 | .RS 12n | |
6146e17e | 1366 | During a \fBzfs destroy\fR operation using \fBfeature@async_destroy\fR a minimum |
83426735 | 1367 | of this much time will be spent working on freeing blocks per txg. |
29714574 TF |
1368 | .sp |
1369 | Default value: \fB1,000\fR. | |
1370 | .RE | |
1371 | ||
1372 | .sp | |
1373 | .ne 2 | |
1374 | .na | |
1375 | \fBzfs_immediate_write_sz\fR (long) | |
1376 | .ad | |
1377 | .RS 12n | |
83426735 | 1378 | Largest data block to write to zil. Larger blocks will be treated as if the |
6146e17e | 1379 | dataset being written to had the property setting \fBlogbias=throughput\fR. |
29714574 TF |
1380 | .sp |
1381 | Default value: \fB32,768\fR. | |
1382 | .RE | |
1383 | ||
f1512ee6 MA |
1384 | .sp |
1385 | .ne 2 | |
1386 | .na | |
1387 | \fBzfs_max_recordsize\fR (int) | |
1388 | .ad | |
1389 | .RS 12n | |
1390 | We currently support block sizes from 512 bytes to 16MB. The benefits of | |
1391 | larger blocks, and thus larger IO, need to be weighed against the cost of | |
1392 | COWing a giant block to modify one byte. Additionally, very large blocks | |
1393 | can have an impact on i/o latency, and also potentially on the memory | |
1394 | allocator. Therefore, we do not allow the recordsize to be set larger than | |
1395 | zfs_max_recordsize (default 1MB). Larger blocks can be created by changing | |
1396 | this tunable, and pools with larger blocks can always be imported and used, | |
1397 | regardless of this setting. | |
1398 | .sp | |
1399 | Default value: \fB1,048,576\fR. | |
1400 | .RE | |
1401 | ||
29714574 TF |
1402 | .sp |
1403 | .ne 2 | |
1404 | .na | |
1405 | \fBzfs_mdcomp_disable\fR (int) | |
1406 | .ad | |
1407 | .RS 12n | |
1408 | Disable meta data compression | |
1409 | .sp | |
1410 | Use \fB1\fR for yes and \fB0\fR for no (default). | |
1411 | .RE | |
1412 | ||
f3a7f661 GW |
1413 | .sp |
1414 | .ne 2 | |
1415 | .na | |
1416 | \fBzfs_metaslab_fragmentation_threshold\fR (int) | |
1417 | .ad | |
1418 | .RS 12n | |
1419 | Allow metaslabs to keep their active state as long as their fragmentation | |
1420 | percentage is less than or equal to this value. An active metaslab that | |
1421 | exceeds this threshold will no longer keep its active status allowing | |
1422 | better metaslabs to be selected. | |
1423 | .sp | |
1424 | Default value: \fB70\fR. | |
1425 | .RE | |
1426 | ||
1427 | .sp | |
1428 | .ne 2 | |
1429 | .na | |
1430 | \fBzfs_mg_fragmentation_threshold\fR (int) | |
1431 | .ad | |
1432 | .RS 12n | |
1433 | Metaslab groups are considered eligible for allocations if their | |
83426735 | 1434 | fragmentation metric (measured as a percentage) is less than or equal to |
f3a7f661 GW |
1435 | this value. If a metaslab group exceeds this threshold then it will be |
1436 | skipped unless all metaslab groups within the metaslab class have also | |
1437 | crossed this threshold. | |
1438 | .sp | |
1439 | Default value: \fB85\fR. | |
1440 | .RE | |
1441 | ||
f4a4046b TC |
1442 | .sp |
1443 | .ne 2 | |
1444 | .na | |
1445 | \fBzfs_mg_noalloc_threshold\fR (int) | |
1446 | .ad | |
1447 | .RS 12n | |
1448 | Defines a threshold at which metaslab groups should be eligible for | |
1449 | allocations. The value is expressed as a percentage of free space | |
1450 | beyond which a metaslab group is always eligible for allocations. | |
1451 | If a metaslab group's free space is less than or equal to the | |
6b4e21c6 | 1452 | threshold, the allocator will avoid allocating to that group |
f4a4046b TC |
1453 | unless all groups in the pool have reached the threshold. Once all |
1454 | groups have reached the threshold, all groups are allowed to accept | |
1455 | allocations. The default value of 0 disables the feature and causes | |
1456 | all metaslab groups to be eligible for allocations. | |
1457 | ||
b58237e7 | 1458 | This parameter allows one to deal with pools having heavily imbalanced |
f4a4046b TC |
1459 | vdevs such as would be the case when a new vdev has been added. |
1460 | Setting the threshold to a non-zero percentage will stop allocations | |
1461 | from being made to vdevs that aren't filled to the specified percentage | |
1462 | and allow lesser filled vdevs to acquire more allocations than they | |
1463 | otherwise would under the old \fBzfs_mg_alloc_failures\fR facility. | |
1464 | .sp | |
1465 | Default value: \fB0\fR. | |
1466 | .RE | |
1467 | ||
379ca9cf OF |
1468 | .sp |
1469 | .ne 2 | |
1470 | .na | |
1471 | \fBzfs_multihost_history\fR (int) | |
1472 | .ad | |
1473 | .RS 12n | |
1474 | Historical statistics for the last N multihost updates will be available in | |
1475 | \fB/proc/spl/kstat/zfs/<pool>/multihost\fR | |
1476 | .sp | |
1477 | Default value: \fB0\fR. | |
1478 | .RE | |
1479 | ||
1480 | .sp | |
1481 | .ne 2 | |
1482 | .na | |
1483 | \fBzfs_multihost_interval\fR (ulong) | |
1484 | .ad | |
1485 | .RS 12n | |
1486 | Used to control the frequency of multihost writes which are performed when the | |
1487 | \fBmultihost\fR pool property is on. This is one factor used to determine | |
1488 | the length of the activity check during import. | |
1489 | .sp | |
1490 | The multihost write period is \fBzfs_multihost_interval / leaf-vdevs\fR milliseconds. | |
1491 | This means that on average a multihost write will be issued for each leaf vdev every | |
1492 | \fBzfs_multihost_interval\fR milliseconds. In practice, the observed period can | |
1493 | vary with the I/O load and this observed value is the delay which is stored in | |
1494 | the uberblock. | |
1495 | .sp | |
1496 | On import the activity check waits a minimum amount of time determined by | |
1497 | \fBzfs_multihost_interval * zfs_multihost_import_intervals\fR. The activity | |
1498 | check time may be further extended if the value of mmp delay found in the best | |
1499 | uberblock indicates actual multihost updates happened at longer intervals than | |
1500 | \fBzfs_multihost_interval\fR. A minimum value of \fB100ms\fR is enforced. | |
1501 | .sp | |
1502 | Default value: \fB1000\fR. | |
1503 | .RE | |
1504 | ||
1505 | .sp | |
1506 | .ne 2 | |
1507 | .na | |
1508 | \fBzfs_multihost_import_intervals\fR (uint) | |
1509 | .ad | |
1510 | .RS 12n | |
1511 | Used to control the duration of the activity test on import. Smaller values of | |
1512 | \fBzfs_multihost_import_intervals\fR will reduce the import time but increase | |
1513 | the risk of failing to detect an active pool. The total activity check time is | |
1514 | never allowed to drop below one second. A value of 0 is ignored and treated as | |
1515 | if it was set to 1 | |
1516 | .sp | |
1517 | Default value: \fB10\fR. | |
1518 | .RE | |
1519 | ||
1520 | .sp | |
1521 | .ne 2 | |
1522 | .na | |
1523 | \fBzfs_multihost_fail_intervals\fR (uint) | |
1524 | .ad | |
1525 | .RS 12n | |
1526 | Controls the behavior of the pool when multihost write failures are detected. | |
1527 | .sp | |
1528 | When \fBzfs_multihost_fail_intervals = 0\fR then multihost write failures are ignored. | |
1529 | The failures will still be reported to the ZED which depending on its | |
1530 | configuration may take action such as suspending the pool or offlining a device. | |
1531 | .sp | |
1532 | When \fBzfs_multihost_fail_intervals > 0\fR then sequential multihost write failures | |
1533 | will cause the pool to be suspended. This occurs when | |
1534 | \fBzfs_multihost_fail_intervals * zfs_multihost_interval\fR milliseconds have | |
1535 | passed since the last successful multihost write. This guarantees the activity test | |
1536 | will see multihost writes if the pool is imported. | |
1537 | .sp | |
1538 | Default value: \fB5\fR. | |
1539 | .RE | |
1540 | ||
29714574 TF |
1541 | .sp |
1542 | .ne 2 | |
1543 | .na | |
1544 | \fBzfs_no_scrub_io\fR (int) | |
1545 | .ad | |
1546 | .RS 12n | |
83426735 D |
1547 | Set for no scrub I/O. This results in scrubs not actually scrubbing data and |
1548 | simply doing a metadata crawl of the pool instead. | |
29714574 TF |
1549 | .sp |
1550 | Use \fB1\fR for yes and \fB0\fR for no (default). | |
1551 | .RE | |
1552 | ||
1553 | .sp | |
1554 | .ne 2 | |
1555 | .na | |
1556 | \fBzfs_no_scrub_prefetch\fR (int) | |
1557 | .ad | |
1558 | .RS 12n | |
83426735 | 1559 | Set to disable block prefetching for scrubs. |
29714574 TF |
1560 | .sp |
1561 | Use \fB1\fR for yes and \fB0\fR for no (default). | |
1562 | .RE | |
1563 | ||
29714574 TF |
1564 | .sp |
1565 | .ne 2 | |
1566 | .na | |
1567 | \fBzfs_nocacheflush\fR (int) | |
1568 | .ad | |
1569 | .RS 12n | |
83426735 D |
1570 | Disable cache flush operations on disks when writing. Beware, this may cause |
1571 | corruption if disks re-order writes. | |
29714574 TF |
1572 | .sp |
1573 | Use \fB1\fR for yes and \fB0\fR for no (default). | |
1574 | .RE | |
1575 | ||
1576 | .sp | |
1577 | .ne 2 | |
1578 | .na | |
1579 | \fBzfs_nopwrite_enabled\fR (int) | |
1580 | .ad | |
1581 | .RS 12n | |
1582 | Enable NOP writes | |
1583 | .sp | |
1584 | Use \fB1\fR for yes (default) and \fB0\fR to disable. | |
1585 | .RE | |
1586 | ||
66aca247 DB |
1587 | .sp |
1588 | .ne 2 | |
1589 | .na | |
1590 | \fBzfs_dmu_offset_next_sync\fR (int) | |
1591 | .ad | |
1592 | .RS 12n | |
1593 | Enable forcing txg sync to find holes. When enabled forces ZFS to act | |
1594 | like prior versions when SEEK_HOLE or SEEK_DATA flags are used, which | |
1595 | when a dnode is dirty causes txg's to be synced so that this data can be | |
1596 | found. | |
1597 | .sp | |
1598 | Use \fB1\fR for yes and \fB0\fR to disable (default). | |
1599 | .RE | |
1600 | ||
29714574 TF |
1601 | .sp |
1602 | .ne 2 | |
1603 | .na | |
b738bc5a | 1604 | \fBzfs_pd_bytes_max\fR (int) |
29714574 TF |
1605 | .ad |
1606 | .RS 12n | |
83426735 | 1607 | The number of bytes which should be prefetched during a pool traversal |
6146e17e | 1608 | (eg: \fBzfs send\fR or other data crawling operations) |
29714574 | 1609 | .sp |
74aa2ba2 | 1610 | Default value: \fB52,428,800\fR. |
29714574 TF |
1611 | .RE |
1612 | ||
bef78122 DQ |
1613 | .sp |
1614 | .ne 2 | |
1615 | .na | |
1616 | \fBzfs_per_txg_dirty_frees_percent \fR (ulong) | |
1617 | .ad | |
1618 | .RS 12n | |
1619 | Tunable to control percentage of dirtied blocks from frees in one TXG. | |
1620 | After this threshold is crossed, additional dirty blocks from frees | |
1621 | wait until the next TXG. | |
1622 | A value of zero will disable this throttle. | |
1623 | .sp | |
1624 | Default value: \fB30\fR and \fB0\fR to disable. | |
1625 | .RE | |
1626 | ||
1627 | ||
1628 | ||
29714574 TF |
1629 | .sp |
1630 | .ne 2 | |
1631 | .na | |
1632 | \fBzfs_prefetch_disable\fR (int) | |
1633 | .ad | |
1634 | .RS 12n | |
7f60329a MA |
1635 | This tunable disables predictive prefetch. Note that it leaves "prescient" |
1636 | prefetch (e.g. prefetch for zfs send) intact. Unlike predictive prefetch, | |
1637 | prescient prefetch never issues i/os that end up not being needed, so it | |
1638 | can't hurt performance. | |
29714574 TF |
1639 | .sp |
1640 | Use \fB1\fR for yes and \fB0\fR for no (default). | |
1641 | .RE | |
1642 | ||
1643 | .sp | |
1644 | .ne 2 | |
1645 | .na | |
1646 | \fBzfs_read_chunk_size\fR (long) | |
1647 | .ad | |
1648 | .RS 12n | |
1649 | Bytes to read per chunk | |
1650 | .sp | |
1651 | Default value: \fB1,048,576\fR. | |
1652 | .RE | |
1653 | ||
1654 | .sp | |
1655 | .ne 2 | |
1656 | .na | |
1657 | \fBzfs_read_history\fR (int) | |
1658 | .ad | |
1659 | .RS 12n | |
379ca9cf OF |
1660 | Historical statistics for the last N reads will be available in |
1661 | \fB/proc/spl/kstat/zfs/<pool>/reads\fR | |
29714574 | 1662 | .sp |
83426735 | 1663 | Default value: \fB0\fR (no data is kept). |
29714574 TF |
1664 | .RE |
1665 | ||
1666 | .sp | |
1667 | .ne 2 | |
1668 | .na | |
1669 | \fBzfs_read_history_hits\fR (int) | |
1670 | .ad | |
1671 | .RS 12n | |
1672 | Include cache hits in read history | |
1673 | .sp | |
1674 | Use \fB1\fR for yes and \fB0\fR for no (default). | |
1675 | .RE | |
1676 | ||
1677 | .sp | |
1678 | .ne 2 | |
1679 | .na | |
1680 | \fBzfs_recover\fR (int) | |
1681 | .ad | |
1682 | .RS 12n | |
1683 | Set to attempt to recover from fatal errors. This should only be used as a | |
1684 | last resort, as it typically results in leaked space, or worse. | |
1685 | .sp | |
1686 | Use \fB1\fR for yes and \fB0\fR for no (default). | |
1687 | .RE | |
1688 | ||
1689 | .sp | |
1690 | .ne 2 | |
1691 | .na | |
d4a72f23 | 1692 | \fBzfs_resilver_min_time_ms\fR (int) |
29714574 TF |
1693 | .ad |
1694 | .RS 12n | |
d4a72f23 TC |
1695 | Resilvers are processed by the sync thread. While resilvering it will spend |
1696 | at least this much time working on a resilver between txg flushes. | |
29714574 | 1697 | .sp |
d4a72f23 | 1698 | Default value: \fB3,000\fR. |
29714574 TF |
1699 | .RE |
1700 | ||
1701 | .sp | |
1702 | .ne 2 | |
1703 | .na | |
d4a72f23 | 1704 | \fBzfs_scrub_min_time_ms\fR (int) |
29714574 TF |
1705 | .ad |
1706 | .RS 12n | |
d4a72f23 TC |
1707 | Scrubs are processed by the sync thread. While scrubbing it will spend |
1708 | at least this much time working on a scrub between txg flushes. | |
29714574 | 1709 | .sp |
d4a72f23 | 1710 | Default value: \fB1,000\fR. |
29714574 TF |
1711 | .RE |
1712 | ||
1713 | .sp | |
1714 | .ne 2 | |
1715 | .na | |
d4a72f23 | 1716 | \fBzfs_scan_checkpoint_intval\fR (int) |
29714574 TF |
1717 | .ad |
1718 | .RS 12n | |
d4a72f23 TC |
1719 | To preserve progress across reboots the sequential scan algorithm periodically |
1720 | needs to stop metadata scanning and issue all the verifications I/Os to disk. | |
1721 | The frequency of this flushing is determined by the | |
1722 | \fBfBzfs_scan_checkpoint_intval\fR tunable. | |
29714574 | 1723 | .sp |
d4a72f23 | 1724 | Default value: \fB7200\fR seconds (every 2 hours). |
29714574 TF |
1725 | .RE |
1726 | ||
1727 | .sp | |
1728 | .ne 2 | |
1729 | .na | |
d4a72f23 | 1730 | \fBzfs_scan_fill_weight\fR (int) |
29714574 TF |
1731 | .ad |
1732 | .RS 12n | |
d4a72f23 TC |
1733 | This tunable affects how scrub and resilver I/O segments are ordered. A higher |
1734 | number indicates that we care more about how filled in a segment is, while a | |
1735 | lower number indicates we care more about the size of the extent without | |
1736 | considering the gaps within a segment. This value is only tunable upon module | |
1737 | insertion. Changing the value afterwards will have no affect on scrub or | |
1738 | resilver performance. | |
29714574 | 1739 | .sp |
d4a72f23 | 1740 | Default value: \fB3\fR. |
29714574 TF |
1741 | .RE |
1742 | ||
1743 | .sp | |
1744 | .ne 2 | |
1745 | .na | |
d4a72f23 | 1746 | \fBzfs_scan_issue_strategy\fR (int) |
29714574 TF |
1747 | .ad |
1748 | .RS 12n | |
d4a72f23 TC |
1749 | Determines the order that data will be verified while scrubbing or resilvering. |
1750 | If set to \fB1\fR, data will be verified as sequentially as possible, given the | |
1751 | amount of memory reserved for scrubbing (see \fBzfs_scan_mem_lim_fact\fR). This | |
1752 | may improve scrub performance if the pool's data is very fragmented. If set to | |
1753 | \fB2\fR, the largest mostly-contiguous chunk of found data will be verified | |
1754 | first. By deferring scrubbing of small segments, we may later find adjacent data | |
1755 | to coalesce and increase the segment size. If set to \fB0\fR, zfs will use | |
1756 | strategy \fB1\fR during normal verification and strategy \fB2\fR while taking a | |
1757 | checkpoint. | |
29714574 | 1758 | .sp |
d4a72f23 TC |
1759 | Default value: \fB0\fR. |
1760 | .RE | |
1761 | ||
1762 | .sp | |
1763 | .ne 2 | |
1764 | .na | |
1765 | \fBzfs_scan_legacy\fR (int) | |
1766 | .ad | |
1767 | .RS 12n | |
1768 | A value of 0 indicates that scrubs and resilvers will gather metadata in | |
1769 | memory before issuing sequential I/O. A value of 1 indicates that the legacy | |
1770 | algorithm will be used where I/O is initiated as soon as it is discovered. | |
1771 | Changing this value to 0 will not affect scrubs or resilvers that are already | |
1772 | in progress. | |
1773 | .sp | |
1774 | Default value: \fB0\fR. | |
1775 | .RE | |
1776 | ||
1777 | .sp | |
1778 | .ne 2 | |
1779 | .na | |
1780 | \fBzfs_scan_max_ext_gap\fR (int) | |
1781 | .ad | |
1782 | .RS 12n | |
1783 | Indicates the largest gap in bytes between scrub / resilver I/Os that will still | |
1784 | be considered sequential for sorting purposes. Changing this value will not | |
1785 | affect scrubs or resilvers that are already in progress. | |
1786 | .sp | |
1787 | Default value: \fB2097152 (2 MB)\fR. | |
1788 | .RE | |
1789 | ||
1790 | .sp | |
1791 | .ne 2 | |
1792 | .na | |
1793 | \fBzfs_scan_mem_lim_fact\fR (int) | |
1794 | .ad | |
1795 | .RS 12n | |
1796 | Maximum fraction of RAM used for I/O sorting by sequential scan algorithm. | |
1797 | This tunable determines the hard limit for I/O sorting memory usage. | |
1798 | When the hard limit is reached we stop scanning metadata and start issuing | |
1799 | data verification I/O. This is done until we get below the soft limit. | |
1800 | .sp | |
1801 | Default value: \fB20\fR which is 5% of RAM (1/20). | |
1802 | .RE | |
1803 | ||
1804 | .sp | |
1805 | .ne 2 | |
1806 | .na | |
1807 | \fBzfs_scan_mem_lim_soft_fact\fR (int) | |
1808 | .ad | |
1809 | .RS 12n | |
1810 | The fraction of the hard limit used to determined the soft limit for I/O sorting | |
1811 | by the sequential scan algorithm. When we cross this limit from bellow no action | |
1812 | is taken. When we cross this limit from above it is because we are issuing | |
1813 | verification I/O. In this case (unless the metadata scan is done) we stop | |
1814 | issuing verification I/O and start scanning metadata again until we get to the | |
1815 | hard limit. | |
1816 | .sp | |
1817 | Default value: \fB20\fR which is 5% of the hard limit (1/20). | |
1818 | .RE | |
1819 | ||
1820 | .sp | |
1821 | .ne 2 | |
1822 | .na | |
1823 | \fBzfs_scan_vdev_limit\fR (int) | |
1824 | .ad | |
1825 | .RS 12n | |
1826 | Maximum amount of data that can be concurrently issued at once for scrubs and | |
1827 | resilvers per leaf device, given in bytes. | |
1828 | .sp | |
1829 | Default value: \fB41943040\fR. | |
29714574 TF |
1830 | .RE |
1831 | ||
fd8febbd TF |
1832 | .sp |
1833 | .ne 2 | |
1834 | .na | |
1835 | \fBzfs_send_corrupt_data\fR (int) | |
1836 | .ad | |
1837 | .RS 12n | |
83426735 | 1838 | Allow sending of corrupt data (ignore read/checksum errors when sending data) |
fd8febbd TF |
1839 | .sp |
1840 | Use \fB1\fR for yes and \fB0\fR for no (default). | |
1841 | .RE | |
1842 | ||
29714574 TF |
1843 | .sp |
1844 | .ne 2 | |
1845 | .na | |
1846 | \fBzfs_sync_pass_deferred_free\fR (int) | |
1847 | .ad | |
1848 | .RS 12n | |
83426735 | 1849 | Flushing of data to disk is done in passes. Defer frees starting in this pass |
29714574 TF |
1850 | .sp |
1851 | Default value: \fB2\fR. | |
1852 | .RE | |
1853 | ||
1854 | .sp | |
1855 | .ne 2 | |
1856 | .na | |
1857 | \fBzfs_sync_pass_dont_compress\fR (int) | |
1858 | .ad | |
1859 | .RS 12n | |
1860 | Don't compress starting in this pass | |
1861 | .sp | |
1862 | Default value: \fB5\fR. | |
1863 | .RE | |
1864 | ||
1865 | .sp | |
1866 | .ne 2 | |
1867 | .na | |
1868 | \fBzfs_sync_pass_rewrite\fR (int) | |
1869 | .ad | |
1870 | .RS 12n | |
83426735 | 1871 | Rewrite new block pointers starting in this pass |
29714574 TF |
1872 | .sp |
1873 | Default value: \fB2\fR. | |
1874 | .RE | |
1875 | ||
a032ac4b BB |
1876 | .sp |
1877 | .ne 2 | |
1878 | .na | |
1879 | \fBzfs_sync_taskq_batch_pct\fR (int) | |
1880 | .ad | |
1881 | .RS 12n | |
1882 | This controls the number of threads used by the dp_sync_taskq. The default | |
1883 | value of 75% will create a maximum of one thread per cpu. | |
1884 | .sp | |
1885 | Default value: \fB75\fR. | |
1886 | .RE | |
1887 | ||
29714574 TF |
1888 | .sp |
1889 | .ne 2 | |
1890 | .na | |
1891 | \fBzfs_txg_history\fR (int) | |
1892 | .ad | |
1893 | .RS 12n | |
379ca9cf OF |
1894 | Historical statistics for the last N txgs will be available in |
1895 | \fB/proc/spl/kstat/zfs/<pool>/txgs\fR | |
29714574 | 1896 | .sp |
ca85d690 | 1897 | Default value: \fB0\fR. |
29714574 TF |
1898 | .RE |
1899 | ||
29714574 TF |
1900 | .sp |
1901 | .ne 2 | |
1902 | .na | |
1903 | \fBzfs_txg_timeout\fR (int) | |
1904 | .ad | |
1905 | .RS 12n | |
83426735 | 1906 | Flush dirty data to disk at least every N seconds (maximum txg duration) |
29714574 TF |
1907 | .sp |
1908 | Default value: \fB5\fR. | |
1909 | .RE | |
1910 | ||
1911 | .sp | |
1912 | .ne 2 | |
1913 | .na | |
1914 | \fBzfs_vdev_aggregation_limit\fR (int) | |
1915 | .ad | |
1916 | .RS 12n | |
1917 | Max vdev I/O aggregation size | |
1918 | .sp | |
1919 | Default value: \fB131,072\fR. | |
1920 | .RE | |
1921 | ||
1922 | .sp | |
1923 | .ne 2 | |
1924 | .na | |
1925 | \fBzfs_vdev_cache_bshift\fR (int) | |
1926 | .ad | |
1927 | .RS 12n | |
1928 | Shift size to inflate reads too | |
1929 | .sp | |
83426735 | 1930 | Default value: \fB16\fR (effectively 65536). |
29714574 TF |
1931 | .RE |
1932 | ||
1933 | .sp | |
1934 | .ne 2 | |
1935 | .na | |
1936 | \fBzfs_vdev_cache_max\fR (int) | |
1937 | .ad | |
1938 | .RS 12n | |
ca85d690 | 1939 | Inflate reads smaller than this value to meet the \fBzfs_vdev_cache_bshift\fR |
1940 | size (default 64k). | |
83426735 D |
1941 | .sp |
1942 | Default value: \fB16384\fR. | |
29714574 TF |
1943 | .RE |
1944 | ||
1945 | .sp | |
1946 | .ne 2 | |
1947 | .na | |
1948 | \fBzfs_vdev_cache_size\fR (int) | |
1949 | .ad | |
1950 | .RS 12n | |
83426735 D |
1951 | Total size of the per-disk cache in bytes. |
1952 | .sp | |
1953 | Currently this feature is disabled as it has been found to not be helpful | |
1954 | for performance and in some cases harmful. | |
29714574 TF |
1955 | .sp |
1956 | Default value: \fB0\fR. | |
1957 | .RE | |
1958 | ||
29714574 TF |
1959 | .sp |
1960 | .ne 2 | |
1961 | .na | |
9f500936 | 1962 | \fBzfs_vdev_mirror_rotating_inc\fR (int) |
29714574 TF |
1963 | .ad |
1964 | .RS 12n | |
9f500936 | 1965 | A number by which the balancing algorithm increments the load calculation for |
1966 | the purpose of selecting the least busy mirror member when an I/O immediately | |
1967 | follows its predecessor on rotational vdevs for the purpose of making decisions | |
1968 | based on load. | |
29714574 | 1969 | .sp |
9f500936 | 1970 | Default value: \fB0\fR. |
1971 | .RE | |
1972 | ||
1973 | .sp | |
1974 | .ne 2 | |
1975 | .na | |
1976 | \fBzfs_vdev_mirror_rotating_seek_inc\fR (int) | |
1977 | .ad | |
1978 | .RS 12n | |
1979 | A number by which the balancing algorithm increments the load calculation for | |
1980 | the purpose of selecting the least busy mirror member when an I/O lacks | |
1981 | locality as defined by the zfs_vdev_mirror_rotating_seek_offset. I/Os within | |
1982 | this that are not immediately following the previous I/O are incremented by | |
1983 | half. | |
1984 | .sp | |
1985 | Default value: \fB5\fR. | |
1986 | .RE | |
1987 | ||
1988 | .sp | |
1989 | .ne 2 | |
1990 | .na | |
1991 | \fBzfs_vdev_mirror_rotating_seek_offset\fR (int) | |
1992 | .ad | |
1993 | .RS 12n | |
1994 | The maximum distance for the last queued I/O in which the balancing algorithm | |
1995 | considers an I/O to have locality. | |
1996 | See the section "ZFS I/O SCHEDULER". | |
1997 | .sp | |
1998 | Default value: \fB1048576\fR. | |
1999 | .RE | |
2000 | ||
2001 | .sp | |
2002 | .ne 2 | |
2003 | .na | |
2004 | \fBzfs_vdev_mirror_non_rotating_inc\fR (int) | |
2005 | .ad | |
2006 | .RS 12n | |
2007 | A number by which the balancing algorithm increments the load calculation for | |
2008 | the purpose of selecting the least busy mirror member on non-rotational vdevs | |
2009 | when I/Os do not immediately follow one another. | |
2010 | .sp | |
2011 | Default value: \fB0\fR. | |
2012 | .RE | |
2013 | ||
2014 | .sp | |
2015 | .ne 2 | |
2016 | .na | |
2017 | \fBzfs_vdev_mirror_non_rotating_seek_inc\fR (int) | |
2018 | .ad | |
2019 | .RS 12n | |
2020 | A number by which the balancing algorithm increments the load calculation for | |
2021 | the purpose of selecting the least busy mirror member when an I/O lacks | |
2022 | locality as defined by the zfs_vdev_mirror_rotating_seek_offset. I/Os within | |
2023 | this that are not immediately following the previous I/O are incremented by | |
2024 | half. | |
2025 | .sp | |
2026 | Default value: \fB1\fR. | |
29714574 TF |
2027 | .RE |
2028 | ||
29714574 TF |
2029 | .sp |
2030 | .ne 2 | |
2031 | .na | |
2032 | \fBzfs_vdev_read_gap_limit\fR (int) | |
2033 | .ad | |
2034 | .RS 12n | |
83426735 D |
2035 | Aggregate read I/O operations if the gap on-disk between them is within this |
2036 | threshold. | |
29714574 TF |
2037 | .sp |
2038 | Default value: \fB32,768\fR. | |
2039 | .RE | |
2040 | ||
2041 | .sp | |
2042 | .ne 2 | |
2043 | .na | |
2044 | \fBzfs_vdev_scheduler\fR (charp) | |
2045 | .ad | |
2046 | .RS 12n | |
ca85d690 | 2047 | Set the Linux I/O scheduler on whole disk vdevs to this scheduler. Valid options |
2048 | are noop, cfq, bfq & deadline | |
29714574 TF |
2049 | .sp |
2050 | Default value: \fBnoop\fR. | |
2051 | .RE | |
2052 | ||
29714574 TF |
2053 | .sp |
2054 | .ne 2 | |
2055 | .na | |
2056 | \fBzfs_vdev_write_gap_limit\fR (int) | |
2057 | .ad | |
2058 | .RS 12n | |
2059 | Aggregate write I/O over gap | |
2060 | .sp | |
2061 | Default value: \fB4,096\fR. | |
2062 | .RE | |
2063 | ||
ab9f4b0b GN |
2064 | .sp |
2065 | .ne 2 | |
2066 | .na | |
2067 | \fBzfs_vdev_raidz_impl\fR (string) | |
2068 | .ad | |
2069 | .RS 12n | |
c9187d86 | 2070 | Parameter for selecting raidz parity implementation to use. |
ab9f4b0b GN |
2071 | |
2072 | Options marked (always) below may be selected on module load as they are | |
2073 | supported on all systems. | |
2074 | The remaining options may only be set after the module is loaded, as they | |
2075 | are available only if the implementations are compiled in and supported | |
2076 | on the running system. | |
2077 | ||
2078 | Once the module is loaded, the content of | |
2079 | /sys/module/zfs/parameters/zfs_vdev_raidz_impl will show available options | |
2080 | with the currently selected one enclosed in []. | |
2081 | Possible options are: | |
2082 | fastest - (always) implementation selected using built-in benchmark | |
2083 | original - (always) original raidz implementation | |
2084 | scalar - (always) scalar raidz implementation | |
ae25d222 GN |
2085 | sse2 - implementation using SSE2 instruction set (64bit x86 only) |
2086 | ssse3 - implementation using SSSE3 instruction set (64bit x86 only) | |
ab9f4b0b | 2087 | avx2 - implementation using AVX2 instruction set (64bit x86 only) |
7f547f85 RD |
2088 | avx512f - implementation using AVX512F instruction set (64bit x86 only) |
2089 | avx512bw - implementation using AVX512F & AVX512BW instruction sets (64bit x86 only) | |
62a65a65 RD |
2090 | aarch64_neon - implementation using NEON (Aarch64/64 bit ARMv8 only) |
2091 | aarch64_neonx2 - implementation using NEON with more unrolling (Aarch64/64 bit ARMv8 only) | |
ab9f4b0b GN |
2092 | .sp |
2093 | Default value: \fBfastest\fR. | |
2094 | .RE | |
2095 | ||
29714574 TF |
2096 | .sp |
2097 | .ne 2 | |
2098 | .na | |
2099 | \fBzfs_zevent_cols\fR (int) | |
2100 | .ad | |
2101 | .RS 12n | |
83426735 | 2102 | When zevents are logged to the console use this as the word wrap width. |
29714574 TF |
2103 | .sp |
2104 | Default value: \fB80\fR. | |
2105 | .RE | |
2106 | ||
2107 | .sp | |
2108 | .ne 2 | |
2109 | .na | |
2110 | \fBzfs_zevent_console\fR (int) | |
2111 | .ad | |
2112 | .RS 12n | |
2113 | Log events to the console | |
2114 | .sp | |
2115 | Use \fB1\fR for yes and \fB0\fR for no (default). | |
2116 | .RE | |
2117 | ||
2118 | .sp | |
2119 | .ne 2 | |
2120 | .na | |
2121 | \fBzfs_zevent_len_max\fR (int) | |
2122 | .ad | |
2123 | .RS 12n | |
83426735 D |
2124 | Max event queue length. A value of 0 will result in a calculated value which |
2125 | increases with the number of CPUs in the system (minimum 64 events). Events | |
2126 | in the queue can be viewed with the \fBzpool events\fR command. | |
29714574 TF |
2127 | .sp |
2128 | Default value: \fB0\fR. | |
2129 | .RE | |
2130 | ||
a032ac4b BB |
2131 | .sp |
2132 | .ne 2 | |
2133 | .na | |
2134 | \fBzfs_zil_clean_taskq_maxalloc\fR (int) | |
2135 | .ad | |
2136 | .RS 12n | |
2137 | The maximum number of taskq entries that are allowed to be cached. When this | |
2fe61a7e | 2138 | limit is exceeded transaction records (itxs) will be cleaned synchronously. |
a032ac4b BB |
2139 | .sp |
2140 | Default value: \fB1048576\fR. | |
2141 | .RE | |
2142 | ||
2143 | .sp | |
2144 | .ne 2 | |
2145 | .na | |
2146 | \fBzfs_zil_clean_taskq_minalloc\fR (int) | |
2147 | .ad | |
2148 | .RS 12n | |
2149 | The number of taskq entries that are pre-populated when the taskq is first | |
2150 | created and are immediately available for use. | |
2151 | .sp | |
2152 | Default value: \fB1024\fR. | |
2153 | .RE | |
2154 | ||
2155 | .sp | |
2156 | .ne 2 | |
2157 | .na | |
2158 | \fBzfs_zil_clean_taskq_nthr_pct\fR (int) | |
2159 | .ad | |
2160 | .RS 12n | |
2161 | This controls the number of threads used by the dp_zil_clean_taskq. The default | |
2162 | value of 100% will create a maximum of one thread per cpu. | |
2163 | .sp | |
2164 | Default value: \fB100\fR. | |
2165 | .RE | |
2166 | ||
29714574 TF |
2167 | .sp |
2168 | .ne 2 | |
2169 | .na | |
2170 | \fBzil_replay_disable\fR (int) | |
2171 | .ad | |
2172 | .RS 12n | |
83426735 D |
2173 | Disable intent logging replay. Can be disabled for recovery from corrupted |
2174 | ZIL | |
29714574 TF |
2175 | .sp |
2176 | Use \fB1\fR for yes and \fB0\fR for no (default). | |
2177 | .RE | |
2178 | ||
2179 | .sp | |
2180 | .ne 2 | |
2181 | .na | |
1b7c1e5c | 2182 | \fBzil_slog_bulk\fR (ulong) |
29714574 TF |
2183 | .ad |
2184 | .RS 12n | |
1b7c1e5c GDN |
2185 | Limit SLOG write size per commit executed with synchronous priority. |
2186 | Any writes above that will be executed with lower (asynchronous) priority | |
2187 | to limit potential SLOG device abuse by single active ZIL writer. | |
29714574 | 2188 | .sp |
1b7c1e5c | 2189 | Default value: \fB786,432\fR. |
29714574 TF |
2190 | .RE |
2191 | ||
29714574 TF |
2192 | .sp |
2193 | .ne 2 | |
2194 | .na | |
2195 | \fBzio_delay_max\fR (int) | |
2196 | .ad | |
2197 | .RS 12n | |
83426735 | 2198 | A zevent will be logged if a ZIO operation takes more than N milliseconds to |
ab9f4b0b | 2199 | complete. Note that this is only a logging facility, not a timeout on |
83426735 | 2200 | operations. |
29714574 TF |
2201 | .sp |
2202 | Default value: \fB30,000\fR. | |
2203 | .RE | |
2204 | ||
3dfb57a3 DB |
2205 | .sp |
2206 | .ne 2 | |
2207 | .na | |
2208 | \fBzio_dva_throttle_enabled\fR (int) | |
2209 | .ad | |
2210 | .RS 12n | |
2211 | Throttle block allocations in the ZIO pipeline. This allows for | |
2212 | dynamic allocation distribution when devices are imbalanced. | |
e815485f TC |
2213 | When enabled, the maximum number of pending allocations per top-level vdev |
2214 | is limited by \fBzfs_vdev_queue_depth_pct\fR. | |
3dfb57a3 | 2215 | .sp |
27f2b90d | 2216 | Default value: \fB1\fR. |
3dfb57a3 DB |
2217 | .RE |
2218 | ||
29714574 TF |
2219 | .sp |
2220 | .ne 2 | |
2221 | .na | |
2222 | \fBzio_requeue_io_start_cut_in_line\fR (int) | |
2223 | .ad | |
2224 | .RS 12n | |
2225 | Prioritize requeued I/O | |
2226 | .sp | |
2227 | Default value: \fB0\fR. | |
2228 | .RE | |
2229 | ||
dcb6bed1 D |
2230 | .sp |
2231 | .ne 2 | |
2232 | .na | |
2233 | \fBzio_taskq_batch_pct\fR (uint) | |
2234 | .ad | |
2235 | .RS 12n | |
2236 | Percentage of online CPUs (or CPU cores, etc) which will run a worker thread | |
2237 | for IO. These workers are responsible for IO work such as compression and | |
2238 | checksum calculations. Fractional number of CPUs will be rounded down. | |
2239 | .sp | |
2240 | The default value of 75 was chosen to avoid using all CPUs which can result in | |
2241 | latency issues and inconsistent application performance, especially when high | |
2242 | compression is enabled. | |
2243 | .sp | |
2244 | Default value: \fB75\fR. | |
2245 | .RE | |
2246 | ||
29714574 TF |
2247 | .sp |
2248 | .ne 2 | |
2249 | .na | |
2250 | \fBzvol_inhibit_dev\fR (uint) | |
2251 | .ad | |
2252 | .RS 12n | |
83426735 D |
2253 | Do not create zvol device nodes. This may slightly improve startup time on |
2254 | systems with a very large number of zvols. | |
29714574 TF |
2255 | .sp |
2256 | Use \fB1\fR for yes and \fB0\fR for no (default). | |
2257 | .RE | |
2258 | ||
2259 | .sp | |
2260 | .ne 2 | |
2261 | .na | |
2262 | \fBzvol_major\fR (uint) | |
2263 | .ad | |
2264 | .RS 12n | |
83426735 | 2265 | Major number for zvol block devices |
29714574 TF |
2266 | .sp |
2267 | Default value: \fB230\fR. | |
2268 | .RE | |
2269 | ||
2270 | .sp | |
2271 | .ne 2 | |
2272 | .na | |
2273 | \fBzvol_max_discard_blocks\fR (ulong) | |
2274 | .ad | |
2275 | .RS 12n | |
83426735 D |
2276 | Discard (aka TRIM) operations done on zvols will be done in batches of this |
2277 | many blocks, where block size is determined by the \fBvolblocksize\fR property | |
2278 | of a zvol. | |
29714574 TF |
2279 | .sp |
2280 | Default value: \fB16,384\fR. | |
2281 | .RE | |
2282 | ||
9965059a BB |
2283 | .sp |
2284 | .ne 2 | |
2285 | .na | |
2286 | \fBzvol_prefetch_bytes\fR (uint) | |
2287 | .ad | |
2288 | .RS 12n | |
2289 | When adding a zvol to the system prefetch \fBzvol_prefetch_bytes\fR | |
2290 | from the start and end of the volume. Prefetching these regions | |
2291 | of the volume is desirable because they are likely to be accessed | |
2292 | immediately by \fBblkid(8)\fR or by the kernel scanning for a partition | |
2293 | table. | |
2294 | .sp | |
2295 | Default value: \fB131,072\fR. | |
2296 | .RE | |
2297 | ||
692e55b8 CC |
2298 | .sp |
2299 | .ne 2 | |
2300 | .na | |
2301 | \fBzvol_request_sync\fR (uint) | |
2302 | .ad | |
2303 | .RS 12n | |
2304 | When processing I/O requests for a zvol submit them synchronously. This | |
2305 | effectively limits the queue depth to 1 for each I/O submitter. When set | |
2306 | to 0 requests are handled asynchronously by a thread pool. The number of | |
2307 | requests which can be handled concurrently is controller by \fBzvol_threads\fR. | |
2308 | .sp | |
8fa5250f | 2309 | Default value: \fB0\fR. |
692e55b8 CC |
2310 | .RE |
2311 | ||
2312 | .sp | |
2313 | .ne 2 | |
2314 | .na | |
2315 | \fBzvol_threads\fR (uint) | |
2316 | .ad | |
2317 | .RS 12n | |
2318 | Max number of threads which can handle zvol I/O requests concurrently. | |
2319 | .sp | |
2320 | Default value: \fB32\fR. | |
2321 | .RE | |
2322 | ||
cf8738d8 | 2323 | .sp |
2324 | .ne 2 | |
2325 | .na | |
2326 | \fBzvol_volmode\fR (uint) | |
2327 | .ad | |
2328 | .RS 12n | |
2329 | Defines zvol block devices behaviour when \fBvolmode\fR is set to \fBdefault\fR. | |
2330 | Valid values are \fB1\fR (full), \fB2\fR (dev) and \fB3\fR (none). | |
2331 | .sp | |
2332 | Default value: \fB1\fR. | |
2333 | .RE | |
2334 | ||
39ccc909 | 2335 | .sp |
2336 | .ne 2 | |
2337 | .na | |
2338 | \fBzfs_qat_disable\fR (int) | |
2339 | .ad | |
2340 | .RS 12n | |
2341 | This tunable disables qat hardware acceleration for gzip compression. | |
2342 | It is available only if qat acceleration is compiled in and qat driver | |
2343 | is present. | |
2344 | .sp | |
2345 | Use \fB1\fR for yes and \fB0\fR for no (default). | |
2346 | .RE | |
2347 | ||
e8b96c60 MA |
2348 | .SH ZFS I/O SCHEDULER |
2349 | ZFS issues I/O operations to leaf vdevs to satisfy and complete I/Os. | |
2350 | The I/O scheduler determines when and in what order those operations are | |
2351 | issued. The I/O scheduler divides operations into five I/O classes | |
2352 | prioritized in the following order: sync read, sync write, async read, | |
2353 | async write, and scrub/resilver. Each queue defines the minimum and | |
2354 | maximum number of concurrent operations that may be issued to the | |
2355 | device. In addition, the device has an aggregate maximum, | |
2356 | \fBzfs_vdev_max_active\fR. Note that the sum of the per-queue minimums | |
2357 | must not exceed the aggregate maximum. If the sum of the per-queue | |
2358 | maximums exceeds the aggregate maximum, then the number of active I/Os | |
2359 | may reach \fBzfs_vdev_max_active\fR, in which case no further I/Os will | |
2360 | be issued regardless of whether all per-queue minimums have been met. | |
2361 | .sp | |
2362 | For many physical devices, throughput increases with the number of | |
2363 | concurrent operations, but latency typically suffers. Further, physical | |
2364 | devices typically have a limit at which more concurrent operations have no | |
2365 | effect on throughput or can actually cause it to decrease. | |
2366 | .sp | |
2367 | The scheduler selects the next operation to issue by first looking for an | |
2368 | I/O class whose minimum has not been satisfied. Once all are satisfied and | |
2369 | the aggregate maximum has not been hit, the scheduler looks for classes | |
2370 | whose maximum has not been satisfied. Iteration through the I/O classes is | |
2371 | done in the order specified above. No further operations are issued if the | |
2372 | aggregate maximum number of concurrent operations has been hit or if there | |
2373 | are no operations queued for an I/O class that has not hit its maximum. | |
2374 | Every time an I/O is queued or an operation completes, the I/O scheduler | |
2375 | looks for new operations to issue. | |
2376 | .sp | |
2377 | In general, smaller max_active's will lead to lower latency of synchronous | |
2378 | operations. Larger max_active's may lead to higher overall throughput, | |
2379 | depending on underlying storage. | |
2380 | .sp | |
2381 | The ratio of the queues' max_actives determines the balance of performance | |
2382 | between reads, writes, and scrubs. E.g., increasing | |
2383 | \fBzfs_vdev_scrub_max_active\fR will cause the scrub or resilver to complete | |
2384 | more quickly, but reads and writes to have higher latency and lower throughput. | |
2385 | .sp | |
2386 | All I/O classes have a fixed maximum number of outstanding operations | |
2387 | except for the async write class. Asynchronous writes represent the data | |
2388 | that is committed to stable storage during the syncing stage for | |
2389 | transaction groups. Transaction groups enter the syncing state | |
2390 | periodically so the number of queued async writes will quickly burst up | |
2391 | and then bleed down to zero. Rather than servicing them as quickly as | |
2392 | possible, the I/O scheduler changes the maximum number of active async | |
2393 | write I/Os according to the amount of dirty data in the pool. Since | |
2394 | both throughput and latency typically increase with the number of | |
2395 | concurrent operations issued to physical devices, reducing the | |
2396 | burstiness in the number of concurrent operations also stabilizes the | |
2397 | response time of operations from other -- and in particular synchronous | |
2398 | -- queues. In broad strokes, the I/O scheduler will issue more | |
2399 | concurrent operations from the async write queue as there's more dirty | |
2400 | data in the pool. | |
2401 | .sp | |
2402 | Async Writes | |
2403 | .sp | |
2404 | The number of concurrent operations issued for the async write I/O class | |
2405 | follows a piece-wise linear function defined by a few adjustable points. | |
2406 | .nf | |
2407 | ||
2408 | | o---------| <-- zfs_vdev_async_write_max_active | |
2409 | ^ | /^ | | |
2410 | | | / | | | |
2411 | active | / | | | |
2412 | I/O | / | | | |
2413 | count | / | | | |
2414 | | / | | | |
2415 | |-------o | | <-- zfs_vdev_async_write_min_active | |
2416 | 0|_______^______|_________| | |
2417 | 0% | | 100% of zfs_dirty_data_max | |
2418 | | | | |
2419 | | `-- zfs_vdev_async_write_active_max_dirty_percent | |
2420 | `--------- zfs_vdev_async_write_active_min_dirty_percent | |
2421 | ||
2422 | .fi | |
2423 | Until the amount of dirty data exceeds a minimum percentage of the dirty | |
2424 | data allowed in the pool, the I/O scheduler will limit the number of | |
2425 | concurrent operations to the minimum. As that threshold is crossed, the | |
2426 | number of concurrent operations issued increases linearly to the maximum at | |
2427 | the specified maximum percentage of the dirty data allowed in the pool. | |
2428 | .sp | |
2429 | Ideally, the amount of dirty data on a busy pool will stay in the sloped | |
2430 | part of the function between \fBzfs_vdev_async_write_active_min_dirty_percent\fR | |
2431 | and \fBzfs_vdev_async_write_active_max_dirty_percent\fR. If it exceeds the | |
2432 | maximum percentage, this indicates that the rate of incoming data is | |
2433 | greater than the rate that the backend storage can handle. In this case, we | |
2434 | must further throttle incoming writes, as described in the next section. | |
2435 | ||
2436 | .SH ZFS TRANSACTION DELAY | |
2437 | We delay transactions when we've determined that the backend storage | |
2438 | isn't able to accommodate the rate of incoming writes. | |
2439 | .sp | |
2440 | If there is already a transaction waiting, we delay relative to when | |
2441 | that transaction will finish waiting. This way the calculated delay time | |
2442 | is independent of the number of threads concurrently executing | |
2443 | transactions. | |
2444 | .sp | |
2445 | If we are the only waiter, wait relative to when the transaction | |
2446 | started, rather than the current time. This credits the transaction for | |
2447 | "time already served", e.g. reading indirect blocks. | |
2448 | .sp | |
2449 | The minimum time for a transaction to take is calculated as: | |
2450 | .nf | |
2451 | min_time = zfs_delay_scale * (dirty - min) / (max - dirty) | |
2452 | min_time is then capped at 100 milliseconds. | |
2453 | .fi | |
2454 | .sp | |
2455 | The delay has two degrees of freedom that can be adjusted via tunables. The | |
2456 | percentage of dirty data at which we start to delay is defined by | |
2457 | \fBzfs_delay_min_dirty_percent\fR. This should typically be at or above | |
2458 | \fBzfs_vdev_async_write_active_max_dirty_percent\fR so that we only start to | |
2459 | delay after writing at full speed has failed to keep up with the incoming write | |
2460 | rate. The scale of the curve is defined by \fBzfs_delay_scale\fR. Roughly speaking, | |
2461 | this variable determines the amount of delay at the midpoint of the curve. | |
2462 | .sp | |
2463 | .nf | |
2464 | delay | |
2465 | 10ms +-------------------------------------------------------------*+ | |
2466 | | *| | |
2467 | 9ms + *+ | |
2468 | | *| | |
2469 | 8ms + *+ | |
2470 | | * | | |
2471 | 7ms + * + | |
2472 | | * | | |
2473 | 6ms + * + | |
2474 | | * | | |
2475 | 5ms + * + | |
2476 | | * | | |
2477 | 4ms + * + | |
2478 | | * | | |
2479 | 3ms + * + | |
2480 | | * | | |
2481 | 2ms + (midpoint) * + | |
2482 | | | ** | | |
2483 | 1ms + v *** + | |
2484 | | zfs_delay_scale ----------> ******** | | |
2485 | 0 +-------------------------------------*********----------------+ | |
2486 | 0% <- zfs_dirty_data_max -> 100% | |
2487 | .fi | |
2488 | .sp | |
2489 | Note that since the delay is added to the outstanding time remaining on the | |
2490 | most recent transaction, the delay is effectively the inverse of IOPS. | |
2491 | Here the midpoint of 500us translates to 2000 IOPS. The shape of the curve | |
2492 | was chosen such that small changes in the amount of accumulated dirty data | |
2493 | in the first 3/4 of the curve yield relatively small differences in the | |
2494 | amount of delay. | |
2495 | .sp | |
2496 | The effects can be easier to understand when the amount of delay is | |
2497 | represented on a log scale: | |
2498 | .sp | |
2499 | .nf | |
2500 | delay | |
2501 | 100ms +-------------------------------------------------------------++ | |
2502 | + + | |
2503 | | | | |
2504 | + *+ | |
2505 | 10ms + *+ | |
2506 | + ** + | |
2507 | | (midpoint) ** | | |
2508 | + | ** + | |
2509 | 1ms + v **** + | |
2510 | + zfs_delay_scale ----------> ***** + | |
2511 | | **** | | |
2512 | + **** + | |
2513 | 100us + ** + | |
2514 | + * + | |
2515 | | * | | |
2516 | + * + | |
2517 | 10us + * + | |
2518 | + + | |
2519 | | | | |
2520 | + + | |
2521 | +--------------------------------------------------------------+ | |
2522 | 0% <- zfs_dirty_data_max -> 100% | |
2523 | .fi | |
2524 | .sp | |
2525 | Note here that only as the amount of dirty data approaches its limit does | |
2526 | the delay start to increase rapidly. The goal of a properly tuned system | |
2527 | should be to keep the amount of dirty data out of that range by first | |
2528 | ensuring that the appropriate limits are set for the I/O scheduler to reach | |
2529 | optimal throughput on the backend storage, and then by changing the value | |
2530 | of \fBzfs_delay_scale\fR to increase the steepness of the curve. |