Print this page
NEX-6088 ZFS scrub/resilver take excessively long due to issuing lots of random IO (reverting a mismerge in zpool-features.5)
NEX-6088 ZFS scrub/resilver take excessively long due to issuing lots of random IO
Reviewed by: Roman Strashkin <roman.strashkin@nexenta.com>
Reviewed by: Sanjay Nadkarni <sanjay.nadkarni@nexenta.com>
NEX-6197 Description of feature@wbc is incorrect
Reviewed by: Alex Aizman <alex.aizman@nexenta.com>
Reviewed by: Saso Kiselkov <saso.kiselkov@nexenta.com>
NEX-4584 System panic when adding special vdev to a pool that does not support feature flags
Reviewed by: Alex Aizman <alex.aizman@nexenta.com>
Reviewed by: Josef 'Jeff' Sipek <josef.sipek@nexenta.com>
Reviewed by: Saso Kiselkov <saso.kiselkov@nexenta.com>
Reviewed by: Steve Peng <steve.peng@nexenta.com>
NEX-5795 Rename 'wrc' as 'wbc' in the source and in the tech docs
Reviewed by: Alex Aizman <alex.aizman@nexenta.com>
Reviewed by: Sanjay Nadkarni <sanjay.nadkarni@nexenta.com>
Reviewed by: Alek Pinchuk <alek.pinchuk@nexenta.com>
4185 add new cryptographic checksums to ZFS: SHA-512, Skein, Edon-R (fix studio build)
4185 add new cryptographic checksums to ZFS: SHA-512, Skein, Edon-R
Reviewed by: George Wilson <george.wilson@delphix.com>
Reviewed by: Prakash Surya <prakash.surya@delphix.com>
Reviewed by: Saso Kiselkov <saso.kiselkov@nexenta.com>
Reviewed by: Richard Lowe <richlowe@richlowe.net>
Approved by: Garrett D'Amore <garrett@damore.org>
NEX-4476 WRC: Allow to use write back cache per tree of datasets
Reviewed by: Alek Pinchuk <alek.pinchuk@nexenta.com>
Reviewed by: Alex Aizman <alex.aizman@nexenta.com>
Revert "NEX-4476 WRC: Allow to use write back cache per tree of datasets"
This reverts commit fe97b74444278a6f36fec93179133641296312da.
NEX-4476 WRC: Allow to use write back cache per tree of datasets
Reviewed by: Alek Pinchuk <alek.pinchuk@nexenta.com>
Reviewed by: Alex Aizman <alex.aizman@nexenta.com>
SUP-817 Removed references to special device from man and help
Revert "SUP-817 Removed references to special device"
This reverts commit f8970e28f0d8bd6b69711722f341e3e1d0e1babf.
SUP-817 Removed references to special device
4370 avoid transmitting holes during zfs send
4371 DMU code clean up
Reviewed by: Matthew Ahrens <mahrens@delphix.com>
Reviewed by: George Wilson <george.wilson@delphix.com>
Reviewed by: Christopher Siden <christopher.siden@delphix.com>
Reviewed by: Josef 'Jeff' Sipek <jeffpc@josefsipek.net>
Approved by: Garrett D'Amore <garrett@damore.org>
OS-102 add man page info and tests for vdev/CoS properties and ZFS meta features
| Split |
Close |
| Expand all |
| Collapse all |
--- old/usr/src/man/man5/zpool-features.5.man.txt
+++ new/usr/src/man/man5/zpool-features.5.man.txt
1 1 ZPOOL-FEATURES(5) Standards, Environments, and Macros ZPOOL-FEATURES(5)
2 2
3 3
4 4
5 5 NAME
6 6 zpool-features - ZFS pool feature descriptions
7 7
8 8 DESCRIPTION
9 9 ZFS pool on-disk format versions are specified via "features" which
10 10 replace the old on-disk format numbers (the last supported on-disk
11 11 format number is 28). To enable a feature on a pool use the upgrade
12 12 subcommand of the zpool(1M) command, or set the feature@feature_name
13 13 property to enabled.
14 14
15 15
16 16 The pool format does not affect file system version compatibility or
17 17 the ability to send file systems between pools.
18 18
19 19
20 20 Since most features can be enabled independently of each other the
21 21 on-disk format of the pool is specified by the set of all features
22 22 marked as active on the pool. If the pool was created by another
23 23 software version this set may include unsupported features.
24 24
25 25 Identifying features
26 26 Every feature has a guid of the form com.example:feature_name. The
27 27 reverse DNS name ensures that the feature's guid is unique across all
28 28 ZFS implementations. When unsupported features are encountered on a
29 29 pool they will be identified by their guids. Refer to the documentation
30 30 for the ZFS implementation that created the pool for information about
31 31 those features.
32 32
33 33
34 34 Each supported feature also has a short name. By convention a feature's
35 35 short name is the portion of its guid which follows the ':' (e.g.
36 36 com.example:feature_name would have the short name feature_name),
37 37 however a feature's short name may differ across ZFS implementations if
38 38 following the convention would result in name conflicts.
39 39
40 40 Feature states
41 41 Features can be in one of three states:
42 42
43 43 active
44 44 This feature's on-disk format changes are in effect on the
45 45 pool. Support for this feature is required to import the
46 46 pool in read-write mode. If this feature is not read-only
47 47 compatible, support is also required to import the pool in
48 48 read-only mode (see "Read-only compatibility").
49 49
50 50
51 51 enabled
52 52 An administrator has marked this feature as enabled on the
53 53 pool, but the feature's on-disk format changes have not
54 54 been made yet. The pool can still be imported by software
55 55 that does not support this feature, but changes may be made
56 56 to the on-disk format at any time which will move the
57 57 feature to the active state. Some features may support
58 58 returning to the enabled state after becoming active. See
59 59 feature-specific documentation for details.
60 60
61 61
62 62 disabled
63 63 This feature's on-disk format changes have not been made
64 64 and will not be made unless an administrator moves the
65 65 feature to the enabled state. Features cannot be disabled
66 66 once they have been enabled.
67 67
68 68
69 69
70 70 The state of supported features is exposed through pool properties of
71 71 the form feature@short_name.
72 72
73 73 Read-only compatibility
74 74 Some features may make on-disk format changes that do not interfere
75 75 with other software's ability to read from the pool. These features are
76 76 referred to as "read-only compatible". If all unsupported features on a
77 77 pool are read-only compatible, the pool can be imported in read-only
78 78 mode by setting the readonly property during import (see zpool(1M) for
79 79 details on importing pools).
80 80
81 81 Unsupported features
82 82 For each unsupported feature enabled on an imported pool a pool
83 83 property named unsupported@feature_guid will indicate why the import
84 84 was allowed despite the unsupported feature. Possible values for this
85 85 property are:
86 86
87 87
88 88 inactive
89 89 The feature is in the enabled state and therefore the
90 90 pool's on-disk format is still compatible with software
91 91 that does not support this feature.
92 92
93 93
94 94 readonly
95 95 The feature is read-only compatible and the pool has been
96 96 imported in read-only mode.
97 97
98 98
99 99 Feature dependencies
100 100 Some features depend on other features being enabled in order to
101 101 function properly. Enabling a feature will automatically enable any
102 102 features it depends on.
103 103
104 104 FEATURES
105 105 The following features are supported on this system:
106 106
107 107 async_destroy
108 108
109 109 GUID com.delphix:async_destroy
110 110 READ-ONLY COMPATIBLE yes
111 111 DEPENDENCIES none
112 112
113 113 Destroying a file system requires traversing all of its data in
114 114 order to return its used space to the pool. Without async_destroy
115 115 the file system is not fully removed until all space has been
116 116 reclaimed. If the destroy operation is interrupted by a reboot or
117 117 power outage the next attempt to open the pool will need to
118 118 complete the destroy operation synchronously.
119 119
120 120 When async_destroy is enabled the file system's data will be
121 121 reclaimed by a background process, allowing the destroy operation
122 122 to complete without traversing the entire file system. The
123 123 background process is able to resume interrupted destroys after the
124 124 pool has been opened, eliminating the need to finish interrupted
125 125 destroys as part of the open operation. The amount of space
126 126 remaining to be reclaimed by the background process is available
127 127 through the freeing property.
128 128
129 129 This feature is only active while freeing is non-zero.
130 130
131 131
132 132 empty_bpobj
133 133
134 134 GUID com.delphix:empty_bpobj
135 135 READ-ONLY COMPATIBLE yes
136 136 DEPENDENCIES none
137 137
138 138 This feature increases the performance of creating and using a
139 139 large number of snapshots of a single filesystem or volume, and
140 140 also reduces the disk space required.
141 141
142 142 When there are many snapshots, each snapshot uses many Block
143 143 Pointer Objects (bpobj's) to track blocks associated with that
144 144 snapshot. However, in common use cases, most of these bpobj's are
145 145 empty. This feature allows us to create each bpobj on-demand, thus
146 146 eliminating the empty bpobjs.
147 147
148 148 This feature is active while there are any filesystems, volumes, or
149 149 snapshots which were created after enabling this feature.
150 150
151 151
152 152 filesystem_limits
153 153
154 154 GUID com.joyent:filesystem_limits
155 155 READ-ONLY COMPATIBLE yes
156 156 DEPENDENCIES extensible_dataset
157 157
158 158 This feature enables filesystem and snapshot limits. These limits
159 159 can be used to control how many filesystems and/or snapshots can be
160 160 created at the point in the tree on which the limits are set.
161 161
162 162 This feature is active once either of the limit properties has been
163 163 set on a dataset. Once activated the feature is never deactivated.
164 164
165 165
166 166 lz4_compress
167 167
168 168 GUID org.illumos:lz4_compress
169 169 READ-ONLY COMPATIBLE no
170 170 DEPENDENCIES none
171 171
172 172 lz4 is a high-performance real-time compression algorithm that
173 173 features significantly faster compression and decompression as well
174 174 as a higher compression ratio than the older lzjb compression.
175 175 Typically, lz4 compression is approximately 50% faster on
176 176 compressible data and 200% faster on incompressible data than lzjb.
177 177 It is also approximately 80% faster on decompression, while giving
178 178 approximately 10% better compression ratio.
179 179
180 180 When the lz4_compress feature is set to enabled, the administrator
181 181 can turn on lz4 compression on any dataset on the pool using the
182 182 zfs(1M) command. Also, all newly written metadata will be
183 183 compressed with lz4 algorithm. Since this feature is not read-only
184 184 compatible, this operation will render the pool unimportable on
185 185 systems without support for the lz4_compress feature. Booting off
186 186 of lz4-compressed root pools is supported.
187 187
188 188 This feature becomes active as soon as it is enabled and will never
189 189 return to being enabled.
190 190
191 191
192 192 spacemap_histogram
193 193
194 194 GUID com.delphix:spacemap_histogram
195 195 READ-ONLY COMPATIBLE yes
196 196 DEPENDENCIES none
197 197
198 198 This features allows ZFS to maintain more information about how
199 199 free space is organized within the pool. If this feature is
200 200 enabled, ZFS will set this feature to active when a new space map
201 201 object is created or an existing space map is upgraded to the new
202 202 format. Once the feature is active, it will remain in that state
203 203 until the pool is destroyed.
204 204
205 205
206 206 multi_vdev_crash_dump
207 207
208 208 GUID com.joyent:multi_vdev_crash_dump
209 209 READ-ONLY COMPATIBLE no
210 210 DEPENDENCIES none
211 211
212 212 This feature allows a dump device to be configured with a pool
213 213 comprised of multiple vdevs. Those vdevs may be arranged in any
214 214 mirrored or raidz configuration.
215 215
216 216 When the multi_vdev_crash_dump feature is set to enabled, the
217 217 administrator can use the dumpadm(1M) command to configure a dump
218 218 device on a pool comprised of multiple vdevs.
219 219
220 220
221 221 extensible_dataset
222 222
223 223 GUID com.delphix:extensible_dataset
224 224 READ-ONLY COMPATIBLE no
225 225 DEPENDENCIES none
226 226
227 227 This feature allows more flexible use of internal ZFS data
228 228 structures, and exists for other features to depend on.
229 229
230 230 This feature will be active when the first dependent feature uses
231 231 it, and will be returned to the enabled state when all datasets
232 232 that use this feature are destroyed.
233 233
234 234
235 235
236 236 bookmarks
237 237
238 238 GUID com.delphix:bookmarks
239 239 READ-ONLY COMPATIBLE yes
240 240 DEPENDENCIES extensible_dataset
241 241
242 242 This feature enables use of the zfs bookmark subcommand.
243 243
244 244 This feature is active while any bookmarks exist in the pool. All
245 245 bookmarks in the pool can be listed by running zfs list -t bookmark
246 246 -r poolname.
247 247
248 248
249 249
250 250 enabled_txg
251 251
252 252 GUID com.delphix:enabled_txg
253 253 READ-ONLY COMPATIBLE yes
254 254 DEPENDENCIES none
255 255
256 256 Once this feature is enabled ZFS records the transaction group
257 257 number in which new features are enabled. This has no user-visible
258 258 impact, but other features may depend on this feature.
259 259
260 260 This feature becomes active as soon as it is enabled and will never
261 261 return to being enabled.
262 262
263 263
264 264
265 265 hole_birth
266 266
267 267 GUID com.delphix:hole_birth
268 268 READ-ONLY COMPATIBLE no
269 269 DEPENDENCIES enabled_txg
270 270
271 271 This feature improves performance of incremental sends ("zfs send
272 272 -i") and receives for objects with many holes. The most common case
273 273 of hole-filled objects is zvols.
274 274
275 275 An incremental send stream from snapshot A to snapshot B contains
276 276 information about every block that changed between A and B. Blocks
277 277 which did not change between those snapshots can be identified and
278 278 omitted from the stream using a piece of metadata called the 'block
279 279 birth time', but birth times are not recorded for holes (blocks
280 280 filled only with zeroes). Since holes created after A cannot be
281 281 distinguished from holes created before A, information about every
282 282 hole in the entire filesystem or zvol is included in the send
283 283 stream.
284 284
285 285 For workloads where holes are rare this is not a problem. However,
286 286 when incrementally replicating filesystems or zvols with many holes
287 287 (for example a zvol formatted with another filesystem) a lot of
288 288 time will be spent sending and receiving unnecessary information
289 289 about holes that already exist on the receiving side.
290 290
291 291 Once the hole_birth feature has been enabled the block birth times
292 292 of all new holes will be recorded. Incremental sends between
293 293 snapshots created after this feature is enabled will use this new
294 294 metadata to avoid sending information about holes that already
295 295 exist on the receiving side.
296 296
297 297 This feature becomes active as soon as it is enabled and will never
298 298 return to being enabled.
299 299
300 300
301 301
302 302 embedded_data
303 303
304 304 GUID com.delphix:embedded_data
305 305 READ-ONLY COMPATIBLE no
306 306 DEPENDENCIES none
307 307
308 308 This feature improves the performance and compression ratio of
309 309 highly-compressible blocks. Blocks whose contents can compress to
310 310 112 bytes or smaller can take advantage of this feature.
311 311
312 312 When this feature is enabled, the contents of highly-compressible
313 313 blocks are stored in the block "pointer" itself (a misnomer in this
314 314 case, as it contains the compresseed data, rather than a pointer to
315 315 its location on disk). Thus the space of the block (one sector,
316 316 typically 512 bytes or 4KB) is saved, and no additional i/o is
317 317 needed to read and write the data block.
318 318
319 319 This feature becomes active as soon as it is enabled and will never
320 320 return to being enabled.
321 321
322 322
323 323
324 324 device_removal
325 325
326 326 GUID com.delphix:device_removal
327 327 READ-ONLY COMPATIBLE no
328 328 DEPENDENCIES none
329 329
330 330 This feature enables the "zpool remove" subcommand to remove top-
331 331 level vdevs, evacuating them to reduce the total size of the pool.
332 332
333 333 This feature becomes active when the "zpool remove" command is used
334 334 on a top-level vdev, and will never return to being enabled.
335 335
336 336
337 337 obsolete_counts
338 338
339 339 GUID com.delphix:obsolete_counts
340 340 READ-ONLY COMPATIBLE yes
341 341 DEPENDENCIES device_removal
342 342
343 343 This feature is an enhancement of device_removal, which will over
344 344 time reduce the memory used to track removed devices. When
345 345 indirect blocks are freed or remapped, we note that their part of
346 346 the indirect mapping is "obsolete", i.e. no longer needed. See
347 347 also the zfs remap subcommand in zfs(1M).
348 348
349 349 This feature becomes active when the "zpool remove" command is used
350 350 on a top-level vdev, and will never return to being enabled.
351 351
352 352
353 353 large_blocks
354 354
355 355 GUID org.open-zfs:large_block
356 356 READ-ONLY COMPATIBLE no
357 357 DEPENDENCIES extensible_dataset
|
↓ open down ↓ |
357 lines elided |
↑ open up ↑ |
358 358
359 359 The large_block feature allows the record size on a dataset to be
360 360 set larger than 128KB.
361 361
362 362 This feature becomes active once a recordsize property has been set
363 363 larger than 128KB, and will return to being enabled once all
364 364 filesystems that have ever had their recordsize larger than 128KB
365 365 are destroyed.
366 366
367 367
368 +
369 + vdev_properties
370 +
371 + GUID com.nexenta:vdev_properties
372 + READ-ONLY COMPATIBLE yes
373 + DEPENDENCIES none
374 +
375 + This feature indicates that the pool includes on-disk format
376 + changes that support persistent vdev-specific properties. This
377 + feature will be active when the first vdev-specific property is
378 + set.
379 +
380 +
381 +
382 + cos_properties
383 +
384 + GUID com.nexenta:cos_properties
385 + READ-ONLY COMPATIBLE yes
386 + DEPENDENCIES com.nexenta:vdev_properties
387 +
388 + This feature indicates that the pool includes on-disk format
389 + changes that support persistent Class of Storage (CoS) properties.
390 + Such properties can be associated with a collection of device that
391 + belong to a common class from storage management standpoint. This
392 + feature will be active when the first CoS property is set.
393 +
394 +
395 +
396 + meta_devices
397 +
398 + GUID com.nexenta:meta_devices
399 + READ-ONLY COMPATIBLE yes
400 + DEPENDENCIES none
401 +
402 + This feature flag indicates presence of special-vdev in the pool.
403 + Special vdev is used to speed-up read and write operations and can
404 + be used to store ZFS metadata and/or write log (ZIL). In addition,
405 + special vdev can function as a writeback cache (WBC) within the
406 + pool, accelerating ZFS writes via underlying fast media (typically,
407 + write-optimized SSD).
408 +
409 + Note that unlike the first two functions the WBC function is
410 + configurable on a per-dataset tree basis.
411 +
412 +
413 +
414 + wbc
415 +
416 + GUID com.nexenta:wbc
417 + READ-ONLY COMPATIBLE no
418 + DEPENDENCIES com.nexenta:meta_devices
419 +
420 + When enabled, this feature indicates that the pool supports
421 + writeback caching. The latter can be activated on a specific
422 + filesystem (and all its children) or a volume (zvol) within the
423 + pool by setting the corresponding wbc_mode property to 'on'. This
424 + feature will show up as disabled if the pool does not contain
425 + special-vdev.
426 +
427 +
428 +
368 429 sha512
369 430
370 431 GUID org.illumos:sha512
371 432 READ-ONLY COMPATIBLE no
372 433 DEPENDENCIES extensible_dataset
373 434
374 435 This feature enables the use of the SHA-512/256 truncated hash
375 436 algorithm (FIPS 180-4) for checksum and dedup. The native 64-bit
376 437 arithmetic of SHA-512 provides an approximate 50% performance boost
377 438 over SHA-256 on 64-bit hardware and is thus a good minimum-change
378 439 replacement candidate for systems where hash performance is
379 440 important, but these systems cannot for whatever reason utilize the
380 441 faster skein and edonr algorithms.
381 442
382 443 When the sha512 feature is set to enabled, the administrator can
383 444 turn on the sha512 checksum on any dataset using the zfs set
384 445 checksum=sha512 command. This feature becomes active once a
385 446 checksum property has been set to sha512, and will return to being
386 447 enabled once all filesystems that have ever had their checksum set
387 448 to sha512 are destroyed.
388 449
389 450 Booting off of pools utilizing SHA-512/256 is supported (provided
390 451 that the updated GRUB stage2 module is installed).
391 452
392 453
393 454
394 455 skein
395 456
396 457 GUID org.illumos:skein
397 458 READ-ONLY COMPATIBLE no
398 459 DEPENDENCIES extensible_dataset
399 460
400 461 This feature enables the use of the Skein hash algorithm for
401 462 checksum and dedup. Skein is a high-performance secure hash
402 463 algorithm that was a finalist in the NIST SHA-3 competition. It
403 464 provides a very high security margin and high performance on 64-bit
404 465 hardware (80% faster than SHA-256). This implementation also
405 466 utilizes the new salted checksumming functionality in ZFS, which
406 467 means that the checksum is pre-seeded with a secret 256-bit random
407 468 key (stored on the pool) before being fed the data block to be
408 469 checksummed. Thus the produced checksums are unique to a given
409 470 pool, preventing hash collision attacks on systems with dedup.
410 471
411 472 When the skein feature is set to enabled, the administrator can
412 473 turn on the skein checksum on any dataset using the zfs set
413 474 checksum=skein command. This feature becomes active once a
414 475 checksum property has been set to skein, and will return to being
415 476 enabled once all filesystems that have ever had their checksum set
416 477 to skein are destroyed.
417 478
418 479 Booting off of pools using skein is NOT supported -- any attempt to
419 480 enable skein on a root pool will fail with an error.
420 481
421 482
422 483
423 484 edonr
424 485
425 486 GUID org.illumos:edonr
426 487 READ-ONLY COMPATIBLE no
427 488 DEPENDENCIES extensible_dataset
428 489
429 490 This feature enables the use of the Edon-R hash algorithm for
430 491 checksum, including for nopwrite (if compression is also enabled,
431 492 an overwrite of a block whose checksum matches the data being
432 493 written will be ignored). In an abundance of caution, Edon-R can
433 494 not be used with dedup (without verification).
434 495
435 496 Edon-R is a very high-performance hash algorithm that was part of
436 497 the NIST SHA-3 competition. It provides extremely high hash
437 498 performance (over 350% faster than SHA-256), but was not selected
438 499 because of its unsuitability as a general purpose secure hash
439 500 algorithm. This implementation utilizes the new salted
440 501 checksumming functionality in ZFS, which means that the checksum is
441 502 pre-seeded with a secret 256-bit random key (stored on the pool)
442 503 before being fed the data block to be checksummed. Thus the
443 504 produced checksums are unique to a given pool.
444 505
445 506 When the edonr feature is set to enabled, the administrator can
446 507 turn on the edonr checksum on any dataset using the zfs set
447 508 checksum=edonr command. This feature becomes active once a
448 509 checksum property has been set to edonr, and will return to being
449 510 enabled once all filesystems that have ever had their checksum set
450 511 to edonr are destroyed.
|
↓ open down ↓ |
73 lines elided |
↑ open up ↑ |
451 512
452 513 Booting off of pools using edonr is NOT supported -- any attempt to
453 514 enable edonr on a root pool will fail with an error.
454 515
455 516
456 517 SEE ALSO
457 518 zfs(1M), zpool(1M)
458 519
459 520
460 521
461 - August 27, 2013 ZPOOL-FEATURES(5)
522 + March 25, 2016 ZPOOL-FEATURES(5)
XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX