1What: /sys/block/<disk>/alignment_offset 2Date: April 2009 3Contact: Martin K. Petersen <[email protected]> 4Description: 5 Storage devices may report a physical block size that is 6 bigger than the logical block size (for instance a drive 7 with 4KB physical sectors exposing 512-byte logical 8 blocks to the operating system). This parameter 9 indicates how many bytes the beginning of the device is 10 offset from the disk's natural alignment. 11 12 13What: /sys/block/<disk>/discard_alignment 14Date: May 2011 15Contact: Martin K. Petersen <[email protected]> 16Description: 17 Devices that support discard functionality may 18 internally allocate space in units that are bigger than 19 the exported logical block size. The discard_alignment 20 parameter indicates how many bytes the beginning of the 21 device is offset from the internal allocation unit's 22 natural alignment. 23 24What: /sys/block/<disk>/atomic_write_max_bytes 25Date: February 2024 26Contact: Himanshu Madhani <[email protected]> 27Description: 28 [RO] This parameter specifies the maximum atomic write 29 size reported by the device. This parameter is relevant 30 for merging of writes, where a merged atomic write 31 operation must not exceed this number of bytes. 32 This parameter may be greater than the value in 33 atomic_write_unit_max_bytes as 34 atomic_write_unit_max_bytes will be rounded down to a 35 power-of-two and atomic_write_unit_max_bytes may also be 36 limited by some other queue limits, such as max_segments. 37 This parameter - along with atomic_write_unit_min_bytes 38 and atomic_write_unit_max_bytes - will not be larger than 39 max_hw_sectors_kb, but may be larger than max_sectors_kb. 40 41 42What: /sys/block/<disk>/atomic_write_unit_min_bytes 43Date: February 2024 44Contact: Himanshu Madhani <[email protected]> 45Description: 46 [RO] This parameter specifies the smallest block which can 47 be written atomically with an atomic write operation. All 48 atomic write operations must begin at a 49 atomic_write_unit_min boundary and must be multiples of 50 atomic_write_unit_min. This value must be a power-of-two. 51 52 53What: /sys/block/<disk>/atomic_write_unit_max_bytes 54Date: February 2024 55Contact: Himanshu Madhani <[email protected]> 56Description: 57 [RO] This parameter defines the largest block which can be 58 written atomically with an atomic write operation. This 59 value must be a multiple of atomic_write_unit_min and must 60 be a power-of-two. This value will not be larger than 61 atomic_write_max_bytes. 62 63 64What: /sys/block/<disk>/atomic_write_boundary_bytes 65Date: February 2024 66Contact: Himanshu Madhani <[email protected]> 67Description: 68 [RO] A device may need to internally split an atomic write I/O 69 which straddles a given logical block address boundary. This 70 parameter specifies the size in bytes of the atomic boundary if 71 one is reported by the device. This value must be a 72 power-of-two and at least the size as in 73 atomic_write_unit_max_bytes. 74 Any attempt to merge atomic write I/Os must not result in a 75 merged I/O which crosses this boundary (if any). 76 77 78What: /sys/block/<disk>/diskseq 79Date: February 2021 80Contact: Matteo Croce <[email protected]> 81Description: 82 The /sys/block/<disk>/diskseq files reports the disk 83 sequence number, which is a monotonically increasing 84 number assigned to every drive. 85 Some devices, like the loop device, refresh such number 86 every time the backing file is changed. 87 The value type is 64 bit unsigned. 88 89 90What: /sys/block/<disk>/inflight 91Date: October 2009 92Contact: Jens Axboe <[email protected]>, Nikanth Karthikesan <[email protected]> 93Description: 94 Reports the number of I/O requests currently in progress 95 (pending / in flight) in a device driver. This can be less 96 than the number of requests queued in the block device queue. 97 The report contains 2 fields: one for read requests 98 and one for write requests. 99 The value type is unsigned int. 100 Cf. Documentation/block/stat.rst which contains a single value for 101 requests in flight. 102 This is related to /sys/block/<disk>/queue/nr_requests 103 and for SCSI device also its queue_depth. 104 105 106What: /sys/block/<disk>/integrity/device_is_integrity_capable 107Date: July 2014 108Contact: Martin K. Petersen <[email protected]> 109Description: 110 Indicates whether a storage device is capable of storing 111 integrity metadata. Set if the device is T10 PI-capable. 112 113 114What: /sys/block/<disk>/integrity/format 115Date: June 2008 116Contact: Martin K. Petersen <[email protected]> 117Description: 118 Metadata format for integrity capable block device. 119 E.g. T10-DIF-TYPE1-CRC. 120 121 122What: /sys/block/<disk>/integrity/protection_interval_bytes 123Date: July 2015 124Contact: Martin K. Petersen <[email protected]> 125Description: 126 Describes the number of data bytes which are protected 127 by one integrity tuple. Typically the device's logical 128 block size. 129 130 131What: /sys/block/<disk>/integrity/read_verify 132Date: June 2008 133Contact: Martin K. Petersen <[email protected]> 134Description: 135 Indicates whether the block layer should verify the 136 integrity of read requests serviced by devices that 137 support sending integrity metadata. 138 139 140What: /sys/block/<disk>/integrity/tag_size 141Date: June 2008 142Contact: Martin K. Petersen <[email protected]> 143Description: 144 Number of bytes of integrity tag space available per 145 512 bytes of data. 146 147 148What: /sys/block/<disk>/integrity/write_generate 149Date: June 2008 150Contact: Martin K. Petersen <[email protected]> 151Description: 152 Indicates whether the block layer should automatically 153 generate checksums for write requests bound for 154 devices that support receiving integrity metadata. 155 156 157What: /sys/block/<disk>/partscan 158Date: May 2024 159Contact: Christoph Hellwig <[email protected]> 160Description: 161 The /sys/block/<disk>/partscan files reports if partition 162 scanning is enabled for the disk. It returns "1" if partition 163 scanning is enabled, or "0" if not. The value type is a 32-bit 164 unsigned integer, but only "0" and "1" are valid values. 165 166 167What: /sys/block/<disk>/<partition>/alignment_offset 168Date: April 2009 169Contact: Martin K. Petersen <[email protected]> 170Description: 171 Storage devices may report a physical block size that is 172 bigger than the logical block size (for instance a drive 173 with 4KB physical sectors exposing 512-byte logical 174 blocks to the operating system). This parameter 175 indicates how many bytes the beginning of the partition 176 is offset from the disk's natural alignment. 177 178 179What: /sys/block/<disk>/<partition>/discard_alignment 180Date: May 2011 181Contact: Martin K. Petersen <[email protected]> 182Description: 183 Devices that support discard functionality may 184 internally allocate space in units that are bigger than 185 the exported logical block size. The discard_alignment 186 parameter indicates how many bytes the beginning of the 187 partition is offset from the internal allocation unit's 188 natural alignment. 189 190 191What: /sys/block/<disk>/<partition>/stat 192Date: February 2008 193Contact: Jerome Marchand <[email protected]> 194Description: 195 The /sys/block/<disk>/<partition>/stat files display the 196 I/O statistics of partition <partition>. The format is the 197 same as the format of /sys/block/<disk>/stat. 198 199 200What: /sys/block/<disk>/queue/add_random 201Date: June 2010 202Contact: [email protected] 203Description: 204 [RW] This file allows to turn off the disk entropy contribution. 205 Default value of this file is '1'(on). 206 207 208What: /sys/block/<disk>/queue/chunk_sectors 209Date: September 2016 210Contact: Hannes Reinecke <[email protected]> 211Description: 212 [RO] chunk_sectors has different meaning depending on the type 213 of the disk. For a RAID device (dm-raid), chunk_sectors 214 indicates the size in 512B sectors of the RAID volume stripe 215 segment. For a zoned block device, either host-aware or 216 host-managed, chunk_sectors indicates the size in 512B sectors 217 of the zones of the device, with the eventual exception of the 218 last zone of the device which may be smaller. 219 220 221What: /sys/block/<disk>/queue/crypto/ 222Date: February 2022 223Contact: [email protected] 224Description: 225 The presence of this subdirectory of /sys/block/<disk>/queue/ 226 indicates that the device supports inline encryption. This 227 subdirectory contains files which describe the inline encryption 228 capabilities of the device. For more information about inline 229 encryption, refer to Documentation/block/inline-encryption.rst. 230 231 232What: /sys/block/<disk>/queue/crypto/hw_wrapped_keys 233Date: February 2025 234Contact: [email protected] 235Description: 236 [RO] The presence of this file indicates that the device 237 supports hardware-wrapped inline encryption keys, i.e. key blobs 238 that can only be unwrapped and used by dedicated hardware. For 239 more information about hardware-wrapped inline encryption keys, 240 see Documentation/block/inline-encryption.rst. 241 242 243What: /sys/block/<disk>/queue/crypto/max_dun_bits 244Date: February 2022 245Contact: [email protected] 246Description: 247 [RO] This file shows the maximum length, in bits, of data unit 248 numbers accepted by the device in inline encryption requests. 249 250 251What: /sys/block/<disk>/queue/crypto/modes/<mode> 252Date: February 2022 253Contact: [email protected] 254Description: 255 [RO] For each crypto mode (i.e., encryption/decryption 256 algorithm) the device supports with inline encryption, a file 257 will exist at this location. It will contain a hexadecimal 258 number that is a bitmask of the supported data unit sizes, in 259 bytes, for that crypto mode. 260 261 Currently, the crypto modes that may be supported are: 262 263 * AES-256-XTS 264 * AES-128-CBC-ESSIV 265 * Adiantum 266 267 For example, if a device supports AES-256-XTS inline encryption 268 with data unit sizes of 512 and 4096 bytes, the file 269 /sys/block/<disk>/queue/crypto/modes/AES-256-XTS will exist and 270 will contain "0x1200". 271 272 273What: /sys/block/<disk>/queue/crypto/num_keyslots 274Date: February 2022 275Contact: [email protected] 276Description: 277 [RO] This file shows the number of keyslots the device has for 278 use with inline encryption. 279 280 281What: /sys/block/<disk>/queue/crypto/raw_keys 282Date: February 2025 283Contact: [email protected] 284Description: 285 [RO] The presence of this file indicates that the device 286 supports raw inline encryption keys, i.e. keys that are managed 287 in raw, plaintext form in software. 288 289 290What: /sys/block/<disk>/queue/dax 291Date: June 2016 292Contact: [email protected] 293Description: 294 [RO] This file indicates whether the device supports Direct 295 Access (DAX), used by CPU-addressable storage to bypass the 296 pagecache. It shows '1' if true, '0' if not. 297 298 299What: /sys/block/<disk>/queue/discard_granularity 300Date: May 2011 301Contact: Martin K. Petersen <[email protected]> 302Description: 303 [RO] Devices that support discard functionality may internally 304 allocate space using units that are bigger than the logical 305 block size. The discard_granularity parameter indicates the size 306 of the internal allocation unit in bytes if reported by the 307 device. Otherwise the discard_granularity will be set to match 308 the device's physical block size. A discard_granularity of 0 309 means that the device does not support discard functionality. 310 311 312What: /sys/block/<disk>/queue/discard_max_bytes 313Date: May 2011 314Contact: Martin K. Petersen <[email protected]> 315Description: 316 [RW] While discard_max_hw_bytes is the hardware limit for the 317 device, this setting is the software limit. Some devices exhibit 318 large latencies when large discards are issued, setting this 319 value lower will make Linux issue smaller discards and 320 potentially help reduce latencies induced by large discard 321 operations. 322 323 324What: /sys/block/<disk>/queue/discard_max_hw_bytes 325Date: July 2015 326Contact: [email protected] 327Description: 328 [RO] Devices that support discard functionality may have 329 internal limits on the number of bytes that can be trimmed or 330 unmapped in a single operation. The `discard_max_hw_bytes` 331 parameter is set by the device driver to the maximum number of 332 bytes that can be discarded in a single operation. Discard 333 requests issued to the device must not exceed this limit. A 334 `discard_max_hw_bytes` value of 0 means that the device does not 335 support discard functionality. 336 337 338What: /sys/block/<disk>/queue/discard_zeroes_data 339Date: May 2011 340Contact: Martin K. Petersen <[email protected]> 341Description: 342 [RO] Will always return 0. Don't rely on any specific behavior 343 for discards, and don't read this file. 344 345 346What: /sys/block/<disk>/queue/dma_alignment 347Date: May 2022 348Contact: [email protected] 349Description: 350 Reports the alignment that user space addresses must have to be 351 used for raw block device access with O_DIRECT and other driver 352 specific passthrough mechanisms. 353 354 355What: /sys/block/<disk>/queue/fua 356Date: May 2018 357Contact: [email protected] 358Description: 359 [RO] Whether or not the block driver supports the FUA flag for 360 write requests. FUA stands for Force Unit Access. If the FUA 361 flag is set that means that write requests must bypass the 362 volatile cache of the storage device. 363 364 365What: /sys/block/<disk>/queue/hw_sector_size 366Date: January 2008 367Contact: [email protected] 368Description: 369 [RO] This is the hardware sector size of the device, in bytes. 370 371 372What: /sys/block/<disk>/queue/independent_access_ranges/ 373Date: October 2021 374Contact: [email protected] 375Description: 376 [RO] The presence of this sub-directory of the 377 /sys/block/xxx/queue/ directory indicates that the device is 378 capable of executing requests targeting different sector ranges 379 in parallel. For instance, single LUN multi-actuator hard-disks 380 will have an independent_access_ranges directory if the device 381 correctly advertises the sector ranges of its actuators. 382 383 The independent_access_ranges directory contains one directory 384 per access range, with each range described using the sector 385 (RO) attribute file to indicate the first sector of the range 386 and the nr_sectors (RO) attribute file to indicate the total 387 number of sectors in the range starting from the first sector of 388 the range. For example, a dual-actuator hard-disk will have the 389 following independent_access_ranges entries.:: 390 391 $ tree /sys/block/<disk>/queue/independent_access_ranges/ 392 /sys/block/<disk>/queue/independent_access_ranges/ 393 |-- 0 394 | |-- nr_sectors 395 | `-- sector 396 `-- 1 397 |-- nr_sectors 398 `-- sector 399 400 The sector and nr_sectors attributes use 512B sector unit, 401 regardless of the actual block size of the device. Independent 402 access ranges do not overlap and include all sectors within the 403 device capacity. The access ranges are numbered in increasing 404 order of the range start sector, that is, the sector attribute 405 of range 0 always has the value 0. 406 407 408What: /sys/block/<disk>/queue/io_poll 409Date: November 2015 410Contact: [email protected] 411Description: 412 [RW] When read, this file shows whether polling is enabled (1) 413 or disabled (0). Writing '0' to this file will disable polling 414 for this device. Writing any non-zero value will enable this 415 feature. 416 417 418What: /sys/block/<disk>/queue/io_poll_delay 419Date: November 2016 420Contact: [email protected] 421Description: 422 [RW] This was used to control what kind of polling will be 423 performed. It is now fixed to -1, which is classic polling. 424 In this mode, the CPU will repeatedly ask for completions 425 without giving up any time. 426 <deprecated> 427 428 429What: /sys/block/<disk>/queue/io_timeout 430Date: November 2018 431Contact: Weiping Zhang <[email protected]> 432Description: 433 [RW] io_timeout is the request timeout in milliseconds. If a 434 request does not complete in this time then the block driver 435 timeout handler is invoked. That timeout handler can decide to 436 retry the request, to fail it or to start a device recovery 437 strategy. 438 439 440What: /sys/block/<disk>/queue/iostats 441Date: January 2009 442Contact: [email protected] 443Description: 444 [RW] This file is used to control (on/off) the iostats 445 accounting of the disk. 446 447What: /sys/block/<disk>/queue/iostats_passthrough 448Date: October 2024 449Contact: [email protected] 450Description: 451 [RW] This file is used to control (on/off) the iostats 452 accounting of the disk for passthrough commands. 453 454 455What: /sys/block/<disk>/queue/logical_block_size 456Date: May 2009 457Contact: Martin K. Petersen <[email protected]> 458Description: 459 [RO] This is the smallest unit the storage device can address. 460 It is typically 512 bytes. 461 462 463What: /sys/block/<disk>/queue/max_active_zones 464Date: July 2020 465Contact: Niklas Cassel <[email protected]> 466Description: 467 [RO] For zoned block devices (zoned attribute indicating 468 "host-managed" or "host-aware"), the sum of zones belonging to 469 any of the zone states: EXPLICIT OPEN, IMPLICIT OPEN or CLOSED, 470 is limited by this value. If this value is 0, there is no limit. 471 472 If the host attempts to exceed this limit, the driver should 473 report this error with BLK_STS_ZONE_ACTIVE_RESOURCE, which user 474 space may see as the EOVERFLOW errno. 475 476 477What: /sys/block/<disk>/queue/max_discard_segments 478Date: February 2017 479Contact: [email protected] 480Description: 481 [RO] The maximum number of DMA scatter/gather entries in a 482 discard request. 483 484 485What: /sys/block/<disk>/queue/max_hw_sectors_kb 486Date: September 2004 487Contact: [email protected] 488Description: 489 [RO] This is the maximum number of kilobytes supported in a 490 single data transfer. 491 492 493What: /sys/block/<disk>/queue/max_integrity_segments 494Date: September 2010 495Contact: [email protected] 496Description: 497 [RO] Maximum number of elements in a DMA scatter/gather list 498 with integrity data that will be submitted by the block layer 499 core to the associated block driver. 500 501 502What: /sys/block/<disk>/queue/max_open_zones 503Date: July 2020 504Contact: Niklas Cassel <[email protected]> 505Description: 506 [RO] For zoned block devices (zoned attribute indicating 507 "host-managed" or "host-aware"), the sum of zones belonging to 508 any of the zone states: EXPLICIT OPEN or IMPLICIT OPEN, is 509 limited by this value. If this value is 0, there is no limit. 510 511 512What: /sys/block/<disk>/queue/max_sectors_kb 513Date: September 2004 514Contact: [email protected] 515Description: 516 [RW] This is the maximum number of kilobytes that the block 517 layer will allow for a filesystem request. Must be smaller than 518 or equal to the maximum size allowed by the hardware. Write 0 519 to use default kernel settings. 520 521 522What: /sys/block/<disk>/queue/max_segment_size 523Date: March 2010 524Contact: [email protected] 525Description: 526 [RO] Maximum size in bytes of a single element in a DMA 527 scatter/gather list. 528 529 530What: /sys/block/<disk>/queue/max_segments 531Date: March 2010 532Contact: [email protected] 533Description: 534 [RO] Maximum number of elements in a DMA scatter/gather list 535 that is submitted to the associated block driver. 536 537 538What: /sys/block/<disk>/queue/minimum_io_size 539Date: April 2009 540Contact: Martin K. Petersen <[email protected]> 541Description: 542 [RO] Storage devices may report a granularity or preferred 543 minimum I/O size which is the smallest request the device can 544 perform without incurring a performance penalty. For disk 545 drives this is often the physical block size. For RAID arrays 546 it is often the stripe chunk size. A properly aligned multiple 547 of minimum_io_size is the preferred request size for workloads 548 where a high number of I/O operations is desired. 549 550 551What: /sys/block/<disk>/queue/nomerges 552Date: January 2010 553Contact: [email protected] 554Description: 555 [RW] Standard I/O elevator operations include attempts to merge 556 contiguous I/Os. For known random I/O loads these attempts will 557 always fail and result in extra cycles being spent in the 558 kernel. This allows one to turn off this behavior on one of two 559 ways: When set to 1, complex merge checks are disabled, but the 560 simple one-shot merges with the previous I/O request are 561 enabled. When set to 2, all merge tries are disabled. The 562 default value is 0 - which enables all types of merge tries. 563 564 565What: /sys/block/<disk>/queue/nr_requests 566Date: July 2003 567Contact: [email protected] 568Description: 569 [RW] This controls how many requests may be allocated in the 570 block layer for read or write requests. Note that the total 571 allocated number may be twice this amount, since it applies only 572 to reads or writes (not the accumulated sum). 573 574 To avoid priority inversion through request starvation, a 575 request queue maintains a separate request pool per each cgroup 576 when CONFIG_BLK_CGROUP is enabled, and this parameter applies to 577 each such per-block-cgroup request pool. IOW, if there are N 578 block cgroups, each request queue may have up to N request 579 pools, each independently regulated by nr_requests. 580 581 582What: /sys/block/<disk>/queue/nr_zones 583Date: November 2018 584Contact: Damien Le Moal <[email protected]> 585Description: 586 [RO] nr_zones indicates the total number of zones of a zoned 587 block device ("host-aware" or "host-managed" zone model). For 588 regular block devices, the value is always 0. 589 590 591What: /sys/block/<disk>/queue/optimal_io_size 592Date: April 2009 593Contact: Martin K. Petersen <[email protected]> 594Description: 595 [RO] Storage devices may report an optimal I/O size, which is 596 the device's preferred unit for sustained I/O. This is rarely 597 reported for disk drives. For RAID arrays it is usually the 598 stripe width or the internal track size. A properly aligned 599 multiple of optimal_io_size is the preferred request size for 600 workloads where sustained throughput is desired. If no optimal 601 I/O size is reported this file contains 0. 602 603 604What: /sys/block/<disk>/queue/physical_block_size 605Date: May 2009 606Contact: Martin K. Petersen <[email protected]> 607Description: 608 [RO] This is the smallest unit a physical storage device can 609 write atomically. It is usually the same as the logical block 610 size but may be bigger. One example is SATA drives with 4KB 611 sectors that expose a 512-byte logical block size to the 612 operating system. For stacked block devices the 613 physical_block_size variable contains the maximum 614 physical_block_size of the component devices. 615 616 617What: /sys/block/<disk>/queue/read_ahead_kb 618Date: May 2004 619Contact: [email protected] 620Description: 621 [RW] Maximum number of kilobytes to read-ahead for filesystems 622 on this block device. 623 624 For MADV_HUGEPAGE, the readahead size may exceed this setting 625 since its granularity is based on the hugepage size. 626 627 628What: /sys/block/<disk>/queue/rotational 629Date: January 2009 630Contact: [email protected] 631Description: 632 [RW] This file is used to stat if the device is of rotational 633 type or non-rotational type. 634 635 636What: /sys/block/<disk>/queue/rq_affinity 637Date: September 2008 638Contact: [email protected] 639Description: 640 [RW] If this option is '1', the block layer will migrate request 641 completions to the cpu "group" that originally submitted the 642 request. For some workloads this provides a significant 643 reduction in CPU cycles due to caching effects. 644 645 For storage configurations that need to maximize distribution of 646 completion processing setting this option to '2' forces the 647 completion to run on the requesting cpu (bypassing the "group" 648 aggregation logic). 649 650 651What: /sys/block/<disk>/queue/scheduler 652Date: October 2004 653Contact: [email protected] 654Description: 655 [RW] When read, this file will display the current and available 656 IO schedulers for this block device. The currently active IO 657 scheduler will be enclosed in [] brackets. Writing an IO 658 scheduler name to this file will switch control of this block 659 device to that new IO scheduler. Note that writing an IO 660 scheduler name to this file will attempt to load that IO 661 scheduler module, if it isn't already present in the system. 662 663 664What: /sys/block/<disk>/queue/stable_writes 665Date: September 2020 666Contact: [email protected] 667Description: 668 [RW] This file will contain '1' if memory must not be modified 669 while it is being used in a write request to this device. When 670 this is the case and the kernel is performing writeback of a 671 page, the kernel will wait for writeback to complete before 672 allowing the page to be modified again, rather than allowing 673 immediate modification as is normally the case. This 674 restriction arises when the device accesses the memory multiple 675 times where the same data must be seen every time -- for 676 example, once to calculate a checksum and once to actually write 677 the data. If no such restriction exists, this file will contain 678 '0'. This file is writable for testing purposes. 679 680What: /sys/block/<disk>/queue/virt_boundary_mask 681Date: April 2021 682Contact: [email protected] 683Description: 684 [RO] This file shows the I/O segment memory alignment mask for 685 the block device. I/O requests to this device will be split 686 between segments wherever either the memory address of the end 687 of the previous segment or the memory address of the beginning 688 of the current segment is not aligned to virt_boundary_mask + 1 689 bytes. 690 691 692What: /sys/block/<disk>/queue/wbt_lat_usec 693Date: November 2016 694Contact: [email protected] 695Description: 696 [RW] If the device is registered for writeback throttling, then 697 this file shows the target minimum read latency. If this latency 698 is exceeded in a given window of time (see wb_window_usec), then 699 the writeback throttling will start scaling back writes. Writing 700 a value of '0' to this file disables the feature. Writing a 701 value of '-1' to this file resets the value to the default 702 setting. 703 704 705What: /sys/block/<disk>/queue/write_cache 706Date: April 2016 707Contact: [email protected] 708Description: 709 [RW] When read, this file will display whether the device has 710 write back caching enabled or not. It will return "write back" 711 for the former case, and "write through" for the latter. Writing 712 to this file can change the kernels view of the device, but it 713 doesn't alter the device state. This means that it might not be 714 safe to toggle the setting from "write back" to "write through", 715 since that will also eliminate cache flushes issued by the 716 kernel. 717 718 719What: /sys/block/<disk>/queue/write_same_max_bytes 720Date: January 2012 721Contact: Martin K. Petersen <[email protected]> 722Description: 723 [RO] Some devices support a write same operation in which a 724 single data block can be written to a range of several 725 contiguous blocks on storage. This can be used to wipe areas on 726 disk or to initialize drives in a RAID configuration. 727 write_same_max_bytes indicates how many bytes can be written in 728 a single write same command. If write_same_max_bytes is 0, write 729 same is not supported by the device. 730 731 732What: /sys/block/<disk>/queue/write_zeroes_max_bytes 733Date: November 2016 734Contact: Chaitanya Kulkarni <[email protected]> 735Description: 736 [RO] Devices that support write zeroes operation in which a 737 single request can be issued to zero out the range of contiguous 738 blocks on storage without having any payload in the request. 739 This can be used to optimize writing zeroes to the devices. 740 write_zeroes_max_bytes indicates how many bytes can be written 741 in a single write zeroes command. If write_zeroes_max_bytes is 742 0, write zeroes is not supported by the device. 743 744 745What: /sys/block/<disk>/queue/zone_append_max_bytes 746Date: May 2020 747Contact: [email protected] 748Description: 749 [RO] This is the maximum number of bytes that can be written to 750 a sequential zone of a zoned block device using a zone append 751 write operation (REQ_OP_ZONE_APPEND). This value is always 0 for 752 regular block devices. 753 754 755What: /sys/block/<disk>/queue/zone_write_granularity 756Date: January 2021 757Contact: [email protected] 758Description: 759 [RO] This indicates the alignment constraint, in bytes, for 760 write operations in sequential zones of zoned block devices 761 (devices with a zoned attributed that reports "host-managed" or 762 "host-aware"). This value is always 0 for regular block devices. 763 764 765What: /sys/block/<disk>/queue/zoned 766Date: September 2016 767Contact: Damien Le Moal <[email protected]> 768Description: 769 [RO] zoned indicates if the device is a zoned block device and 770 the zone model of the device if it is indeed zoned. The 771 possible values indicated by zoned are "none" for regular block 772 devices and "host-aware" or "host-managed" for zoned block 773 devices. The characteristics of host-aware and host-managed 774 zoned block devices are described in the ZBC (Zoned Block 775 Commands) and ZAC (Zoned Device ATA Command Set) standards. 776 These standards also define the "drive-managed" zone model. 777 However, since drive-managed zoned block devices do not support 778 zone commands, they will be treated as regular block devices and 779 zoned will report "none". 780 781 782What: /sys/block/<disk>/hidden 783Date: March 2023 784Contact: [email protected] 785Description: 786 [RO] the block device is hidden. it doesn’t produce events, and 787 can’t be opened from userspace or using blkdev_get*. 788 Used for the underlying components of multipath devices. 789 790 791What: /sys/block/<disk>/stat 792Date: February 2008 793Contact: Jerome Marchand <[email protected]> 794Description: 795 The /sys/block/<disk>/stat files displays the I/O 796 statistics of disk <disk>. They contain 11 fields: 797 798 == ============================================== 799 1 reads completed successfully 800 2 reads merged 801 3 sectors read 802 4 time spent reading (ms) 803 5 writes completed 804 6 writes merged 805 7 sectors written 806 8 time spent writing (ms) 807 9 I/Os currently in progress 808 10 time spent doing I/Os (ms) 809 11 weighted time spent doing I/Os (ms) 810 12 discards completed 811 13 discards merged 812 14 sectors discarded 813 15 time spent discarding (ms) 814 16 flush requests completed 815 17 time spent flushing (ms) 816 == ============================================== 817 818 For more details refer Documentation/admin-guide/iostats.rst 819