brintos

brintos / linux-shallow public Read only

0
0
Text · 28.4 KiB · 7a820a7 Raw
792 lines · plain
1What:		/sys/block/<disk>/alignment_offset2Date:		April 20093Contact:	Martin K. Petersen <martin.petersen@oracle.com>4Description:5		Storage devices may report a physical block size that is6		bigger than the logical block size (for instance a drive7		with 4KB physical sectors exposing 512-byte logical8		blocks to the operating system).  This parameter9		indicates how many bytes the beginning of the device is10		offset from the disk's natural alignment.11 12 13What:		/sys/block/<disk>/discard_alignment14Date:		May 201115Contact:	Martin K. Petersen <martin.petersen@oracle.com>16Description:17		Devices that support discard functionality may18		internally allocate space in units that are bigger than19		the exported logical block size. The discard_alignment20		parameter indicates how many bytes the beginning of the21		device is offset from the internal allocation unit's22		natural alignment.23 24What:		/sys/block/<disk>/atomic_write_max_bytes25Date:		February 202426Contact:	Himanshu Madhani <himanshu.madhani@oracle.com>27Description:28		[RO] This parameter specifies the maximum atomic write29		size reported by the device. This parameter is relevant30		for merging of writes, where a merged atomic write31		operation must not exceed this number of bytes.32		This parameter may be greater than the value in33		atomic_write_unit_max_bytes as34		atomic_write_unit_max_bytes will be rounded down to a35		power-of-two and atomic_write_unit_max_bytes may also be36		limited by some other queue limits, such as max_segments.37		This parameter - along with atomic_write_unit_min_bytes38		and atomic_write_unit_max_bytes - will not be larger than39		max_hw_sectors_kb, but may be larger than max_sectors_kb.40 41 42What:		/sys/block/<disk>/atomic_write_unit_min_bytes43Date:		February 202444Contact:	Himanshu Madhani <himanshu.madhani@oracle.com>45Description:46		[RO] This parameter specifies the smallest block which can47		be written atomically with an atomic write operation. All48		atomic write operations must begin at a49		atomic_write_unit_min boundary and must be multiples of50		atomic_write_unit_min. This value must be a power-of-two.51 52 53What:		/sys/block/<disk>/atomic_write_unit_max_bytes54Date:		February 202455Contact:	Himanshu Madhani <himanshu.madhani@oracle.com>56Description:57		[RO] This parameter defines the largest block which can be58		written atomically with an atomic write operation. This59		value must be a multiple of atomic_write_unit_min and must60		be a power-of-two. This value will not be larger than61		atomic_write_max_bytes.62 63 64What:		/sys/block/<disk>/atomic_write_boundary_bytes65Date:		February 202466Contact:	Himanshu Madhani <himanshu.madhani@oracle.com>67Description:68		[RO] A device may need to internally split an atomic write I/O69		which straddles a given logical block address boundary. This70		parameter specifies the size in bytes of the atomic boundary if71		one is reported by the device. This value must be a72		power-of-two and at least the size as in73		atomic_write_unit_max_bytes.74		Any attempt to merge atomic write I/Os must not result in a75		merged I/O which crosses this boundary (if any).76 77 78What:		/sys/block/<disk>/diskseq79Date:		February 202180Contact:	Matteo Croce <mcroce@microsoft.com>81Description:82		The /sys/block/<disk>/diskseq files reports the disk83		sequence number, which is a monotonically increasing84		number assigned to every drive.85		Some devices, like the loop device, refresh such number86		every time the backing file is changed.87		The value type is 64 bit unsigned.88 89 90What:		/sys/block/<disk>/inflight91Date:		October 200992Contact:	Jens Axboe <axboe@kernel.dk>, Nikanth Karthikesan <knikanth@suse.de>93Description:94		Reports the number of I/O requests currently in progress95		(pending / in flight) in a device driver. This can be less96		than the number of requests queued in the block device queue.97		The report contains 2 fields: one for read requests98		and one for write requests.99		The value type is unsigned int.100		Cf. Documentation/block/stat.rst which contains a single value for101		requests in flight.102		This is related to /sys/block/<disk>/queue/nr_requests103		and for SCSI device also its queue_depth.104 105 106What:		/sys/block/<disk>/integrity/device_is_integrity_capable107Date:		July 2014108Contact:	Martin K. Petersen <martin.petersen@oracle.com>109Description:110		Indicates whether a storage device is capable of storing111		integrity metadata. Set if the device is T10 PI-capable.112 113 114What:		/sys/block/<disk>/integrity/format115Date:		June 2008116Contact:	Martin K. Petersen <martin.petersen@oracle.com>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_bytes123Date:		July 2015124Contact:	Martin K. Petersen <martin.petersen@oracle.com>125Description:126		Describes the number of data bytes which are protected127		by one integrity tuple. Typically the device's logical128		block size.129 130 131What:		/sys/block/<disk>/integrity/read_verify132Date:		June 2008133Contact:	Martin K. Petersen <martin.petersen@oracle.com>134Description:135		Indicates whether the block layer should verify the136		integrity of read requests serviced by devices that137		support sending integrity metadata.138 139 140What:		/sys/block/<disk>/integrity/tag_size141Date:		June 2008142Contact:	Martin K. Petersen <martin.petersen@oracle.com>143Description:144		Number of bytes of integrity tag space available per145		512 bytes of data.146 147 148What:		/sys/block/<disk>/integrity/write_generate149Date:		June 2008150Contact:	Martin K. Petersen <martin.petersen@oracle.com>151Description:152		Indicates whether the block layer should automatically153		generate checksums for write requests bound for154		devices that support receiving integrity metadata.155 156 157What:		/sys/block/<disk>/partscan158Date:		May 2024159Contact:	Christoph Hellwig <hch@lst.de>160Description:161		The /sys/block/<disk>/partscan files reports if partition162		scanning is enabled for the disk.  It returns "1" if partition163		scanning is enabled, or "0" if not.  The value type is a 32-bit164		unsigned integer, but only "0" and "1" are valid values.165 166 167What:		/sys/block/<disk>/<partition>/alignment_offset168Date:		April 2009169Contact:	Martin K. Petersen <martin.petersen@oracle.com>170Description:171		Storage devices may report a physical block size that is172		bigger than the logical block size (for instance a drive173		with 4KB physical sectors exposing 512-byte logical174		blocks to the operating system).  This parameter175		indicates how many bytes the beginning of the partition176		is offset from the disk's natural alignment.177 178 179What:		/sys/block/<disk>/<partition>/discard_alignment180Date:		May 2011181Contact:	Martin K. Petersen <martin.petersen@oracle.com>182Description:183		Devices that support discard functionality may184		internally allocate space in units that are bigger than185		the exported logical block size. The discard_alignment186		parameter indicates how many bytes the beginning of the187		partition is offset from the internal allocation unit's188		natural alignment.189 190 191What:		/sys/block/<disk>/<partition>/stat192Date:		February 2008193Contact:	Jerome Marchand <jmarchan@redhat.com>194Description:195		The /sys/block/<disk>/<partition>/stat files display the196		I/O statistics of partition <partition>. The format is the197		same as the format of /sys/block/<disk>/stat.198 199 200What:		/sys/block/<disk>/queue/add_random201Date:		June 2010202Contact:	linux-block@vger.kernel.org203Description: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_sectors209Date:		September 2016210Contact:	Hannes Reinecke <hare@suse.com>211Description:212		[RO] chunk_sectors has different meaning depending on the type213		of the disk. For a RAID device (dm-raid), chunk_sectors214		indicates the size in 512B sectors of the RAID volume stripe215		segment. For a zoned block device, either host-aware or216		host-managed, chunk_sectors indicates the size in 512B sectors217		of the zones of the device, with the eventual exception of the218		last zone of the device which may be smaller.219 220 221What:		/sys/block/<disk>/queue/crypto/222Date:		February 2022223Contact:	linux-block@vger.kernel.org224Description:225		The presence of this subdirectory of /sys/block/<disk>/queue/226		indicates that the device supports inline encryption.  This227		subdirectory contains files which describe the inline encryption228		capabilities of the device.  For more information about inline229		encryption, refer to Documentation/block/inline-encryption.rst.230 231 232What:		/sys/block/<disk>/queue/crypto/max_dun_bits233Date:		February 2022234Contact:	linux-block@vger.kernel.org235Description:236		[RO] This file shows the maximum length, in bits, of data unit237		numbers accepted by the device in inline encryption requests.238 239 240What:		/sys/block/<disk>/queue/crypto/modes/<mode>241Date:		February 2022242Contact:	linux-block@vger.kernel.org243Description:244		[RO] For each crypto mode (i.e., encryption/decryption245		algorithm) the device supports with inline encryption, a file246		will exist at this location.  It will contain a hexadecimal247		number that is a bitmask of the supported data unit sizes, in248		bytes, for that crypto mode.249 250		Currently, the crypto modes that may be supported are:251 252		   * AES-256-XTS253		   * AES-128-CBC-ESSIV254		   * Adiantum255 256		For example, if a device supports AES-256-XTS inline encryption257		with data unit sizes of 512 and 4096 bytes, the file258		/sys/block/<disk>/queue/crypto/modes/AES-256-XTS will exist and259		will contain "0x1200".260 261 262What:		/sys/block/<disk>/queue/crypto/num_keyslots263Date:		February 2022264Contact:	linux-block@vger.kernel.org265Description:266		[RO] This file shows the number of keyslots the device has for267		use with inline encryption.268 269 270What:		/sys/block/<disk>/queue/dax271Date:		June 2016272Contact:	linux-block@vger.kernel.org273Description:274		[RO] This file indicates whether the device supports Direct275		Access (DAX), used by CPU-addressable storage to bypass the276		pagecache.  It shows '1' if true, '0' if not.277 278 279What:		/sys/block/<disk>/queue/discard_granularity280Date:		May 2011281Contact:	Martin K. Petersen <martin.petersen@oracle.com>282Description:283		[RO] Devices that support discard functionality may internally284		allocate space using units that are bigger than the logical285		block size. The discard_granularity parameter indicates the size286		of the internal allocation unit in bytes if reported by the287		device. Otherwise the discard_granularity will be set to match288		the device's physical block size. A discard_granularity of 0289		means that the device does not support discard functionality.290 291 292What:		/sys/block/<disk>/queue/discard_max_bytes293Date:		May 2011294Contact:	Martin K. Petersen <martin.petersen@oracle.com>295Description:296		[RW] While discard_max_hw_bytes is the hardware limit for the297		device, this setting is the software limit. Some devices exhibit298		large latencies when large discards are issued, setting this299		value lower will make Linux issue smaller discards and300		potentially help reduce latencies induced by large discard301		operations.302 303 304What:		/sys/block/<disk>/queue/discard_max_hw_bytes305Date:		July 2015306Contact:	linux-block@vger.kernel.org307Description:308		[RO] Devices that support discard functionality may have309		internal limits on the number of bytes that can be trimmed or310		unmapped in a single operation.  The `discard_max_hw_bytes`311		parameter is set by the device driver to the maximum number of312		bytes that can be discarded in a single operation.  Discard313		requests issued to the device must not exceed this limit.  A314		`discard_max_hw_bytes` value of 0 means that the device does not315		support discard functionality.316 317 318What:		/sys/block/<disk>/queue/discard_zeroes_data319Date:		May 2011320Contact:	Martin K. Petersen <martin.petersen@oracle.com>321Description:322		[RO] Will always return 0.  Don't rely on any specific behavior323		for discards, and don't read this file.324 325 326What:		/sys/block/<disk>/queue/dma_alignment327Date:		May 2022328Contact:	linux-block@vger.kernel.org329Description:330		Reports the alignment that user space addresses must have to be331		used for raw block device access with O_DIRECT and other driver332		specific passthrough mechanisms.333 334 335What:		/sys/block/<disk>/queue/fua336Date:		May 2018337Contact:	linux-block@vger.kernel.org338Description:339		[RO] Whether or not the block driver supports the FUA flag for340		write requests.  FUA stands for Force Unit Access. If the FUA341		flag is set that means that write requests must bypass the342		volatile cache of the storage device.343 344 345What:		/sys/block/<disk>/queue/hw_sector_size346Date:		January 2008347Contact:	linux-block@vger.kernel.org348Description:349		[RO] This is the hardware sector size of the device, in bytes.350 351 352What:		/sys/block/<disk>/queue/independent_access_ranges/353Date:		October 2021354Contact:	linux-block@vger.kernel.org355Description:356		[RO] The presence of this sub-directory of the357		/sys/block/xxx/queue/ directory indicates that the device is358		capable of executing requests targeting different sector ranges359		in parallel. For instance, single LUN multi-actuator hard-disks360		will have an independent_access_ranges directory if the device361		correctly advertises the sector ranges of its actuators.362 363		The independent_access_ranges directory contains one directory364		per access range, with each range described using the sector365		(RO) attribute file to indicate the first sector of the range366		and the nr_sectors (RO) attribute file to indicate the total367		number of sectors in the range starting from the first sector of368		the range.  For example, a dual-actuator hard-disk will have the369		following independent_access_ranges entries.::370 371			$ tree /sys/block/<disk>/queue/independent_access_ranges/372			/sys/block/<disk>/queue/independent_access_ranges/373			|-- 0374			|   |-- nr_sectors375			|   `-- sector376			`-- 1377			    |-- nr_sectors378			    `-- sector379 380		The sector and nr_sectors attributes use 512B sector unit,381		regardless of the actual block size of the device. Independent382		access ranges do not overlap and include all sectors within the383		device capacity. The access ranges are numbered in increasing384		order of the range start sector, that is, the sector attribute385		of range 0 always has the value 0.386 387 388What:		/sys/block/<disk>/queue/io_poll389Date:		November 2015390Contact:	linux-block@vger.kernel.org391Description:392		[RW] When read, this file shows whether polling is enabled (1)393		or disabled (0).  Writing '0' to this file will disable polling394		for this device.  Writing any non-zero value will enable this395		feature.396 397 398What:		/sys/block/<disk>/queue/io_poll_delay399Date:		November 2016400Contact:	linux-block@vger.kernel.org401Description:402		[RW] This was used to control what kind of polling will be403		performed.  It is now fixed to -1, which is classic polling.404		In this mode, the CPU will repeatedly ask for completions405		without giving up any time.406		<deprecated>407 408 409What:		/sys/block/<disk>/queue/io_timeout410Date:		November 2018411Contact:	Weiping Zhang <zhangweiping@didiglobal.com>412Description:413		[RW] io_timeout is the request timeout in milliseconds. If a414		request does not complete in this time then the block driver415		timeout handler is invoked. That timeout handler can decide to416		retry the request, to fail it or to start a device recovery417		strategy.418 419 420What:		/sys/block/<disk>/queue/iostats421Date:		January 2009422Contact:	linux-block@vger.kernel.org423Description:424		[RW] This file is used to control (on/off) the iostats425		accounting of the disk.426 427 428What:		/sys/block/<disk>/queue/logical_block_size429Date:		May 2009430Contact:	Martin K. Petersen <martin.petersen@oracle.com>431Description:432		[RO] This is the smallest unit the storage device can address.433		It is typically 512 bytes.434 435 436What:		/sys/block/<disk>/queue/max_active_zones437Date:		July 2020438Contact:	Niklas Cassel <niklas.cassel@wdc.com>439Description:440		[RO] For zoned block devices (zoned attribute indicating441		"host-managed" or "host-aware"), the sum of zones belonging to442		any of the zone states: EXPLICIT OPEN, IMPLICIT OPEN or CLOSED,443		is limited by this value. If this value is 0, there is no limit.444 445		If the host attempts to exceed this limit, the driver should446		report this error with BLK_STS_ZONE_ACTIVE_RESOURCE, which user447		space may see as the EOVERFLOW errno.448 449 450What:		/sys/block/<disk>/queue/max_discard_segments451Date:		February 2017452Contact:	linux-block@vger.kernel.org453Description:454		[RO] The maximum number of DMA scatter/gather entries in a455		discard request.456 457 458What:		/sys/block/<disk>/queue/max_hw_sectors_kb459Date:		September 2004460Contact:	linux-block@vger.kernel.org461Description:462		[RO] This is the maximum number of kilobytes supported in a463		single data transfer.464 465 466What:		/sys/block/<disk>/queue/max_integrity_segments467Date:		September 2010468Contact:	linux-block@vger.kernel.org469Description:470		[RO] Maximum number of elements in a DMA scatter/gather list471		with integrity data that will be submitted by the block layer472		core to the associated block driver.473 474 475What:		/sys/block/<disk>/queue/max_open_zones476Date:		July 2020477Contact:	Niklas Cassel <niklas.cassel@wdc.com>478Description:479		[RO] For zoned block devices (zoned attribute indicating480		"host-managed" or "host-aware"), the sum of zones belonging to481		any of the zone states: EXPLICIT OPEN or IMPLICIT OPEN, is482		limited by this value. If this value is 0, there is no limit.483 484 485What:		/sys/block/<disk>/queue/max_sectors_kb486Date:		September 2004487Contact:	linux-block@vger.kernel.org488Description:489		[RW] This is the maximum number of kilobytes that the block490		layer will allow for a filesystem request. Must be smaller than491		or equal to the maximum size allowed by the hardware. Write 0492		to use default kernel settings.493 494 495What:		/sys/block/<disk>/queue/max_segment_size496Date:		March 2010497Contact:	linux-block@vger.kernel.org498Description:499		[RO] Maximum size in bytes of a single element in a DMA500		scatter/gather list.501 502 503What:		/sys/block/<disk>/queue/max_segments504Date:		March 2010505Contact:	linux-block@vger.kernel.org506Description:507		[RO] Maximum number of elements in a DMA scatter/gather list508		that is submitted to the associated block driver.509 510 511What:		/sys/block/<disk>/queue/minimum_io_size512Date:		April 2009513Contact:	Martin K. Petersen <martin.petersen@oracle.com>514Description:515		[RO] Storage devices may report a granularity or preferred516		minimum I/O size which is the smallest request the device can517		perform without incurring a performance penalty.  For disk518		drives this is often the physical block size.  For RAID arrays519		it is often the stripe chunk size.  A properly aligned multiple520		of minimum_io_size is the preferred request size for workloads521		where a high number of I/O operations is desired.522 523 524What:		/sys/block/<disk>/queue/nomerges525Date:		January 2010526Contact:	linux-block@vger.kernel.org527Description:528		[RW] Standard I/O elevator operations include attempts to merge529		contiguous I/Os. For known random I/O loads these attempts will530		always fail and result in extra cycles being spent in the531		kernel. This allows one to turn off this behavior on one of two532		ways: When set to 1, complex merge checks are disabled, but the533		simple one-shot merges with the previous I/O request are534		enabled. When set to 2, all merge tries are disabled. The535		default value is 0 - which enables all types of merge tries.536 537 538What:		/sys/block/<disk>/queue/nr_requests539Date:		July 2003540Contact:	linux-block@vger.kernel.org541Description:542		[RW] This controls how many requests may be allocated in the543		block layer for read or write requests. Note that the total544		allocated number may be twice this amount, since it applies only545		to reads or writes (not the accumulated sum).546 547		To avoid priority inversion through request starvation, a548		request queue maintains a separate request pool per each cgroup549		when CONFIG_BLK_CGROUP is enabled, and this parameter applies to550		each such per-block-cgroup request pool.  IOW, if there are N551		block cgroups, each request queue may have up to N request552		pools, each independently regulated by nr_requests.553 554 555What:		/sys/block/<disk>/queue/nr_zones556Date:		November 2018557Contact:	Damien Le Moal <damien.lemoal@wdc.com>558Description:559		[RO] nr_zones indicates the total number of zones of a zoned560		block device ("host-aware" or "host-managed" zone model). For561		regular block devices, the value is always 0.562 563 564What:		/sys/block/<disk>/queue/optimal_io_size565Date:		April 2009566Contact:	Martin K. Petersen <martin.petersen@oracle.com>567Description:568		[RO] Storage devices may report an optimal I/O size, which is569		the device's preferred unit for sustained I/O.  This is rarely570		reported for disk drives.  For RAID arrays it is usually the571		stripe width or the internal track size.  A properly aligned572		multiple of optimal_io_size is the preferred request size for573		workloads where sustained throughput is desired.  If no optimal574		I/O size is reported this file contains 0.575 576 577What:		/sys/block/<disk>/queue/physical_block_size578Date:		May 2009579Contact:	Martin K. Petersen <martin.petersen@oracle.com>580Description:581		[RO] This is the smallest unit a physical storage device can582		write atomically.  It is usually the same as the logical block583		size but may be bigger.  One example is SATA drives with 4KB584		sectors that expose a 512-byte logical block size to the585		operating system.  For stacked block devices the586		physical_block_size variable contains the maximum587		physical_block_size of the component devices.588 589 590What:		/sys/block/<disk>/queue/read_ahead_kb591Date:		May 2004592Contact:	linux-block@vger.kernel.org593Description:594		[RW] Maximum number of kilobytes to read-ahead for filesystems595		on this block device.596 597		For MADV_HUGEPAGE, the readahead size may exceed this setting598		since its granularity is based on the hugepage size.599 600 601What:		/sys/block/<disk>/queue/rotational602Date:		January 2009603Contact:	linux-block@vger.kernel.org604Description:605		[RW] This file is used to stat if the device is of rotational606		type or non-rotational type.607 608 609What:		/sys/block/<disk>/queue/rq_affinity610Date:		September 2008611Contact:	linux-block@vger.kernel.org612Description:613		[RW] If this option is '1', the block layer will migrate request614		completions to the cpu "group" that originally submitted the615		request. For some workloads this provides a significant616		reduction in CPU cycles due to caching effects.617 618		For storage configurations that need to maximize distribution of619		completion processing setting this option to '2' forces the620		completion to run on the requesting cpu (bypassing the "group"621		aggregation logic).622 623 624What:		/sys/block/<disk>/queue/scheduler625Date:		October 2004626Contact:	linux-block@vger.kernel.org627Description:628		[RW] When read, this file will display the current and available629		IO schedulers for this block device. The currently active IO630		scheduler will be enclosed in [] brackets. Writing an IO631		scheduler name to this file will switch control of this block632		device to that new IO scheduler. Note that writing an IO633		scheduler name to this file will attempt to load that IO634		scheduler module, if it isn't already present in the system.635 636 637What:		/sys/block/<disk>/queue/stable_writes638Date:		September 2020639Contact:	linux-block@vger.kernel.org640Description:641		[RW] This file will contain '1' if memory must not be modified642		while it is being used in a write request to this device.  When643		this is the case and the kernel is performing writeback of a644		page, the kernel will wait for writeback to complete before645		allowing the page to be modified again, rather than allowing646		immediate modification as is normally the case.  This647		restriction arises when the device accesses the memory multiple648		times where the same data must be seen every time -- for649		example, once to calculate a checksum and once to actually write650		the data.  If no such restriction exists, this file will contain651		'0'.  This file is writable for testing purposes.652 653What:		/sys/block/<disk>/queue/virt_boundary_mask654Date:		April 2021655Contact:	linux-block@vger.kernel.org656Description:657		[RO] This file shows the I/O segment memory alignment mask for658		the block device.  I/O requests to this device will be split659		between segments wherever either the memory address of the end660		of the previous segment or the memory address of the beginning661		of the current segment is not aligned to virt_boundary_mask + 1662		bytes.663 664 665What:		/sys/block/<disk>/queue/wbt_lat_usec666Date:		November 2016667Contact:	linux-block@vger.kernel.org668Description:669		[RW] If the device is registered for writeback throttling, then670		this file shows the target minimum read latency. If this latency671		is exceeded in a given window of time (see wb_window_usec), then672		the writeback throttling will start scaling back writes. Writing673		a value of '0' to this file disables the feature. Writing a674		value of '-1' to this file resets the value to the default675		setting.676 677 678What:		/sys/block/<disk>/queue/write_cache679Date:		April 2016680Contact:	linux-block@vger.kernel.org681Description:682		[RW] When read, this file will display whether the device has683		write back caching enabled or not. It will return "write back"684		for the former case, and "write through" for the latter. Writing685		to this file can change the kernels view of the device, but it686		doesn't alter the device state. This means that it might not be687		safe to toggle the setting from "write back" to "write through",688		since that will also eliminate cache flushes issued by the689		kernel.690 691 692What:		/sys/block/<disk>/queue/write_same_max_bytes693Date:		January 2012694Contact:	Martin K. Petersen <martin.petersen@oracle.com>695Description:696		[RO] Some devices support a write same operation in which a697		single data block can be written to a range of several698		contiguous blocks on storage. This can be used to wipe areas on699		disk or to initialize drives in a RAID configuration.700		write_same_max_bytes indicates how many bytes can be written in701		a single write same command. If write_same_max_bytes is 0, write702		same is not supported by the device.703 704 705What:		/sys/block/<disk>/queue/write_zeroes_max_bytes706Date:		November 2016707Contact:	Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>708Description:709		[RO] Devices that support write zeroes operation in which a710		single request can be issued to zero out the range of contiguous711		blocks on storage without having any payload in the request.712		This can be used to optimize writing zeroes to the devices.713		write_zeroes_max_bytes indicates how many bytes can be written714		in a single write zeroes command. If write_zeroes_max_bytes is715		0, write zeroes is not supported by the device.716 717 718What:		/sys/block/<disk>/queue/zone_append_max_bytes719Date:		May 2020720Contact:	linux-block@vger.kernel.org721Description:722		[RO] This is the maximum number of bytes that can be written to723		a sequential zone of a zoned block device using a zone append724		write operation (REQ_OP_ZONE_APPEND). This value is always 0 for725		regular block devices.726 727 728What:		/sys/block/<disk>/queue/zone_write_granularity729Date:		January 2021730Contact:	linux-block@vger.kernel.org731Description:732		[RO] This indicates the alignment constraint, in bytes, for733		write operations in sequential zones of zoned block devices734		(devices with a zoned attributed that reports "host-managed" or735		"host-aware"). This value is always 0 for regular block devices.736 737 738What:		/sys/block/<disk>/queue/zoned739Date:		September 2016740Contact:	Damien Le Moal <damien.lemoal@wdc.com>741Description:742		[RO] zoned indicates if the device is a zoned block device and743		the zone model of the device if it is indeed zoned.  The744		possible values indicated by zoned are "none" for regular block745		devices and "host-aware" or "host-managed" for zoned block746		devices. The characteristics of host-aware and host-managed747		zoned block devices are described in the ZBC (Zoned Block748		Commands) and ZAC (Zoned Device ATA Command Set) standards.749		These standards also define the "drive-managed" zone model.750		However, since drive-managed zoned block devices do not support751		zone commands, they will be treated as regular block devices and752		zoned will report "none".753 754 755What:		/sys/block/<disk>/hidden756Date:		March 2023757Contact:	linux-block@vger.kernel.org758Description:759		[RO] the block device is hidden. it doesn’t produce events, and760		can’t be opened from userspace or using blkdev_get*.761		Used for the underlying components of multipath devices.762 763 764What:		/sys/block/<disk>/stat765Date:		February 2008766Contact:	Jerome Marchand <jmarchan@redhat.com>767Description:768		The /sys/block/<disk>/stat files displays the I/O769		statistics of disk <disk>. They contain 11 fields:770 771		==  ==============================================772		 1  reads completed successfully773		 2  reads merged774		 3  sectors read775		 4  time spent reading (ms)776		 5  writes completed777		 6  writes merged778		 7  sectors written779		 8  time spent writing (ms)780		 9  I/Os currently in progress781		10  time spent doing I/Os (ms)782		11  weighted time spent doing I/Os (ms)783		12  discards completed784		13  discards merged785		14  sectors discarded786		15  time spent discarding (ms)787		16  flush requests completed788		17  time spent flushing (ms)789		==  ==============================================790 791		For more details refer Documentation/admin-guide/iostats.rst792