Loading...
Note: File does not exist in v6.8.
1What: /sys/block/<disk>/stat
2Date: February 2008
3Contact: Jerome Marchand <jmarchan@redhat.com>
4Description:
5 The /sys/block/<disk>/stat files displays the I/O
6 statistics of disk <disk>. They contain 11 fields:
7 1 - reads completed successfully
8 2 - reads merged
9 3 - sectors read
10 4 - time spent reading (ms)
11 5 - writes completed
12 6 - writes merged
13 7 - sectors written
14 8 - time spent writing (ms)
15 9 - I/Os currently in progress
16 10 - time spent doing I/Os (ms)
17 11 - weighted time spent doing I/Os (ms)
18 12 - discards completed
19 13 - discards merged
20 14 - sectors discarded
21 15 - time spent discarding (ms)
22 16 - flush requests completed
23 17 - time spent flushing (ms)
24 For more details refer Documentation/admin-guide/iostats.rst
25
26
27What: /sys/block/<disk>/<part>/stat
28Date: February 2008
29Contact: Jerome Marchand <jmarchan@redhat.com>
30Description:
31 The /sys/block/<disk>/<part>/stat files display the
32 I/O statistics of partition <part>. The format is the
33 same as the above-written /sys/block/<disk>/stat
34 format.
35
36
37What: /sys/block/<disk>/integrity/format
38Date: June 2008
39Contact: Martin K. Petersen <martin.petersen@oracle.com>
40Description:
41 Metadata format for integrity capable block device.
42 E.g. T10-DIF-TYPE1-CRC.
43
44
45What: /sys/block/<disk>/integrity/read_verify
46Date: June 2008
47Contact: Martin K. Petersen <martin.petersen@oracle.com>
48Description:
49 Indicates whether the block layer should verify the
50 integrity of read requests serviced by devices that
51 support sending integrity metadata.
52
53
54What: /sys/block/<disk>/integrity/tag_size
55Date: June 2008
56Contact: Martin K. Petersen <martin.petersen@oracle.com>
57Description:
58 Number of bytes of integrity tag space available per
59 512 bytes of data.
60
61
62What: /sys/block/<disk>/integrity/device_is_integrity_capable
63Date: July 2014
64Contact: Martin K. Petersen <martin.petersen@oracle.com>
65Description:
66 Indicates whether a storage device is capable of storing
67 integrity metadata. Set if the device is T10 PI-capable.
68
69What: /sys/block/<disk>/integrity/protection_interval_bytes
70Date: July 2015
71Contact: Martin K. Petersen <martin.petersen@oracle.com>
72Description:
73 Describes the number of data bytes which are protected
74 by one integrity tuple. Typically the device's logical
75 block size.
76
77What: /sys/block/<disk>/integrity/write_generate
78Date: June 2008
79Contact: Martin K. Petersen <martin.petersen@oracle.com>
80Description:
81 Indicates whether the block layer should automatically
82 generate checksums for write requests bound for
83 devices that support receiving integrity metadata.
84
85What: /sys/block/<disk>/alignment_offset
86Date: April 2009
87Contact: Martin K. Petersen <martin.petersen@oracle.com>
88Description:
89 Storage devices may report a physical block size that is
90 bigger than the logical block size (for instance a drive
91 with 4KB physical sectors exposing 512-byte logical
92 blocks to the operating system). This parameter
93 indicates how many bytes the beginning of the device is
94 offset from the disk's natural alignment.
95
96What: /sys/block/<disk>/<partition>/alignment_offset
97Date: April 2009
98Contact: Martin K. Petersen <martin.petersen@oracle.com>
99Description:
100 Storage devices may report a physical block size that is
101 bigger than the logical block size (for instance a drive
102 with 4KB physical sectors exposing 512-byte logical
103 blocks to the operating system). This parameter
104 indicates how many bytes the beginning of the partition
105 is offset from the disk's natural alignment.
106
107What: /sys/block/<disk>/queue/logical_block_size
108Date: May 2009
109Contact: Martin K. Petersen <martin.petersen@oracle.com>
110Description:
111 This is the smallest unit the storage device can
112 address. It is typically 512 bytes.
113
114What: /sys/block/<disk>/queue/physical_block_size
115Date: May 2009
116Contact: Martin K. Petersen <martin.petersen@oracle.com>
117Description:
118 This is the smallest unit a physical storage device can
119 write atomically. It is usually the same as the logical
120 block size but may be bigger. One example is SATA
121 drives with 4KB sectors that expose a 512-byte logical
122 block size to the operating system. For stacked block
123 devices the physical_block_size variable contains the
124 maximum physical_block_size of the component devices.
125
126What: /sys/block/<disk>/queue/minimum_io_size
127Date: April 2009
128Contact: Martin K. Petersen <martin.petersen@oracle.com>
129Description:
130 Storage devices may report a granularity or preferred
131 minimum I/O size which is the smallest request the
132 device can perform without incurring a performance
133 penalty. For disk drives this is often the physical
134 block size. For RAID arrays it is often the stripe
135 chunk size. A properly aligned multiple of
136 minimum_io_size is the preferred request size for
137 workloads where a high number of I/O operations is
138 desired.
139
140What: /sys/block/<disk>/queue/optimal_io_size
141Date: April 2009
142Contact: Martin K. Petersen <martin.petersen@oracle.com>
143Description:
144 Storage devices may report an optimal I/O size, which is
145 the device's preferred unit for sustained I/O. This is
146 rarely reported for disk drives. For RAID arrays it is
147 usually the stripe width or the internal track size. A
148 properly aligned multiple of optimal_io_size is the
149 preferred request size for workloads where sustained
150 throughput is desired. If no optimal I/O size is
151 reported this file contains 0.
152
153What: /sys/block/<disk>/queue/nomerges
154Date: January 2010
155Contact:
156Description:
157 Standard I/O elevator operations include attempts to
158 merge contiguous I/Os. For known random I/O loads these
159 attempts will always fail and result in extra cycles
160 being spent in the kernel. This allows one to turn off
161 this behavior on one of two ways: When set to 1, complex
162 merge checks are disabled, but the simple one-shot merges
163 with the previous I/O request are enabled. When set to 2,
164 all merge tries are disabled. The default value is 0 -
165 which enables all types of merge tries.
166
167What: /sys/block/<disk>/discard_alignment
168Date: May 2011
169Contact: Martin K. Petersen <martin.petersen@oracle.com>
170Description:
171 Devices that support discard functionality may
172 internally allocate space in units that are bigger than
173 the exported logical block size. The discard_alignment
174 parameter indicates how many bytes the beginning of the
175 device is offset from the internal allocation unit's
176 natural alignment.
177
178What: /sys/block/<disk>/<partition>/discard_alignment
179Date: May 2011
180Contact: Martin K. Petersen <martin.petersen@oracle.com>
181Description:
182 Devices that support discard functionality may
183 internally allocate space in units that are bigger than
184 the exported logical block size. The discard_alignment
185 parameter indicates how many bytes the beginning of the
186 partition is offset from the internal allocation unit's
187 natural alignment.
188
189What: /sys/block/<disk>/queue/discard_granularity
190Date: May 2011
191Contact: Martin K. Petersen <martin.petersen@oracle.com>
192Description:
193 Devices that support discard functionality may
194 internally allocate space using units that are bigger
195 than the logical block size. The discard_granularity
196 parameter indicates the size of the internal allocation
197 unit in bytes if reported by the device. Otherwise the
198 discard_granularity will be set to match the device's
199 physical block size. A discard_granularity of 0 means
200 that the device does not support discard functionality.
201
202What: /sys/block/<disk>/queue/discard_max_bytes
203Date: May 2011
204Contact: Martin K. Petersen <martin.petersen@oracle.com>
205Description:
206 Devices that support discard functionality may have
207 internal limits on the number of bytes that can be
208 trimmed or unmapped in a single operation. Some storage
209 protocols also have inherent limits on the number of
210 blocks that can be described in a single command. The
211 discard_max_bytes parameter is set by the device driver
212 to the maximum number of bytes that can be discarded in
213 a single operation. Discard requests issued to the
214 device must not exceed this limit. A discard_max_bytes
215 value of 0 means that the device does not support
216 discard functionality.
217
218What: /sys/block/<disk>/queue/discard_zeroes_data
219Date: May 2011
220Contact: Martin K. Petersen <martin.petersen@oracle.com>
221Description:
222 Will always return 0. Don't rely on any specific behavior
223 for discards, and don't read this file.
224
225What: /sys/block/<disk>/queue/write_same_max_bytes
226Date: January 2012
227Contact: Martin K. Petersen <martin.petersen@oracle.com>
228Description:
229 Some devices support a write same operation in which a
230 single data block can be written to a range of several
231 contiguous blocks on storage. This can be used to wipe
232 areas on disk or to initialize drives in a RAID
233 configuration. write_same_max_bytes indicates how many
234 bytes can be written in a single write same command. If
235 write_same_max_bytes is 0, write same is not supported
236 by the device.
237
238What: /sys/block/<disk>/queue/write_zeroes_max_bytes
239Date: November 2016
240Contact: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
241Description:
242 Devices that support write zeroes operation in which a
243 single request can be issued to zero out the range of
244 contiguous blocks on storage without having any payload
245 in the request. This can be used to optimize writing zeroes
246 to the devices. write_zeroes_max_bytes indicates how many
247 bytes can be written in a single write zeroes command. If
248 write_zeroes_max_bytes is 0, write zeroes is not supported
249 by the device.
250
251What: /sys/block/<disk>/queue/zoned
252Date: September 2016
253Contact: Damien Le Moal <damien.lemoal@wdc.com>
254Description:
255 zoned indicates if the device is a zoned block device
256 and the zone model of the device if it is indeed zoned.
257 The possible values indicated by zoned are "none" for
258 regular block devices and "host-aware" or "host-managed"
259 for zoned block devices. The characteristics of
260 host-aware and host-managed zoned block devices are
261 described in the ZBC (Zoned Block Commands) and ZAC
262 (Zoned Device ATA Command Set) standards. These standards
263 also define the "drive-managed" zone model. However,
264 since drive-managed zoned block devices do not support
265 zone commands, they will be treated as regular block
266 devices and zoned will report "none".
267
268What: /sys/block/<disk>/queue/nr_zones
269Date: November 2018
270Contact: Damien Le Moal <damien.lemoal@wdc.com>
271Description:
272 nr_zones indicates the total number of zones of a zoned block
273 device ("host-aware" or "host-managed" zone model). For regular
274 block devices, the value is always 0.
275
276What: /sys/block/<disk>/queue/max_active_zones
277Date: July 2020
278Contact: Niklas Cassel <niklas.cassel@wdc.com>
279Description:
280 For zoned block devices (zoned attribute indicating
281 "host-managed" or "host-aware"), the sum of zones belonging to
282 any of the zone states: EXPLICIT OPEN, IMPLICIT OPEN or CLOSED,
283 is limited by this value. If this value is 0, there is no limit.
284
285What: /sys/block/<disk>/queue/max_open_zones
286Date: July 2020
287Contact: Niklas Cassel <niklas.cassel@wdc.com>
288Description:
289 For zoned block devices (zoned attribute indicating
290 "host-managed" or "host-aware"), the sum of zones belonging to
291 any of the zone states: EXPLICIT OPEN or IMPLICIT OPEN,
292 is limited by this value. If this value is 0, there is no limit.
293
294What: /sys/block/<disk>/queue/chunk_sectors
295Date: September 2016
296Contact: Hannes Reinecke <hare@suse.com>
297Description:
298 chunk_sectors has different meaning depending on the type
299 of the disk. For a RAID device (dm-raid), chunk_sectors
300 indicates the size in 512B sectors of the RAID volume
301 stripe segment. For a zoned block device, either
302 host-aware or host-managed, chunk_sectors indicates the
303 size in 512B sectors of the zones of the device, with
304 the eventual exception of the last zone of the device
305 which may be smaller.
306
307What: /sys/block/<disk>/queue/io_timeout
308Date: November 2018
309Contact: Weiping Zhang <zhangweiping@didiglobal.com>
310Description:
311 io_timeout is the request timeout in milliseconds. If a request
312 does not complete in this time then the block driver timeout
313 handler is invoked. That timeout handler can decide to retry
314 the request, to fail it or to start a device recovery strategy.