1 What: /sys/block/<disk>/stat
3 Contact: Jerome Marchand <jmarchan@redhat.com>
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
10 4 - time spent reading (ms)
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 For more details refer Documentation/iostats.txt
21 What: /sys/block/<disk>/<part>/stat
23 Contact: Jerome Marchand <jmarchan@redhat.com>
25 The /sys/block/<disk>/<part>/stat files display the
26 I/O statistics of partition <part>. The format is the
27 same as the above-written /sys/block/<disk>/stat
31 What: /sys/block/<disk>/integrity/format
33 Contact: Martin K. Petersen <martin.petersen@oracle.com>
35 Metadata format for integrity capable block device.
36 E.g. T10-DIF-TYPE1-CRC.
39 What: /sys/block/<disk>/integrity/read_verify
41 Contact: Martin K. Petersen <martin.petersen@oracle.com>
43 Indicates whether the block layer should verify the
44 integrity of read requests serviced by devices that
45 support sending integrity metadata.
48 What: /sys/block/<disk>/integrity/tag_size
50 Contact: Martin K. Petersen <martin.petersen@oracle.com>
52 Number of bytes of integrity tag space available per
56 What: /sys/block/<disk>/integrity/device_is_integrity_capable
58 Contact: Martin K. Petersen <martin.petersen@oracle.com>
60 Indicates whether a storage device is capable of storing
61 integrity metadata. Set if the device is T10 PI-capable.
64 What: /sys/block/<disk>/integrity/write_generate
66 Contact: Martin K. Petersen <martin.petersen@oracle.com>
68 Indicates whether the block layer should automatically
69 generate checksums for write requests bound for
70 devices that support receiving integrity metadata.
72 What: /sys/block/<disk>/alignment_offset
74 Contact: Martin K. Petersen <martin.petersen@oracle.com>
76 Storage devices may report a physical block size that is
77 bigger than the logical block size (for instance a drive
78 with 4KB physical sectors exposing 512-byte logical
79 blocks to the operating system). This parameter
80 indicates how many bytes the beginning of the device is
81 offset from the disk's natural alignment.
83 What: /sys/block/<disk>/<partition>/alignment_offset
85 Contact: Martin K. Petersen <martin.petersen@oracle.com>
87 Storage devices may report a physical block size that is
88 bigger than the logical block size (for instance a drive
89 with 4KB physical sectors exposing 512-byte logical
90 blocks to the operating system). This parameter
91 indicates how many bytes the beginning of the partition
92 is offset from the disk's natural alignment.
94 What: /sys/block/<disk>/queue/logical_block_size
96 Contact: Martin K. Petersen <martin.petersen@oracle.com>
98 This is the smallest unit the storage device can
99 address. It is typically 512 bytes.
101 What: /sys/block/<disk>/queue/physical_block_size
103 Contact: Martin K. Petersen <martin.petersen@oracle.com>
105 This is the smallest unit a physical storage device can
106 write atomically. It is usually the same as the logical
107 block size but may be bigger. One example is SATA
108 drives with 4KB sectors that expose a 512-byte logical
109 block size to the operating system. For stacked block
110 devices the physical_block_size variable contains the
111 maximum physical_block_size of the component devices.
113 What: /sys/block/<disk>/queue/minimum_io_size
115 Contact: Martin K. Petersen <martin.petersen@oracle.com>
117 Storage devices may report a granularity or preferred
118 minimum I/O size which is the smallest request the
119 device can perform without incurring a performance
120 penalty. For disk drives this is often the physical
121 block size. For RAID arrays it is often the stripe
122 chunk size. A properly aligned multiple of
123 minimum_io_size is the preferred request size for
124 workloads where a high number of I/O operations is
127 What: /sys/block/<disk>/queue/optimal_io_size
129 Contact: Martin K. Petersen <martin.petersen@oracle.com>
131 Storage devices may report an optimal I/O size, which is
132 the device's preferred unit for sustained I/O. This is
133 rarely reported for disk drives. For RAID arrays it is
134 usually the stripe width or the internal track size. A
135 properly aligned multiple of optimal_io_size is the
136 preferred request size for workloads where sustained
137 throughput is desired. If no optimal I/O size is
138 reported this file contains 0.
140 What: /sys/block/<disk>/queue/nomerges
144 Standard I/O elevator operations include attempts to
145 merge contiguous I/Os. For known random I/O loads these
146 attempts will always fail and result in extra cycles
147 being spent in the kernel. This allows one to turn off
148 this behavior on one of two ways: When set to 1, complex
149 merge checks are disabled, but the simple one-shot merges
150 with the previous I/O request are enabled. When set to 2,
151 all merge tries are disabled. The default value is 0 -
152 which enables all types of merge tries.
154 What: /sys/block/<disk>/discard_alignment
156 Contact: Martin K. Petersen <martin.petersen@oracle.com>
158 Devices that support discard functionality may
159 internally allocate space in units that are bigger than
160 the exported logical block size. The discard_alignment
161 parameter indicates how many bytes the beginning of the
162 device is offset from the internal allocation unit's
165 What: /sys/block/<disk>/<partition>/discard_alignment
167 Contact: Martin K. Petersen <martin.petersen@oracle.com>
169 Devices that support discard functionality may
170 internally allocate space in units that are bigger than
171 the exported logical block size. The discard_alignment
172 parameter indicates how many bytes the beginning of the
173 partition is offset from the internal allocation unit's
176 What: /sys/block/<disk>/queue/discard_granularity
178 Contact: Martin K. Petersen <martin.petersen@oracle.com>
180 Devices that support discard functionality may
181 internally allocate space using units that are bigger
182 than the logical block size. The discard_granularity
183 parameter indicates the size of the internal allocation
184 unit in bytes if reported by the device. Otherwise the
185 discard_granularity will be set to match the device's
186 physical block size. A discard_granularity of 0 means
187 that the device does not support discard functionality.
189 What: /sys/block/<disk>/queue/discard_max_bytes
191 Contact: Martin K. Petersen <martin.petersen@oracle.com>
193 Devices that support discard functionality may have
194 internal limits on the number of bytes that can be
195 trimmed or unmapped in a single operation. Some storage
196 protocols also have inherent limits on the number of
197 blocks that can be described in a single command. The
198 discard_max_bytes parameter is set by the device driver
199 to the maximum number of bytes that can be discarded in
200 a single operation. Discard requests issued to the
201 device must not exceed this limit. A discard_max_bytes
202 value of 0 means that the device does not support
203 discard functionality.
205 What: /sys/block/<disk>/queue/discard_zeroes_data
207 Contact: Martin K. Petersen <martin.petersen@oracle.com>
209 Devices that support discard functionality may return
210 stale or random data when a previously discarded block
211 is read back. This can cause problems if the filesystem
212 expects discarded blocks to be explicitly cleared. If a
213 device reports that it deterministically returns zeroes
214 when a discarded area is read the discard_zeroes_data
215 parameter will be set to one. Otherwise it will be 0 and
216 the result of reading a discarded area is undefined.
218 What: /sys/block/<disk>/queue/write_same_max_bytes
220 Contact: Martin K. Petersen <martin.petersen@oracle.com>
222 Some devices support a write same operation in which a
223 single data block can be written to a range of several
224 contiguous blocks on storage. This can be used to wipe
225 areas on disk or to initialize drives in a RAID
226 configuration. write_same_max_bytes indicates how many
227 bytes can be written in a single write same command. If
228 write_same_max_bytes is 0, write same is not supported