1=================== 2Block IO Controller 3=================== 4 5Overview 6======== 7cgroup subsys "blkio" implements the block io controller. There seems to be 8a need of various kinds of IO control policies (like proportional BW, max BW) 9both at leaf nodes as well as at intermediate nodes in a storage hierarchy. 10Plan is to use the same cgroup based management interface for blkio controller 11and based on user options switch IO policies in the background. 12 13One IO control policy is throttling policy which can be used to 14specify upper IO rate limits on devices. This policy is implemented in 15generic block layer and can be used on leaf nodes as well as higher 16level logical devices like device mapper. 17 18HOWTO 19===== 20Throttling/Upper Limit policy 21----------------------------- 22- Enable Block IO controller:: 23 24 CONFIG_BLK_CGROUP=y 25 26- Enable throttling in block layer:: 27 28 CONFIG_BLK_DEV_THROTTLING=y 29 30- Mount blkio controller (see cgroups.txt, Why are cgroups needed?):: 31 32 mount -t cgroup -o blkio none /sys/fs/cgroup/blkio 33 34- Specify a bandwidth rate on particular device for root group. The format 35 for policy is "<major>:<minor> <bytes_per_second>":: 36 37 echo "8:16 1048576" > /sys/fs/cgroup/blkio/blkio.throttle.read_bps_device 38 39 Above will put a limit of 1MB/second on reads happening for root group 40 on device having major/minor number 8:16. 41 42- Run dd to read a file and see if rate is throttled to 1MB/s or not:: 43 44 # dd iflag=direct if=/mnt/common/zerofile of=/dev/null bs=4K count=1024 45 1024+0 records in 46 1024+0 records out 47 4194304 bytes (4.2 MB) copied, 4.0001 s, 1.0 MB/s 48 49 Limits for writes can be put using blkio.throttle.write_bps_device file. 50 51Hierarchical Cgroups 52==================== 53 54Throttling implements hierarchy support; however, 55throttling's hierarchy support is enabled iff "sane_behavior" is 56enabled from cgroup side, which currently is a development option and 57not publicly available. 58 59If somebody created a hierarchy like as follows:: 60 61 root 62 / \ 63 test1 test2 64 | 65 test3 66 67Throttling with "sane_behavior" will handle the 68hierarchy correctly. For throttling, all limits apply 69to the whole subtree while all statistics are local to the IOs 70directly generated by tasks in that cgroup. 71 72Throttling without "sane_behavior" enabled from cgroup side will 73practically treat all groups at same level as if it looks like the 74following:: 75 76 pivot 77 / / \ \ 78 root test1 test2 test3 79 80Various user visible config options 81=================================== 82CONFIG_BLK_CGROUP 83 - Block IO controller. 84 85CONFIG_BFQ_CGROUP_DEBUG 86 - Debug help. Right now some additional stats file show up in cgroup 87 if this option is enabled. 88 89CONFIG_BLK_DEV_THROTTLING 90 - Enable block device throttling support in block layer. 91 92Details of cgroup files 93======================= 94Proportional weight policy files 95-------------------------------- 96- blkio.weight 97 - Specifies per cgroup weight. This is default weight of the group 98 on all the devices until and unless overridden by per device rule. 99 (See blkio.weight_device). 100 Currently allowed range of weights is from 10 to 1000. 101 102- blkio.weight_device 103 - One can specify per cgroup per device rules using this interface. 104 These rules override the default value of group weight as specified 105 by blkio.weight. 106 107 Following is the format:: 108 109 # echo dev_maj:dev_minor weight > blkio.weight_device 110 111 Configure weight=300 on /dev/sdb (8:16) in this cgroup:: 112 113 # echo 8:16 300 > blkio.weight_device 114 # cat blkio.weight_device 115 dev weight 116 8:16 300 117 118 Configure weight=500 on /dev/sda (8:0) in this cgroup:: 119 120 # echo 8:0 500 > blkio.weight_device 121 # cat blkio.weight_device 122 dev weight 123 8:0 500 124 8:16 300 125 126 Remove specific weight for /dev/sda in this cgroup:: 127 128 # echo 8:0 0 > blkio.weight_device 129 # cat blkio.weight_device 130 dev weight 131 8:16 300 132 133- blkio.time 134 - disk time allocated to cgroup per device in milliseconds. First 135 two fields specify the major and minor number of the device and 136 third field specifies the disk time allocated to group in 137 milliseconds. 138 139- blkio.sectors 140 - number of sectors transferred to/from disk by the group. First 141 two fields specify the major and minor number of the device and 142 third field specifies the number of sectors transferred by the 143 group to/from the device. 144 145- blkio.io_service_bytes 146 - Number of bytes transferred to/from the disk by the group. These 147 are further divided by the type of operation - read or write, sync 148 or async. First two fields specify the major and minor number of the 149 device, third field specifies the operation type and the fourth field 150 specifies the number of bytes. 151 152- blkio.io_serviced 153 - Number of IOs (bio) issued to the disk by the group. These 154 are further divided by the type of operation - read or write, sync 155 or async. First two fields specify the major and minor number of the 156 device, third field specifies the operation type and the fourth field 157 specifies the number of IOs. 158 159- blkio.io_service_time 160 - Total amount of time between request dispatch and request completion 161 for the IOs done by this cgroup. This is in nanoseconds to make it 162 meaningful for flash devices too. For devices with queue depth of 1, 163 this time represents the actual service time. When queue_depth > 1, 164 that is no longer true as requests may be served out of order. This 165 may cause the service time for a given IO to include the service time 166 of multiple IOs when served out of order which may result in total 167 io_service_time > actual time elapsed. This time is further divided by 168 the type of operation - read or write, sync or async. First two fields 169 specify the major and minor number of the device, third field 170 specifies the operation type and the fourth field specifies the 171 io_service_time in ns. 172 173- blkio.io_wait_time 174 - Total amount of time the IOs for this cgroup spent waiting in the 175 scheduler queues for service. This can be greater than the total time 176 elapsed since it is cumulative io_wait_time for all IOs. It is not a 177 measure of total time the cgroup spent waiting but rather a measure of 178 the wait_time for its individual IOs. For devices with queue_depth > 1 179 this metric does not include the time spent waiting for service once 180 the IO is dispatched to the device but till it actually gets serviced 181 (there might be a time lag here due to re-ordering of requests by the 182 device). This is in nanoseconds to make it meaningful for flash 183 devices too. This time is further divided by the type of operation - 184 read or write, sync or async. First two fields specify the major and 185 minor number of the device, third field specifies the operation type 186 and the fourth field specifies the io_wait_time in ns. 187 188- blkio.io_merged 189 - Total number of bios/requests merged into requests belonging to this 190 cgroup. This is further divided by the type of operation - read or 191 write, sync or async. 192 193- blkio.io_queued 194 - Total number of requests queued up at any given instant for this 195 cgroup. This is further divided by the type of operation - read or 196 write, sync or async. 197 198- blkio.avg_queue_size 199 - Debugging aid only enabled if CONFIG_BFQ_CGROUP_DEBUG=y. 200 The average queue size for this cgroup over the entire time of this 201 cgroup's existence. Queue size samples are taken each time one of the 202 queues of this cgroup gets a timeslice. 203 204- blkio.group_wait_time 205 - Debugging aid only enabled if CONFIG_BFQ_CGROUP_DEBUG=y. 206 This is the amount of time the cgroup had to wait since it became busy 207 (i.e., went from 0 to 1 request queued) to get a timeslice for one of 208 its queues. This is different from the io_wait_time which is the 209 cumulative total of the amount of time spent by each IO in that cgroup 210 waiting in the scheduler queue. This is in nanoseconds. If this is 211 read when the cgroup is in a waiting (for timeslice) state, the stat 212 will only report the group_wait_time accumulated till the last time it 213 got a timeslice and will not include the current delta. 214 215- blkio.empty_time 216 - Debugging aid only enabled if CONFIG_BFQ_CGROUP_DEBUG=y. 217 This is the amount of time a cgroup spends without any pending 218 requests when not being served, i.e., it does not include any time 219 spent idling for one of the queues of the cgroup. This is in 220 nanoseconds. If this is read when the cgroup is in an empty state, 221 the stat will only report the empty_time accumulated till the last 222 time it had a pending request and will not include the current delta. 223 224- blkio.idle_time 225 - Debugging aid only enabled if CONFIG_BFQ_CGROUP_DEBUG=y. 226 This is the amount of time spent by the IO scheduler idling for a 227 given cgroup in anticipation of a better request than the existing ones 228 from other queues/cgroups. This is in nanoseconds. If this is read 229 when the cgroup is in an idling state, the stat will only report the 230 idle_time accumulated till the last idle period and will not include 231 the current delta. 232 233- blkio.dequeue 234 - Debugging aid only enabled if CONFIG_BFQ_CGROUP_DEBUG=y. This 235 gives the statistics about how many a times a group was dequeued 236 from service tree of the device. First two fields specify the major 237 and minor number of the device and third field specifies the number 238 of times a group was dequeued from a particular device. 239 240- blkio.*_recursive 241 - Recursive version of various stats. These files show the 242 same information as their non-recursive counterparts but 243 include stats from all the descendant cgroups. 244 245Throttling/Upper limit policy files 246----------------------------------- 247- blkio.throttle.read_bps_device 248 - Specifies upper limit on READ rate from the device. IO rate is 249 specified in bytes per second. Rules are per device. Following is 250 the format:: 251 252 echo "<major>:<minor> <rate_bytes_per_second>" > /cgrp/blkio.throttle.read_bps_device 253 254- blkio.throttle.write_bps_device 255 - Specifies upper limit on WRITE rate to the device. IO rate is 256 specified in bytes per second. Rules are per device. Following is 257 the format:: 258 259 echo "<major>:<minor> <rate_bytes_per_second>" > /cgrp/blkio.throttle.write_bps_device 260 261- blkio.throttle.read_iops_device 262 - Specifies upper limit on READ rate from the device. IO rate is 263 specified in IO per second. Rules are per device. Following is 264 the format:: 265 266 echo "<major>:<minor> <rate_io_per_second>" > /cgrp/blkio.throttle.read_iops_device 267 268- blkio.throttle.write_iops_device 269 - Specifies upper limit on WRITE rate to the device. IO rate is 270 specified in io per second. Rules are per device. Following is 271 the format:: 272 273 echo "<major>:<minor> <rate_io_per_second>" > /cgrp/blkio.throttle.write_iops_device 274 275Note: If both BW and IOPS rules are specified for a device, then IO is 276 subjected to both the constraints. 277 278- blkio.throttle.io_serviced 279 - Number of IOs (bio) issued to the disk by the group. These 280 are further divided by the type of operation - read or write, sync 281 or async. First two fields specify the major and minor number of the 282 device, third field specifies the operation type and the fourth field 283 specifies the number of IOs. 284 285- blkio.throttle.io_service_bytes 286 - Number of bytes transferred to/from the disk by the group. These 287 are further divided by the type of operation - read or write, sync 288 or async. First two fields specify the major and minor number of the 289 device, third field specifies the operation type and the fourth field 290 specifies the number of bytes. 291 292Common files among various policies 293----------------------------------- 294- blkio.reset_stats 295 - Writing an int to this file will result in resetting all the stats 296 for that cgroup. 297