Blame view
Documentation/cgroup-v1/blkio-controller.txt
15.2 KB
72f924f62 blkio: Documentation |
1 2 3 4 5 6 7 8 9 |
Block IO Controller =================== Overview ======== cgroup subsys "blkio" implements the block io controller. There seems to be a need of various kinds of IO control policies (like proportional BW, max BW) both at leaf nodes as well as at intermediate nodes in a storage hierarchy. Plan is to use the same cgroup based management interface for blkio controller and based on user options switch IO policies in the background. |
2786c4e5e blkio: Documentat... |
10 11 12 13 14 15 |
Currently two IO control policies are implemented. First one is proportional weight time based division of disk policy. It is implemented in CFQ. Hence this policy takes effect only on leaf nodes when CFQ is being used. The second one is throttling policy which can be used to specify upper IO rate limits on devices. This policy is implemented in generic block layer and can be used on leaf nodes as well as higher level logical devices like device mapper. |
72f924f62 blkio: Documentation |
16 17 18 |
HOWTO ===== |
2786c4e5e blkio: Documentat... |
19 20 |
Proportional Weight division of bandwidth ----------------------------------------- |
72f924f62 blkio: Documentation |
21 22 |
You can do a very simple testing of running two dd threads in two different cgroups. Here is what you can do. |
afc24d49c blk-cgroup: confi... |
23 24 |
- Enable Block IO controller CONFIG_BLK_CGROUP=y |
72f924f62 blkio: Documentation |
25 26 |
- Enable group scheduling in CFQ CONFIG_CFQ_GROUP_IOSCHED=y |
f6e07d380 Documentation: up... |
27 28 |
- Compile and boot into kernel and mount IO controller (blkio); see cgroups.txt, Why are cgroups needed?. |
72f924f62 blkio: Documentation |
29 |
|
f6e07d380 Documentation: up... |
30 31 32 |
mount -t tmpfs cgroup_root /sys/fs/cgroup mkdir /sys/fs/cgroup/blkio mount -t cgroup -o blkio none /sys/fs/cgroup/blkio |
72f924f62 blkio: Documentation |
33 34 |
- Create two cgroups |
f6e07d380 Documentation: up... |
35 |
mkdir -p /sys/fs/cgroup/blkio/test1/ /sys/fs/cgroup/blkio/test2 |
72f924f62 blkio: Documentation |
36 37 |
- Set weights of group test1 and test2 |
f6e07d380 Documentation: up... |
38 39 |
echo 1000 > /sys/fs/cgroup/blkio/test1/blkio.weight echo 500 > /sys/fs/cgroup/blkio/test2/blkio.weight |
72f924f62 blkio: Documentation |
40 41 42 43 44 45 46 47 |
- Create two same size files (say 512MB each) on same disk (file1, file2) and launch two dd threads in different cgroup to read those files. sync echo 3 > /proc/sys/vm/drop_caches dd if=/mnt/sdb/zerofile1 of=/dev/null & |
f6e07d380 Documentation: up... |
48 49 |
echo $! > /sys/fs/cgroup/blkio/test1/tasks cat /sys/fs/cgroup/blkio/test1/tasks |
72f924f62 blkio: Documentation |
50 51 |
dd if=/mnt/sdb/zerofile2 of=/dev/null & |
f6e07d380 Documentation: up... |
52 53 |
echo $! > /sys/fs/cgroup/blkio/test2/tasks cat /sys/fs/cgroup/blkio/test2/tasks |
72f924f62 blkio: Documentation |
54 55 56 57 |
- At macro level, first dd should finish first. To get more precise data, keep on looking at (with the help of script), at blkio.disk_time and blkio.disk_sectors files of both test1 and test2 groups. This will tell how |
55d015954 Documentation: cg... |
58 |
much disk time (in milliseconds), each group got and how many sectors each |
72f924f62 blkio: Documentation |
59 60 |
group dispatched to the disk. We provide fairness in terms of disk time, so ideally io.disk_time of cgroups should be in proportion to the weight. |
2786c4e5e blkio: Documentat... |
61 62 63 64 65 66 67 |
Throttling/Upper Limit policy ----------------------------- - Enable Block IO controller CONFIG_BLK_CGROUP=y - Enable throttling in block layer CONFIG_BLK_DEV_THROTTLING=y |
f6e07d380 Documentation: up... |
68 69 |
- Mount blkio controller (see cgroups.txt, Why are cgroups needed?) mount -t cgroup -o blkio none /sys/fs/cgroup/blkio |
2786c4e5e blkio: Documentat... |
70 71 |
- Specify a bandwidth rate on particular device for root group. The format |
52b233c86 Documentation/cgr... |
72 |
for policy is "<major>:<minor> <bytes_per_second>". |
2786c4e5e blkio: Documentat... |
73 |
|
9b61fc4cf Documentation: fi... |
74 |
echo "8:16 1048576" > /sys/fs/cgroup/blkio/blkio.throttle.read_bps_device |
2786c4e5e blkio: Documentat... |
75 76 77 78 79 |
Above will put a limit of 1MB/second on reads happening for root group on device having major/minor number 8:16. - Run dd to read a file and see if rate is throttled to 1MB/s or not. |
e11362bb2 Subject: cgroup: ... |
80 |
# dd iflag=direct if=/mnt/common/zerofile of=/dev/null bs=4K count=1024 |
2786c4e5e blkio: Documentat... |
81 82 83 |
1024+0 records in 1024+0 records out 4194304 bytes (4.2 MB) copied, 4.0001 s, 1.0 MB/s |
9b61fc4cf Documentation: fi... |
84 |
Limits for writes can be put using blkio.throttle.write_bps_device file. |
2786c4e5e blkio: Documentat... |
85 |
|
bdc85df7a blk-cgroup: Allow... |
86 87 |
Hierarchical Cgroups ==================== |
bdc85df7a blk-cgroup: Allow... |
88 |
|
9138125be blk-throttle: imp... |
89 90 91 92 93 94 |
Both CFQ and throttling implement hierarchy support; however, throttling's hierarchy support is enabled iff "sane_behavior" is enabled from cgroup side, which currently is a development option and not publicly available. If somebody created a hierarchy like as follows. |
bdc85df7a blk-cgroup: Allow... |
95 96 97 98 99 100 |
root / \ test1 test2 | test3 |
9138125be blk-throttle: imp... |
101 102 103 104 105 106 107 108 109 |
CFQ by default and throttling with "sane_behavior" will handle the hierarchy correctly. For details on CFQ hierarchy support, refer to Documentation/block/cfq-iosched.txt. For throttling, all limits apply to the whole subtree while all statistics are local to the IOs directly generated by tasks in that cgroup. Throttling without "sane_behavior" enabled from cgroup side will practically treat all groups at same level as if it looks like the following. |
bdc85df7a blk-cgroup: Allow... |
110 111 |
pivot |
67de0162f Documentation: fi... |
112 |
/ / \ \ |
bdc85df7a blk-cgroup: Allow... |
113 |
root test1 test2 test3 |
72f924f62 blkio: Documentation |
114 115 |
Various user visible config options =================================== |
72f924f62 blkio: Documentation |
116 |
CONFIG_BLK_CGROUP |
afc24d49c blk-cgroup: confi... |
117 |
- Block IO controller. |
72f924f62 blkio: Documentation |
118 119 |
CONFIG_DEBUG_BLK_CGROUP |
afc24d49c blk-cgroup: confi... |
120 121 122 123 124 125 |
- Debug help. Right now some additional stats file show up in cgroup if this option is enabled. CONFIG_CFQ_GROUP_IOSCHED - Enables group scheduling in CFQ. Currently only 1 level of group creation is allowed. |
72f924f62 blkio: Documentation |
126 |
|
2786c4e5e blkio: Documentat... |
127 128 |
CONFIG_BLK_DEV_THROTTLING - Enable block device throttling support in block layer. |
72f924f62 blkio: Documentation |
129 130 |
Details of cgroup files ======================= |
2786c4e5e blkio: Documentat... |
131 132 |
Proportional weight policy files -------------------------------- |
72f924f62 blkio: Documentation |
133 |
- blkio.weight |
da69da184 io-controller: Do... |
134 135 136 |
- Specifies per cgroup weight. This is default weight of the group on all the devices until and unless overridden by per device rule. (See blkio.weight_device). |
df457f845 blk-cgroup: Lower... |
137 |
Currently allowed range of weights is from 10 to 1000. |
72f924f62 blkio: Documentation |
138 |
|
da69da184 io-controller: Do... |
139 140 141 142 143 144 |
- blkio.weight_device - One can specify per cgroup per device rules using this interface. These rules override the default value of group weight as specified by blkio.weight. Following is the format. |
f6e07d380 Documentation: up... |
145 |
# echo dev_maj:dev_minor weight > blkio.weight_device |
da69da184 io-controller: Do... |
146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 |
Configure weight=300 on /dev/sdb (8:16) in this cgroup # echo 8:16 300 > blkio.weight_device # cat blkio.weight_device dev weight 8:16 300 Configure weight=500 on /dev/sda (8:0) in this cgroup # echo 8:0 500 > blkio.weight_device # cat blkio.weight_device dev weight 8:0 500 8:16 300 Remove specific weight for /dev/sda in this cgroup # echo 8:0 0 > blkio.weight_device # cat blkio.weight_device dev weight 8:16 300 |
d02f7aa8d cfq-iosched: enab... |
164 165 166 167 168 |
- blkio.leaf_weight[_device] - Equivalents of blkio.weight[_device] for the purpose of deciding how much weight tasks in the given cgroup has while competing with the cgroup's child cgroups. For details, please refer to Documentation/block/cfq-iosched.txt. |
72f924f62 blkio: Documentation |
169 170 171 172 173 174 175 176 177 178 179 |
- blkio.time - disk time allocated to cgroup per device in milliseconds. First two fields specify the major and minor number of the device and third field specifies the disk time allocated to group in milliseconds. - blkio.sectors - number of sectors transferred to/from disk by the group. First two fields specify the major and minor number of the device and third field specifies the number of sectors transferred by the group to/from the device. |
84c124da9 blkio: Changes to... |
180 181 182 183 184 185 186 187 |
- blkio.io_service_bytes - Number of bytes transferred to/from the disk by the group. These are further divided by the type of operation - read or write, sync or async. First two fields specify the major and minor number of the device, third field specifies the operation type and the fourth field specifies the number of bytes. - blkio.io_serviced |
77ea73388 blkcg: move io_se... |
188 |
- Number of IOs (bio) issued to the disk by the group. These |
84c124da9 blkio: Changes to... |
189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 |
are further divided by the type of operation - read or write, sync or async. First two fields specify the major and minor number of the device, third field specifies the operation type and the fourth field specifies the number of IOs. - blkio.io_service_time - Total amount of time between request dispatch and request completion for the IOs done by this cgroup. This is in nanoseconds to make it meaningful for flash devices too. For devices with queue depth of 1, this time represents the actual service time. When queue_depth > 1, that is no longer true as requests may be served out of order. This may cause the service time for a given IO to include the service time of multiple IOs when served out of order which may result in total io_service_time > actual time elapsed. This time is further divided by the type of operation - read or write, sync or async. First two fields specify the major and minor number of the device, third field specifies the operation type and the fourth field specifies the io_service_time in ns. - blkio.io_wait_time - Total amount of time the IOs for this cgroup spent waiting in the scheduler queues for service. This can be greater than the total time elapsed since it is cumulative io_wait_time for all IOs. It is not a measure of total time the cgroup spent waiting but rather a measure of the wait_time for its individual IOs. For devices with queue_depth > 1 this metric does not include the time spent waiting for service once the IO is dispatched to the device but till it actually gets serviced (there might be a time lag here due to re-ordering of requests by the device). This is in nanoseconds to make it meaningful for flash devices too. This time is further divided by the type of operation - read or write, sync or async. First two fields specify the major and minor number of the device, third field specifies the operation type and the fourth field specifies the io_wait_time in ns. |
812d40264 blkio: Add io_mer... |
222 223 224 225 |
- blkio.io_merged - Total number of bios/requests merged into requests belonging to this cgroup. This is further divided by the type of operation - read or write, sync or async. |
cdc1184cf blkio: Add io_que... |
226 227 228 229 230 231 |
- blkio.io_queued - Total number of requests queued up at any given instant for this cgroup. This is further divided by the type of operation - read or write, sync or async. - blkio.avg_queue_size |
afc24d49c blk-cgroup: confi... |
232 |
- Debugging aid only enabled if CONFIG_DEBUG_BLK_CGROUP=y. |
cdc1184cf blkio: Add io_que... |
233 234 235 |
The average queue size for this cgroup over the entire time of this cgroup's existence. Queue size samples are taken each time one of the queues of this cgroup gets a timeslice. |
812df48d1 blkio: Add more d... |
236 |
- blkio.group_wait_time |
afc24d49c blk-cgroup: confi... |
237 |
- Debugging aid only enabled if CONFIG_DEBUG_BLK_CGROUP=y. |
812df48d1 blkio: Add more d... |
238 239 240 241 242 243 244 245 246 247 |
This is the amount of time the cgroup had to wait since it became busy (i.e., went from 0 to 1 request queued) to get a timeslice for one of its queues. This is different from the io_wait_time which is the cumulative total of the amount of time spent by each IO in that cgroup waiting in the scheduler queue. This is in nanoseconds. If this is read when the cgroup is in a waiting (for timeslice) state, the stat will only report the group_wait_time accumulated till the last time it got a timeslice and will not include the current delta. - blkio.empty_time |
afc24d49c blk-cgroup: confi... |
248 |
- Debugging aid only enabled if CONFIG_DEBUG_BLK_CGROUP=y. |
812df48d1 blkio: Add more d... |
249 250 251 252 253 254 255 256 |
This is the amount of time a cgroup spends without any pending requests when not being served, i.e., it does not include any time spent idling for one of the queues of the cgroup. This is in nanoseconds. If this is read when the cgroup is in an empty state, the stat will only report the empty_time accumulated till the last time it had a pending request and will not include the current delta. - blkio.idle_time |
afc24d49c blk-cgroup: confi... |
257 |
- Debugging aid only enabled if CONFIG_DEBUG_BLK_CGROUP=y. |
812df48d1 blkio: Add more d... |
258 |
This is the amount of time spent by the IO scheduler idling for a |
40e47125e Documentation: Fi... |
259 |
given cgroup in anticipation of a better request than the existing ones |
812df48d1 blkio: Add more d... |
260 261 262 263 |
from other queues/cgroups. This is in nanoseconds. If this is read when the cgroup is in an idling state, the stat will only report the idle_time accumulated till the last idle period and will not include the current delta. |
72f924f62 blkio: Documentation |
264 |
- blkio.dequeue |
afc24d49c blk-cgroup: confi... |
265 |
- Debugging aid only enabled if CONFIG_DEBUG_BLK_CGROUP=y. This |
72f924f62 blkio: Documentation |
266 267 268 269 |
gives the statistics about how many a times a group was dequeued from service tree of the device. First two fields specify the major and minor number of the device and third field specifies the number of times a group was dequeued from a particular device. |
d02f7aa8d cfq-iosched: enab... |
270 271 272 273 |
- blkio.*_recursive - Recursive version of various stats. These files show the same information as their non-recursive counterparts but include stats from all the descendant cgroups. |
2786c4e5e blkio: Documentat... |
274 275 276 277 |
Throttling/Upper limit policy files ----------------------------------- - blkio.throttle.read_bps_device - Specifies upper limit on READ rate from the device. IO rate is |
40e47125e Documentation: Fi... |
278 |
specified in bytes per second. Rules are per device. Following is |
2786c4e5e blkio: Documentat... |
279 |
the format. |
9b61fc4cf Documentation: fi... |
280 |
echo "<major>:<minor> <rate_bytes_per_second>" > /cgrp/blkio.throttle.read_bps_device |
2786c4e5e blkio: Documentat... |
281 282 283 |
- blkio.throttle.write_bps_device - Specifies upper limit on WRITE rate to the device. IO rate is |
40e47125e Documentation: Fi... |
284 |
specified in bytes per second. Rules are per device. Following is |
2786c4e5e blkio: Documentat... |
285 |
the format. |
9b61fc4cf Documentation: fi... |
286 |
echo "<major>:<minor> <rate_bytes_per_second>" > /cgrp/blkio.throttle.write_bps_device |
2786c4e5e blkio: Documentat... |
287 288 289 |
- blkio.throttle.read_iops_device - Specifies upper limit on READ rate from the device. IO rate is |
40e47125e Documentation: Fi... |
290 |
specified in IO per second. Rules are per device. Following is |
2786c4e5e blkio: Documentat... |
291 |
the format. |
9b61fc4cf Documentation: fi... |
292 |
echo "<major>:<minor> <rate_io_per_second>" > /cgrp/blkio.throttle.read_iops_device |
2786c4e5e blkio: Documentat... |
293 294 295 |
- blkio.throttle.write_iops_device - Specifies upper limit on WRITE rate to the device. IO rate is |
40e47125e Documentation: Fi... |
296 |
specified in io per second. Rules are per device. Following is |
2786c4e5e blkio: Documentat... |
297 |
the format. |
9b61fc4cf Documentation: fi... |
298 |
echo "<major>:<minor> <rate_io_per_second>" > /cgrp/blkio.throttle.write_iops_device |
2786c4e5e blkio: Documentat... |
299 300 |
Note: If both BW and IOPS rules are specified for a device, then IO is |
40e47125e Documentation: Fi... |
301 |
subjected to both the constraints. |
2786c4e5e blkio: Documentat... |
302 303 |
- blkio.throttle.io_serviced |
77ea73388 blkcg: move io_se... |
304 305 306 307 308 |
- Number of IOs (bio) issued to the disk by the group. These are further divided by the type of operation - read or write, sync or async. First two fields specify the major and minor number of the device, third field specifies the operation type and the fourth field specifies the number of IOs. |
2786c4e5e blkio: Documentat... |
309 310 311 312 313 314 315 |
- blkio.throttle.io_service_bytes - Number of bytes transferred to/from the disk by the group. These are further divided by the type of operation - read or write, sync or async. First two fields specify the major and minor number of the device, third field specifies the operation type and the fourth field specifies the number of bytes. |
2786c4e5e blkio: Documentat... |
316 317 |
Common files among various policies ----------------------------------- |
84c124da9 blkio: Changes to... |
318 319 320 |
- blkio.reset_stats - Writing an int to this file will result in resetting all the stats for that cgroup. |
72f924f62 blkio: Documentation |
321 322 |
CFQ sysfs tunable ================= |
6d6ac1c1a cfq-iosched: Docu... |
323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 |
/sys/block/<disk>/queue/iosched/slice_idle ------------------------------------------ On a faster hardware CFQ can be slow, especially with sequential workload. This happens because CFQ idles on a single queue and single queue might not drive deeper request queue depths to keep the storage busy. In such scenarios one can try setting slice_idle=0 and that would switch CFQ to IOPS (IO operations per second) mode on NCQ supporting hardware. That means CFQ will not idle between cfq queues of a cfq group and hence be able to driver higher queue depth and achieve better throughput. That also means that cfq provides fairness among groups in terms of IOPS and not in terms of disk time. /sys/block/<disk>/queue/iosched/group_idle ------------------------------------------ If one disables idling on individual cfq queues and cfq service trees by setting slice_idle=0, group_idle kicks in. That means CFQ will still idle on the group in an attempt to provide fairness among groups. By default group_idle is same as slice_idle and does not do anything if slice_idle is enabled. One can experience an overall throughput drop if you have created multiple groups and put applications in that group which are not driving enough IO to keep disk busy. In that case set group_idle=0, and CFQ will not idle on individual groups and throughput should improve. |