summaryrefslogtreecommitdiffstats
path: root/ipc
diff options
context:
space:
mode:
authorShaohua Li <shli@fb.com>2017-03-27 15:19:43 -0700
committerJens Axboe <axboe@fb.com>2017-03-28 08:02:20 -0600
commit53696b8d212f4a0f0e5dcdb3df64558dcdf03d1a (patch)
tree843090a882b03bbaa9731b1bab546be79f7a79c5 /ipc
parentb9147dd1bae2b15d6931ecd42f8606c775fecbc9 (diff)
downloadlinux-53696b8d212f4a0f0e5dcdb3df64558dcdf03d1a.tar.gz
linux-53696b8d212f4a0f0e5dcdb3df64558dcdf03d1a.tar.bz2
linux-53696b8d212f4a0f0e5dcdb3df64558dcdf03d1a.zip
blk-throttle: add latency target support
One hard problem adding .low limit is to detect idle cgroup. If one cgroup doesn't dispatch enough IO against its low limit, we must have a mechanism to determine if other cgroups dispatch more IO. We added the think time detection mechanism before, but it doesn't work for all workloads. Here we add a latency based approach. We already have mechanism to calculate latency threshold for each IO size. For every IO dispatched from a cgorup, we compare its latency against its threshold and record the info. If most IO latency is below threshold (in the code I use 75%), the cgroup could be treated idle and other cgroups can dispatch more IO. Currently this latency target check is only for SSD as we can't calcualte the latency target for hard disk. And this is only for cgroup leaf node so far. Signed-off-by: Shaohua Li <shli@fb.com> Signed-off-by: Jens Axboe <axboe@fb.com>
Diffstat (limited to 'ipc')
0 files changed, 0 insertions, 0 deletions