5 Control Groupstats is inspired by the discussion at
6 http://lkml.org/lkml/2007/4/11/187 and implements per cgroup statistics as
7 suggested by Andrew Morton in http://lkml.org/lkml/2007/4/11/263.
9 Per cgroup statistics infrastructure re-uses code from the taskstats
10 interface. A new set of cgroup operations are registered with commands
11 and attributes specific to cgroups. It should be very easy to
12 extend per cgroup statistics, by adding members to the cgroupstats
15 The current model for cgroupstats is a pull, a push model (to post
16 statistics on interesting events), should be very easy to add. Currently
17 user space requests for statistics by passing the cgroup path.
18 Statistics about the state of all the tasks in the cgroup is returned to
21 NOTE: We currently rely on delay accounting for extracting information
22 about tasks blocked on I/O. If CONFIG_TASK_DELAY_ACCT is disabled, this
23 information will not be available.
25 To extract cgroup statistics a utility very similar to getdelays.c
26 has been developed, the sample output of the utility is shown below::
28 ~/balbir/cgroupstats # ./getdelays -C "/sys/fs/cgroup/a"
29 sleeping 1, blocked 0, running 1, stopped 0, uninterruptible 0
30 ~/balbir/cgroupstats # ./getdelays -C "/sys/fs/cgroup"
31 sleeping 155, blocked 0, running 1, stopped 0, uninterruptible 2