5 Tasks encounter delays in execution when they wait
6 for some kernel resource to become available e.g. a
7 runnable task may wait for a free CPU to run on.
9 The per-task delay accounting functionality measures
10 the delays experienced by a task while
12 a) waiting for a CPU (while being runnable)
13 b) completion of synchronous block I/O initiated by the task
17 and makes these statistics available to userspace through
18 the taskstats interface.
20 Such delays provide feedback for setting a task's cpu priority,
21 io priority and rss limit values appropriately. Long delays for
22 important tasks could be a trigger for raising its corresponding priority.
24 The functionality, through its use of the taskstats interface, also provides
25 delay statistics aggregated for all tasks (or threads) belonging to a
26 thread group (corresponding to a traditional Unix process). This is a commonly
27 needed aggregation that is more efficiently done by the kernel.
29 Userspace utilities, particularly resource management applications, can also
30 aggregate delay statistics into arbitrary groups. To enable this, delay
31 statistics of a task are available both during its lifetime as well as on its
32 exit, ensuring continuous and complete monitoring can be done.
38 Delay accounting uses the taskstats interface which is described
39 in detail in a separate document in this directory. Taskstats returns a
40 generic data structure to userspace corresponding to per-pid and per-tgid
41 statistics. The delay accounting functionality populates specific fields of
44 include/linux/taskstats.h
46 for a description of the fields pertaining to delay accounting.
47 It will generally be in the form of counters returning the cumulative
48 delay seen for cpu, sync block I/O, swapin, memory reclaim etc.
50 Taking the difference of two successive readings of a given
51 counter (say cpu_delay_total) for a task will give the delay
52 experienced by the task waiting for the corresponding resource
55 When a task exits, records containing the per-task statistics
56 are sent to userspace without requiring a command. If it is the last exiting
57 task of a thread group, the per-tgid statistics are also sent. More details
58 are given in the taskstats interface description.
60 The getdelays.c userspace utility in tools/accounting directory allows simple
61 commands to be run and the corresponding delay statistics to be displayed. It
62 also serves as an example of using the taskstats interface.
67 Compile the kernel with::
69 CONFIG_TASK_DELAY_ACCT=y
72 Delay accounting is enabled by default at boot up.
77 to the kernel boot options. The rest of the instructions
78 below assume this has not been done.
80 After the system has booted up, use a utility
81 similar to getdelays.c to access the delays
82 seen by a given task or a task group (tgid).
83 The utility also allows a given command to be
84 executed and the corresponding delays to be
87 General format of the getdelays command::
89 getdelays [-t tgid] [-p pid] [-c cmd...]
92 Get delays, since system boot, for pid 10::
95 (output similar to next case)
97 Get sum of delays, since system boot, for all pids with tgid 5::
102 CPU count real total virtual total delay total
103 7876 92005750 100000000 24001500
106 SWAP count delay total
108 RECLAIM count delay total
111 Get delays seen in executing a given simple command::
113 # ./getdelays -c ls /
115 bin data1 data3 data5 dev home media opt root srv sys usr
116 boot data2 data4 data6 etc lib mnt proc sbin subdomain tmp var
119 CPU count real total virtual total delay total
123 SWAP count delay total
125 RECLAIM count delay total