linux/kernel/latencytop.c

3  * latencytop.c: Latency display infrastructure
10  * CONFIG_LATENCYTOP enables a kernel latency tracking infrastructure that is
11  * used by the "latencytop" userspace tool. The latency that is tracked is not
12  * the 'traditional' interrupt latency (which is primarily caused by something
13  * else consuming CPU), but instead, it is the latency an application encounters
17  * 1) System level latency
18  * 2) Per process latency
20  * The latency is stored in fixed sized data structures in an accumulated form;
21  * if the "same" latency cause is hit twice, this will be tracked as one entry
22  * in the data structure. Both the count, total accumulated latency and maximum
23  * latency are tracked in this data structure. When the fixed size structure is
27  * A latency cause is identified by a stringified backtrace at the point that
29  * identify the cause of the latency in human readable form.
31  * The information is exported via /proc/latency_stats and /proc/<pid>/latency.
34  * Latency Top version : v0.1
38  * |    |    +---------> The maximum latency for this entry in microseconds
39  * |    +--------------> The accumulated latency for this entry (microseconds)
42  * (note: the average latency is the accumulated latency divided by the number
161  * __account_scheduler_latency - record an occurred latency
162  * @tsk - the task struct of the task hitting the latency
163  * @usecs - the duration of the latency in microseconds
166  * This function is the main entry point for recording latency entries
169  * This function has a few special cases to deal with normal 'non-latency'
247 	seq_puts(m, "Latency Top version : v0.1\n");  in lstats_show()