[PATCH] sched: split sched_switch trace event into two

From: Cong Wang
Date: Wed Jun 24 2015 - 19:19:48 EST


Currently we only have one sched_switch trace event
for task switching, which is generated very early during
task switch. When we try to monitor per-container events,
this is not what we expect.

For example, we have a process A which is in the cgroup
we monitor, and process B which isn't, when kernel switches
from B to A, the sched_switch event is not recorded for this
cgroup since it belongs to B (current process is still B
util we finish the switch), but we require this event to
signal that process A in this cgroup gets scheduled. This is
crucial for calculating schedule latency.

So split the sched_switch event into two: sched_in event
before we perform the switch, and sched_out event after we
perform the switch.

For compatibility, the sched_switch event is not touched.

Cc: Steven Rostedt <rostedt@xxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Signed-off-by: Cong Wang <xiyou.wangcong@xxxxxxxxx>
Signed-off-by: Cong Wang <cwang@xxxxxxxxxxxxxxxx>
---
include/trace/events/sched.h | 51 +++++++++++++++++++++++++++++++++++++++++++-
kernel/sched/core.c | 2 ++
2 files changed, 52 insertions(+), 1 deletion(-)

diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index d57a575..c31f1e0 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -112,8 +112,57 @@ static inline long __trace_sched_switch_state(struct task_struct *p)
#endif /* CREATE_TRACE_POINTS */

/*
- * Tracepoint for task switches, performed by the scheduler:
+ * Tracepoints for task switches, performed by the scheduler:
*/
+TRACE_EVENT(sched_out,
+
+ TP_PROTO(struct task_struct *curr),
+
+ TP_ARGS(curr),
+
+ TP_STRUCT__entry(
+ __array( char, comm, TASK_COMM_LEN )
+ __field( int, prio )
+ __field( long, state )
+ ),
+
+ TP_fast_assign(
+ __entry->prio = curr->prio;
+ __entry->state = __trace_sched_switch_state(curr);
+ memcpy(__entry->comm, curr->comm, TASK_COMM_LEN);
+ ),
+
+ TP_printk("comm=%s prio=%d state=%s%s",
+ __entry->comm, __entry->prio,
+ __entry->state & (TASK_STATE_MAX-1) ?
+ __print_flags(__entry->state & (TASK_STATE_MAX-1), "|",
+ { 1, "S"} , { 2, "D" }, { 4, "T" }, { 8, "t" },
+ { 16, "Z" }, { 32, "X" }, { 64, "x" },
+ { 128, "K" }, { 256, "W" }, { 512, "P" },
+ { 1024, "N" }) : "R",
+ __entry->state & TASK_STATE_MAX ? "+" : "")
+);
+
+TRACE_EVENT(sched_in,
+
+ TP_PROTO(struct task_struct *next),
+
+ TP_ARGS(next),
+
+ TP_STRUCT__entry(
+ __array( char, comm, TASK_COMM_LEN )
+ __field( int, prio )
+ ),
+
+ TP_fast_assign(
+ memcpy(__entry->comm, next->comm, TASK_COMM_LEN);
+ __entry->prio = next->prio;
+ ),
+
+ TP_printk("comm=%s prio=%d",
+ __entry->comm, __entry->prio)
+);
+
TRACE_EVENT(sched_switch,

TP_PROTO(struct task_struct *prev,
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index c86935a..681fc50 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2219,6 +2219,7 @@ prepare_task_switch(struct rq *rq, struct task_struct *prev,
struct task_struct *next)
{
trace_sched_switch(prev, next);
+ trace_sched_out(prev);
sched_info_switch(rq, prev, next);
perf_event_task_sched_out(prev, next);
fire_sched_out_preempt_notifiers(prev, next);
@@ -2288,6 +2289,7 @@ static struct rq *finish_task_switch(struct task_struct *prev)
}

tick_nohz_task_switch(current);
+ trace_sched_in(current);
return rq;
}

--
1.8.3.1

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/