| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <1324337005-31718-3-git-send-email-asharma@fb.com>
Date: Mon, 19 Dec 2011 15:23:25 -0800
From: Arun Sharma <asharma@...com>
To: linux-kernel@...r.kernel.org
Cc: Arun Sharma <asharma@...com>,
Peter Zijlstra <a.p.zijlstra@...llo.nl>,
Steven Rostedt <rostedt@...dmis.org>,
Mathieu Desnoyers <mathieu.desnoyers@...icios.com>,
Arnaldo Carvalho de Melo <acme@...radead.org>,
Andrew Vagin <avagin@...nvz.org>,
Frederic Weisbecker <fweisbec@...il.com>,
Ingo Molnar <mingo@...e.hu>
Subject: [PATCH 2/2] tracing, sched: Add delay info to sched_switch
If CONFIG_SCHEDSTATS is defined, the kernel maintains
information about how long the task was sleeping or
in the case of iowait, blocking in the kernel before
getting woken up.
Note: this information is only provided for sched_fair.
Other scheduling classes may choose to provide this in
the future.
Note: the delay includes the time spent on the runqueue
as well.
Signed-off-by: Arun Sharma <asharma@...com>
Cc: Peter Zijlstra <a.p.zijlstra@...llo.nl>
Cc: Steven Rostedt <rostedt@...dmis.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@...icios.com>
Cc: Arnaldo Carvalho de Melo <acme@...radead.org>
Cc: Andrew Vagin <avagin@...nvz.org>
Cc: Frederic Weisbecker <fweisbec@...il.com>
Cc: Ingo Molnar <mingo@...e.hu>
Cc: linux-kernel@...r.kernel.org
---
include/trace/events/sched.h | 21 +++++++++++++++++----
kernel/sched_fair.c | 6 ++++--
kernel/trace/trace_sched_switch.c | 2 +-
3 files changed, 22 insertions(+), 7 deletions(-)
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index 959ff18..830784b 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -113,9 +113,10 @@ static inline long __trace_sched_switch_state(struct task_struct *p)
TRACE_EVENT(sched_switch,
TP_PROTO(struct task_struct *prev,
- struct task_struct *next),
+ struct task_struct *next,
+ unsigned long now),
- TP_ARGS(prev, next),
+ TP_ARGS(prev, next, now),
TP_STRUCT__entry(
__array( char, prev_comm, TASK_COMM_LEN )
@@ -125,6 +126,7 @@ TRACE_EVENT(sched_switch,
__array( char, next_comm, TASK_COMM_LEN )
__field( pid_t, next_pid )
__field( int, next_prio )
+ __field( long, delay )
),
TP_fast_assign(
@@ -135,9 +137,20 @@ TRACE_EVENT(sched_switch,
memcpy(__entry->prev_comm, prev->comm, TASK_COMM_LEN);
__entry->next_pid = next->pid;
__entry->next_prio = next->prio;
+#ifdef CONFIG_SCHEDSTATS
+ __entry->delay = next->se.statistics.block_start ? next->se.statistics.block_start
+ : next->se.statistics.sleep_start ? next->se.statistics.sleep_start : 0;
+ __entry->delay = __entry->delay ? now - __entry->delay : 0;
+#else
+ __entry->delay = 0;
+#endif
+ )
+
+ TP_perf_assign(
+ __perf_count(__entry->delay);
),
- TP_printk("prev_comm=%s prev_pid=%d prev_prio=%d prev_state=%s%s ==> next_comm=%s next_pid=%d next_prio=%d",
+ TP_printk("prev_comm=%s prev_pid=%d prev_prio=%d prev_state=%s%s ==> next_comm=%s next_pid=%d next_prio=%d delay=%ld",
__entry->prev_comm, __entry->prev_pid, __entry->prev_prio,
__entry->prev_state & (TASK_STATE_MAX-1) ?
__print_flags(__entry->prev_state & (TASK_STATE_MAX-1), "|",
@@ -145,7 +158,7 @@ TRACE_EVENT(sched_switch,
{ 16, "Z" }, { 32, "X" }, { 64, "x" },
{ 128, "W" }) : "R",
__entry->prev_state & TASK_STATE_MAX ? "+" : "",
- __entry->next_comm, __entry->next_pid, __entry->next_prio)
+ __entry->next_comm, __entry->next_pid, __entry->next_prio, __entry->delay)
);
/*
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 8a39fa3..b51a613 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -893,7 +893,6 @@ static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
if (unlikely(delta > se->statistics.sleep_max))
se->statistics.sleep_max = delta;
- se->statistics.sleep_start = 0;
se->statistics.sum_sleep_runtime += delta;
if (tsk) {
@@ -910,7 +909,6 @@ static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
if (unlikely(delta > se->statistics.block_max))
se->statistics.block_max = delta;
- se->statistics.block_start = 0;
se->statistics.sum_sleep_runtime += delta;
if (tsk) {
@@ -1083,8 +1081,12 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
if (tsk->state & TASK_INTERRUPTIBLE)
se->statistics.sleep_start = rq_of(cfs_rq)->clock;
+ else
+ se->statistics.sleep_start = 0;
if (tsk->state & TASK_UNINTERRUPTIBLE)
se->statistics.block_start = rq_of(cfs_rq)->clock;
+ else
+ se->statistics.block_start = 0;
}
#endif
}
diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c
index 7e62c0a..b8b98d4 100644
--- a/kernel/trace/trace_sched_switch.c
+++ b/kernel/trace/trace_sched_switch.c
@@ -50,7 +50,7 @@ tracing_sched_switch_trace(struct trace_array *tr,
}
static void
-probe_sched_switch(void *ignore, struct task_struct *prev, struct task_struct *next)
+probe_sched_switch(void *ignore, struct task_struct *prev, struct task_struct *next, unsigned long now)
{
struct trace_array_cpu *data;
unsigned long flags;
--
1.7.4
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists