summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorYang Yang <yang.yang19@zte.com.cn>2023-04-08 17:28:35 +0800
committerAndrew Morton <akpm@linux-foundation.org>2023-04-18 16:39:34 -0700
commita3b2aeac9d154e5e15ddbf19de934c0c606b6acd (patch)
tree570fca8accf783e4fee4aba32c4263a4dde7116c
parent29692fc92c5b6a2c7cfe6f588ef68272e3343647 (diff)
delayacct: track delays from IRQ/SOFTIRQ
Delay accounting does not track the delay of IRQ/SOFTIRQ. While IRQ/SOFTIRQ could have obvious impact on some workloads productivity, such as when workloads are running on system which is busy handling network IRQ/SOFTIRQ. Get the delay of IRQ/SOFTIRQ could help users to reduce such delay. Such as setting interrupt affinity or task affinity, using kernel thread for NAPI etc. This is inspired by "sched/psi: Add PSI_IRQ to track IRQ/SOFTIRQ pressure"[1]. Also fix some code indent problems of older code. And update tools/accounting/getdelays.c: / # ./getdelays -p 156 -di print delayacct stats ON printing IO accounting PID 156 CPU count real total virtual total delay total delay average 15 15836008 16218149 275700790 18.380ms IO count delay total delay average 0 0 0.000ms SWAP count delay total delay average 0 0 0.000ms RECLAIM count delay total delay average 0 0 0.000ms THRASHING count delay total delay average 0 0 0.000ms COMPACT count delay total delay average 0 0 0.000ms WPCOPY count delay total delay average 36 7586118 0.211ms IRQ count delay total delay average 42 929161 0.022ms [1] commit 52b1364ba0b1("sched/psi: Add PSI_IRQ to track IRQ/SOFTIRQ pressure") Link: https://lkml.kernel.org/r/202304081728353557233@zte.com.cn Signed-off-by: Yang Yang <yang.yang29@zte.com.cn> Cc: Jiang Xuexin <jiang.xuexin@zte.com.cn> Cc: wangyong <wang.yong12@zte.com.cn> Cc: junhua huang <huang.junhua@zte.com.cn> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Juri Lelli <juri.lelli@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
-rw-r--r--Documentation/accounting/delay-accounting.rst7
-rw-r--r--include/linux/delayacct.h15
-rw-r--r--include/uapi/linux/taskstats.h6
-rw-r--r--kernel/delayacct.c14
-rw-r--r--kernel/sched/core.c1
-rw-r--r--tools/accounting/getdelays.c30
6 files changed, 58 insertions, 15 deletions
diff --git a/Documentation/accounting/delay-accounting.rst b/Documentation/accounting/delay-accounting.rst
index 79f537c9f160..f61c01fc376e 100644
--- a/Documentation/accounting/delay-accounting.rst
+++ b/Documentation/accounting/delay-accounting.rst
@@ -16,6 +16,7 @@ d) memory reclaim
e) thrashing
f) direct compact
g) write-protect copy
+h) IRQ/SOFTIRQ
and makes these statistics available to userspace through
the taskstats interface.
@@ -49,7 +50,7 @@ this structure. See
for a description of the fields pertaining to delay accounting.
It will generally be in the form of counters returning the cumulative
delay seen for cpu, sync block I/O, swapin, memory reclaim, thrash page
-cache, direct compact, write-protect copy etc.
+cache, direct compact, write-protect copy, IRQ/SOFTIRQ etc.
Taking the difference of two successive readings of a given
counter (say cpu_delay_total) for a task will give the delay
@@ -118,7 +119,9 @@ Get sum of delays, since system boot, for all pids with tgid 5::
0 0 0.000ms
COMPACT count delay total delay average
0 0 0.000ms
- WPCOPY count delay total delay average
+ WPCOPY count delay total delay average
+ 0 0 0.000ms
+ IRQ count delay total delay average
0 0 0.000ms
Get IO accounting for pid 1, it works only with -p::
diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h
index 0da97dba9ef8..6639f48dac36 100644
--- a/include/linux/delayacct.h
+++ b/include/linux/delayacct.h
@@ -48,10 +48,13 @@ struct task_delay_info {
u64 wpcopy_start;
u64 wpcopy_delay; /* wait for write-protect copy */
+ u64 irq_delay; /* wait for IRQ/SOFTIRQ */
+
u32 freepages_count; /* total count of memory reclaim */
u32 thrashing_count; /* total count of thrash waits */
u32 compact_count; /* total count of memory compact */
u32 wpcopy_count; /* total count of write-protect copy */
+ u32 irq_count; /* total count of IRQ/SOFTIRQ */
};
#endif
@@ -81,6 +84,7 @@ extern void __delayacct_compact_start(void);
extern void __delayacct_compact_end(void);
extern void __delayacct_wpcopy_start(void);
extern void __delayacct_wpcopy_end(void);
+extern void __delayacct_irq(struct task_struct *task, u32 delta);
static inline void delayacct_tsk_init(struct task_struct *tsk)
{
@@ -215,6 +219,15 @@ static inline void delayacct_wpcopy_end(void)
__delayacct_wpcopy_end();
}
+static inline void delayacct_irq(struct task_struct *task, u32 delta)
+{
+ if (!static_branch_unlikely(&delayacct_key))
+ return;
+
+ if (task->delays)
+ __delayacct_irq(task, delta);
+}
+
#else
static inline void delayacct_init(void)
{}
@@ -253,6 +266,8 @@ static inline void delayacct_wpcopy_start(void)
{}
static inline void delayacct_wpcopy_end(void)
{}
+static inline void delayacct_irq(struct task_struct *task, u32 delta)
+{}
#endif /* CONFIG_TASK_DELAY_ACCT */
diff --git a/include/uapi/linux/taskstats.h b/include/uapi/linux/taskstats.h
index a7f5b11a8f1b..b50b2eb257a0 100644
--- a/include/uapi/linux/taskstats.h
+++ b/include/uapi/linux/taskstats.h
@@ -34,7 +34,7 @@
*/
-#define TASKSTATS_VERSION 13
+#define TASKSTATS_VERSION 14
#define TS_COMM_LEN 32 /* should be >= TASK_COMM_LEN
* in linux/sched.h */
@@ -198,6 +198,10 @@ struct taskstats {
/* v13: Delay waiting for write-protect copy */
__u64 wpcopy_count;
__u64 wpcopy_delay_total;
+
+ /* v14: Delay waiting for IRQ/SOFTIRQ */
+ __u64 irq_count;
+ __u64 irq_delay_total;
};
diff --git a/kernel/delayacct.c b/kernel/delayacct.c
index e39cb696cfbd..6f0c358e73d8 100644
--- a/kernel/delayacct.c
+++ b/kernel/delayacct.c
@@ -179,12 +179,15 @@ int delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk)
d->compact_delay_total = (tmp < d->compact_delay_total) ? 0 : tmp;
tmp = d->wpcopy_delay_total + tsk->delays->wpcopy_delay;
d->wpcopy_delay_total = (tmp < d->wpcopy_delay_total) ? 0 : tmp;
+ tmp = d->irq_delay_total + tsk->delays->irq_delay;
+ d->irq_delay_total = (tmp < d->irq_delay_total) ? 0 : tmp;
d->blkio_count += tsk->delays->blkio_count;
d->swapin_count += tsk->delays->swapin_count;
d->freepages_count += tsk->delays->freepages_count;
d->thrashing_count += tsk->delays->thrashing_count;
d->compact_count += tsk->delays->compact_count;
d->wpcopy_count += tsk->delays->wpcopy_count;
+ d->irq_count += tsk->delays->irq_count;
raw_spin_unlock_irqrestore(&tsk->delays->lock, flags);
return 0;
@@ -274,3 +277,14 @@ void __delayacct_wpcopy_end(void)
&current->delays->wpcopy_delay,
&current->delays->wpcopy_count);
}
+
+void __delayacct_irq(struct task_struct *task, u32 delta)
+{
+ unsigned long flags;
+
+ raw_spin_lock_irqsave(&task->delays->lock, flags);
+ task->delays->irq_delay += delta;
+ task->delays->irq_count++;
+ raw_spin_unlock_irqrestore(&task->delays->lock, flags);
+}
+
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 0d18c3969f90..5473e831daf3 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -704,6 +704,7 @@ static void update_rq_clock_task(struct rq *rq, s64 delta)
rq->prev_irq_time += irq_delta;
delta -= irq_delta;
psi_account_irqtime(rq->curr, irq_delta);
+ delayacct_irq(rq->curr, irq_delta);
#endif
#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING
if (static_key_false((&paravirt_steal_rq_enabled))) {
diff --git a/tools/accounting/getdelays.c b/tools/accounting/getdelays.c
index 23a15d8f2bf4..1334214546d7 100644
--- a/tools/accounting/getdelays.c
+++ b/tools/accounting/getdelays.c
@@ -198,17 +198,19 @@ static void print_delayacct(struct taskstats *t)
printf("\n\nCPU %15s%15s%15s%15s%15s\n"
" %15llu%15llu%15llu%15llu%15.3fms\n"
"IO %15s%15s%15s\n"
- " %15llu%15llu%15.3fms\n"
+ " %15llu%15llu%15.3fms\n"
"SWAP %15s%15s%15s\n"
- " %15llu%15llu%15.3fms\n"
+ " %15llu%15llu%15.3fms\n"
"RECLAIM %12s%15s%15s\n"
- " %15llu%15llu%15.3fms\n"
+ " %15llu%15llu%15.3fms\n"
"THRASHING%12s%15s%15s\n"
- " %15llu%15llu%15.3fms\n"
+ " %15llu%15llu%15.3fms\n"
"COMPACT %12s%15s%15s\n"
- " %15llu%15llu%15.3fms\n"
+ " %15llu%15llu%15.3fms\n"
"WPCOPY %12s%15s%15s\n"
- " %15llu%15llu%15.3fms\n",
+ " %15llu%15llu%15.3fms\n"
+ "IRQ %15s%15s%15s\n"
+ " %15llu%15llu%15.3fms\n",
"count", "real total", "virtual total",
"delay total", "delay average",
(unsigned long long)t->cpu_count,
@@ -219,27 +221,31 @@ static void print_delayacct(struct taskstats *t)
"count", "delay total", "delay average",
(unsigned long long)t->blkio_count,
(unsigned long long)t->blkio_delay_total,
- average_ms((double)t->blkio_delay_total, t->blkio_count),
+ average_ms((double)t->blkio_delay_total, t->blkio_count),
"count", "delay total", "delay average",
(unsigned long long)t->swapin_count,
(unsigned long long)t->swapin_delay_total,
- average_ms((double)t->swapin_delay_total, t->swapin_count),
+ average_ms((double)t->swapin_delay_total, t->swapin_count),
"count", "delay total", "delay average",
(unsigned long long)t->freepages_count,
(unsigned long long)t->freepages_delay_total,
- average_ms((double)t->freepages_delay_total, t->freepages_count),
+ average_ms((double)t->freepages_delay_total, t->freepages_count),
"count", "delay total", "delay average",
(unsigned long long)t->thrashing_count,
(unsigned long long)t->thrashing_delay_total,
- average_ms((double)t->thrashing_delay_total, t->thrashing_count),
+ average_ms((double)t->thrashing_delay_total, t->thrashing_count),
"count", "delay total", "delay average",
(unsigned long long)t->compact_count,
(unsigned long long)t->compact_delay_total,
- average_ms((double)t->compact_delay_total, t->compact_count),
+ average_ms((double)t->compact_delay_total, t->compact_count),
"count", "delay total", "delay average",
(unsigned long long)t->wpcopy_count,
(unsigned long long)t->wpcopy_delay_total,
- average_ms((double)t->wpcopy_delay_total, t->wpcopy_count));
+ average_ms((double)t->wpcopy_delay_total, t->wpcopy_count),
+ "count", "delay total", "delay average",
+ (unsigned long long)t->irq_count,
+ (unsigned long long)t->irq_delay_total,
+ average_ms((double)t->irq_delay_total, t->irq_count));
}
static void task_context_switch_counts(struct taskstats *t)