All of lore.kernel.org
 help / color / mirror / Atom feed
From: Steven Rostedt <rostedt@goodmis.org>
To: linux-kernel@vger.kernel.org
Cc: Ingo Molnar <mingo@kernel.org>,
	Andrew Morton <akpm@linux-foundation.org>,
	Song Chen <chensong_2000@189.cn>
Subject: [for-next][PATCH 15/15] kernel: trace: preemptirq_delay_test: add cpu affinity
Date: Wed, 03 Feb 2021 11:05:32 -0500	[thread overview]
Message-ID: <20210203160550.868939346@goodmis.org> (raw)
In-Reply-To: 20210203160517.982448432@goodmis.org

From: Song Chen <chensong_2000@189.cn>

The kernel thread executing test can run on any cpu, which might be
different cpu latency tracer is running on, as a result, the
big latency caused by preemptirq delay test can't be detected.

Therefore, the argument cpu_affinity is added to be passed to test,
ensure it's running on the same cpu with latency tracer.

e.g.
cyclictest -p 90 -m -c 0 -i 1000 -a 3
modprobe preemptirq_delay_test test_mode=preempt delay=500 \
burst_size=3 cpu_affinity=3

Link: https://lkml.kernel.org/r/1611797713-20965-1-git-send-email-chensong_2000@189.cn

Signed-off-by: Song Chen <chensong_2000@189.cn>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/Kconfig                 |  4 ++++
 kernel/trace/preemptirq_delay_test.c | 14 ++++++++++++++
 2 files changed, 18 insertions(+)

diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 4f976f8d9a38..799dbcfe65ad 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -886,6 +886,10 @@ config PREEMPTIRQ_DELAY_TEST
 	  irq-disabled critical sections for 500us:
 	  modprobe preemptirq_delay_test test_mode=irq delay=500 burst_size=3
 
+	  What's more, if you want to attach the test on the cpu which the latency
+	  tracer is running on, specify cpu_affinity=cpu_num at the end of the
+	  command.
+
 	  If unsure, say N
 
 config SYNTH_EVENT_GEN_TEST
diff --git a/kernel/trace/preemptirq_delay_test.c b/kernel/trace/preemptirq_delay_test.c
index 312d1a0ca3b6..8c4ffd076162 100644
--- a/kernel/trace/preemptirq_delay_test.c
+++ b/kernel/trace/preemptirq_delay_test.c
@@ -21,13 +21,16 @@
 static ulong delay = 100;
 static char test_mode[12] = "irq";
 static uint burst_size = 1;
+static int  cpu_affinity = -1;
 
 module_param_named(delay, delay, ulong, 0444);
 module_param_string(test_mode, test_mode, 12, 0444);
 module_param_named(burst_size, burst_size, uint, 0444);
+module_param_named(cpu_affinity, cpu_affinity, int, 0444);
 MODULE_PARM_DESC(delay, "Period in microseconds (100 us default)");
 MODULE_PARM_DESC(test_mode, "Mode of the test such as preempt, irq, or alternate (default irq)");
 MODULE_PARM_DESC(burst_size, "The size of a burst (default 1)");
+MODULE_PARM_DESC(cpu_affinity, "Cpu num test is running on");
 
 static struct completion done;
 
@@ -36,7 +39,9 @@ static struct completion done;
 static void busy_wait(ulong time)
 {
 	u64 start, end;
+
 	start = trace_clock_local();
+
 	do {
 		end = trace_clock_local();
 		if (kthread_should_stop())
@@ -47,6 +52,7 @@ static void busy_wait(ulong time)
 static __always_inline void irqoff_test(void)
 {
 	unsigned long flags;
+
 	local_irq_save(flags);
 	busy_wait(delay);
 	local_irq_restore(flags);
@@ -113,6 +119,14 @@ static int preemptirq_delay_run(void *data)
 {
 	int i;
 	int s = MIN(burst_size, NR_TEST_FUNCS);
+	struct cpumask cpu_mask;
+
+	if (cpu_affinity > -1) {
+		cpumask_clear(&cpu_mask);
+		cpumask_set_cpu(cpu_affinity, &cpu_mask);
+		if (set_cpus_allowed_ptr(current, &cpu_mask))
+			pr_err("cpu_affinity:%d, failed\n", cpu_affinity);
+	}
 
 	for (i = 0; i < s; i++)
 		(testfuncs[i])(i);
-- 
2.29.2



      parent reply	other threads:[~2021-02-03 16:10 UTC|newest]

Thread overview: 22+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-02-03 16:05 [for-next][PATCH 00/15] tracing: Updates for 5.12 Steven Rostedt
2021-02-03 16:05 ` [for-next][PATCH 01/15] tracing: Add printf attribute to log function Steven Rostedt
2021-02-03 16:05 ` [for-next][PATCH 02/15] tracing: Update trace_ignore_this_task() kernel-doc comment Steven Rostedt
2021-02-03 16:05 ` [for-next][PATCH 03/15] tracing: Remove get/put_cpu() from function_trace_init Steven Rostedt
2021-02-03 16:05 ` [for-next][PATCH 04/15] ring-buffer: Remove cpu_buffer argument from the rb_inc_page() Steven Rostedt
2021-02-03 16:05 ` [for-next][PATCH 05/15] ring-buffer: Drop unneeded check in ring_buffer_resize() Steven Rostedt
2021-02-03 16:05 ` [for-next][PATCH 07/15] tracing: Inline tracing_gen_ctx_flags() Steven Rostedt
2021-02-03 16:05 ` [for-next][PATCH 08/15] tracing: Use in_serving_softirq() to deduct softirq status Steven Rostedt
2021-02-03 16:05 ` [for-next][PATCH 09/15] tracing: Remove NULL check from current in tracing_generic_entry_update() Steven Rostedt
2021-02-03 16:05 ` [for-next][PATCH 10/15] tracing: Fix spelling mistake in Kconfig "infinit" -> "infinite" Steven Rostedt
2021-02-03 16:05 ` [for-next][PATCH 11/15] tracing: Fix spelling of controlling in uprobes Steven Rostedt
2021-02-03 16:05 ` [for-next][PATCH 12/15] tracing: Fix a kernel doc warning Steven Rostedt
2021-02-03 16:05 ` [for-next][PATCH 13/15] tracing: Remove definition of DEBUG in trace_mmiotrace.c Steven Rostedt
2021-02-03 16:05 ` [for-next][PATCH 14/15] tracepoint: Do not fail unregistering a probe due to memory failure Steven Rostedt
2021-02-03 17:05   ` Peter Zijlstra
2021-02-03 17:09   ` Peter Zijlstra
2021-02-03 17:23     ` Steven Rostedt
2021-02-03 17:57   ` Mathieu Desnoyers
2021-02-04 16:50     ` Steven Rostedt
2021-02-03 17:57   ` [PATCH 1/1] tracepoint: cleanup: do not fail unregistration Mathieu Desnoyers
2021-02-04 17:47     ` Steven Rostedt
2021-02-03 16:05 ` Steven Rostedt [this message]

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20210203160550.868939346@goodmis.org \
    --to=rostedt@goodmis.org \
    --cc=akpm@linux-foundation.org \
    --cc=chensong_2000@189.cn \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.