linux-kernel.vger.kernel.org archive mirror
 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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).