From: Steven Rostedt <rostedt@goodmis.org>
To: linux-kernel@vger.kernel.org
Cc: Ingo Molnar <mingo@kernel.org>,
Andrew Morton <akpm@linux-foundation.org>,
Chris Wilson <chris@chris-wilson.co.uk>
Subject: [for-next][PATCH 03/18] tracing: Default to using trace_global_clock if sched_clock is unstable
Date: Fri, 06 Apr 2018 09:00:38 -0400 [thread overview]
Message-ID: <20180406130112.118951478@goodmis.org> (raw)
In-Reply-To: 20180406130035.400292196@goodmis.org
[-- Attachment #1: 0003-tracing-Default-to-using-trace_global_clock-if-sched.patch --]
[-- Type: text/plain, Size: 2076 bytes --]
From: Chris Wilson <chris@chris-wilson.co.uk>
Across suspend, we may see a very large drift in timestamps if the sched
clock is unstable, prompting the global trace's ringbuffer code to warn
and suggest switching to the global clock. Preempt this request by
detecting when the sched clock is unstable (determined during
late_initcall) and automatically switching the default clock over to
trace_global_clock.
This should prevent requiring user interaction to resolve warnings such
as:
Delta way too big! 18446743856563626466 ts=18446744054496180323 write stamp = 197932553857
If you just came from a suspend/resume,
please switch to the trace global clock:
echo global > /sys/kernel/debug/tracing/trace_clock
Link: http://lkml.kernel.org/r/20180330150132.16903-1-chris@chris-wilson.co.uk
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
kernel/trace/trace.c | 19 +++++++++++++++++++
1 file changed, 19 insertions(+)
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 551a7cd0d705..0f47e653ffd8 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -41,6 +41,7 @@
#include <linux/nmi.h>
#include <linux/fs.h>
#include <linux/trace.h>
+#include <linux/sched/clock.h>
#include <linux/sched/rt.h>
#include "trace.h"
@@ -8596,3 +8597,21 @@ __init static int clear_boot_tracer(void)
fs_initcall(tracer_init_tracefs);
late_initcall_sync(clear_boot_tracer);
+
+#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
+__init static int tracing_set_default_clock(void)
+{
+ /* sched_clock_stable() is determined in late_initcall */
+ if (trace_boot_clock || sched_clock_stable()) {
+ printk(KERN_WARNING
+ "Unstable clock detected, switching default tracing clock to \"global\"\n"
+ "If you want to keep using the local clock, then add:\n"
+ " \"trace_clock=local\"\n"
+ "on the kernel command line\n");
+ tracing_set_clock(&global_trace, "global");
+ }
+
+ return 0;
+}
+late_initcall_sync(tracing_set_default_clock);
+#endif
--
2.15.1
next prev parent reply other threads:[~2018-04-06 13:05 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-04-06 13:00 [for-next][PATCH 00/18] tracing: Last minute updates before pushing to Linus Steven Rostedt
2018-04-06 13:00 ` [for-next][PATCH 01/18] tracing: Fix a potential NULL dereference Steven Rostedt
2018-04-06 13:00 ` [for-next][PATCH 02/18] init: Fix initcall0 name as it is "pure" not "early" Steven Rostedt
2018-04-06 13:00 ` Steven Rostedt [this message]
2018-04-06 13:00 ` [for-next][PATCH 04/18] tracing: Mention trace_clock=global when warning about unstable clocks Steven Rostedt
2018-04-06 13:00 ` [for-next][PATCH 05/18] ftrace: Drop a VLA in module_exists() Steven Rostedt
2018-04-06 13:00 ` [for-next][PATCH 06/18] tracing: Fix display of hist trigger expressions containing timestamps Steven Rostedt
2018-04-06 13:00 ` [for-next][PATCH 07/18] tracing: Dont add flag strings when displaying variable references Steven Rostedt
2018-04-06 13:00 ` [for-next][PATCH 08/18] tracing: Add action comparisons when testing matching hist triggers Steven Rostedt
2018-04-06 13:00 ` [for-next][PATCH 09/18] tracing: Make sure variable string fields are NULL-terminated Steven Rostedt
2018-04-06 13:00 ` [for-next][PATCH 10/18] tracing: Uninitialized variable in create_tracing_map_fields() Steven Rostedt
2018-04-06 13:00 ` [for-next][PATCH 11/18] vsprintf: Do not preprocess non-dereferenced pointers for bprintf (%px and %pK) Steven Rostedt
2018-04-06 13:00 ` [for-next][PATCH 12/18] lockdep: Add print_irqtrace_events() to __warn Steven Rostedt
2018-04-06 13:00 ` [for-next][PATCH 13/18] ring-buffer: Check if memory is available before allocation Steven Rostedt
2018-04-06 13:00 ` [for-next][PATCH 14/18] ring-buffer: Add set/clear_current_oom_origin() during allocations Steven Rostedt
2018-04-06 13:00 ` [for-next][PATCH 15/18] tracing: Hide global trace clock from lockdep Steven Rostedt
2018-04-06 13:00 ` [for-next][PATCH 16/18] tracing: Fixup logic inversion on setting trace_global_clock defaults Steven Rostedt
2018-04-06 13:00 ` [for-next][PATCH 17/18] tracing: Add rcu dereference annotation for filter->prog Steven Rostedt
2018-04-06 13:00 ` [for-next][PATCH 18/18] tracing: Add rcu dereference annotation for test func that touches filter->prog Steven Rostedt
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=20180406130112.118951478@goodmis.org \
--to=rostedt@goodmis.org \
--cc=akpm@linux-foundation.org \
--cc=chris@chris-wilson.co.uk \
--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