Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]


Groups > linux.kernel > #1588432

Re: [tip:perf/urgent] perf/core: Fix the perf_cpu_time_max_percent check

From Tan Xiaojun <tanxiaojun@huawei.com>
Newsgroups linux.kernel
Subject Re: [tip:perf/urgent] perf/core: Fix the perf_cpu_time_max_percent check
Date 2017-02-27 01:50 +0100
Message-ID <tfhFM-675-5@gated-at.bofh.it> (permalink)
References <tdUBz-5jM-5@gated-at.bofh.it> <tekcG-6wz-31@gated-at.bofh.it> <teFKa-4VJ-19@gated-at.bofh.it> <teHiW-5T6-5@gated-at.bofh.it>
Organization linux.* mail to news gateway

Show all headers | View raw


On 2017/2/25 17:51, Peter Zijlstra wrote:
> On Sat, Feb 25, 2017 at 04:10:37PM +0800, Tan Xiaojun wrote:
> 
>> Recently I was using perf_fuzzer for testing in Hisilicon
>> D03/D05(arm64, linux-4.10-rc1).
>>
>> As we know perf_fuzzer will write a random value to procfs interface
>> of perf event(like sysctl_perf_cpu_time_max_percent). The value may be
>> 0 or 100, and I get logs like below:
>>
>> ----------------------------------
>> [ 4046.358811] perf: Dynamic interrupt throttling disabled, can hang your system!
>> ----------------------------------
>>
>> Most of the time, there is no problem, and the perf_fuzzer test can
>> end without any warings or errors.  But there is a small probability
>> that triggers the RCU and watchdog (The log is attached at the end).
>> It hungs after local_irq_enable() in __do_softirq.
>>
>> I think this is due to the dynamic interrupt throttling disabled and
>> too many hardware interruptions come. So I limit the
>> sysctl_perf_cpu_time_max_percent can only be set 1 to 99 in the kernel
>> codes. I test more than 20 times in D03, and there are no errors or
>> warnings in the test.
>>
>> So I want to ask:
>>
>> 1)Is it a problem or not? (It has already given you a warning.)
>>
>> 2)If it is, where we will fix it more appropriate, perf_fuzzer(not set
>> 0 or 100) or kernel(limit 1 to 99), or maybe it is the bug of
>> hardware(too many hardware interruptions)?
> 
> I think the best would be if the fuzzer would not set 0,100, those are
> clearly 'unsafe' settings and you pretty much get to keep the pieces.
> 
> I would like to preserve these settings for people that 'know' what
> they're doing and are willing to take the risk, but clearly, when you
> take the guard-rails off, things can come apart.
> 

OK. It makes sense, I agree.

Thank you for your answer.
Xiaojun.

> .
> 

Back to linux.kernel | Previous | NextPrevious in thread | Find similar | Unroll thread


Thread

[PATCH] perf/core: Fix to check perf_cpu_time_max_percent Tan Xiaojun <tanxiaojun@huawei.com> - 2017-02-23 07:00 +0100
  [tip:perf/urgent] perf/core: Fix the perf_cpu_time_max_percent  check tip-bot for Tan Xiaojun <tipbot@zytor.com> - 2017-02-24 10:20 +0100
    Re: [tip:perf/urgent] perf/core: Fix the perf_cpu_time_max_percent  check Tan Xiaojun <tanxiaojun@huawei.com> - 2017-02-25 09:20 +0100
      Re: [tip:perf/urgent] perf/core: Fix the perf_cpu_time_max_percent  check Peter Zijlstra <peterz@infradead.org> - 2017-02-25 11:00 +0100
        Re: [tip:perf/urgent] perf/core: Fix the perf_cpu_time_max_percent  check Tan Xiaojun <tanxiaojun@huawei.com> - 2017-02-27 01:50 +0100

csiph-web