Hi Steven! Sorry to bother you ;)
(I resend this email because the last one was not cc to mailing list.)
It has been ten days since my last email. What's your opinion about my
patch "[PATCH 3/3] mm: mmap_lock: add ip to mmap_lock tracepoints"?
Briefly, lock events are so frequent that ip collection and lock event
collection cannot be separated, otherwise it will cause the wrong order
of data.
I am developing a tool to analyze mmap_lock contend using this feature.
Adding ip to mmap_lock tracepoints is quite convenient.
Sorry to bother you again. Hoping for your reply. Thanks!
-- Gang
On 8/20/21 2:18 AM, Gang Li wrote:
> On 8/2/21 10:44 AM, Gang Li wrote:
>> On 7/31/21 4:03 AM, Steven Rostedt wrote:
>>> Yes, synthetic events are just like normal events, and have triggers,
>>> stack traces, and do pretty much anything that another event can do.
>>>
> Hi!
>
> I find that sometimes the output data is out of order, which leads to
inaccurate time stamps and make it hard to analyze.
