Re: [PATCH] Fix slow and non-deterministic behavior of isspace() and tolower()

[Pedro Alves <palves@redhat.com>]

On 6/21/19 9:30 PM, Shawn Landden wrote:
> On Fri, Jun 21, 2019 at 3:12 PM Pedro Alves <palves@redhat.com> wrote:
>> On 6/21/19 8:19 PM, Shawn Landden wrote:
>>> I was getting 8% and 6% cpu usage in tolower() and isspace(),
>>> respectively, waiting for a breakpoint on ppc64el.
>>>
>>> Also, gdb doesn't want non-deterministic behavior here.
>>>
>>> v2: do not touch C namespace
>>> v3: Turns out there are two places using these in performance-critical
>>> parts.
>>>     Follow GNU coding standards.
>> This doesn't address my comments about
>> <https://sourceware.org/ml/gdb-patches/2019-06/msg00442.html>.
>>
>> Something like this.  How does this compare?  Any significant
>> difference in your benchmark?  And again, how are you benchmarking
>> this?
> perf record. 

What was the use case?  Did you have some speficic set of commands?
Some script?  Please be detailed/more specific, so that
others can reproduce it, either now, or in the future when we
look back into this thread.

> goes from like 6-8% to almost nothing (if you remove the static).

What do you mean by "remove the static"?

Thanks,
Pedro Alves