Large parallel glibc builds.

[Carlos O'Donell]

On 12/23/2015 11:00 AM, Florian Weimer wrote:
>> What do you think is the bottleneck here?
> 
> On top of the scaling issue of some of the threading tests, it looks as
> if lack of parallelism between subdirectories is the major culprit.
> This means that single-thread performance determines build and test
> times to a large extent.

Interesting. Is it avoidable though?

I do see problems, for example, build and test on a 24 core box is:
real    20m0.705s
user    44m27.832s
sys     30m57.313s

While build and test on a 4 core box is:
real	22m46.742s
user	18m52.517s
sys	12m4.294s

Where I would expect the 24 core box to be much much faster.

Would the next step be to time subdirectories and see which ones
are the slowest?

> math/gen-libm-test.pl is major seralization point during builds (not
> tests).  During tests, it's compilation test-tgmath2.c (related to poor
> performance of debugging information generation in GCC, as discussed
> before).

That step is relatively fast, even if were to serialize all operations,
it can't entirely explain the abysmal performance above?

Cheers,
Carlos.