This is the mail archive of the mailing list for the glibc project.

Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]
Other format: [Raw text]

Re: Large parallel glibc builds.

On 12/23/2015 08:37 AM, Florian Weimer wrote:
> On 12/22/2015 08:25 PM, Carlos O'Donell wrote:
>> Community,
>> I am consistently doing parallel (-j56) builds for glibc
>> on Intel Xeon CPU E5-2697 v3 @ 2.60GHz (2 socket x 14 cores x 2HT).
>> I have not seen any failures or artifacts that look like hazards
>> or races in our makefiles.
>> Is anyone else using larger boxes for builds and still seeing 
>> problems?
> I still see the linknamespace failures
> FAIL: conform/ISO/assert.h/linknamespace
> FAIL: conform/ISO/ctype.h/linknamespace
> FAIL: conform/ISO/errno.h/linknamespace
> FAIL: conform/ISO/locale.h/linknamespace
> â
> reported here first:
>   <>

Please file a bug about this so we can track it (like the locale
issue H.J. reported).
> Some tests have problems because they run into scalability issues
> (thread creation is particularly slow on large machines, likely due to
> mmap being extremely expensive).

If we could find out which tests have problems that would be useful.

> The build itself is fine.
> All this was observed on an 80-core, 160-thread x86-64 machine, with
> -j160, running Fedora 23.  Parallelization is extremely low.
> PARALLELMFLAGS does not make a difference.
> Consequently, this machine is not significantly faster for building
> glibc than an average laptop, and testing is in fact quite a bit slower.

What do you think is the bottleneck here?


Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]