This is the mail archive of the
libc-alpha@sourceware.org
mailing list for the glibc project.
Re: [RFC][PATCH] LD_DEBUG option to measure init time
- From: pinskia at gmail dot com
- To: Carlos O'Donell <carlos at redhat dot com>
- Cc: Maria Guseva <m dot guseva at samsung dot com>, "libc-alpha at sourceware dot org" <libc-alpha at sourceware dot org>, Yury Gribov <y dot gribov at samsung dot com>, "v dot garbuzov at samsung dot com" <v dot garbuzov at samsung dot com>
- Date: Thu, 30 Jul 2015 21:13:49 -0700
- Subject: Re: [RFC][PATCH] LD_DEBUG option to measure init time
- Authentication-results: sourceware.org; auth=none
- References: <"027601d0cac7$952818c0$bf784a40$ at guseva"@samsung.com> <55BAF138 dot 1070904 at redhat dot com> <6908D9A3-3615-41A8-B8BC-20CCD871AD65 at gmail dot com> <55BAF4C8 dot 40200 at redhat dot com>
> On Jul 30, 2015, at 9:08 PM, Carlos O'Donell <carlos@redhat.com> wrote:
>
>> On 07/30/2015 11:58 PM, pinskia@gmail.com wrote:
>> Note aarch64 really should be using the virtual timer which is
>> optional part of armv8 but not an optional part of the server base.
>> It is sad that arm is blocking a glibc patch due to it being an
>> optional feature of v8 but is required for servers.
>
> ARM doesn't block this patch at all. Such machines that don't implement
> hptiming could fall back to more expensive interfaces like gettimeofday
> (vdso) or clock_gettime?
I am saying they are blocking the patch which adds hptiming. They reverted it being an option feature. There is another thread about this already.
Thanks,
Andrew
>
> We really should be doing something better for AArhc64, but why not
> ask ARM to fix this via Linaro? :-)
>
> c.