This is the mail archive of the
libc-alpha@sourceware.org
mailing list for the glibc project.
Re: [PATCH] Fix tcache count maximum
- From: DJ Delorie <dj at redhat dot com>
- To: Wilco Dijkstra <Wilco dot Dijkstra at arm dot com>
- Cc: codonell at redhat dot com, libc-alpha at sourceware dot org, nd at arm dot com
- Date: Fri, 10 May 2019 12:30:23 -0400
- Subject: Re: [PATCH] Fix tcache count maximum
Wilco Dijkstra <Wilco.Dijkstra@arm.com> writes:
> Sure, bit documenting this value means we might have to update it
> when changing the internal implementation of tcache.
Yup, but that's always the way with documentation, when users care about
internals.
>> The only tricky part is agreeing on which benchmarks are valid ;-)
>
> All in principle! jemalloc is gaining popularity so any case where it beats
> GLIBC is a reason to improve it to stay competitive.
Well, mostly. If jemalloc is better at some synthetic benchmark that
doesn't reflect any real-world uses, I don't care. That's why I did the
whole trace-workload-simulator thing, so we could benchmark real-world
use cases like OpenOffice, QEMU, 389ds, etc.