Re: Conceptual talk about distributed pbulk on exotic port

[Jonathan Perkin <jperkin%joyent.com@localhost>]

* On 2018-07-08 at 08:07 BST, Julien Savard wrote:

> @Jonathan when you say "Spin up as many processes as your hosts will take"
> correct me if i'm wrong but qemu-system-sparc is not the same as a
> kvm-qemu. qemu-system-sparc rely on dynamic translation and will emulate
> cpu architecture as well as cpu speed. Even if I had a 6Ghz proc with
> bazillion cores, it will still be capped with one 170Mhz cpu per "Emulated
> VM" ?

Yeh, I mean start up as many qemu-system-sparc processes as your
host(s) can take.  They will be slow individually so each will only
build one package at a time, but the point of distributed pbulk is to
parallelise the build across as many cores and hosts as you can.

You will always get better throughput with multiple build processes
running single threaded than a single build process with a high
MAKE_JOBS, assuming you're building more than a couple of packages.

-- 
Jonathan Perkin  -  Joyent, Inc.  -  www.joyent.com