Date: Sun, 09 Oct 2022 20:46:20 +0100 From: Kristof Provost <kp@FreeBSD.org> To: Gleb Smirnoff <glebius@freebsd.org> Cc: src-committers@freebsd.org, dev-commits-src-all@freebsd.org, dev-commits-src-main@freebsd.org Subject: Re: git: 133935d26f20 - main - pf: atomically increment state ids Message-ID: <01432728-6156-4519-A970-BB11DE290DE8@FreeBSD.org> In-Reply-To: <Y0H4/IQ3STFvnm6m@FreeBSD.org> References: <202210081641.298GfT2F036984@gitrepo.freebsd.org> <Y0H4/IQ3STFvnm6m@FreeBSD.org>
next in thread | previous in thread | raw e-mail | index | archive | help
On 8 Oct 2022, at 23:26, Gleb Smirnoff wrote: > On Sat, Oct 08, 2022 at 04:41:29PM +0000, Kristof Provost wrote: > K> commit 133935d26f20c0b9c433da9a2b32bcbe562bc2c5 > K> Author: Kristof Provost <kp@FreeBSD.org> > K> AuthorDate: 2022-10-07 17:17:06 +0000 > K> Commit: Kristof Provost <kp@FreeBSD.org> > K> CommitDate: 2022-10-08 16:27:29 +0000 > K> > K> pf: atomically increment state ids > K> > K> Rather than using a per-cpu state counter, and adding in the CPU= id we > K> can atomically increment the number. > K> This has the advantage of removing the assumption that the CPU I= D fits > K> in 8 bits. > K> > K> Event: Aberdeen Hackathon 2022 > K> Reviewed by: mjg > K> Differential Revision: https://reviews.freebsd.org/D36915 > > This adds an atomic operation on a single word on a state creation :( > Previously two state creations could run in parallel without negatively= > affecting each other. > Slightly related: has anyone ever run a benchmark on state creation? All of the benchmarking I=E2=80=99ve done so far focussed on traffic rate= s, so state lookups rather than state creation. (Which I think is the mor= e important metric, but obviously we don=E2=80=99t want to overly pessimi= se state creation either.) This change does buy us =E2=80=9Cwe actually work on > 256 CPU machines=E2= =80=9D, and I strongly suspect this isn=E2=80=99t actually going to be th= e bottleneck on state creation either. Especially not once mjg improves u= nr64. Best regards, Kristof
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?01432728-6156-4519-A970-BB11DE290DE8>