Date: Mon, 13 Mar 2017 14:32:11 +0200 From: Andriy Gapon <avg@FreeBSD.org> To: Andrew Gallatin <gallatin@cs.duke.edu>, freebsd-arch@FreeBSD.org, Jeff Roberson <jroberson@jroberson.net> Subject: Re: UMA_ZONE_CACHESPREAD and uma_zsecond_add Message-ID: <b76fc0ab-3820-e64c-a84f-11cc3ce9d9b3@FreeBSD.org> In-Reply-To: <035f48ea-8722-f697-cc71-cb8ee772e062@cs.duke.edu> References: <76a47d9a-da39-75f4-5794-24724d0befc7@FreeBSD.org> <035f48ea-8722-f697-cc71-cb8ee772e062@cs.duke.edu>
next in thread | previous in thread | raw e-mail | index | archive | help
On 12/03/2017 20:55, Andrew Gallatin wrote: > On 03/08/2017 10:56, Andriy Gapon wrote: >> >> First, the history of UMA_ZONE_CACHESPREAD and uma_zsecond_add(): >> https://lists.freebsd.org/pipermail/freebsd-arch/2008-December/008800.html >> >> Now, more than 8 years after those features were introduced, we still don't have >> a single in-tree consumer for them. >> Does anyone use those features out of tree? >> Does anyone still have plans to make use of them? >> Will anyone get sad if those features get garbage collected? > > This is something that I keep getting suggestions to try at Netflix > on our 100G boxes. From the description, it really seems like > it might help us to have a few data types allocated like this. > > Can you give me, say, one month to look into this before axing > it? Sure! That's exactly why I wanted to ask everyone first. I am not itching to remove that code :) -- Andriy Gapon
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?b76fc0ab-3820-e64c-a84f-11cc3ce9d9b3>