Date: Mon, 8 May 2017 00:02:41 +0200 From: Richard Weinberger <richard@....at> To: Daniel Gruss <daniel.gruss@...k.tugraz.at> Cc: Christoph Hellwig <hch@...radead.org>, kernel list <linux-kernel@...r.kernel.org>, "kernel-hardening@...ts.openwall.com" <kernel-hardening@...ts.openwall.com>, "clementine.maurice@...k.tugraz.at" <clementine.maurice@...k.tugraz.at>, "moritz.lipp@...k.tugraz.at" <moritz.lipp@...k.tugraz.at>, Michael Schwarz <michael.schwarz@...k.tugraz.at>, Richard Fellner <richard.fellner@...dent.tugraz.at>, "Kirill A. Shutemov" <kirill.shutemov@...ux.intel.com>, Ingo Molnar <mingo@...nel.org>, "anders.fogh@...ta-adan.de" <anders.fogh@...ta-adan.de> Subject: Re: Re: [RFC, PATCH] x86_64: KAISER - do not map kernel in user mode Daniel, Am 07.05.2017 um 23:45 schrieb Daniel Gruss: >> Just did a quick test on my main KVM host, a 8 core Intel(R) Xeon(R) >> CPU E3-1240 V2. >> KVM guests are 4.10 w/o CONFIG_KAISER and kvmconfig without CONFIG_PARAVIRT. >> Building a defconfig kernel within that guests is about 10% slower >> when CONFIG_KAISER >> is enabled. > > Thank you for testing it! :) > >> Is this expected? > > It sounds plausible. First, I would expect any form of virtualization to increase the overhead. Second, for the processor (Ivy Bridge), I would have expected even higher > performance overheads. KAISER utilizes very recent performance improvements in Intel processors... Ahh, *very* recent is the keyword then. ;) I was a bit confused since in your paper the overhead is less than 1%. What platforms did you test? i.e. how does it perform on recent AMD systems? Thanks, //richard
Powered by blists - more mailing lists
Confused about mailing lists and their use? Read about mailing lists on Wikipedia and check out these guidelines on proper formatting of your messages.