From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from gnu.wildebeest.org (wildebeest.demon.nl [212.238.236.112]) by sourceware.org (Postfix) with ESMTPS id 2B7EC398D040 for ; Thu, 8 Jul 2021 15:04:30 +0000 (GMT) DMARC-Filter: OpenDMARC Filter v1.4.1 sourceware.org 2B7EC398D040 Authentication-Results: sourceware.org; dmarc=none (p=none dis=none) header.from=klomp.org Authentication-Results: sourceware.org; spf=pass smtp.mailfrom=klomp.org Received: from tarox.wildebeest.org (83-87-18-245.cable.dynamic.v4.ziggo.nl [83.87.18.245]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by gnu.wildebeest.org (Postfix) with ESMTPSA id 09FDD302FBA6; Thu, 8 Jul 2021 17:04:29 +0200 (CEST) Received: by tarox.wildebeest.org (Postfix, from userid 1000) id BF7AD4003072; Thu, 8 Jul 2021 17:04:28 +0200 (CEST) Message-ID: <579416e4b2be929fe44005a6273b8444d62ba37c.camel@klomp.org> Subject: Re: PR: 25978 From: Mark Wielaard To: "Frank Ch. Eigler" Cc: Noah Sanci , elfutils-devel@sourceware.org Date: Thu, 08 Jul 2021 17:04:28 +0200 In-Reply-To: <20210708131220.GB31689@redhat.com> References: <6360cc559a7ab536688ce70e79fc6334709eddee.camel@klomp.org> <20210708131220.GB31689@redhat.com> Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable X-Mailer: Evolution 3.28.5 (3.28.5-10.el7) Mime-Version: 1.0 X-Spam-Status: No, score=-4.0 required=5.0 tests=BAYES_00, JMQ_SPF_NEUTRAL, KAM_DMARC_STATUS, KAM_NUMSUBJECT, SPF_HELO_NONE, SPF_PASS, TXREP autolearn=no autolearn_force=no version=3.4.4 X-Spam-Checker-Version: SpamAssassin 3.4.4 (2020-01-24) on server2.sourceware.org X-BeenThere: elfutils-devel@sourceware.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Elfutils-devel mailing list List-Unsubscribe: , List-Archive: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 08 Jul 2021 15:04:31 -0000 Hi, On Thu, 2021-07-08 at 09:12 -0400, Frank Ch. Eigler wrote: > > If they are portions of the full fdcache shouldn't there be a check > > in the code that the specified fdcache_prefetch_fds and > > fdcache_prefetch_mbs aren't larger than fdcache_fds and fdcache_mbs? Or > > maybe they should be given as percentages? >=20 > We've iterated on a couple of ways of representing & controlling this. > The code makes the lru and prefetch caches separate, in that they have > separate limits and separate metrics. So there is no requirement for > the prefetch one to be smaller than the other. Aha, yes, that does look like how the code actually works. Lets make sure the documentation matches that description (or at least remove the phrase "portion of"). Cheers, Mar