From mboxrd@z Thu Jan 1 00:00:00 1970 X-Msuck: nntp://news.gmane.org/gmane.linux.lib.musl.general/87 Path: news.gmane.org!not-for-mail From: Rich Felker Newsgroups: gmane.linux.lib.musl.general Subject: Re: Anti-bloat side project Date: Mon, 27 Jun 2011 17:37:39 -0400 Message-ID: <20110627213739.GA12592@brightrain.aerifal.cx> References: <20110627170806.GA24833@brightrain.aerifal.cx> <20110627211625.GC5036@port70.net> <20110627211909.GZ12592@brightrain.aerifal.cx> <20110627213805.GD5036@port70.net> Reply-To: musl@lists.openwall.com NNTP-Posting-Host: lo.gmane.org Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Trace: dough.gmane.org 1309211073 32337 80.91.229.12 (27 Jun 2011 21:44:33 GMT) X-Complaints-To: usenet@dough.gmane.org NNTP-Posting-Date: Mon, 27 Jun 2011 21:44:33 +0000 (UTC) To: musl@lists.openwall.com Original-X-From: musl-return-171-gllmg-musl=m.gmane.org@lists.openwall.com Mon Jun 27 23:44:30 2011 Return-path: Envelope-to: gllmg-musl@lo.gmane.org Original-Received: from mother.openwall.net ([195.42.179.200]) by lo.gmane.org with smtp (Exim 4.69) (envelope-from ) id 1QbJba-0002Al-4N for gllmg-musl@lo.gmane.org; Mon, 27 Jun 2011 23:44:30 +0200 Original-Received: (qmail 18390 invoked by uid 550); 27 Jun 2011 21:44:29 -0000 Mailing-List: contact musl-help@lists.openwall.com; run by ezmlm Precedence: bulk List-Post: List-Help: List-Unsubscribe: List-Subscribe: Original-Received: (qmail 18381 invoked from network); 27 Jun 2011 21:44:29 -0000 Content-Disposition: inline In-Reply-To: <20110627213805.GD5036@port70.net> User-Agent: Mutt/1.5.21 (2010-09-15) Xref: news.gmane.org gmane.linux.lib.musl.general:87 Archived-At: On Mon, Jun 27, 2011 at 11:38:05PM +0200, Szabolcs Nagy wrote: > * Rich Felker [2011-06-27 17:19:09 -0400]: > > Bleh. Has there been any serious work to document the causes and how > > the code could be changed to fix the syscall bloat though? Or just > > preliminat strace and wc -l? > > most of the syscalls are due to python module imports check > 100 different locations before finding the good one > > imho they measured it and concluded that with modern > filesystem caching this does not matter much.. Well they're wrong. Even if the syscall did nothing but enter and leave kernelspace, it would still be very expensive. Using a module cache/registry of some sort could solve the problem, or they could first tackle all the non-open() syscalls which still make up a heavy share of the cost.. Rich