From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail.seebs.net (mail.seebs.net [162.213.38.76]) by mail.openembedded.org (Postfix) with ESMTP id 75CC374D3C for ; Wed, 4 Apr 2018 21:45:06 +0000 (UTC) Received: from seebsdell (unknown [24.196.59.174]) by mail.seebs.net (Postfix) with ESMTPSA id B95002E8922; Wed, 4 Apr 2018 16:45:06 -0500 (CDT) Date: Wed, 4 Apr 2018 16:45:05 -0500 From: Seebs To: Khem Raj Message-ID: <20180404164505.00553b97@seebsdell> In-Reply-To: <39787e20-0d21-00bd-a5bb-73faa52c0839@gmail.com> References: <20180327154802.14611-1-ross.burton@intel.com> <39787e20-0d21-00bd-a5bb-73faa52c0839@gmail.com> X-Mailer: Claws Mail 3.15.1-dirty (GTK+ 2.24.30; x86_64-pc-linux-gnu) MIME-Version: 1.0 Cc: openembedded-core@lists.openembedded.org Subject: Re: [PATCH][RFC] pseudo: intercept syscall() and return ENOTSUP for renameat2 X-BeenThere: openembedded-core@lists.openembedded.org X-Mailman-Version: 2.1.12 Precedence: list List-Id: Patches and discussions about the oe-core layer List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 04 Apr 2018 21:45:06 -0000 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit On Wed, 4 Apr 2018 14:28:11 -0700 Khem Raj wrote: > what is the performance impact of adding another stack frame and > function call in the chain here. Do we have data ? Very close to unmeasurable, because *almost nothing ever uses syscall*. This is used only for the case where someone is explicitly calling syscall(), not for any other system call use case. And my implementation (which is not the same as this one) also overrides the wrapper generation, so there's no standard pseudo wrapper overhead (which is several times larger and involves mutexes and signal mask changing), it's just passing the call on unless it's SYS_renameat2. -s