From mboxrd@z Thu Jan 1 00:00:00 1970 From: "Frank Ch. Eigler" Subject: Re: [PATCH v2 0/2] Tracepoint for tcp retransmission Date: Mon, 6 Feb 2012 11:21:36 -0500 Message-ID: <20120206162136.GJ27935@redhat.com> References: <65795E11DBF1E645A09CEC7EAEE94B9CB8D3EA7B@USINDEVS02.corp.hds.com> <20120204142823.GA7000@neilslaptop.think-freely.org> <20120204155807.GA2657@nuttenaction> <20120204200937.GA2670@neilslaptop.think-freely.org> <20120205125325.GA31578@elastic.org> <20120205191708.GA5337@neilslaptop.think-freely.org> <20120205200428.GB2816@nuttenaction> <20120206013247.GA5681@neilslaptop.think-freely.org> <20120206152019.GG27935@redhat.com> <20120206155305.GB3620@hmsreliant.think-freely.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: Hagen Paul Pfeifer , "Frank Ch. Eigler" , Satoru Moriya , David Miller , "netdev@vger.kernel.org" , "tgraf@infradead.org" , "stephen.hemminger@vyatta.com" , "eric.dumazet@gmail.com" , Seiji Aguchi , fche@sourceware.org, mathieu.desnoyers@polymtl.ca, rostedt@goodmis.org To: Neil Horman Return-path: Received: from mx1.redhat.com ([209.132.183.28]:30338 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754852Ab2BFQWh (ORCPT ); Mon, 6 Feb 2012 11:22:37 -0500 Content-Disposition: inline In-Reply-To: <20120206155305.GB3620@hmsreliant.think-freely.org> Sender: netdev-owner@vger.kernel.org List-ID: Hi - On Mon, Feb 06, 2012 at 10:53:05AM -0500, Neil Horman wrote: > [...] If you're unfamiliar with them, netfilter hooks are those > standard points in the network input/output/forwarding paths at > which we can watch and maniupulate network traffic. [...] Aha, nf_register_hook and friends. Thanks for the pointer. > > Does this mean that this netfilter hook mechanism is sufficient to > > adapt to the current/future diversity of behaviors? Why not make > > *that* into a tracepoint then, so perf/stap scripts could get at it in > > userspace? > I suppose you could. [...] I'm suggesting a kernel module because > then you wouldn't have the performance overhead of moving all those > frames to user space. (For what it's worth, if there were a tracepoint in the netfilter hook machinery, stap would be able to process the packets likewise, in-kernel, with no kernel debuginfo installed.) - FChE