From: Evgeniy Polyakov Subject: Re: [RFC 1/4] kevent: core files. Date: Mon, 31 Jul 2006 14:50:37 +0400 Message-ID: <20060731105037.GA2073@2ka.mipt.ru> References: <20060731103322.GA1898@2ka.mipt.ru> Mime-Version: 1.0 Content-Type: text/plain; charset=koi8-r Cc: drepper@redhat.com, zach.brown@oracle.com, davem@davemloft.net, linux-kernel@vger.kernel.org, netdev@vger.kernel.org Return-path: Received: from relay.2ka.mipt.ru ([194.85.82.65]:7839 "EHLO 2ka.mipt.ru") by vger.kernel.org with ESMTP id S1751514AbWGaKvQ (ORCPT ); Mon, 31 Jul 2006 06:51:16 -0400 To: Herbert Xu Content-Disposition: inline In-Reply-To: Sender: netdev-owner@vger.kernel.org List-Id: netdev.vger.kernel.org On Mon, Jul 31, 2006 at 08:35:55PM +1000, Herbert Xu (herbert@gondor.apana.org.au) wrote: > Evgeniy Polyakov wrote: > > > >> - if there is space, report it in the ring buffer. Yes, the buffer > >> can be optional, then all events are reported by the system call. > > > > That requires a copy, which can neglect syscall overhead. > > Do we really want it to be done? > > Please note that we're talking about events here, not actual data. So > only the event is being copied, which is presumably rather small compared > to the data. In syscall time kevents copy 40bytes for each event + 12 bytes of header (number of events, timeout and command number). That's likely two cache lines if only one event is reported. -- Evgeniy Polyakov