From mboxrd@z Thu Jan 1 00:00:00 1970 From: Francois Romieu Subject: Re: [PATCH v2 net] r8169: fix NAPI handling under high load Date: Fri, 19 Oct 2018 00:59:00 +0200 Message-ID: <20181018225900.GA16653@electric-eye.fr.zoreil.com> References: <8d75498e-6f43-a699-3a0a-fb4a2b5dc860@gmail.com> <05eb4233-bf98-4aeb-73f6-94fec46ca3de@gmail.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: Heiner Kallweit , David Miller , Realtek linux nic maintainers , "netdev@vger.kernel.org" To: Eric Dumazet Return-path: Received: from violet.fr.zoreil.com ([92.243.8.30]:48700 "EHLO violet.fr.zoreil.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1725774AbeJSHCX (ORCPT ); Fri, 19 Oct 2018 03:02:23 -0400 Content-Disposition: inline In-Reply-To: <05eb4233-bf98-4aeb-73f6-94fec46ca3de@gmail.com> Sender: netdev-owner@vger.kernel.org List-ID: Eric Dumazet : [...] > One has to wonder why rtl8169_poll(), which might be called in a loop under DOS, > has to call rtl_ack_events() ? So as to cover a wider temporal range before any event can trigger an extra irq. I was more worried about irq cost than about IO cost (and I still am). -- Ueimor