From mboxrd@z Thu Jan 1 00:00:00 1970 From: Bruce Cole Subject: Re: e1000 driver and samba Date: Fri, 21 Sep 2007 11:21:54 -0700 Message-ID: <46F40BC2.2000806@gmail.com> References: <46F302A8.7040008@gmail.com> <780b6f780709210713s62f6d51s90eb0a54cda2a3fb@mail.gmail.com> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: netdev@vger.kernel.org, bacole@gmail.com To: L F Return-path: Received: from wa-out-1112.google.com ([209.85.146.183]:25650 "EHLO wa-out-1112.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751693AbXIUSZT (ORCPT ); Fri, 21 Sep 2007 14:25:19 -0400 Received: by wa-out-1112.google.com with SMTP id v27so1068678wah for ; Fri, 21 Sep 2007 11:25:19 -0700 (PDT) In-Reply-To: <780b6f780709210713s62f6d51s90eb0a54cda2a3fb@mail.gmail.com> Sender: netdev-owner@vger.kernel.org List-Id: netdev.vger.kernel.org L F wrote: > Aha. This doesn't seem to be in mr. Romieu's patch above: should it go > in on top of that? > His newer 0002-r8169-workaround-against-ignored-TxPoll-writes-8168.patch does the same thing as the older quoted version, and is also included in the roll-up patch he pointed you to. I agree re. performance, and don't want to clutter the thread realtek issues. I just wanted to clarify this particular realtek-samba issue in case it's relevant. For a long time folks suspected similar culprits (bad cable, half duplex, etc.) when it was the driver. Perhaps you should try doing a ping flood between server&client during your test. That healed the problem by keeping the queue busy in the realtek case.