From owner-freebsd-net@FreeBSD.ORG Wed Feb 12 23:36:40 2014 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1 with cipher ADH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 74EC4F13; Wed, 12 Feb 2014 23:36:40 +0000 (UTC) Received: from mail-qc0-x22e.google.com (mail-qc0-x22e.google.com [IPv6:2607:f8b0:400d:c01::22e]) (using TLSv1 with cipher ECDHE-RSA-RC4-SHA (128/128 bits)) (No client certificate requested) by mx1.freebsd.org (Postfix) with ESMTPS id D3F471AC3; Wed, 12 Feb 2014 23:36:39 +0000 (UTC) Received: by mail-qc0-f174.google.com with SMTP id x13so16361929qcv.5 for ; Wed, 12 Feb 2014 15:36:39 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=mime-version:sender:in-reply-to:references:date:message-id:subject :from:to:cc:content-type; bh=RwfKH+5KON8WTuVODWmO2xavTqFByN5RXO9c/LZIPD4=; b=b9oFWmBnOAaznkB5baajBMS/KnWpGJbH74ztJgAByUvXyIiA0ElWHdFt20gSYmLNeW uyo8/IlwdQNqoeIVT9+k2Q2iubQlB124fZp1pbuk8vbva/WWaJ1XvrFlUTWhv09uJOeb kXGcmtCuxz4HlLmwqNv40BhJl5a9s4xeyxDpVO+2GnglJhvW1TBgiEwlH/0yZQuHcTBn z9jEbzrxmmAXKrBb1oYGhSiOgCAwgpnZcsE127dF7iXxvYCIHyvwB7dnHS2xGuEQZSlx ENyhfVP9vGZSp+MybUw5WjVgeTJy3tFo3wIGm+Lph2q+apPv4FNvtTCNwrChN6hAAL7b m5Xw== MIME-Version: 1.0 X-Received: by 10.140.42.138 with SMTP id c10mr20711264qga.24.1392248199042; Wed, 12 Feb 2014 15:36:39 -0800 (PST) Sender: adrian.chadd@gmail.com Received: by 10.224.16.10 with HTTP; Wed, 12 Feb 2014 15:36:38 -0800 (PST) In-Reply-To: <201402121446.19278.jhb@freebsd.org> References: <21216.22944.314697.179039@hergotha.csail.mit.edu> <201402111348.52135.jhb@freebsd.org> <201402121446.19278.jhb@freebsd.org> Date: Wed, 12 Feb 2014 15:36:38 -0800 X-Google-Sender-Auth: N3Rn8cmu0ZnH5limp9FP92J-NFc Message-ID: Subject: Re: Use of contiguous physical memory in cxgbe driver From: Adrian Chadd To: John Baldwin Content-Type: text/plain; charset=ISO-8859-1 Cc: FreeBSD Net , Garrett Wollman , Navdeep Parhar , "net@freebsd.org" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.17 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 12 Feb 2014 23:36:40 -0000 On 12 February 2014 11:46, John Baldwin wrote: > Is this because UMA keeps lots of mbufs cached in your workload? The physmem > buddy allocator certainly seeks to minimize fragmentation. However, it can't > go yank memory out of UMA caches to do so. I'll ask you on irc, but where's that happening? My read of the code is that once it grabs a larger page and fragments it, it's lost. -a