From owner-freebsd-net@FreeBSD.ORG Thu Feb 13 18:07:03 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 87D15D82 for ; Thu, 13 Feb 2014 18:07:03 +0000 (UTC) Received: from nm12-vm6.bullet.mail.ne1.yahoo.com (nm12-vm6.bullet.mail.ne1.yahoo.com [98.138.91.105]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (No client certificate requested) by mx1.freebsd.org (Postfix) with ESMTPS id 347511078 for ; Thu, 13 Feb 2014 18:07:02 +0000 (UTC) Received: from [98.138.100.116] by nm12.bullet.mail.ne1.yahoo.com with NNFMP; 13 Feb 2014 18:05:21 -0000 Received: from [98.138.84.47] by tm107.bullet.mail.ne1.yahoo.com with NNFMP; 13 Feb 2014 18:05:21 -0000 Received: from [127.0.0.1] by smtp115.mail.ne1.yahoo.com with NNFMP; 13 Feb 2014 18:05:21 -0000 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=yahoo.com; s=s1024; t=1392314721; bh=lUMyH2oRapzQQg3Lud9os5vVWrztGENz1fBfWWP/wE8=; h=X-Yahoo-Newman-Id:X-Yahoo-Newman-Property:X-YMail-OSG:X-Yahoo-SMTP:X-Rocket-Received:Content-Type:Mime-Version:Subject:From:In-Reply-To:Date:Cc:Content-Transfer-Encoding:Message-Id:References:To:X-Mailer; b=55ViOZVYN+GH2rEVI3lK13QXp6kt5KEABIGk0sTHBo5HA0xvhSgqd7asZIASW56dVgMuBgTZTrHeOV72oEXSMd8ojjG/oMfA3xcJlgctewrUvnc1uBuEix4pqzdC8EY/Y15EGZcaSRnUBehhf8L+4Ttt1U26++s9CKuIXZXt+j4= X-Yahoo-Newman-Id: 102697.20749.bm@smtp115.mail.ne1.yahoo.com X-Yahoo-Newman-Property: ymail-3 X-YMail-OSG: pKf4SzkVM1m5cmNOjnT3bOKZHqGqji3nbm31jnEaxI6l59x Ncvb5WGzfdnSdp1DDGFyNLrBMqLvbjgD.LbwrWh2BHa.2WBMKsGcG263YJuz DbLQRWQ0riU5O.QNMmQIBmxE583t61gsv9.Mt2t1vB54xGP0_j0b7cD235_K GTaDKRk3xN8rM9hxBUjFKw2cyVoouFWEE1kace6r.MO5UVCC0uFHtiWNSAt3 QiPdHKSM4EviZrUsW7dZzy90LwLXp729nrJSOawuOJVH.D3worzVmAbG4.mw Nw15Gj3rdsZpjsNR_oeEwpRFD5oMhBO95sLd515A6yVeLpl3DAdvPv2pOc.E bsSNZPmwrfaHwNzhBIsse31aQu3swcy.H72Ao.F9STQVWxfPvS83tFhJW_Bl YKYuTq17lzWNtgZpu7HuTTs1PQBT0vWh2ia.T8KOgdKh.i4bdkLLNM5rAwMm 1_Bvphv_jkfvE_bj2W_bjhyf9DygOAvjdyEIAidgkdcLDAmYs2FXIyIyQptE LiojvoUNTH4PABvumaV2hT28Uf3GUdj4f0MpPoOw5POGvYxQ_KLz7If1kX1s Gqak_RPNHg1Ce0g-- X-Yahoo-SMTP: clhABp.swBB7fs.LwIJpv3jkWgo2NU8- X-Rocket-Received: from [10.0.102.27] (scott4long@50.242.69.61 with plain [63.250.193.228]) by smtp115.mail.ne1.yahoo.com with SMTP; 13 Feb 2014 10:05:21 -0800 PST Content-Type: text/plain; charset=windows-1252 Mime-Version: 1.0 (Mac OS X Mail 7.1 \(1827\)) Subject: Re: Use of contiguous physical memory in cxgbe driver From: Scott Long In-Reply-To: <21245.1163.754141.154430@hergotha.csail.mit.edu> Date: Thu, 13 Feb 2014 10:05:18 -0800 Content-Transfer-Encoding: quoted-printable Message-Id: <5CAE71A4-EA1D-481D-AFBA-3738F8E66087@yahoo.com> References: <21216.22944.314697.179039@hergotha.csail.mit.edu> <201402111348.52135.jhb@freebsd.org> <201402121446.19278.jhb@freebsd.org> <21244.20212.423983.960018@hergotha.csail.mit.edu> <20140213075651.GY34851@funkthat.com> <21245.1163.754141.154430@hergotha.csail.mit.edu> To: Garrett Wollman X-Mailer: Apple Mail (2.1827) Cc: FreeBSD Net , John-Mark Gurney 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: Thu, 13 Feb 2014 18:07:03 -0000 On Feb 13, 2014, at 9:44 AM, Garrett Wollman = wrote: > < said: >=20 >> Though we might want to keep a few mbufs reserved for receive now = that >> you mention it... We should never get to the point where we can't >> allocate even one frame for receive... >=20 > It's very easy to get to that state if the driver insists on getting > three physically contiguous pages (which is what it takes to allocate > a single 9k cluster) >=20 So what you=92re saying is that all of the other memory allocations that = go along with moving data through a socket wind up fragmenting the free memory pool to = the point where it becomes impossible to find 3 contig pages for a 9k jumbo RX = frame. The old Tigon drivers used to solve this by having a private slab = allocator for RX. There was deliberate work more than 5 years ago to eliminate private = allocators like this and have a common jumbo allocator. I think it=92s possible to = say that that has been a theoretical success and a practical failure. Scott