From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mails.dpdk.org (mails.dpdk.org [217.70.189.124]) by inbox.dpdk.org (Postfix) with ESMTP id 13E1843D62; Tue, 26 Mar 2024 22:10:49 +0100 (CET) Received: from mails.dpdk.org (localhost [127.0.0.1]) by mails.dpdk.org (Postfix) with ESMTP id 9399040E6E; Tue, 26 Mar 2024 22:10:48 +0100 (CET) Received: from mail-pf1-f170.google.com (mail-pf1-f170.google.com [209.85.210.170]) by mails.dpdk.org (Postfix) with ESMTP id 06D3840E4A for ; Tue, 26 Mar 2024 22:10:46 +0100 (CET) Received: by mail-pf1-f170.google.com with SMTP id d2e1a72fcca58-6e6ca2ac094so5201379b3a.0 for ; Tue, 26 Mar 2024 14:10:46 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=damore-org.20230601.gappssmtp.com; s=20230601; t=1711487446; x=1712092246; darn=dpdk.org; h=mime-version:subject:references:in-reply-to:message-id:cc:to:from :date:from:to:cc:subject:date:message-id:reply-to; bh=0rIicpX+XkoxRiY3jn/t04afMzRFOc6A8/iOc7maSFk=; b=gsCzP6OZczgGCKtNzmdgvlC+Aqrk6C34McUt2jBEzpvfyAd7O2ZaYu05lteOB3pji6 lNLFjWfwJWRCf0wy7f8xRIudrR9zms9N5tmsbT5KOKNcmYuixhxZOUjDqYXErhljr8xi fv4Yorh7rcA2OzAUavovkplxy+jlywJ3NiL6C8JlgDSHnSaQrkHSUnks/FBQ2h+KzLcM mdzOURYkaotVVIGZyX0nJZ43C+cacDnZkUcLzAr2BC3a9A0jdG8B22lzQHswxnWuNg9O Q0QZGobfD04uX4esypbeW2DsZ7hQ0TD1fhAhg+cxFHQC1SEju5ne4rg0xJs+NgPGa48t fhdg== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1711487446; x=1712092246; h=mime-version:subject:references:in-reply-to:message-id:cc:to:from :date:x-gm-message-state:from:to:cc:subject:date:message-id:reply-to; bh=0rIicpX+XkoxRiY3jn/t04afMzRFOc6A8/iOc7maSFk=; b=WNNMZUR5ZVsMEcoiyaViJ8SMqG3zKwSszjRsh7gCuUTlotFpiCv1Za3jgAomuYNyKq V2osqhijnM0R9U9mNyVMiiC4KxzW8byMPvHPtA1fBZTSqJW71AO2otRLSBz+/8rs3Ujp kdu8iu8//wny7o+8RCTW+3CmYv07vckaCzAiHHCB6KBXWUYOzbA+Xg+qercbZYKxnF2K lZAfIcVWOEkt3RJ1yg8YJP6Pgt5di/WstTTmQCa5DnXOFmEV96KjN9gnFr76t2JwrtVa EWJSbVa2Yc86ZB9QONW9xXCjBis6QnUXmrOkSvzdkT8I6A/KAhotAr+733dSkIabliPe 5OCA== X-Forwarded-Encrypted: i=1; AJvYcCWtAOAQEiZqEksFbvoWqs7DVZsGzSGljqUGL4goM7DA6jBrX+p1HpDsbBb7CEzJX0ugBaPW7Y3dcMBozdg= X-Gm-Message-State: AOJu0Yx5lWctUKpti75bQyW7SBEOtuxHRJq1NclVSPX79w8O9mo7oHyj nLVJVAarR/IW22ETiQ87/6c8/ZLhWmUm9FSbKqGt9hKn+W1Uq3ggsVUjebBZpIM= X-Google-Smtp-Source: AGHT+IG/wMHJbdApUQwXr6TCpg5Fys58+t5o49hfTltpVihfTtiySFeZYs//4CzB7NoSTz3jGljyXw== X-Received: by 2002:a05:6a20:12d2:b0:1a3:6fef:3a80 with SMTP id v18-20020a056a2012d200b001a36fef3a80mr11865980pzg.40.1711487445988; Tue, 26 Mar 2024 14:10:45 -0700 (PDT) Received: from [10.41.69.223] ([149.20.194.220]) by smtp.gmail.com with ESMTPSA id v10-20020aa799ca000000b006e9afb31e4bsm6609502pfi.12.2024.03.26.14.10.44 (version=TLS1_2 cipher=ECDHE-ECDSA-AES128-GCM-SHA256 bits=128/128); Tue, 26 Mar 2024 14:10:45 -0700 (PDT) Date: Tue, 26 Mar 2024 14:10:38 -0700 From: Garrett D'Amore To: Stephen Hemminger Cc: =?utf-8?Q?Morten_Br=C3=B8rup?= , dev@dpdk.org, Parthakumar Roy , Bruce Richardson Message-ID: <6b0309b9-efae-459f-a437-b234f0f6f2fe@Spark> In-Reply-To: <20240326133506.6d4fb00f@hermes.local> References: <20240325102030.46913a06@hermes.local> <98CBD80474FA8B44BF855DF32C47DC35E9F32D@smartserver.smartshare.dk> <98CBD80474FA8B44BF855DF32C47DC35E9F337@smartserver.smartshare.dk> <20240326133506.6d4fb00f@hermes.local> Subject: Re: meson option to customize RTE_PKTMBUF_HEADROOM patch X-Readdle-Message-ID: 6b0309b9-efae-459f-a437-b234f0f6f2fe@Spark MIME-Version: 1.0 Content-Type: multipart/alternative; boundary="660339d3_3d7e2658_118d0" X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: DPDK patches and discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces@dpdk.org --660339d3_3d7e2658_118d0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable Content-Disposition: inline =46air enough... I think that is just something we're going to have to li= ve with. The other solutions are either much more painful, or much more work. If we can use header/buffer splitting that would be superior.=C2=A0=C2=A0= Right now we can't use that everywhere because it isn't available everywh= ere. On Mar 26, 2024 at 1:35=E2=80=AFPM -0700, Stephen Hemminger , wrote: > On Tue, 26 Mar 2024 10:43:30 -0700 > Garrett D'Amore wrote: > > > This had occurred to me as well.=C2=A0=C2=A0I think most hardware DMA= engines can align on 32-bit boundaries.=C2=A0=C2=A0I've yet to see a dev= ice that actually requires 64-bit DMA alignment.=C2=A0=C2=A0(But I have o= nly looked at a subset=C2=A0=C2=A0of devices, and most of the=C2=A0=C2=A0= ones I have looked at are not ones that would be considered 'modern'.) > > There maybe a PCI transaction performance penalty if not aligned. --660339d3_3d7e2658_118d0 Content-Type: text/html; charset="utf-8" Content-Transfer-Encoding: quoted-printable Content-Disposition: inline
=46air enough... I think that is just something we'= re going to have to live with.

The other solutions are either much more painful, or much more work.

If we can use header/buffer splitting that would be superior.&=23160;&=23= 160;Right now we can't use that everywhere because it isn't available eve= rywhere.
On Mar 26, 2024 at 1:35=E2=80=AFPM = -0700, Stephen Hemminger <stephen=40networkplumber.org>, wrote:
On Tue, 26 Mar 2024 10:43:30 -0700
Garrett D'Amore <garrett=40damore.org> wrote:

This had occurred to me as well.&=23160;&=23160;I think most ha= rdware DMA engines can align on 32-bit boundaries.&=23160;&=23160;I've ye= t to see a device that actually requires 64-bit DMA alignment.&=23160;&=23= 160;(But I have only looked at a subset&=23160;&=23160;of devices, and mo= st of the&=23160;&=23160;ones I have looked at are not ones that would be= considered 'modern'.)

There maybe a PCI transaction performance penalty if not aligned.
--660339d3_3d7e2658_118d0--