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 36C4943D32; Sat, 23 Mar 2024 21:51:37 +0100 (CET) Received: from mails.dpdk.org (localhost [127.0.0.1]) by mails.dpdk.org (Postfix) with ESMTP id C474040274; Sat, 23 Mar 2024 21:51:36 +0100 (CET) Received: from mail-pl1-f174.google.com (mail-pl1-f174.google.com [209.85.214.174]) by mails.dpdk.org (Postfix) with ESMTP id 6CBFE4026E for ; Sat, 23 Mar 2024 21:51:35 +0100 (CET) Received: by mail-pl1-f174.google.com with SMTP id d9443c01a7336-1dddbeac9f9so20301115ad.3 for ; Sat, 23 Mar 2024 13:51:35 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=damore-org.20230601.gappssmtp.com; s=20230601; t=1711227093; x=1711831893; darn=dpdk.org; h=mime-version:subject:references:in-reply-to:message-id:to:from:date :from:to:cc:subject:date:message-id:reply-to; bh=4NxFCYHg3OSVZpJi8HwF1kCVu+oQDBu+J9h+T1ght8o=; b=1lKnmQW7yyYauXwcOTKEmRgCvRUQBWSk1TexYBzWn4kYO3poE3ar0wPwJolJqyTZ0j 1Pi2f2DbejRU5utcUOOChkf3ocNZlcWBXmCTbp3xVUt65VdQT8DdHDJpItgTAhe+dNcT ii9ry/zM0MaIZDQeJBU7fjFns7JJhd3ycGi4N4xRvYoAEQmu1KpxMe/jzsPxcb25yt5W LTrK0UYpKt4Up/x7PXyahJJZ/AFyDy73w3ZBkQvJ9wh1+FI3NMV2zzFxy4JDs6upOqDA s7XKIbXjL/WaTPV12zPTqWNfhb6by15Gbm3GEG9qcnBnC4C9TufcauUUnDOIokEK4oQl eIIg== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1711227093; x=1711831893; h=mime-version:subject:references:in-reply-to:message-id:to:from:date :x-gm-message-state:from:to:cc:subject:date:message-id:reply-to; bh=4NxFCYHg3OSVZpJi8HwF1kCVu+oQDBu+J9h+T1ght8o=; b=hHkmNRfzN+DCwVpY8FYHrKjfNo82nhS1/g/2FF6z26ctcGSrSyYCBiwtIrEEKC1n4j TM19D6Wn/amwLkkOUp1U98deN62d6cd+Fjv1ES/fNGp/jvLyw2NqJnYgbcn61P6aAV4u 1rLNe6svI4ii1oyBtTFPGR9qngwr+OtA0MWJuynArxxcW3T3pE8G5fq/9ii9B8n38rgF YLPFtQ0w2gRp8olA4o90TOyNU6jEGoSSi5UUZ2ZD845APSOT74ob3rmXcEiissID3Oo0 IM8mDb98mFD2PIqPearKuxJNdVl+uOiii7ZR1lsbMZXciQHsuqXcbbjAZxgsT333wipi MlUQ== X-Gm-Message-State: AOJu0YwkvrnRmGuE9TUjxZNjKAfJ9cxgHdmbDW6XfUgvCvKsk1RKMV8V vSUX76MjslDVCFX0kCf50R4XL3IZESHBtWGul7r3i51/DOHh+3H3xO41tfQMIDSvNI26/qpY4O7 iJ5o= X-Google-Smtp-Source: AGHT+IEjgkbmGCzl3B8IiptITW8oTuyx4XAxhJt1Y3VCCVSlLM3c11+3eJ4x+zlY0pVhRmZHaIuN0Q== X-Received: by 2002:a17:902:ed4c:b0:1dd:1c6f:af45 with SMTP id y12-20020a170902ed4c00b001dd1c6faf45mr2746732plb.63.1711227093330; Sat, 23 Mar 2024 13:51:33 -0700 (PDT) Received: from [10.0.4.28] (ip68-6-176-252.sd.sd.cox.net. [68.6.176.252]) by smtp.gmail.com with ESMTPSA id l14-20020a170903120e00b001dd7d00f7afsm1976963plh.18.2024.03.23.13.51.31 (version=TLS1_2 cipher=ECDHE-ECDSA-AES128-GCM-SHA256 bits=128/128); Sat, 23 Mar 2024 13:51:32 -0700 (PDT) Date: Sat, 23 Mar 2024 13:51:25 -0700 From: Garrett D'Amore To: "=?utf-8?Q?dev=40dpdk.org?=" , Parthakumar Roy Message-ID: In-Reply-To: References: Subject: Re: meson option to customize RTE_PKTMBUF_HEADROOM patch X-Readdle-Message-ID: c8e79fc1-c11e-48ab-8e23-7bc89d074ba3@Spark MIME-Version: 1.0 Content-Type: multipart/alternative; boundary="65ff40d2_254dc22f_59e2" 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 --65ff40d2_254dc22f_59e2 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable Content-Disposition: inline So we right now (at WEKA) have a somewhat older version of DPDK that we h= ave customized heavily, and I am going to to need to to make the headroom= *dynamic* (passed in at run time, and per port.) We have this requirement because we need payload to be at a specific offs= et, but have to deal with different header lengths for IPv4 and now IPv6.= My reason for pointing this out, is that I would dearly like if we could = collaborate on this -- this change is going to touch pretty much every PM= D (we don't need it on all of them as we only support a subset of PMDs, b= ut its still a significant set.) I'm not sure if anyone else has considered such a need -- this particular= message caught my eye as I'm looking specifically in this area right now= . On =46eb 15, 2024 at 11:02=E2=80=AFAM -0800, Parthakumar Roy , wrote: > Hello, > Bruce Richardson suggested that I submit this patch - at IBM we needed = to adjust the pkt=5Fmbuf=5Fheadroom=E2=80=8B for our application to work.= This is my first ever patch through a mailing list, I have only done it = through Pull Requests before, so let me know if I need to correct somethi= ng. > > Message: > =C2=A0 =C2=A0 Add meson configuration option to adjust RTE=5FPKTMBU=46=5F= HEADROOM > > diff --git a/config/meson.build b/config/meson.build > index 7cd375e991..43b765ade1 100644 > --- a/config/meson.build > +++ b/config/meson.build > =40=40 -304,6 +304,7 =40=40 endforeach > =C2=A0dpdk=5Fconf.set('RTE=5FMAX=5FETHPORTS', get=5Foption('max=5Fethpo= rts')) > =C2=A0dpdk=5Fconf.set('RTE=5FLIBEAL=5FUSE=5FHPET', get=5Foption('use=5F= hpet')) > =C2=A0dpdk=5Fconf.set('RTE=5FENABLE=5FTRACE=5F=46P', get=5Foption('enab= le=5Ftrace=5Ffp')) > +dpdk=5Fconf.set('RTE=5FPKTMBU=46=5FHEADROOM', get=5Foption('pkt=5Fmbuf= =5Fheadroom')) > =C2=A0=23 values which have defaults which may be overridden > =C2=A0dpdk=5Fconf.set('RTE=5FMAX=5FV=46IO=5FGROUPS', 64) > =C2=A0dpdk=5Fconf.set('RTE=5FDRIVER=5FMEMPOOL=5FBUCKET=5FSIZE=5FKB', 64= ) > diff --git a/config/rte=5Fconfig.h b/config/rte=5Fconfig.h > index 7b8c85e948..a2bb4ea61b 100644 > --- a/config/rte=5Fconfig.h > +++ b/config/rte=5Fconfig.h > =40=40 -51,7 +51,6 =40=40 > > =C2=A0/* mbuf defines */ > =C2=A0=23define RTE=5FMBU=46=5FDE=46AULT=5FMEMPOOL=5FOPS =22ring=5Fmp=5F= mc=22 > -=23define RTE=5FPKTMBU=46=5FHEADROOM 128 > > =C2=A0/* ether defines */ > =C2=A0=23define RTE=5FMAX=5FQUEUES=5FPER=5FPORT 1024 > diff --git a/meson=5Foptions.txt b/meson=5Foptions.txt > index 08528492f7..169fcc94c7 100644 > --- a/meson=5Foptions.txt > +++ b/meson=5Foptions.txt > =40=40 -36,6 +36,8 =40=40 option('machine', type: 'string', value: 'aut= o', description: > =C2=A0 =C2=A0 =C2=A0 =C2=A0=C2=A0'Alias of cpu=5Finstruction=5Fset.') > =C2=A0option('max=5Fethports', type: 'integer', value: 32, description:= > =C2=A0 =C2=A0 =C2=A0 =C2=A0=C2=A0'maximum number of Ethernet devices') > +option('pkt=5Fmbuf=5Fheadroom', type: 'integer', value: 128, descripti= on: > +=C2=A0=C2=A0 =C2=A0 =C2=A0=C2=A0'number of bytes skipped on Rx at the = start of the packet buffer to leave room for additional packet headers') > =C2=A0option('max=5Flcores', type: 'string', value: 'default', descript= ion: > =C2=A0 =C2=A0 =C2=A0 =C2=A0=C2=A0'Set maximum number of cores/threads s= upported by EAL; =22default=22 is different per-arch, =22detect=22 detect= s the number of cores on the build machine.') > =C2=A0option('max=5Fnuma=5Fnodes', type: 'string', value: 'default', de= scription: > --65ff40d2_254dc22f_59e2 Content-Type: text/html; charset="utf-8" Content-Transfer-Encoding: quoted-printable Content-Disposition: inline
So we right now (at WEKA) have a somewhat older ver= sion of DPDK that we have customized heavily, and I am going to to need t= o to make the headroom *dynamic* (passed in at run time, and per port.)
We have this requirement because we need payload to be at a specific offs= et, but have to deal with different header lengths for IPv4 and now IPv6.= &=23160;

My reason for pointing this out, is that I would dearly like if we could = collaborate on this -- this change is going to touch pretty much every PM= D (we don't need it on all of them as we only support a subset of PMDs, b= ut its still a significant set.)

I'm not sure if anyone else has considered such a need -- this particular= message caught my eye as I'm looking specifically in this area right now= .
On =46eb 15, 2024 at 11:02=E2=80=AF= AM -0800, Parthakumar Roy <Parthakumar.Roy=40ibm.com>, wrote:
=
Hello,
Bruce Richardson suggested that I submit th= is patch - at IBM we needed to adjust the pkt=5Fmbuf=5Fheadroom=E2=80=8B for our application to work. This is my first ever patch thr= ough a mailing list, I have only done it through Pull Requests before, so= let me know if I need to correct something.

Message:
&=23160; &=23160; Add meson configuration option to adjust RTE=5FPKTMBU=46= =5FHEADROOM

diff --git a/config/meson.build b/config/meson.build

index 7cd375e991..43b765ade1 100644

--- a/config/meson.build

+++ b/config/meson.build

=40=40 -304,6 +304,7 =40=40 endforeach

&=23160;dpdk=5Fconf.set('RTE=5FMAX=5FETHPORTS', get=5Foption('max=5Fethports')= )

&=23160;dpdk=5Fconf.set('RTE=5FLIBEAL=5FUSE=5FHPET', get=5Foption('use=5Fhpet'= ))

&=23160;dpdk=5Fconf.set('RTE=5FENABLE=5FTRACE=5F=46P', get=5Foption('enable=5F= trace=5Ffp'))

+dpdk=5Fconf.set('RTE=5FPKTMBU=46=5FHEADROOM', get=5Foption('pkt=5Fmbuf=5F= headroom'))

&=23160;=23 values which have defaults which may be overridden

&=23160;dpdk=5Fconf.set('RTE=5FMAX=5FV=46IO=5FGROUPS', 64)

&=23160;dpdk=5Fconf.set('RTE=5FDRIVER=5FMEMPOOL=5FBUCKET=5FSIZE=5FKB', 64)

diff --git a/config/rte=5Fconfig.h b/config/rte=5Fconfig.h

index 7b8c85e948..a2bb4ea61b 100644

--- a/config/rte=5Fconfig.h

+++ b/config/rte=5Fconfig.h

=40=40 -51,7 +51,6 =40=40

&=23160;<= /p>

&=23160;/* mbuf defines */

&=23160;=23define RTE=5FMBU=46=5FDE=46AULT=5FMEMPOOL=5FOPS =22ring=5Fmp=5Fmc=22=

-=23define RTE=5FPKTMBU=46=5FHEADROOM 128

&=23160;<= /p>

&=23160;/* ether defines */

&=23160;=23define RTE=5FMAX=5FQUEUES=5FPER=5FPORT 1024

diff --git a/meson=5Foptions.txt b/meson=5Foptions.txt

index 08528492f7..169fcc94c7 100644

--- a/meson=5Foptions.txt

+++ b/meson=5Foptions.txt

=40=40 -36,6 +36,8 =40=40 option('machine', type: 'string', value: 'auto= ', description:

&=23160; &=23= 160; &=23160; &=23160;&=23160;<= /span>'Alias of cpu=5Finstruction=5Fset.')

&=23160;option('max=5Fethports', type: 'integer', value: 32, description:

&=23160; &=23= 160; &=23160; &=23160;&=23160;<= /span>'maximum number of Ethernet devices')

+option('pkt=5Fmbuf=5Fheadroom', type: 'integer', value: 128, descriptio= n:

+&=23160;&=23160; &=23160; &=23160;&=23160;'number of bytes skipped on Rx at the start of the packet buf= fer to leave room for additional packet headers')

&=23160;option('max=5Flcores', type: 'string', value: 'default', description:<= /span>

&=23160; &=23= 160; &=23160; &=23160;&=23160;<= /span>'Set maximum number of cores/threads supported by EAL; =22default=22= is different per-arch, =22detect=22 detects the number of cores on the b= uild machine.')

&=23160;option('max=5Fnuma=5Fnodes', type: 'string', value: 'default', descrip= tion:


--65ff40d2_254dc22f_59e2--