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 5B6AEA034F; Wed, 31 Mar 2021 10:52:59 +0200 (CEST) Received: from [217.70.189.124] (localhost [127.0.0.1]) by mails.dpdk.org (Postfix) with ESMTP id 477A34069E; Wed, 31 Mar 2021 10:52:59 +0200 (CEST) Received: from smtp-4.sys.kth.se (smtp-4.sys.kth.se [130.237.48.193]) by mails.dpdk.org (Postfix) with ESMTP id 84E1840141 for ; Wed, 31 Mar 2021 10:52:57 +0200 (CEST) Received: from smtp-4.sys.kth.se (localhost.localdomain [127.0.0.1]) by smtp-4.sys.kth.se (Postfix) with ESMTP id 42A666DE2; Wed, 31 Mar 2021 10:52:57 +0200 (CEST) X-Virus-Scanned: by amavisd-new at kth.se Received: from smtp-4.sys.kth.se ([127.0.0.1]) by smtp-4.sys.kth.se (smtp-4.sys.kth.se [127.0.0.1]) (amavisd-new, port 10024) with LMTP id 6eVbVFf0U1qe; Wed, 31 Mar 2021 10:52:56 +0200 (CEST) X-KTH-Auth: barbette [78.129.119.184] DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=kth.se; s=default; t=1617180776; bh=0PPFRsm5Hs+9fOOpiuzYxPBuMDvPiX7qru93ZxZeSx8=; h=Subject:To:Cc:References:From:Date:In-Reply-To; b=SF8TIe4N9i1l2Ibu9JtrH6j0Afk4/acoJXrA4xw9ssa3LcnMOoCyC3q1Unv7v+dA5 Zfw34EGeQXBdAJ6MQR7JgXvaxh8i8Uiyyd6BtXuPvPvL+fDXSsUqyWTrAh2yY1jF0i KXtiT+ouwSYP3e5GIA8j+rq0DSyPpOpKnTdBM2C8= X-KTH-mail-from: barbette@kth.se Received: from [192.168.1.77] (host-78-129-119-184.dynamic.voo.be [78.129.119.184]) by smtp-4.sys.kth.se (Postfix) with ESMTPSA id 083426DCD; Wed, 31 Mar 2021 10:52:55 +0200 (CEST) To: Honnappa Nagarahalli , "dev@dpdk.org" Cc: nd , Alireza Farshin References: From: Tom Barbette Message-ID: Date: Wed, 31 Mar 2021 10:52:58 +0200 User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:78.0) Gecko/20100101 Thunderbird/78.9.0 MIME-Version: 1.0 In-Reply-To: Content-Type: text/plain; charset=utf-8; format=flowed Content-Transfer-Encoding: quoted-printable Content-Language: fr Subject: Re: [dpdk-dev] Minutes of Technical Board Meeting, 2021-03-10 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 Sender: "dev" Le 31-03-21 =C3=A0 02:44, Honnappa Nagarahalli a =C3=A9crit=C2=A0: > - Ability to tune the values of #defines > * Few prominent points discussed > - This will result in #ifdefs in the code (for ex: in testpmd) > - One option is for all the PMDs to document their configurable #defin= es in PMD specific header files. Having these distributed is much easier = to search. > - Can some of the existing #defines be converted to runtime configurat= ions? For ex: RTE_MAX_LCORE? This might impact ABI. > * Bruce to think about converting the doc to a blog or an email on = the mailing list. But soliciting feedback is most important. One alternative path worth looking at is to encourage the use of LTO,=20 and modify APIs so the configuration can be provided at linking time,=20 and propagated by the compiler. E.g. one can define rte_max_lcore as a weak constant symbol, equal to=20 128. At linking time the user may provide a rte_max_lcore that is more=20 tailored, and still, dynamic arrays[rte_max_lcore] will be allocatable=20 on the .bss section, avoiding an indirection. The compiler will be able=20 to optimize loops etc which is impossible with pure runtime configuration= =2E In packetmill.io we actually pushed this to the next level where the=20 driver can completely change its behavior without recompiling DPDK=20 itself and spawning ifdefs everywhere. However the price is the slowiness of LTO... My 2 cents. Tom