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 10B2743CFE; Wed, 20 Mar 2024 08:50:46 +0100 (CET) Received: from mails.dpdk.org (localhost [127.0.0.1]) by mails.dpdk.org (Postfix) with ESMTP id 8F3B2402B9; Wed, 20 Mar 2024 08:50:45 +0100 (CET) Received: from dkmailrelay1.smartsharesystems.com (smartserver.smartsharesystems.com [77.243.40.215]) by mails.dpdk.org (Postfix) with ESMTP id 88CD1402A2 for ; Wed, 20 Mar 2024 08:50:44 +0100 (CET) Received: from smartserver.smartsharesystems.com (smartserver.smartsharesys.local [192.168.4.10]) by dkmailrelay1.smartsharesystems.com (Postfix) with ESMTP id 5A46820C80 for ; Wed, 20 Mar 2024 08:50:44 +0100 (CET) Content-class: urn:content-classes:message MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: quoted-printable Subject: Minutes of Technical Board meeting 06-March-2024 Date: Wed, 20 Mar 2024 08:50:42 +0100 X-MimeOLE: Produced By Microsoft Exchange V6.5 Message-ID: <98CBD80474FA8B44BF855DF32C47DC35E9F30F@smartserver.smartshare.dk> X-MS-Has-Attach: X-MS-TNEF-Correlator: Thread-Topic: Minutes of Technical Board meeting 06-March-2024 Thread-Index: AdpwiMOXDwGtKpd8R0SopcD+XiJTrQKEnD/A From: =?iso-8859-1?Q?Morten_Br=F8rup?= To: 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 Members Attending =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D Aaron Conole Bruce Richardson Hemant Agrawal Honappa Nagarahalli Jerin Jacob Kevin Traynor Konstantin Ananyev Maxime Coquelin Morten Br=F8rup (chair) Stephen Hemminger Thomas Monjalon NOTE =3D=3D=3D=3D The technical board meetings are on every second Wednesday at 3 pm UTC. Meetings are public. DPDK community members are welcome to attend on = Zoom: https://zoom-lfx.platform.linuxfoundation.org/meeting/96459488340? password=3Dd808f1f6-0a28-4165-929e-5a5bcae7efeb Agenda: https://annuel.framapad.org/p/r.0c3cc4d1e011214183872a98f6b5c7db Minutes of previous meetings: http://core.dpdk.org/techboard/minutes Next meeting will be on Wednesday 20-March-2024 at 3pm UTC, and will be chaired by Stephen. Agenda Items =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D 1. DPDK Code Challenge proposal (Ben) ------------------------------------- Launching a DPDK Code Challenge series was proposed by Ben. The purpose is to attract more developers to the DPDK community. The tech board supports the idea. Ben will setup a Slack channel to discuss details. 2. Marketing & Tech Writer status update (Nathan) ------------------------------------------------- Natan gave a brief update on marketing and tech writer status. The new tech writer has started, and is making positive progress. 3. Lab Server Refresh (Aaron) ----------------------------- The lab server refresh was discussed. Multiple tiers were proposed, with 3, 5 or 9 new servers, depending on = how much money we want to spend on it. Upgrading the test environment has more details than meets the eye. It is important that vendor access to equipment is restricted, so one = vendor cannot (inadvertently) affect tests of equipment from other = vendors. When evaluating the remaining lifetime of existing lab servers, we must = take into consideration that another three years are likely to pass = before the next lab server refresh. No conclusion was reached. Discussion will continue on the techboard mailing list. 4. RTE Bitset [4a] / Bitops [4b] RFC (Mattias) ---------------------------------------------- [4a]: = https://inbox.dpdk.org/dev/20240216102348.480407-1-mattias.ronnblom@erics= son.com/ [4b]: = https://inbox.dpdk.org/dev/20240302135328.531940-1-mattias.ronnblom@erics= son.com/ Only 15 minutes were remaining when starting this topic, which did not = leave enough time for discussion. Mattias briefly presented the Bitops RFC. It offers three categories of bit operations: 1) "simple", non-atomic, compiler optimizable, for use in e.g. control = plane. 2) "single access", volatile, where each read or write is guaranteed to = go all the way through to hardware, for use in e.g. drivers. 3) "atomic", with explicit memory ordering, for use where atomicity is = required. Having three categories of bit operations with similar function names = will make code cleaner in the long term. Features and function names were compared with similar functions in = Linux. The use of C11 _Atomic vs compiler specific intrinsics was briefly = touched; this is quite complex, and needs a separate discussion. No detailed conclusion was reached. The tech board supports the overall concept. The use of C11 _Generic to avoid size-specific operations, e.g. = rte_bit_op() instead of rte_bit_op32() and rte_bit_op64() was discussed. When changing the size of a variable, it is a big advantage that we = don't also have to update which functions are used on that variable. Also, many other operations, such "++" and "--", are agnostic of = variable size. The tech board supports the use of C11 _Generic in this library. Ran out of time. Discussion will continue on the mailing list. 5. Lcore Variables [5] RFC (Mattias) ------------------------------------ [5]: = https://inbox.dpdk.org/dev/20240228100928.524277-1-mattias.ronnblom@erics= son.com/ Ran out of time; did not start this topic. Postponed to a later meeting. Med venlig hilsen / Kind regards, -Morten Br=F8rup