From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mga09.intel.com (mga09.intel.com [134.134.136.24]) by dpdk.org (Postfix) with ESMTP id 68CC62BB9 for ; Tue, 3 Jan 2017 03:40:44 +0100 (CET) Received: from orsmga005.jf.intel.com ([10.7.209.41]) by orsmga102.jf.intel.com with ESMTP; 02 Jan 2017 18:40:43 -0800 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="unknown"; e="0x0't"; a="48648878" Received: from silpixa00397515.ir.intel.com (HELO silpixa00397515.ger.corp.intel.com) ([10.237.223.14]) by orsmga005.jf.intel.com with ESMTP; 02 Jan 2017 09:21:33 -0800 From: David Hunt To: dev@dpdk.org Cc: bruce.richardson@intel.com Date: Mon, 2 Jan 2017 10:22:20 +0000 Message-Id: <1483352546-171068-1-git-send-email-david.hunt@intel.com> X-Mailer: git-send-email 2.7.4 In-Reply-To: <1482381428-148094-2-git-send-email-david.hunt@intel.com> References: <1482381428-148094-2-git-send-email-david.hunt@intel.com> Subject: [dpdk-dev] [WARNING: A/V UNSCANNABLE][PATCH v3 0/6] distributor-performance-improvements X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: DPDK patches and discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 03 Jan 2017 02:40:44 -0000 This patch aims to improve the throughput of the distributor library. It uses a similar handshake mechanism to the previous version of the library, in that bits are used to indicate when packets are ready to be sent to a worker and ready to be returned from a worker. One main difference is that instead of sending one packet in a cache line, it makes use of the 7 free spaces in the same cache line in order to send up to 8 packets at a time to/from a worker. The flow matching algorithm has had significant re-work, and now keeps an array of inflight flows and an array of backlog flows, and matches incoming flows to the inflight/backlog flows of all workers so that flow pinning to workers can be maintained. The Flow Match algorithm has both scalar and a vector versions, and a function pointer is used to select the post appropriate function at run time, depending on the presence of the SSE2 cpu flag. On non-x86 platforms, the the scalar match function is selected, which should still gives a good boost in performance over the non-burst API. v2 changes: * Created a common distributor_priv.h header file with common definitions and structures. * Added a scalar version so it can be built and used on machines without sse2 instruction set * Added unit autotests * Added perf autotest v3 changes: * Addressed mailing list review comments * Test code removal * Split out SSE match into separate file to facilitate NEON addition * Cleaned up conditional compilation flags for SSE2 * Addressed c99 style compilation errors * rebased on latest head (Jan 2 2017, Happy New Year to all) Notes: Apps must now work in bursts, as up to 8 are given to a worker at a time For performance in matching, Flow ID's are 15-bits Original API (and code) is kept for backward compatibility Performance Gains 2.2GHz Intel(R) Xeon(R) CPU E5-2699 v4 @ 2.20GHz 2 x XL710 40GbE NICS to 2 x 40Gbps traffic generator channels 64b packets separate cores for rx, tx, distributor 1 worker - 4.8x 4 workers - 2.9x 8 workers - 1.8x 12 workers - 2.1x 16 workers - 1.8x [PATCH v3 1/6] lib: distributor performance enhancements [PATCH v3 2/6] lib: add distributor vector flow matching [PATCH v3 3/6] test: unit tests for new distributor burst api [PATCH v3 4/6] test: add distributor_perf autotest [PATCH v3 5/6] example: distributor app showing burst api [PATCH v3 6/6] doc: distributor library changes for new burst api