From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-1.0 required=3.0 tests=HEADER_FROM_DIFFERENT_DOMAINS, MAILING_LIST_MULTI,SPF_PASS autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id F20D5C43381 for ; Wed, 6 Mar 2019 16:15:29 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.kernel.org (Postfix) with ESMTP id CC8F220684 for ; Wed, 6 Mar 2019 16:15:29 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1729546AbfCFQPZ (ORCPT ); Wed, 6 Mar 2019 11:15:25 -0500 Received: from mail-pg1-f193.google.com ([209.85.215.193]:33917 "EHLO mail-pg1-f193.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1729401AbfCFQPY (ORCPT ); Wed, 6 Mar 2019 11:15:24 -0500 Received: by mail-pg1-f193.google.com with SMTP id i130so8785966pgd.1; Wed, 06 Mar 2019 08:15:24 -0800 (PST) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:message-id:subject:from:to:cc:date:in-reply-to :references:mime-version:content-transfer-encoding; bh=7CpHa6t6to0r574VyJ/7qSNmNIGZZsE1qy5W5MHvdrI=; b=kw3zFhph6UsAmf1DPisr+L1Pe3HLHkeJMb03XRhIz49riBzxKA1rEgo0cVrusIgR20 JFuqVI+gngMjZhYt8jdCjlvjRIRj9x2paR9r2G1d/SC3e2LUJAGzyswsHHqVTk4sPgC9 AbiU6jBApmTMD8ODnakOUCRog1nuPs7amGMmMQhc/Zt3XqetWjwX0l7CFLblSJQqvKGQ wo+MAdRZ+wAQt41MAFJdsNYvMm1QQG9ehVGtSyaZzHM51ZwrWKiGoK4ALACS0l7J4zTq yHWcL/Vs2awqQENZyU0c0o2o9ibhHuHWprIBxJ3uXT64toV4OsRqFi70WeSpAFHlLIlQ OAow== X-Gm-Message-State: APjAAAU36qYVGA/iHHiMGBB82G1wF4hxCcOeUfVWeGUvBfFPE0LxnOxt /9ABkTFV51RUH09N4y48BKI= X-Google-Smtp-Source: APXvYqyIu9LlyyQ4FFxnglpH6DDXtIflHLDtG33Q2S1EFzl0fqUtOAB4nAaZ7seyD12LLTCT3sInxw== X-Received: by 2002:a65:510c:: with SMTP id f12mr7094491pgq.40.1551888923495; Wed, 06 Mar 2019 08:15:23 -0800 (PST) Received: from ?IPv6:2620:15c:2cd:203:5cdc:422c:7b28:ebb5? ([2620:15c:2cd:203:5cdc:422c:7b28:ebb5]) by smtp.gmail.com with ESMTPSA id s4sm3408248pfe.16.2019.03.06.08.15.22 (version=TLS1_2 cipher=ECDHE-RSA-CHACHA20-POLY1305 bits=256/256); Wed, 06 Mar 2019 08:15:22 -0800 (PST) Message-ID: <1551888921.9796.2.camel@acm.org> Subject: Re: [RFC/PATCH net-next 0/9] net/dim: Support for multiple implementations From: Bart Van Assche To: Tal Gilboa , linux-rdma@vger.kernel.org, linux-nvme@lists.infradead.org, linux-block@vger.kernel.org Cc: Yamin Friedman , Leon Romanovsky , Saeed Mahameed , Yishai Hadas , Jason Gunthorpe , Doug Ledford , Max Gurtovoy , Idan Burstein , Tariq Toukan Date: Wed, 06 Mar 2019 08:15:21 -0800 In-Reply-To: <20190306084832.57753-1-talgi@mellanox.com> References: <20190306084832.57753-1-talgi@mellanox.com> Content-Type: text/plain; charset="UTF-7" X-Mailer: Evolution 3.26.2-1 Mime-Version: 1.0 Content-Transfer-Encoding: 7bit Sender: linux-block-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-block@vger.kernel.org On Wed, 2019-03-06 at 10:48 +-0200, Tal Gilboa wrote: +AD4 net+AF8-dim.h lib exposes an implementation of the DIM algorithm for dynamically-tuned interrupt +AD4 moderation for networking interfaces. +AD4 +AD4 We need the same behavior for any block CQ. The main motivation is two benefit from maximized +AD4 completion rate and reduced interrupt overhead that DIM may provide. What is a +ACI-block CQ+ACI? How does net+AF8-dim compare to lib/irq+AF8-poll? Which approach results in the best performance and lowest latency? Thanks, Bart. From mboxrd@z Thu Jan 1 00:00:00 1970 From: bvanassche@acm.org (Bart Van Assche) Date: Wed, 06 Mar 2019 08:15:21 -0800 Subject: [RFC/PATCH net-next 0/9] net/dim: Support for multiple implementations In-Reply-To: <20190306084832.57753-1-talgi@mellanox.com> References: <20190306084832.57753-1-talgi@mellanox.com> Message-ID: <1551888921.9796.2.camel@acm.org> On Wed, 2019-03-06@10:48 +0200, Tal Gilboa wrote: > net_dim.h lib exposes an implementation of the DIM algorithm for dynamically-tuned interrupt > moderation for networking interfaces. > > We need the same behavior for any block CQ. The main motivation is two benefit from maximized > completion rate and reduced interrupt overhead that DIM may provide. What is a "block CQ"? How does net_dim compare to lib/irq_poll? Which approach results in the best performance and lowest latency? Thanks, Bart.