List comments

GET /api/patches/144/comments/
HTTP 200 OK
Allow: GET, HEAD, OPTIONS
Content-Type: application/json
Vary: Accept

[
    {
        "id": 354,
        "web_url": "https://patches.dpdk.org/comment/354/",
        "msgid": "<53E9FA58.1060600@6wind.com>",
        "date": "2014-08-12T11:28:24",
        "subject": "Re: [dpdk-dev] [RFC PATCH 09/14] Fix performance regression due to\n\tmoved pool ptr",
        "submitter": {
            "id": 8,
            "url": "https://patches.dpdk.org/api/people/8/",
            "name": "Olivier Matz",
            "email": "olivier.matz@6wind.com"
        },
        "content": "Hi Bruce,\n\nOn 08/11/2014 10:44 PM, Bruce Richardson wrote:\n> Adjust the fast-path code to fix the regression caused by the pool\n> pointer moving to the second cache line. This change adjusts the\n> prefetching and also the way in which the mbufs are freed back to the\n> mempool.\n>\n> Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>\n\nJust one comment here (maybe this code should be reviewed by someone\nknowing the ixgbe driver better than me):\n\n\n> @@ -252,14 +250,6 @@ tx_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts,\n>   \tvolatile union ixgbe_adv_tx_desc *tx_r = txq->tx_ring;\n>   \tuint16_t n = 0;\n>\n> -\t/*\n> -\t * Begin scanning the H/W ring for done descriptors when the\n> -\t * number of available descriptors drops below tx_free_thresh.  For\n> -\t * each done descriptor, free the associated buffer.\n> -\t */\n> -\tif (txq->nb_tx_free < txq->tx_free_thresh)\n> -\t\tixgbe_tx_free_bufs(txq);\n> -\n>   \t/* Only use descriptors that are available */\n>   \tnb_pkts = (uint16_t)RTE_MIN(txq->nb_tx_free, nb_pkts);\n>   \tif (unlikely(nb_pkts == 0))\n> @@ -323,6 +313,15 @@ tx_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts,\n>   \tif (txq->tx_tail >= txq->nb_tx_desc)\n>   \t\ttxq->tx_tail = 0;\n>\n> +\t/*\n> +\t * Begin scanning the H/W ring for done descriptors when the\n> +\t * number of available descriptors drops below tx_free_thresh.  For\n> +\t * each done descriptor, free the associated buffer.\n> +\t */\n> +\tif (txq->nb_tx_free < txq->tx_free_thresh)\n> +\t\tixgbe_tx_free_bufs(txq);\n> +\n> +\n>   \t/* update tail pointer */\n>   \trte_wmb();\n>   \tIXGBE_PCI_REG_WRITE(txq->tdt_reg_addr, txq->tx_tail);\n\nIt looks like these 2 hunks are reverted in next commit. I'm not sure\nthis is what you expected.",
        "headers": {
            "List-Subscribe": "<http://dpdk.org/ml/listinfo/dev>,\n\t<mailto:dev-request@dpdk.org?subject=subscribe>",
            "Content-Transfer-Encoding": "7bit",
            "X-Google-DKIM-Signature": "v=1; a=rsa-sha256; c=relaxed/relaxed;\n\td=1e100.net; s=20130820;\n\th=x-gm-message-state:message-id:date:from:user-agent:mime-version:to\n\t:subject:references:in-reply-to:content-type\n\t:content-transfer-encoding;\n\tbh=zetaJygrURgQHcm6AUTHKQRViT/jOm2DYNm5adDOw40=;\n\tb=XGLLenA8bbVHllkMoQY5aLNSuD6Imr1rnDxcZSwBpW0MODXY/TdkqKWfCe8VO9qJbw\n\tjsHoKeWwyRcHK9n4ykjug4jiEEtcMIEM7+kbYnr7hH51UPnoMztK9v0ddNLhn0KQ+wJu\n\tAyZRDAXplAB2Q14mFJVruVg87p+veIdF3oaWUf8bL/KJPNJcmylUBHZebHaiXWPMiGQt\n\tZPs0Ea2O2OVWPY0lAeyicPhHydbtw0PQtl4r8woFg6oJ+fcLt7OoLtZL8tLhg3hH8hD/\n\tVxGkjTOFoIPCZRfEcQKaXm7rKgnlcBk+th/L8ATAFXYJFEcPPtDG2Wnmc1DbpWduUEDx\n\tzSVw==",
            "List-Help": "<mailto:dev-request@dpdk.org?subject=help>",
            "Date": "Tue, 12 Aug 2014 13:28:24 +0200",
            "Precedence": "list",
            "X-BeenThere": "dev@dpdk.org",
            "References": "<1407789890-17355-1-git-send-email-bruce.richardson@intel.com>\n\t<1407789890-17355-10-git-send-email-bruce.richardson@intel.com>",
            "In-Reply-To": "<1407789890-17355-10-git-send-email-bruce.richardson@intel.com>",
            "X-Gm-Message-State": "ALoCoQlRhU0LP1n+LRMelLinm18DMb11mBIOwGlbmLFiNYf3wXvBCBud10LFmqphb9ciVF8Tk8K+",
            "Content-Type": "text/plain; charset=ISO-8859-1; format=flowed",
            "To": "Bruce Richardson <bruce.richardson@intel.com>, dev@dpdk.org",
            "User-Agent": "Mozilla/5.0 (X11; Linux x86_64;\n\trv:24.0) Gecko/20100101 Icedove/24.5.0",
            "MIME-Version": "1.0",
            "Received": [
                "from mail-we0-f180.google.com (mail-we0-f180.google.com\n\t[74.125.82.180]) by dpdk.org (Postfix) with ESMTP id 4ADF7B3BB\n\tfor <dev@dpdk.org>; Tue, 12 Aug 2014 13:25:31 +0200 (CEST)",
                "by mail-we0-f180.google.com with SMTP id w61so9790704wes.39\n\tfor <dev@dpdk.org>; Tue, 12 Aug 2014 04:28:26 -0700 (PDT)",
                "from [10.16.0.195] (guy78-3-82-239-227-177.fbx.proxad.net.\n\t[82.239.227.177]) by mx.google.com with ESMTPSA id\n\tgc8sm55247224wic.3.2014.08.12.04.28.25 for <multiple recipients>\n\t(version=TLSv1 cipher=ECDHE-RSA-RC4-SHA bits=128/128);\n\tTue, 12 Aug 2014 04:28:25 -0700 (PDT)"
            ],
            "From": "Olivier MATZ <olivier.matz@6wind.com>",
            "Message-ID": "<53E9FA58.1060600@6wind.com>",
            "List-Id": "patches and discussions about DPDK <dev.dpdk.org>",
            "Subject": "Re: [dpdk-dev] [RFC PATCH 09/14] Fix performance regression due to\n\tmoved pool ptr",
            "List-Archive": "<http://dpdk.org/ml/archives/dev/>",
            "X-List-Received-Date": "Tue, 12 Aug 2014 11:25:31 -0000",
            "List-Unsubscribe": "<http://dpdk.org/ml/options/dev>,\n\t<mailto:dev-request@dpdk.org?subject=unsubscribe>",
            "Return-Path": "<olivier.matz@6wind.com>",
            "List-Post": "<mailto:dev@dpdk.org>",
            "X-Received": "by 10.194.187.4 with SMTP id fo4mr4543463wjc.35.1407842906417;\n\tTue, 12 Aug 2014 04:28:26 -0700 (PDT)",
            "X-Mailman-Version": "2.1.15"
        }
    }
]