List comments

GET /api/patches/349/comments/?order=submitter
HTTP 200 OK
Allow: GET, HEAD, OPTIONS
Content-Type: application/json
Vary: Accept

[
    {
        "id": 779,
        "web_url": "https://patches.dpdk.org/comment/779/",
        "msgid": "<59AF69C657FD0841A61C55336867B5B0343F160F@IRSMSX103.ger.corp.intel.com>",
        "date": "2014-09-15T08:19:31",
        "subject": "Re: [dpdk-dev] [PATCH v2 02/13] mbuf: reorder fields by time of use",
        "submitter": {
            "id": 20,
            "url": "https://patches.dpdk.org/api/people/20/",
            "name": "Bruce Richardson",
            "email": "bruce.richardson@intel.com"
        },
        "content": "> -----Original Message-----\n> From: Liu, Jijiang\n> Sent: Monday, September 15, 2014 8:12 AM\n> To: Richardson, Bruce; dev@dpdk.org\n> Subject: RE: [dpdk-dev] [PATCH v2 02/13] mbuf: reorder fields by time of use\n> \n> Hi Bruce,\n> \n> > -----Original Message-----\n> > From: dev [mailto:dev-bounces@dpdk.org] On Behalf Of Bruce Richardson\n> > Sent: Thursday, September 11, 2014 9:16 PM\n> > To: dev@dpdk.org\n> > Subject: [dpdk-dev] [PATCH v2 02/13] mbuf: reorder fields by time of use\n> >\n> > *  Reorder the fields in the mbuf so that we have fields that are used together\n> > side-by-side in the structure. This means that we have a contiguous block of\n> > 8-bytes in the mbuf which are used to reset an mbuf of descriptor rearm, and a\n> > block of 16-bytes of data (excluding flags) which are set on RX from the\n> > received packet descriptor.\n> > * Use dummy fields as appropriate to ensure alignment or to reserve gaps for\n> > later field additions.\n> > * Place most items which are not used by fast-path RX separately at the end of\n> > the structure so they can later be moved to a separate cache line.\n> > [The l2/l3 length fields are not moved at this stage as doing so will cause\n> > overflow to the next cache line].\n> >\n> > Updated in V2:\n> > * Updated the KNI buffer structure to match that of new mbuf\n> > * Cleaned up commit message typos.\n> >\n> > Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>\n> > ---\n> >  .../linuxapp/eal/include/exec-env/rte_kni_common.h | 12 ++++++-----\n> >  lib/librte_mbuf/rte_mbuf.h                         | 25\n> > ++++++++++++----------\n> >  2 files changed, 21 insertions(+), 16 deletions(-)\n> >\n> > diff --git a/lib/librte_eal/linuxapp/eal/include/exec-env/rte_kni_common.h\n> > b/lib/librte_eal/linuxapp/eal/include/exec-env/rte_kni_common.h\n> > index 07908ac..f2b502c 100644\n> > --- a/lib/librte_eal/linuxapp/eal/include/exec-env/rte_kni_common.h\n> > +++ b/lib/librte_eal/linuxapp/eal/include/exec-env/rte_kni_common.h\n> > @@ -108,15 +108,17 @@ struct rte_kni_fifo {\n> >   * Padding is necessary to assure the offsets of these fields\n> >   */\n> >  struct rte_kni_mbuf {\n> > -\tvoid *pool;\n> >  \tvoid *buf_addr;\n> > -\tchar pad0[16];\n> > -\tvoid *next;\n> > +\tchar pad0[10];\n> >  \tuint16_t data_off;      /**< Start address of data in segment buffer. */\n> > +\tchar pad1[4];\n> > +\tuint16_t ol_flags;      /**< Offload features. */\n> > +\tchar pad2[8];\n> >  \tuint16_t data_len;      /**< Amount of data in segment buffer. */\n> >  \tuint32_t pkt_len;       /**< Total pkt len: sum of all segment data_len.\n> > */\n> > -\tchar pad2[4];\n> > -\tuint16_t ol_flags;      /**< Offload features. */\n> > +\tchar pad3[8];\n> > +\tvoid *pool;\n> > +\tvoid *next;\n> >  } __attribute__((__aligned__(64)));\n> >\n> >  /*\n> > diff --git a/lib/librte_mbuf/rte_mbuf.h b/lib/librte_mbuf/rte_mbuf.h index\n> > 71080e5..413a5a1 100644\n> > --- a/lib/librte_mbuf/rte_mbuf.h\n> > +++ b/lib/librte_mbuf/rte_mbuf.h\n> > @@ -115,16 +115,12 @@ extern \"C\" {\n> >   * The generic rte_mbuf, containing a packet mbuf.\n> >   */\n> >  struct rte_mbuf {\n> > -\tstruct rte_mempool *pool; /**< Pool from which mbuf was allocated.\n> */\n> >  \tvoid *buf_addr;           /**< Virtual address of segment buffer. */\n> >  \tphys_addr_t buf_physaddr; /**< Physical address of segment buffer. */\n> > -\tuint16_t buf_len;         /**< Length of segment buffer. */\n> >\n> > -\t/* valid for any segment */\n> > -\tstruct rte_mbuf *next;    /**< Next segment of scattered packet. */\n> > +\t/* next 8 bytes are initialised on RX descriptor rearm */\n> > +\tuint16_t buf_len;         /**< Length of segment buffer. */\n> >  \tuint16_t data_off;\n> > -\tuint16_t data_len;        /**< Amount of data in segment buffer. */\n> > -\tuint32_t pkt_len;         /**< Total pkt len: sum of all segments. */\n> >\n> >  #ifdef RTE_MBUF_REFCNT\n> >  \t/**\n> > @@ -142,14 +138,17 @@ struct rte_mbuf {\n> >  #else\n> >  \tuint16_t refcnt_reserved;     /**< Do not use this field */\n> >  #endif\n> > -\tuint16_t reserved;            /**< Unused field. Required for padding\n> > */\n> > -\tuint16_t ol_flags;            /**< Offload features. */\n> > -\n> > -\t/* these fields are valid for first segment only */\n> >  \tuint8_t nb_segs;        /**< Number of segments. */\n> >  \tuint8_t port;           /**< Input port. */\n> >\n> > -\t/* offload features, valid for first segment only */\n> > +\tuint16_t ol_flags;      /**< Offload features. */\n> > +\tuint16_t reserved0;     /**< Unused field. Required for padding */\n> > +\tuint32_t reserved1;     /**< Unused field. Required for padding */\n> > +\n> > +\t/* remaining bytes are set on RX when pulling packet from descriptor */\n> > +\tuint16_t reserved2;     /**< Unused field. Required for padding */\n> > +\tuint16_t data_len;      /**< Amount of data in segment buffer. */\n> > +\tuint32_t pkt_len;       /**< Total pkt len: sum of all segments. */\n> >  \tunion {\n> >  \t\tuint16_t l2_l3_len; /**< combined l2/l3 lengths as single var */\n> >  \t\tstruct {\n> > @@ -167,6 +166,10 @@ struct rte_mbuf {\n> >  \t\tuint32_t sched;     /**< Hierarchical scheduler */\n> >  \t} hash;                 /**< hash information */\n> >\n> > +\t/* fields only used in slow path or on TX */\n> > +\tstruct rte_mempool *pool; /**< Pool from which mbuf was allocated.\n> */\n> > +\tstruct rte_mbuf *next;    /**< Next segment of scattered packet. */\n> > +\n> >  \tunion {\n> >  \t\tuint8_t metadata[0];\n> >  \t\tuint16_t metadata16[0];\n> > --\n> > 1.9.3\n> \n> It seems that you removed the inner_l3_len and inner_l2_len fields from the\n> rte_mbuf.h structure, what is the reason?\n> \n> /Jijiang Liu\n\nNo, those fields were never added to the mbuf, they were simply proposed as a new field addition in an RFC patch set. The adding of new fields to the mbuf is beyond the scope of the two patch sets already submitted. Those patch sets merely reorder the existing l2 and l3 length fields without changing their size or name.\n\n/Bruce",
        "headers": {
            "Return-Path": "<dev-bounces@dpdk.org>",
            "References": "<1409759378-10113-1-git-send-email-bruce.richardson@intel.com>\n\t<1410441347-22840-1-git-send-email-bruce.richardson@intel.com>\n\t<1410441347-22840-3-git-send-email-bruce.richardson@intel.com>\n\t<1ED644BD7E0A5F4091CF203DAFB8E4CC01D701BA@SHSMSX101.ccr.corp.intel.com>",
            "X-Mailman-Version": "2.1.15",
            "X-IronPort-AV": "E=Sophos;i=\"5.04,526,1406617200\"; d=\"scan'208\";a=\"599619762\"",
            "Date": "Mon, 15 Sep 2014 08:19:31 +0000",
            "x-originating-ip": "[163.33.239.182]",
            "List-Post": "<mailto:dev@dpdk.org>",
            "Thread-Index": "AQHPzcKnAqnQAGI7DUOex+lsgDJZ2JwBvFuAgAAjCgA=",
            "Content-Type": "text/plain; charset=\"us-ascii\"",
            "Delivered-To": "patchwork@dpdk.org",
            "X-Original-To": "patchwork@dpdk.org",
            "Received": [
                "from [92.243.14.124] (localhost [IPv6:::1])\n\tby dpdk.org (Postfix) with ESMTP id E7BB4595B;\n\tMon, 15 Sep 2014 10:14:10 +0200 (CEST)",
                "from mga01.intel.com (mga01.intel.com [192.55.52.88])\n\tby dpdk.org (Postfix) with ESMTP id 297C058E8\n\tfor <dev@dpdk.org>; Mon, 15 Sep 2014 10:14:08 +0200 (CEST)",
                "from fmsmga002.fm.intel.com ([10.253.24.26])\n\tby fmsmga101.fm.intel.com with ESMTP; 15 Sep 2014 01:19:39 -0700",
                "from irsmsx101.ger.corp.intel.com ([163.33.3.153])\n\tby fmsmga002.fm.intel.com with ESMTP; 15 Sep 2014 01:19:34 -0700",
                "from irsmsx106.ger.corp.intel.com (163.33.3.31) by\n\tIRSMSX101.ger.corp.intel.com (163.33.3.153) with Microsoft SMTP\n\tServer (TLS) id 14.3.195.1; Mon, 15 Sep 2014 09:19:33 +0100",
                "from irsmsx103.ger.corp.intel.com ([169.254.3.112]) by\n\tIRSMSX106.ger.corp.intel.com ([169.254.8.3]) with mapi id\n\t14.03.0195.001; Mon, 15 Sep 2014 09:19:32 +0100"
            ],
            "Subject": "Re: [dpdk-dev] [PATCH v2 02/13] mbuf: reorder fields by time of use",
            "Sender": "\"dev\" <dev-bounces@dpdk.org>",
            "List-Help": "<mailto:dev-request@dpdk.org?subject=help>",
            "Content-Language": "en-US",
            "Accept-Language": "en-GB, en-US",
            "Message-ID": "<59AF69C657FD0841A61C55336867B5B0343F160F@IRSMSX103.ger.corp.intel.com>",
            "X-MS-Has-Attach": "",
            "X-BeenThere": "dev@dpdk.org",
            "From": "\"Richardson, Bruce\" <bruce.richardson@intel.com>",
            "List-Archive": "<http://dpdk.org/ml/archives/dev/>",
            "X-ExtLoop1": "1",
            "List-Subscribe": "<http://dpdk.org/ml/listinfo/dev>,\n\t<mailto:dev-request@dpdk.org?subject=subscribe>",
            "List-Id": "patches and discussions about DPDK <dev.dpdk.org>",
            "Precedence": "list",
            "Thread-Topic": "[dpdk-dev] [PATCH v2 02/13] mbuf: reorder fields by time of use",
            "In-Reply-To": "<1ED644BD7E0A5F4091CF203DAFB8E4CC01D701BA@SHSMSX101.ccr.corp.intel.com>",
            "Errors-To": "dev-bounces@dpdk.org",
            "List-Unsubscribe": "<http://dpdk.org/ml/options/dev>,\n\t<mailto:dev-request@dpdk.org?subject=unsubscribe>",
            "MIME-Version": "1.0",
            "Content-Transfer-Encoding": "quoted-printable",
            "To": "\"Liu, Jijiang\" <jijiang.liu@intel.com>, \"dev@dpdk.org\" <dev@dpdk.org>",
            "X-MS-TNEF-Correlator": ""
        }
    },
    {
        "id": 776,
        "web_url": "https://patches.dpdk.org/comment/776/",
        "msgid": "<1ED644BD7E0A5F4091CF203DAFB8E4CC01D701BA@SHSMSX101.ccr.corp.intel.com>",
        "date": "2014-09-15T07:11:51",
        "subject": "Re: [dpdk-dev] [PATCH v2 02/13] mbuf: reorder fields by time of use",
        "submitter": {
            "id": 52,
            "url": "https://patches.dpdk.org/api/people/52/",
            "name": "Jijiang Liu",
            "email": "jijiang.liu@intel.com"
        },
        "content": "Hi Bruce,\n\n> -----Original Message-----\n> From: dev [mailto:dev-bounces@dpdk.org] On Behalf Of Bruce Richardson\n> Sent: Thursday, September 11, 2014 9:16 PM\n> To: dev@dpdk.org\n> Subject: [dpdk-dev] [PATCH v2 02/13] mbuf: reorder fields by time of use\n> \n> *  Reorder the fields in the mbuf so that we have fields that are used together\n> side-by-side in the structure. This means that we have a contiguous block of\n> 8-bytes in the mbuf which are used to reset an mbuf of descriptor rearm, and a\n> block of 16-bytes of data (excluding flags) which are set on RX from the\n> received packet descriptor.\n> * Use dummy fields as appropriate to ensure alignment or to reserve gaps for\n> later field additions.\n> * Place most items which are not used by fast-path RX separately at the end of\n> the structure so they can later be moved to a separate cache line.\n> [The l2/l3 length fields are not moved at this stage as doing so will cause\n> overflow to the next cache line].\n> \n> Updated in V2:\n> * Updated the KNI buffer structure to match that of new mbuf\n> * Cleaned up commit message typos.\n> \n> Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>\n> ---\n>  .../linuxapp/eal/include/exec-env/rte_kni_common.h | 12 ++++++-----\n>  lib/librte_mbuf/rte_mbuf.h                         | 25\n> ++++++++++++----------\n>  2 files changed, 21 insertions(+), 16 deletions(-)\n> \n> diff --git a/lib/librte_eal/linuxapp/eal/include/exec-env/rte_kni_common.h\n> b/lib/librte_eal/linuxapp/eal/include/exec-env/rte_kni_common.h\n> index 07908ac..f2b502c 100644\n> --- a/lib/librte_eal/linuxapp/eal/include/exec-env/rte_kni_common.h\n> +++ b/lib/librte_eal/linuxapp/eal/include/exec-env/rte_kni_common.h\n> @@ -108,15 +108,17 @@ struct rte_kni_fifo {\n>   * Padding is necessary to assure the offsets of these fields\n>   */\n>  struct rte_kni_mbuf {\n> -\tvoid *pool;\n>  \tvoid *buf_addr;\n> -\tchar pad0[16];\n> -\tvoid *next;\n> +\tchar pad0[10];\n>  \tuint16_t data_off;      /**< Start address of data in segment buffer. */\n> +\tchar pad1[4];\n> +\tuint16_t ol_flags;      /**< Offload features. */\n> +\tchar pad2[8];\n>  \tuint16_t data_len;      /**< Amount of data in segment buffer. */\n>  \tuint32_t pkt_len;       /**< Total pkt len: sum of all segment data_len.\n> */\n> -\tchar pad2[4];\n> -\tuint16_t ol_flags;      /**< Offload features. */\n> +\tchar pad3[8];\n> +\tvoid *pool;\n> +\tvoid *next;\n>  } __attribute__((__aligned__(64)));\n> \n>  /*\n> diff --git a/lib/librte_mbuf/rte_mbuf.h b/lib/librte_mbuf/rte_mbuf.h index\n> 71080e5..413a5a1 100644\n> --- a/lib/librte_mbuf/rte_mbuf.h\n> +++ b/lib/librte_mbuf/rte_mbuf.h\n> @@ -115,16 +115,12 @@ extern \"C\" {\n>   * The generic rte_mbuf, containing a packet mbuf.\n>   */\n>  struct rte_mbuf {\n> -\tstruct rte_mempool *pool; /**< Pool from which mbuf was allocated. */\n>  \tvoid *buf_addr;           /**< Virtual address of segment buffer. */\n>  \tphys_addr_t buf_physaddr; /**< Physical address of segment buffer. */\n> -\tuint16_t buf_len;         /**< Length of segment buffer. */\n> \n> -\t/* valid for any segment */\n> -\tstruct rte_mbuf *next;    /**< Next segment of scattered packet. */\n> +\t/* next 8 bytes are initialised on RX descriptor rearm */\n> +\tuint16_t buf_len;         /**< Length of segment buffer. */\n>  \tuint16_t data_off;\n> -\tuint16_t data_len;        /**< Amount of data in segment buffer. */\n> -\tuint32_t pkt_len;         /**< Total pkt len: sum of all segments. */\n> \n>  #ifdef RTE_MBUF_REFCNT\n>  \t/**\n> @@ -142,14 +138,17 @@ struct rte_mbuf {\n>  #else\n>  \tuint16_t refcnt_reserved;     /**< Do not use this field */\n>  #endif\n> -\tuint16_t reserved;            /**< Unused field. Required for padding\n> */\n> -\tuint16_t ol_flags;            /**< Offload features. */\n> -\n> -\t/* these fields are valid for first segment only */\n>  \tuint8_t nb_segs;        /**< Number of segments. */\n>  \tuint8_t port;           /**< Input port. */\n> \n> -\t/* offload features, valid for first segment only */\n> +\tuint16_t ol_flags;      /**< Offload features. */\n> +\tuint16_t reserved0;     /**< Unused field. Required for padding */\n> +\tuint32_t reserved1;     /**< Unused field. Required for padding */\n> +\n> +\t/* remaining bytes are set on RX when pulling packet from descriptor */\n> +\tuint16_t reserved2;     /**< Unused field. Required for padding */\n> +\tuint16_t data_len;      /**< Amount of data in segment buffer. */\n> +\tuint32_t pkt_len;       /**< Total pkt len: sum of all segments. */\n>  \tunion {\n>  \t\tuint16_t l2_l3_len; /**< combined l2/l3 lengths as single var */\n>  \t\tstruct {\n> @@ -167,6 +166,10 @@ struct rte_mbuf {\n>  \t\tuint32_t sched;     /**< Hierarchical scheduler */\n>  \t} hash;                 /**< hash information */\n> \n> +\t/* fields only used in slow path or on TX */\n> +\tstruct rte_mempool *pool; /**< Pool from which mbuf was allocated. */\n> +\tstruct rte_mbuf *next;    /**< Next segment of scattered packet. */\n> +\n>  \tunion {\n>  \t\tuint8_t metadata[0];\n>  \t\tuint16_t metadata16[0];\n> --\n> 1.9.3\n\nIt seems that you removed the inner_l3_len and inner_l2_len fields from the rte_mbuf.h structure, what is the reason?\n\n/Jijiang Liu",
        "headers": {
            "Return-Path": "<dev-bounces@dpdk.org>",
            "References": "<1409759378-10113-1-git-send-email-bruce.richardson@intel.com>\n\t<1410441347-22840-1-git-send-email-bruce.richardson@intel.com>\n\t<1410441347-22840-3-git-send-email-bruce.richardson@intel.com>",
            "X-Mailman-Version": "2.1.15",
            "X-IronPort-AV": "E=Sophos;i=\"5.04,525,1406617200\"; d=\"scan'208\";a=\"602895685\"",
            "Date": "Mon, 15 Sep 2014 07:11:51 +0000",
            "x-originating-ip": "[10.239.127.40]",
            "List-Post": "<mailto:dev@dpdk.org>",
            "Thread-Index": "AQHPzcLMqNDrboJBO0uxnAn2xplffZwByHfw",
            "Content-Type": "text/plain; charset=\"us-ascii\"",
            "Delivered-To": "patchwork@dpdk.org",
            "X-Original-To": "patchwork@dpdk.org",
            "Received": [
                "from [92.243.14.124] (localhost [IPv6:::1])\n\tby dpdk.org (Postfix) with ESMTP id 860223976;\n\tMon, 15 Sep 2014 09:06:28 +0200 (CEST)",
                "from mga09.intel.com (mga09.intel.com [134.134.136.24])\n\tby dpdk.org (Postfix) with ESMTP id DE8792E81\n\tfor <dev@dpdk.org>; Mon, 15 Sep 2014 09:06:25 +0200 (CEST)",
                "from orsmga002.jf.intel.com ([10.7.209.21])\n\tby orsmga102.jf.intel.com with ESMTP; 15 Sep 2014 00:05:46 -0700",
                "from fmsmsx108.amr.corp.intel.com ([10.18.124.206])\n\tby orsmga002.jf.intel.com with ESMTP; 15 Sep 2014 00:11:54 -0700",
                "from fmsmsx118.amr.corp.intel.com (10.18.116.18) by\n\tFMSMSX108.amr.corp.intel.com (10.18.124.206) with Microsoft SMTP\n\tServer (TLS) id 14.3.195.1; Mon, 15 Sep 2014 00:11:54 -0700",
                "from shsmsx151.ccr.corp.intel.com (10.239.6.50) by\n\tfmsmsx118.amr.corp.intel.com (10.18.116.18) with Microsoft SMTP\n\tServer (TLS) id 14.3.195.1; Mon, 15 Sep 2014 00:11:54 -0700",
                "from shsmsx101.ccr.corp.intel.com ([169.254.1.203]) by\n\tSHSMSX151.ccr.corp.intel.com ([169.254.3.172]) with mapi id\n\t14.03.0195.001; Mon, 15 Sep 2014 15:11:52 +0800"
            ],
            "Subject": "Re: [dpdk-dev] [PATCH v2 02/13] mbuf: reorder fields by time of use",
            "Sender": "\"dev\" <dev-bounces@dpdk.org>",
            "List-Help": "<mailto:dev-request@dpdk.org?subject=help>",
            "Content-Language": "en-US",
            "Accept-Language": "en-US",
            "Message-ID": "<1ED644BD7E0A5F4091CF203DAFB8E4CC01D701BA@SHSMSX101.ccr.corp.intel.com>",
            "X-MS-Has-Attach": "",
            "X-BeenThere": "dev@dpdk.org",
            "From": "\"Liu, Jijiang\" <jijiang.liu@intel.com>",
            "List-Archive": "<http://dpdk.org/ml/archives/dev/>",
            "X-ExtLoop1": "1",
            "List-Subscribe": "<http://dpdk.org/ml/listinfo/dev>,\n\t<mailto:dev-request@dpdk.org?subject=subscribe>",
            "List-Id": "patches and discussions about DPDK <dev.dpdk.org>",
            "Precedence": "list",
            "Thread-Topic": "[dpdk-dev] [PATCH v2 02/13] mbuf: reorder fields by time of use",
            "In-Reply-To": "<1410441347-22840-3-git-send-email-bruce.richardson@intel.com>",
            "Errors-To": "dev-bounces@dpdk.org",
            "List-Unsubscribe": "<http://dpdk.org/ml/options/dev>,\n\t<mailto:dev-request@dpdk.org?subject=unsubscribe>",
            "MIME-Version": "1.0",
            "Content-Transfer-Encoding": "quoted-printable",
            "To": "\"Richardson, Bruce\" <bruce.richardson@intel.com>, \"dev@dpdk.org\"\n\t<dev@dpdk.org>",
            "X-MS-TNEF-Correlator": ""
        }
    }
]