DPDK patches and discussions
 help / color / mirror / Atom feed
From: Raslan Darawsheh <rasland@mellanox.com>
To: Pavan Nikhilesh Bhagavatula <pbhagavatula@marvell.com>,
	Jerin Jacob Kollanukkaran <jerinj@marvell.com>,
	Thomas Monjalon <thomas@monjalon.net>,
	"arybchenko@solarflare.com" <arybchenko@solarflare.com>,
	"ferruh.yigit@intel.com" <ferruh.yigit@intel.com>,
	"bernard.iremonger@intel.com" <bernard.iremonger@intel.com>,
	Ali Alnubani <alialnu@mellanox.com>
Cc: "dev@dpdk.org" <dev@dpdk.org>
Subject: Re: [dpdk-dev] [PATCH v6 1/4] app/testpmd: move eth header generation outside the loop
Date: Tue, 2 Apr 2019 15:21:30 +0000	[thread overview]
Message-ID: <DB3PR0502MB3964BC85EF42425F7113000EC2560@DB3PR0502MB3964.eurprd05.prod.outlook.com> (raw)
Message-ID: <20190402152130.-06zH4yQFVaa5jptp1CBI_d_g8a7EEoJxwXtZv8sGv8@z> (raw)
In-Reply-To: <20190402095255.848-1-pbhagavatula@marvell.com>

Hi,

The performance issue that we saw in Mellanox is now fixed with latest version:

The issue was with the packet len calculation that was changed in the latest versions > 4:
diff --git a/app/test-pmd/txonly.c b/app/test-pmd/txonly.c
index af0be89..2f40949 100644
--- a/app/test-pmd/txonly.c
+++ b/app/test-pmd/txonly.c
@@ -176,6 +176,7 @@ pkt_burst_prepare(struct rte_mbuf *pkt, struct rte_mempool *mbp,
        pkt->l3_len = sizeof(struct ipv4_hdr);

        pkt_seg = pkt;
+       pkt_len = pkt->data_len;
        for (i = 1; i < nb_segs; i++) {
                pkt_seg->next = pkt_segs[i - 1];
                pkt_seg = pkt_seg->next;
@@ -198,7 +199,7 @@ pkt_burst_prepare(struct rte_mbuf *pkt, struct rte_mempool *mbp,
         * burst of packets to be transmitted.
         */
        pkt->nb_segs = nb_segs;
-       pkt->pkt_len += pkt_len;
+       pkt->pkt_len = pkt_len;

        return true;

and now we see ~20% improvement in performance.

Kindest regards,
Raslan Darawsheh

> -----Original Message-----
> From: dev <dev-bounces@dpdk.org> On Behalf Of Pavan Nikhilesh
> Bhagavatula
> Sent: Tuesday, April 2, 2019 12:53 PM
> To: Jerin Jacob Kollanukkaran <jerinj@marvell.com>; Thomas Monjalon
> <thomas@monjalon.net>; arybchenko@solarflare.com;
> ferruh.yigit@intel.com; bernard.iremonger@intel.com; Ali Alnubani
> <alialnu@mellanox.com>
> Cc: dev@dpdk.org; Pavan Nikhilesh Bhagavatula
> <pbhagavatula@marvell.com>
> Subject: [dpdk-dev] [PATCH v6 1/4] app/testpmd: move eth header
> generation outside the loop
> 
> From: Pavan Nikhilesh <pbhagavatula@marvell.com>
> 
> Testpmd txonly copies the src/dst mac address of the port being
> processed to ethernet header structure on the stack for every packet.
> Move it outside the loop and reuse it.
> 
> Signed-off-by: Pavan Nikhilesh <pbhagavatula@marvell.com>
> ---
>  v6 Changes
>  - Rebase onto ToT.
>  - Split the changes further
> 
>  v5 Changes
>  - Remove unnecessary change to struct rte_port *txp (movement).
> (Bernard)
> 
>  v4 Changes:
>  - Fix packet len calculation.
> 
>  v3 Changes:
>  - Split the patches for easier review. (Thomas)
>  - Remove unnecessary assignments to 0. (Bernard)
> 
>  v2 Changes:
>  - Use bulk ops for fetching segments. (Andrew Rybchenko)
>  - Fallback to rte_mbuf_raw_alloc if bulk get fails. (Andrew Rybchenko)
>  - Fix mbufs not being freed when there is no more mbufs available for
>  segments. (Andrew Rybchenko)
> 
>  app/test-pmd/txonly.c | 15 ++++++++-------
>  1 file changed, 8 insertions(+), 7 deletions(-)
> 
> diff --git a/app/test-pmd/txonly.c b/app/test-pmd/txonly.c
> index def52a048..0d411dbf4 100644
> --- a/app/test-pmd/txonly.c
> +++ b/app/test-pmd/txonly.c
> @@ -190,6 +190,14 @@ pkt_burst_transmit(struct fwd_stream *fs)
>  		ol_flags |= PKT_TX_QINQ_PKT;
>  	if (tx_offloads & DEV_TX_OFFLOAD_MACSEC_INSERT)
>  		ol_flags |= PKT_TX_MACSEC;
> +
> +	/*
> +	 * Initialize Ethernet header.
> +	 */
> +	ether_addr_copy(&peer_eth_addrs[fs->peer_addr],
> &eth_hdr.d_addr);
> +	ether_addr_copy(&ports[fs->tx_port].eth_addr, &eth_hdr.s_addr);
> +	eth_hdr.ether_type = rte_cpu_to_be_16(ETHER_TYPE_IPv4);
> +
>  	for (nb_pkt = 0; nb_pkt < nb_pkt_per_burst; nb_pkt++) {
>  		pkt = rte_mbuf_raw_alloc(mbp);
>  		if (pkt == NULL) {
> @@ -226,13 +234,6 @@ pkt_burst_transmit(struct fwd_stream *fs)
>  		}
>  		pkt_seg->next = NULL; /* Last segment of packet. */
> 
> -		/*
> -		 * Initialize Ethernet header.
> -		 */
> -		ether_addr_copy(&peer_eth_addrs[fs-
> >peer_addr],&eth_hdr.d_addr);
> -		ether_addr_copy(&ports[fs->tx_port].eth_addr,
> &eth_hdr.s_addr);
> -		eth_hdr.ether_type =
> rte_cpu_to_be_16(ETHER_TYPE_IPv4);
> -
>  		/*
>  		 * Copy headers in first packet segment(s).
>  		 */
> --
> 2.21.0


  parent reply	other threads:[~2019-04-02 15:21 UTC|newest]

Thread overview: 68+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-02-28 19:42 [dpdk-dev] [PATCH] app/testpmd: use mempool bulk get for txonly mode Pavan Nikhilesh Bhagavatula
2019-03-01  7:38 ` Andrew Rybchenko
2019-03-01  8:45   ` [dpdk-dev] [EXT] " Pavan Nikhilesh Bhagavatula
2019-03-01 13:47 ` [dpdk-dev] [PATCH v2] app/testpmd: add " Pavan Nikhilesh Bhagavatula
2019-03-19 16:48   ` Ferruh Yigit
2019-03-19 16:48     ` Ferruh Yigit
2019-03-20  4:53     ` Pavan Nikhilesh Bhagavatula
2019-03-20  4:53       ` Pavan Nikhilesh Bhagavatula
2019-03-26  8:43       ` Ferruh Yigit
2019-03-26  8:43         ` Ferruh Yigit
2019-03-26 11:00   ` Thomas Monjalon
2019-03-26 11:00     ` Thomas Monjalon
2019-03-26 11:50     ` Iremonger, Bernard
2019-03-26 11:50       ` Iremonger, Bernard
2019-03-26 12:06       ` Pavan Nikhilesh Bhagavatula
2019-03-26 12:06         ` Pavan Nikhilesh Bhagavatula
2019-03-26 13:16         ` Jerin Jacob Kollanukkaran
2019-03-26 13:16           ` Jerin Jacob Kollanukkaran
2019-03-26 12:26 ` [dpdk-dev] [PATCH v3 1/2] app/testpmd: optimize testpmd " Pavan Nikhilesh Bhagavatula
2019-03-26 12:26   ` Pavan Nikhilesh Bhagavatula
2019-03-26 12:27   ` [dpdk-dev] [PATCH v3 2/2] app/testpmd: add mempool bulk get for " Pavan Nikhilesh Bhagavatula
2019-03-26 12:27     ` Pavan Nikhilesh Bhagavatula
2019-03-26 13:03 ` [dpdk-dev] [PATCH v4 1/2] app/testpmd: optimize testpmd " Pavan Nikhilesh Bhagavatula
2019-03-26 13:03   ` Pavan Nikhilesh Bhagavatula
2019-03-26 13:03   ` [dpdk-dev] [PATCH v4 2/2] app/testpmd: add mempool bulk get for " Pavan Nikhilesh Bhagavatula
2019-03-26 13:03     ` Pavan Nikhilesh Bhagavatula
2019-03-26 16:13   ` [dpdk-dev] [PATCH v4 1/2] app/testpmd: optimize testpmd " Iremonger, Bernard
2019-03-26 16:13     ` Iremonger, Bernard
2019-03-31 13:14 ` [dpdk-dev] [PATCH v5 " Pavan Nikhilesh Bhagavatula
2019-03-31 13:14   ` Pavan Nikhilesh Bhagavatula
2019-03-31 13:14   ` [dpdk-dev] [PATCH v5 2/2] app/testpmd: add mempool bulk get for " Pavan Nikhilesh Bhagavatula
2019-03-31 13:14     ` Pavan Nikhilesh Bhagavatula
2019-04-01 20:25   ` [dpdk-dev] [PATCH v5 1/2] app/testpmd: optimize testpmd " Ferruh Yigit
2019-04-01 20:25     ` Ferruh Yigit
2019-04-01 20:53     ` Thomas Monjalon
2019-04-01 20:53       ` Thomas Monjalon
2019-04-02  1:03       ` Jerin Jacob Kollanukkaran
2019-04-02  1:03         ` Jerin Jacob Kollanukkaran
2019-04-02  7:06         ` Thomas Monjalon
2019-04-02  7:06           ` Thomas Monjalon
2019-04-02  8:31           ` Jerin Jacob Kollanukkaran
2019-04-02  8:31             ` Jerin Jacob Kollanukkaran
2019-04-02  9:03   ` Ali Alnubani
2019-04-02  9:03     ` Ali Alnubani
2019-04-02  9:06     ` Pavan Nikhilesh Bhagavatula
2019-04-02  9:06       ` Pavan Nikhilesh Bhagavatula
2019-04-02  9:53 ` [dpdk-dev] [PATCH v6 1/4] app/testpmd: move eth header generation outside the loop Pavan Nikhilesh Bhagavatula
2019-04-02  9:53   ` Pavan Nikhilesh Bhagavatula
2019-04-02  9:53   ` [dpdk-dev] [PATCH v6 2/4] app/testpmd: use bulk ops for allocating segments Pavan Nikhilesh Bhagavatula
2019-04-02  9:53     ` Pavan Nikhilesh Bhagavatula
2019-04-02  9:53   ` [dpdk-dev] [PATCH v6 3/4] app/testpmd: move pkt prepare logic into a separate function Pavan Nikhilesh Bhagavatula
2019-04-02  9:53     ` Pavan Nikhilesh Bhagavatula
2019-04-09  9:28     ` Lin, Xueqin
2019-04-09  9:28       ` Lin, Xueqin
2019-04-09  9:32       ` Pavan Nikhilesh Bhagavatula
2019-04-09  9:32         ` Pavan Nikhilesh Bhagavatula
2019-04-09 12:24         ` Yao, Lei A
2019-04-09 12:24           ` Yao, Lei A
2019-04-09 12:29           ` Ferruh Yigit
2019-04-09 12:29             ` Ferruh Yigit
2019-04-02  9:53   ` [dpdk-dev] [PATCH v6 4/4] app/testpmd: add mempool bulk get for txonly mode Pavan Nikhilesh Bhagavatula
2019-04-02  9:53     ` Pavan Nikhilesh Bhagavatula
2019-04-02 15:21   ` Raslan Darawsheh [this message]
2019-04-02 15:21     ` [dpdk-dev] [PATCH v6 1/4] app/testpmd: move eth header generation outside the loop Raslan Darawsheh
2019-04-04 16:23   ` Ferruh Yigit
2019-04-04 16:23     ` Ferruh Yigit
2019-04-05 17:37   ` Ferruh Yigit
2019-04-05 17:37     ` Ferruh Yigit

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=DB3PR0502MB3964BC85EF42425F7113000EC2560@DB3PR0502MB3964.eurprd05.prod.outlook.com \
    --to=rasland@mellanox.com \
    --cc=alialnu@mellanox.com \
    --cc=arybchenko@solarflare.com \
    --cc=bernard.iremonger@intel.com \
    --cc=dev@dpdk.org \
    --cc=ferruh.yigit@intel.com \
    --cc=jerinj@marvell.com \
    --cc=pbhagavatula@marvell.com \
    --cc=thomas@monjalon.net \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).