DPDK patches and discussions
 help / color / mirror / Atom feed
From: zengxg14 <zengxg14@gmail.com>
To: dev <dev@dpdk.org>
Subject: [dpdk-dev] testpmd drops many packets
Date: Tue, 18 Jun 2013 12:18:07 +0800	[thread overview]
Message-ID: <2013061812175449782514@gmail.com> (raw)

[-- Attachment #1: Type: text/plain, Size: 2320 bytes --]

Hi.

I use testpmd to test the throughput, but it drops many packets.

Here is my hardware:
Intel Xeon E5645,   2 sockets,  HT is closed, the total cores number is 12.
64GB memory
Intel 82599EB SFP+,  only one port.
Redhat 6.3 (2.6.32-279.el6.x86_64)
ixia send packets, line rate with 200 bytes packet. Packets are have random source ip and dest ip.

The command i run:
 ./testpmd -c fff -n 3 -- -i  --coremask=1e --portmask=1 --rss-ip --rxq 4 --txq 4 --rxd 2048 --txd 2048 --burst 512
The coremask set to 1e, so i can use 4 cores to receive packets from 4 queues.

Set the engine to rx_only_engine.
         struct fwd_engine *cur_fwd_eng = &rx_only_engine;

I also changed testpmd.c and ixgbe_82599.c to make it run.  
Here is what i changed:
(1) In main(), I delete the function rte_igb_pmd_init(), SSH need to use igb nic.

(2) In fucntion init_config(), i reset the nb_mbuf_per_pool. I have to, otherwise the testpmd tells alloc rx mbufs failed.
nb_mbuf_per_pool = (nb_rxd + (nb_lcores * mb_mempool_cache) +
                nb_txd + MAX_PKT_BURST) * nb_rxq;

(3) In lib/librte_pmd_ixgbe/ixgbe/ixgbe_82599.c, function "ixgbe_setup_sfp_modules_82599".
I comment this three lines.

//                      DEBUGOUT("sfp module setup not complete\n");
//                      ret_val = IXGBE_ERR_SFP_SETUP_NOT_COMPLETE;
//                      goto setup_sfp_out;

I don't know why the "sfp module setup not complete", I simply comment them to make ixgbe can be  init. 

Run the command, use ixia send some packets after start. Here is the output.

testpmd> start
  rxonly packet forwarding - CRC stripping disabled - packets/burst=512
  nb forwarding cores=4 - nb forwarding ports=1
  RX queues=4 - RX desc=2048 - RX free threshold=0
  RX threshold registers: pthresh=8 hthresh=8 wthresh=4
  TX queues=4 - TX desc=2048 - TX free threshold=0
  TX threshold registers: pthresh=36 hthresh=0 wthresh=0
  TX RS bit threshold=0
testpmd> show port stats 0

  ######################## NIC statistics for port 0  ########################
  RX-packets: 737543992  RX-errors: 393984575 RX-bytes: 68719476735
  TX-packets: 0          TX-errors: 0         TX-bytes: 0
  ############################################################################
testpmd> quit





zengxg14

[-- Attachment #2: Type: text/html, Size: 4294 bytes --]

                 reply	other threads:[~2013-06-18  4:18 UTC|newest]

Thread overview: [no followups] expand[flat|nested]  mbox.gz  Atom feed

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=2013061812175449782514@gmail.com \
    --to=zengxg14@gmail.com \
    --cc=dev@dpdk.org \
    /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).