DPDK patches and discussions
 help / color / mirror / Atom feed
From: Gregory Etelson <gregory@weka.io>
To: dev <dev@dpdk.org>
Cc: users@dpdk.org
Subject: Re: [dpdk-dev] net/i40e: TX descriptor is not done
Date: Sun, 15 Jan 2017 11:08:53 +0200	[thread overview]
Message-ID: <CAO--2fGACYp++H-04spf4KDXWya5iaZfEVTwa0SMWgdgot2O_Q@mail.gmail.com> (raw)
In-Reply-To: <36207324.ubtIbUzSEP@polaris>

Update

The fault is relevant to VF only
DPDK over i40e PF functions correctly

Regards,
Gregory

On Thu, Jan 12, 2017 at 11:14 AM, Gregory Etelson <gregory@weka.io> wrote:

> Hello,
>
>
>
> I have a standalone utility that implements
>
> ICMP ping over DPDK.
>
> When I run the utility with i40e PMD over VF it stacks with the following
> output and never recovers.
>
> The last reported  tx_tail value was 4095. TX queue length in that run was
> 4096
>
> The fault was reproduced on several Dell PowerEdge R630 servers
>
>
>
> My environment:
>
> DPDK 16.11 + 6809e62e555c7b36d248a0e8086e3c3bbbb87a37 (net/i40e: enable
> VF MTU change)
>
> i40e: version: 1.5.25, firmware-version: 5.04 0x80002537 0.0.0
>
> Regards,
>
> Gregory
>
> PMD: i40e_xmit_pkts(): port_id=0 queue_id=0 tx_tail=4094 nb_tx=1
>
> PMD: i40e_rxd_to_vlan_tci(): Mbuf vlan_tci: 0, vlan_tci_outer: 0
>
> PMD: i40e_rxd_to_vlan_tci(): Mbuf vlan_tci: 0, vlan_tci_outer: 0
>
> PMD: i40e_rxd_to_vlan_tci(): Mbuf vlan_tci: 0, vlan_tci_outer: 0
>
> IN[0] ETH[00:50:56:88:A4:F9->46:51:31:29:89:82 proto 0800]
> IP[10.222.35.7->10.222.131.1 len 498 proto 01] ICMP[REPLY seq 4090]
>
> IN[0] ETH[00:50:56:88:A4:F9->46:51:31:29:89:82 proto 0800]
> IP[10.222.35.7->10.222.131.1 len 498 proto 01] ICMP[REPLY seq 4091]
>
> IN[0] ETH[00:50:56:88:A4:F9->46:51:31:29:89:82 proto 0800]
> IP[10.222.35.7->10.222.131.1 len 498 proto 01] ICMP[REPLY seq 4092]
>
> OUT[0] ETH[46:51:31:29:89:82->00:50:56:88:A4:F9 proto 0800]
> IP[10.222.131.1->10.222.35.7 len 498 proto 01] ICMP[REQUEST seq 4093]
>
> PMD: i40e_xmit_cleanup(): TX descriptor 31 is not done (port=0 queue=0)
>
> PMD: i40e_xmit_pkts(): mbuf: 0x7efebc07c500, TDD[4094]:
>
> buf_dma_addr: 0x81de7c600;
>
> td_cmd: 0x4;
>
> td_offset: 0;
>
> td_len: 512;
>
> td_tag: 0;
>
>
>
>
>
> PMD: i40e_xmit_pkts(): port_id=0 queue_id=0 tx_tail=4095 nb_tx=1
>
> PMD: i40e_rxd_to_vlan_tci(): Mbuf vlan_tci: 0, vlan_tci_outer: 0
>
> IN[0] ETH[00:50:56:88:A4:F9->46:51:31:29:89:82 proto 0800]
> IP[10.222.35.7->10.222.131.1 len 498 proto 01] ICMP[REPLY seq 4093]
>
> OUT[0] ETH[46:51:31:29:89:82->00:50:56:88:A4:F9 proto 0800]
> IP[10.222.131.1->10.222.35.7 len 498 proto 01] ICMP[REQUEST seq 4094]
>
> PMD: i40e_xmit_cleanup(): TX descriptor 31 is not done (port=0 queue=0)
>
> PMD: i40e_xmit_cleanup(): TX descriptor 31 is not done (port=0 queue=0)
>
> PMD: i40e_xmit_cleanup(): TX descriptor 31 is not done (port=0 queue=0)
>

  reply	other threads:[~2017-01-15  9:08 UTC|newest]

Thread overview: 3+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-01-12  9:14 Gregory Etelson
2017-01-15  9:08 ` Gregory Etelson [this message]
2017-01-27  9:43   ` [dpdk-dev] [dpdk-users] " Muhammad Zain-ul-Abideen

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=CAO--2fGACYp++H-04spf4KDXWya5iaZfEVTwa0SMWgdgot2O_Q@mail.gmail.com \
    --to=gregory@weka.io \
    --cc=dev@dpdk.org \
    --cc=users@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).