DPDK usage discussions
 help / color / mirror / Atom feed
From: Stephen Hemminger <stephen@networkplumber.org>
To: longtb5@viettel.com.vn
Cc: users@dpdk.org
Subject: Re: [dpdk-users] [VMXNET3] vmxnet3_dev_stats_get() segfault when called by pktgen
Date: Thu, 7 Sep 2017 07:58:08 -0700	[thread overview]
Message-ID: <20170907075808.09fc227a@xeon-e3> (raw)
In-Reply-To: <1551920177.73501197.1504745506408.JavaMail.zimbra@viettel.com.vn>

On Thu,  7 Sep 2017 07:51:46 +0700 (ICT)
longtb5@viettel.com.vn wrote:

> Hi, 
> 
> I'm running Ubuntu 16.04 on my VM with vmxnet3 as the NIC. I have successfully installed DPDK
> and managed to run a few sample apps. However when I tried pktgen the kernel threw a SIGSEGV
> without me doing anything yet.
> 
> $ sudo .app/x86_64-native-linuxapp-gcc/pktgen
> 
> Pktgen:/&gt; 
> ====== Pktgen got a Segment Fault
> 
> Obtained 11 stack frames.
> app/x86_64-native-linuxapp-gcc/pktgen() [0x468ba5]
> /lib/x86_64-linux-gnu/libc.so.6(+0x354b0) [0x7f1e618de4b0]
> app/x86_64-native-linuxapp-gcc/pktgen() [0x6c7c70]
> app/x86_64-native-linuxapp-gcc/pktgen(rte_eth_stats_get+0x79) [0x4a3fe9]
> app/x86_64-native-linuxapp-gcc/pktgen(pktgen_process_stats+0xa9) [0x46f0f9]
> app/x86_64-native-linuxapp-gcc/pktgen(rte_timer_manage+0x526) [0x48ca96]
> app/x86_64-native-linuxapp-gcc/pktgen(cli_start+0x26d) [0x71276d]
> app/x86_64-native-linuxapp-gcc/pktgen(pktgen_cli_start+0xb) [0x4509bb]
> app/x86_64-native-linuxapp-gcc/pktgen(main+0x7a6) [0x447b86]
> /lib/x86_64-linux-gnu/libc.so.6(__libc_start_main+0xf0) [0x7f1e618c9830]
> app/x86_64-native-linuxapp-gcc/pktgen(_start+0x29) [0x44a639]
> 
> # gdb .app/x86_64-native-linuxapp-gcc/pktgen
> 
> Pktgen:/&gt; 
> Thread 1 "pktgen" received signal SIGSEGV, Segmentation fault.
> 0x00000000006c7c70 in vmxnet3_dev_stats_get ()
> 
> I tried using older versions of DPDK and pktgen but nothing worked so far.
> 
> Is it a problem on my end? Like, the way I set up the NICs in my VM? Or is it a bug?
> 
> BR,
> 
> Long.

If you modify the Makefiles for pktgen, ethdev, and vmxnet3 to have -g flag
then you will get more symbolic data which makes better backtrace.

  parent reply	other threads:[~2017-09-07 14:58 UTC|newest]

Thread overview: 11+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <142883318.73479844.1504745082183.JavaMail.zimbra@viettel.com.vn>
2017-09-07  0:51 ` longtb5
2017-09-07  7:42   ` longtb5
2017-09-07  9:15     ` longtb5
2017-09-07 14:58   ` Stephen Hemminger [this message]
2017-09-07 16:49     ` Wiles, Keith
2017-09-08  2:07       ` longtb5
2017-09-08  2:22         ` Wiles, Keith
2017-09-08  3:13           ` longtb5
     [not found]           ` <1873902514.79394236.1504839292666.JavaMail.zimbra@viettel.com.vn>
     [not found]             ` <E36F82B2-E740-46D0-9E8E-39DBDC17DC87@intel.com>
2017-09-08  4:41               ` longtb5
2017-09-08 11:43               ` longtb5
2017-09-09  2:28         ` longtb5

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=20170907075808.09fc227a@xeon-e3 \
    --to=stephen@networkplumber.org \
    --cc=longtb5@viettel.com.vn \
    --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).