DPDK patches and discussions
 help / color / mirror / Atom feed
From: gowrishankar muthukrishnan <gowrishankar.m@linux.vnet.ibm.com>
To: Priyanka <ppnaik@cse.iitb.ac.in>, "dev@dpdk.org" <dev@dpdk.org>,
	"users@dpdk.org" <users@dpdk.org>
Cc: "mitaliyada@cse.iitb.ac.in" <mitaliyada@cse.iitb.ac.in>
Subject: Re: [dpdk-dev] Unable to run test_pmd_perf
Date: Thu, 2 Feb 2017 15:28:45 +0530	[thread overview]
Message-ID: <accc2aef-f310-8270-991c-7ecf4d6c7c88@linux.vnet.ibm.com> (raw)
In-Reply-To: <588F35BE.1000409@cse.iitb.ac.in>

On Monday 30 January 2017 06:16 PM, Priyanka wrote:
> Hi All,
>
> We have VMs on a physical server  with both VMs having 1 core 7 GB RAM 
> with DPDK 16.04. The VMs are communicating using SR-IOV (per VM 1 VF 
> is assigned). We thought of running the test_pmd_perf to test the 
> number of cycles taken for RX/TX. But we are unable to get it working. 
> Even if we assign 4 VCPUs to the VM the app says "*no avail lcore to 
> test*."  The command we are using are:
>

As far as I trail its origin in source, alloc_lcore() errors out in a 
situation when you do not have those lcores mentioned in -c or -l to app 
which are from socket where your ports are actually attached. You can 
print out target socket through te_eth_dev_socket_id(port_id).
You need to pass one lcore atleast from this socket, instead of socket 0 
(which is case by default for lcores 0xf).

Use lscpu and find out what lcores you can pass from target socket id.

Thanks,
Gowrishankar

> cd dpdk16.04/app/test
>
> ./build/app/test -c f -- -p 1
>
> RTE>> pmd_perf_autotest
>
> On searching we found that it might be an issue with our VMs using SRIOV.
>
> Please guide us on this.
>
>
> Thanks,
>
> Priyanka
>
>

      reply	other threads:[~2017-02-02  9:59 UTC|newest]

Thread overview: 2+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-01-30 12:46 Priyanka
2017-02-02  9:58 ` gowrishankar muthukrishnan [this message]

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=accc2aef-f310-8270-991c-7ecf4d6c7c88@linux.vnet.ibm.com \
    --to=gowrishankar.m@linux.vnet.ibm.com \
    --cc=dev@dpdk.org \
    --cc=mitaliyada@cse.iitb.ac.in \
    --cc=ppnaik@cse.iitb.ac.in \
    --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).