dev.dpdk.org archive mirror
 help / color / mirror / Atom feed
From: "Burakov, Anatoly" <anatoly.burakov@intel.com>
To: Nilesh <nileshunhale@cse.iitb.ac.in>, dev@dpdk.org
Cc: diptyaroop <diptyaroop@cse.iitb.ac.in>
Subject: Re: [dpdk-dev] WARNING! Base virtual address hint not respected!
Date: Mon, 12 Aug 2019 10:31:22 +0100	[thread overview]
Message-ID: <06560e08-d865-c4d8-a3c7-62ae7a482e39@intel.com> (raw)
In-Reply-To: <4c9d1b7f-c27c-62db-5160-adc5af87dbc3@cse.iitb.ac.in>

On 07-Aug-19 11:51 AM, Nilesh wrote:
> Hello,
> 
> We are trying to build an application over DPDK, but we are getting this 
> warning when we call
> rte_eal_init().
> 
> EAL: Detected 24 lcore(s)
> EAL: Detected 2 NUMA nodes
> EAL: Multi-process socket /var/run/dpdk/rte/mp_socket
> EAL: No available hugepages reported in hugepages-1048576kB
> EAL: Probing VFIO support...
> EAL: WARNING! Base virtual address hint (0x100005000 != 0x7f63aed91000) 
> not respected!
> EAL:    This may cause issues with mapping memory into secondary processes
> EAL: WARNING! Base virtual address hint (0x10000b000 != 0x7f63a937f000) 
> not respected!
> EAL:    This may cause issues with mapping memory into secondary processes
> EAL: WARNING! Base virtual address hint (0x100a0c000 != 0x7f5fa7800000) 
> not respected!
> EAL:    This may cause issues with mapping memory into secondary processes
> EAL: WARNING! Base virtual address hint (0x100c11000 != 0x7f63a931e000) 
> not respected!
> EAL:    This may cause issues with mapping memory into secondary processes
> 
> rte_eal_init() is returning successfully, but we wanted to know why this 
> warning is coming and
> what are the potential issues that may arise due to this warning.
> 
> Note: NIC is bound with igb_uio. Hugepages are mapped and there are 
> enough free pages.
> 
> System specification :
> 2 machines with
> Distributor ID:    Ubuntu
> Description:    Ubuntu 18.04.2 LTS
> Release:    18.04
> Codename:    bionic
> 
> Kernel: 4.15.0-55-generic
> *DPDK* version: 19.05.0
> 
> Hardware:
> CPU: Intel(R) Xeon(R) CPU E5-2650 v4 @ 2.20GHz
> NIC 1: Intel Corporation Ethernet Controller XL710 for 40GbE QSFP+ (i40e)
> 
> (If any extra setup configuration information required will be provided)
> 
> Thanks,
> Nilesh
> 
> 

Hi,

This is normal. This happens because, by default, shared memory in EAL 
is mapped starting at a specific memory offset due to certain issues 
with DPDK's multiprocess support. Sometimes these offsets will not be 
available, so things will get mapped at other addresses. Because this 
event may cause issues with subsequent secondary process mappings, EAL 
warns about this on initialization.

If you're not using secondary processes, you may disregard this warning.

-- 
Thanks,
Anatoly

      reply	other threads:[~2019-08-12  9:31 UTC|newest]

Thread overview: 2+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-08-07 10:51 [dpdk-dev] WARNING! Base virtual address hint not respected! Nilesh
2019-08-12  9:31 ` Burakov, Anatoly [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=06560e08-d865-c4d8-a3c7-62ae7a482e39@intel.com \
    --to=anatoly.burakov@intel.com \
    --cc=dev@dpdk.org \
    --cc=diptyaroop@cse.iitb.ac.in \
    --cc=nileshunhale@cse.iitb.ac.in \
    /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).