DPDK patches and discussions
 help / color / mirror / Atom feed
From: "Kumar, Ravi1" <Ravi1.Kumar@amd.com>
To: "Burakov, Anatoly" <anatoly.burakov@intel.com>,
	"dev@dpdk.org" <dev@dpdk.org>
Subject: Re: [dpdk-dev] DPDK 18.05 only works with up to 4 NUMAs systems
Date: Thu, 28 Jun 2018 07:03:07 +0000	[thread overview]
Message-ID: <CY4PR12MB1509A82377AF9CDCA7D94523AE4F0@CY4PR12MB1509.namprd12.prod.outlook.com> (raw)
In-Reply-To: <ff7c2d63-3b16-af9e-0bdf-e76dc1b9d858@intel.com>

>On 22-Jun-18 5:37 PM, Kumar, Ravi1 wrote:
>> Hi,
>> 
>> As the memory subsystem in DPDK 18.05 is reworked, it has introduced a problem for AMD EPYC 2P platforms.
>> The issue is that DPDK 18.05 only works with up to 4 NUMAs. For AMD EPYC 2P platforms, DPDK now only works with P0 (NUMA 0-3) and does not work with P1 (NUMA 4-7).
>> 
>> The problem can be fixed by reducing some of the default settings of the memory subsystem.
>> 
>> To solve this issue:
>> -              We can create our own config file for our integrated 10G NIC, that is for amd_xgbe PMD. This will make amd_xgbe immune to this problem.
>> -              However, when any other NIC (Intel, Mellanox, Cavium or Broadcom etc.) is plugged into NUMA 4-7, the problem will still be exposed.
>> -              If we only fix it in "config/common_base", it will cover all cases.
>> 
>> Our current workaround is:
>> Edit config file "./config/common_base" and change the following line
>>                  CONFIG_RTE_MAX_MEM_MB_PER_TYPE=131072
>> TO
>>                  CONFIG_RTE_MAX_MEM_MB_PER_TYPE=65536
>> 
>> Any better solution for this issue is welcome.
>> 
>> We would appreciate if this issue can be fixed in the next release (18.08) so the STOCK version of DPDK works on AMD EPYC 2P platforms.
>> 
>> Regards,
>> Ravi
>> 
>
>Hi Ravi,
>
>What is the reason behind this limitation? Is it too much virtual memory being preallocated?
>
>--
>Thanks,
>Anatoly
>
Hi Anatoly,

We believe this is true.  By default, too much virtual memory is being preallocated. The result is it can only support up to 4 NUMAs.

Our workaround is to reduce the amount of preallocated virtual memory by half, so to support up to 8 NUMAs.

Regards,
Ravi

  reply	other threads:[~2018-06-28  7:03 UTC|newest]

Thread overview: 13+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-06-22 16:37 Kumar, Ravi1
2018-06-25 16:16 ` Burakov, Anatoly
2018-06-28  7:03   ` Kumar, Ravi1 [this message]
2018-06-28  8:42     ` Burakov, Anatoly
2018-07-14  9:44       ` Kumar, Ravi1
2018-07-16 10:35         ` Burakov, Anatoly
2018-07-24  8:09           ` Kumar, Ravi1
2018-07-24  9:03             ` Burakov, Anatoly
2018-07-24  9:39               ` Kumar, Ravi1
2018-10-05  8:32                 ` Burakov, Anatoly
2018-10-05  8:56                   ` Kumar, Ravi1
2018-10-04 17:07 Sandeep Raman
2018-10-05 15:31 ` Burakov, Anatoly

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=CY4PR12MB1509A82377AF9CDCA7D94523AE4F0@CY4PR12MB1509.namprd12.prod.outlook.com \
    --to=ravi1.kumar@amd.com \
    --cc=anatoly.burakov@intel.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).