DPDK usage discussions
 help / color / mirror / Atom feed
From: Vladimir Medvedkin <medvedkinv@gmail.com>
To: Heung Sik Choi <hschoi@os.korea.ac.kr>
Cc: users@dpdk.org
Subject: Re: [dpdk-users] does the 'rte_softrss_be' function match NIC RSS value well? please help me.
Date: Tue, 30 May 2017 13:01:59 +0300	[thread overview]
Message-ID: <CANDrEHn3uvVUGm_jDDo5mw0B94rLPV2NYgmHWuy4hHxKkw=i9g@mail.gmail.com> (raw)
In-Reply-To: <CAAZV7DCmTF==YGdQ9eqSaFa8=z640G+Q5rgFVN-Do+fw73_POw@mail.gmail.com>

What do you have in tuple? What byte order are ip addresses and ports?

2017-05-30 12:15 GMT+03:00 Heung Sik Choi <hschoi@os.korea.ac.kr>:

> Thanks to reply Vladimir.
>
> I does not custom configure ixgbe, thus default compile and load.
>
> My calculation softrss code is below:
>
> uint8_t rss_key_be[RTE_DIM(default_rss_key)];
>
> uint8_t default_rss_key[] = {
> 0x6d, 0x5a, 0x56, 0xda, 0x25, 0x5b, 0x0e, 0xc2,
> 0x41, 0x67, 0x25, 0x3d, 0x43, 0xa3, 0x8f, 0xb0,
> 0xd0, 0xca, 0x2b, 0xcb, 0xae, 0x7b, 0x30, 0xb4,
> 0x77, 0xcb, 0x2d, 0xa3, 0x80, 0x30, 0xf2, 0x0c,
> 0x6a, 0x42, 0xb7, 0x3b, 0xbe, 0xac, 0x01, 0xfa
> };
>
> rte_convert_rss_key((uint32_t *)&default_rss_key,(uint32_t *)rss_key_be,
> RTE_DIM(default_rss_key));
>
> rte_softrss_be((uint32_t *)&tuple, RTE_THASH_V4_L4_LEN, rss_key_be);//
> print it.
>
> i used rte convert_rss_key's implementation code which be base in X86.
>
> i also change the RTE_THASH_V4_L4_LEN parameter with RTE_THASH_V4_L3_LEN.
>
> but doesn't match.
>
> Is it wrong to use it that way?
>
> please help me.
>
>
>
> 2017-05-30 17:01 GMT+09:00 Vladimir Medvedkin <medvedkinv@gmail.com>:
>
>> Hi,
>>
>> How do you configure your NIC and calculate softrss?
>>
>>
>> 2017-05-30 10:47 GMT+03:00 Heung Sik Choi <hschoi@os.korea.ac.kr>:
>>
>>> Hi
>>>
>>> I want to match NIC RSS value with toeplitz hash function value. And I
>>> find
>>> out 'rte_softrss_be' can makes it.
>>>
>>> However, when I experiment it, It doesn't match well. (print two value on
>>> terminal through code level)
>>> I use the environment below:
>>>
>>> CPU: xeon 2213 v2 *2 (NUMA)
>>> NIC: intel 82599ES
>>> kernel 3.16.4
>>> ixgbe driver: 3.22
>>> DPDK 16.11
>>>
>>> Please let me know if you have any insights.
>>>
>>
>>
>>
>> --
>> Regards,
>> Vladimir
>>
>
>


-- 
Regards,
Vladimir

  reply	other threads:[~2017-05-30 10:02 UTC|newest]

Thread overview: 7+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-05-30  7:47 Heung Sik Choi
2017-05-30  8:01 ` Vladimir Medvedkin
2017-05-30  9:15   ` Heung Sik Choi
2017-05-30 10:01     ` Vladimir Medvedkin [this message]
2017-05-30 10:28       ` Heung Sik Choi
2017-05-30 13:00         ` Vladimir Medvedkin
2017-06-07  5:55           ` Heung Sik Choi

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='CANDrEHn3uvVUGm_jDDo5mw0B94rLPV2NYgmHWuy4hHxKkw=i9g@mail.gmail.com' \
    --to=medvedkinv@gmail.com \
    --cc=hschoi@os.korea.ac.kr \
    --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).