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 16:00:12 +0300 [thread overview]
Message-ID: <CANDrEH=gkFO=CEk0H4T1+KJ_YeD1VyzWrB0wVD-zzG0RJmBDsA@mail.gmail.com> (raw)
In-Reply-To: <CAAZV7DDcgT77mZ9yfFURA4W+s_mKRnuTkQm=dKdK216+wyOpKQ@mail.gmail.com>
How do you insert src and dst ips? Try it with rte_be_to_cpu_32() for
example
tuple.v4.src_addr =rte_be_to_cpu_32(ip_hdr->src_addr)
P.S. https://en.wikipedia.org/wiki/Endianness
2017-05-30 13:28 GMT+03:00 Heung Sik Choi <hschoi@os.korea.ac.kr>:
> I insert ip source, ip destination, port source, port destination to the
> tuple but sctp_tag is null. But, I think it is not necessary because the
> test_thash.c in DPDK souce files shows example of rte_softrss_be and also
> sctp_tage is null.
>
> I don't know byte order. How can I check this? can you tell me the way?
>
> Thanks, Vladimir.
>
> 2017-05-30 19:01 GMT+09:00 Vladimir Medvedkin <medvedkinv@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
>>
>
>
--
Regards,
Vladimir
next prev parent reply other threads:[~2017-05-30 13:00 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
2017-05-30 10:28 ` Heung Sik Choi
2017-05-30 13:00 ` Vladimir Medvedkin [this message]
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='CANDrEH=gkFO=CEk0H4T1+KJ_YeD1VyzWrB0wVD-zzG0RJmBDsA@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).