DPDK usage discussions
 help / color / mirror / Atom feed
From: Balakrishnan K <Balakrishnan.K1@tatacommunications.com>
To: Volodymyr Fialko <vfialko@marvell.com>,
	"users@dpdk.org" <users@dpdk.org>
Subject: RE: Reg.dpdk reorder library usage
Date: Tue, 21 Mar 2023 05:10:30 +0000	[thread overview]
Message-ID: <PSAPR04MB551693A1B11CAFCD63D2A039D6819@PSAPR04MB5516.apcprd04.prod.outlook.com> (raw)
In-Reply-To: <PSAPR04MB5516DF85BB3D64532B2BA2E0D6809@PSAPR04MB5516.apcprd04.prod.outlook.com>

[-- Attachment #1: Type: text/plain, Size: 4029 bytes --]

Hi volodymyr,
      I checked the app/test/test_reorder.c code.

Could you please provide some clarification on below queries:
Reorder library ensure packet goes out in the same order they are received in RX?
Sequence number in the mbuf decides the packet index in buffer?
Is the reorder works based on the sequence number that we insert in mbuf not based on the sequence number present in the packet header?
Sequence number should be incremental ?

In my use case TCP packets are coming in out of order to the RX itself , how can I use the reorder library to fix the ordering while sending out.
TCP sequence number cannot be incremental , sequence number will be decide based on the number bytes transferred .


Thanks ,
Bala


From: Balakrishnan K <Balakrishnan.K1@tatacommunications.com>
Sent: Monday, March 20, 2023 5:24 PM
To: Volodymyr Fialko <vfialko@marvell.com>; users@dpdk.org
Subject: Re: Reg.dpdk reorder library usage

Hi volodymyr,
  Thanks for the quick response.
Let me go through the test code and come back if i need any clarifications.

Thanks,
Bala

________________________________
From: Volodymyr Fialko <vfialko@marvell.com<mailto:vfialko@marvell.com>>
Sent: Monday, March 20, 2023, 4:50 PM
To: Balakrishnan K <Balakrishnan.K1@tatacommunications.com<mailto:Balakrishnan.K1@tatacommunications.com>>; users@dpdk.org<mailto:users@dpdk.org> <users@dpdk.org<mailto:users@dpdk.org>>
Subject: RE: Reg.dpdk reorder library usage


CAUTION: This email originated from outside of the organization. Do not click links or open attachments unless you recognize the sender and know the content is safe.
Hi,

Could you take a look at the app/test/test_reorder.c `test_reorder_drain()` test case. It follows your steps closely and includes comments that describe the internal state of buffers, which could be helpful during debugging.

From: Balakrishnan K <Balakrishnan.K1@tatacommunications.com<mailto:Balakrishnan.K1@tatacommunications.com>>
Sent: Monday, March 20, 2023 11:54 AM
To: users@dpdk.org<mailto:users@dpdk.org>
Cc: Volodymyr Fialko <vfialko@marvell.com<mailto:vfialko@marvell.com>>
Subject: [EXT] Reg.dpdk reorder library usage

External Email
________________________________
Hi All,
     I am planning to use dpdk reorder library in my application.
Used reorder library API's by refereeing  the packet ordering example.
Steps:
Our application uses dpdk pipeline.
1.read the packet from rx
2.Create the rte_reorder_create() if not created already or use the existing buffer.
3.iterate through the rx packets and set the sequence number using *rte_reorder_seqn(pkt) = seqn++.
4.insert the packets using the API rte_reorder_insert(ro_buf, pkt);
5.after insert completed I am using rte_reorder_drain API to get the reorder packets .

In step 5 always getting zero packets.
Even though all the rx packets are in order rte_reoder_drain API not giving the output.

Could any please help on this am I missing anything in the implementation .
How to use this library properly.
Tried to run the packet ordering example with 4 ports .
Sent traffic in port 1 there is no packet out in port 1 as mentioned in application example page.
https://doc.dpdk.org/guides/sample_app_ug/packet_ordering.html<https://apc01.safelinks.protection.outlook.com/?url=https%3A%2F%2Furldefense.proofpoint.com%2Fv2%2Furl%3Fu%3Dhttps-3A__doc.dpdk.org_guides_sample-5Fapp-5Fug_packet-5Fordering.html%26d%3DDwMFAg%26c%3DnKjWec2b6R0mOyPaz7xtfQ%26r%3D4iVvgx5PfauIDNaDpT1Ph7naVrkBkhwh2wdQ1AUXVjo%26m%3DLRnVWVWJFPG262ii-XDMQhsmNnSxIXzBIwBY_fRUQsmMdsEDvqC9-T16uF0eYOxo%26s%3D1Oji8GpXbRO608Vsx4e_m1MT1oOXqYA1hx5C6JSiDLY%26e%3D&data=05%7C01%7CBalakrishnan.K1%40tatacommunications.com%7C361fa04625c147b4fb0a08db29350923%7C202104622c5e4ec8b3e20be950f292ca%7C0%7C0%7C638149080000239969%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=P8ZAZ2wJY%2FTIqz9XnjvWusNy8iDSzbXvhYjDTJMgf%2Bc%3D&reserved=0>


Regards,
Bala


[-- Attachment #2: Type: text/html, Size: 9548 bytes --]

      reply	other threads:[~2023-03-21  5:10 UTC|newest]

Thread overview: 4+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-03-20 10:53 Balakrishnan K
2023-03-20 11:19 ` Volodymyr Fialko
2023-03-20 11:54   ` Balakrishnan K
2023-03-21  5:10     ` Balakrishnan K [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=PSAPR04MB551693A1B11CAFCD63D2A039D6819@PSAPR04MB5516.apcprd04.prod.outlook.com \
    --to=balakrishnan.k1@tatacommunications.com \
    --cc=users@dpdk.org \
    --cc=vfialko@marvell.com \
    /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).