From: "Wiles, Keith" <keith.wiles@intel.com>
To: SAKTHIVEL ANAND S <anand.sa88@gmail.com>, "dev@dpdk.org" <dev@dpdk.org>
Subject: Re: [dpdk-dev] [dpdk-users] memory tracker in PMD level
Date: Tue, 31 May 2016 15:12:47 +0000 [thread overview]
Message-ID: <9D6F629A-2B3E-4E44-8ED3-83C231C421A0@intel.com> (raw)
In-Reply-To: <68349471-4A9C-46EB-90EA-3FF67C28F0F5@intel.com>
Resend to the list for others to view.
Regards,
Keith
>Please do not send HTML based text to the list only plain text emails.
>
>Regards,
>Keith
>
>
>From: SAKTHIVEL ANAND S <anand.sa88@gmail.com>
>Date: Tuesday, May 31, 2016 at 10:05 AM
>To: Keith Wiles <keith.wiles@intel.com>
>Subject: Re: [dpdk-users] memory tracker in PMD level
>
>it looks it prints tx and rx counts in terms of number of packets and related status(error type of that droped packetr). but actually i need mbuf status which is associated with that interface. tx and rx cound is secondary part for me.. i would like to check memory leak if any, in my code.
>
KW: All TX count drops are handled by the applications as that number of packets placed on the TX ring is returned in the tx_burst call not in the PMD. On the RX side if the mbufs are not available to attach to the data then you can look at the mempool stats, but that is about it.
>
>On Tue, May 31, 2016 at 8:29 PM, SAKTHIVEL ANAND S <anand.sa88@gmail.com> wrote:
>Ok thanks.
>
>
>On Tue, May 31, 2016 at 8:19 PM, Wiles, Keith <keith.wiles@intel.com> wrote:
>
>From: SAKTHIVEL ANAND S <anand.sa88@gmail.com>
>Date: Tuesday, May 31, 2016 at 9:45 AM
>To: Keith Wiles <keith.wiles@intel.com>
>Subject: Re: [dpdk-users] memory tracker in PMD level
>
>Hi
>
>so what is the api , should i call to print those on .. is it like
>i40e_dev_stats_get() ??
>
>Please have a look at the Docs in the area of rte_eth_stats_get() https://readthedocs.org/projects/dpdk/
>
>Thanks
>
>
>On Tue, May 31, 2016 at 8:12 PM, Wiles, Keith <keith.wiles@intel.com> wrote:
>
>>Hi
>>
>>How can we track the packet drops in the PMD level, when receiving rings is
>>full or by some other means.
>>
>>Lets assume my processing speed is less than receiving line rate so PMD
>>rings are over run and incoming packets are getting dropped. how should i
>>track this issue(status of mbufs and dropping packets counts in PMD). Is
>>there any APIs or any tool available? is libtrace will help here?
>
>In most/all of the PMD drivers the stats will give you dropped packets at the wire.
>
>>
>>any help would be much appreciated.
>>
>>--
>>Thanks
>>Sakthivel S OM
>>
>
>
>
>
>
>--
>Thanks
>Sakthivel S OM
>
>
>
>
>
>
>--
>Thanks
>Sakthivel S OM
>
>
>
>--
>Thanks
>Sakthivel S OM
>
>
>
>
>
parent reply other threads:[~2016-05-31 15:12 UTC|newest]
Thread overview: expand[flat|nested] mbox.gz Atom feed
[parent not found: <68349471-4A9C-46EB-90EA-3FF67C28F0F5@intel.com>]
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=9D6F629A-2B3E-4E44-8ED3-83C231C421A0@intel.com \
--to=keith.wiles@intel.com \
--cc=anand.sa88@gmail.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).