DPDK patches and discussions
 help / color / mirror / Atom feed
From: "Burakov, Anatoly" <anatoly.burakov@intel.com>
To: "Shubhachint, Chaitanya" <Chaitanya.Shubhachint@netscout.com>,
	"dev@dpdk.org" <dev@dpdk.org>
Subject: Re: [dpdk-dev] /run/dpdk cleanup
Date: Tue, 9 Jul 2019 10:58:15 +0100	[thread overview]
Message-ID: <9e415b49-9b4a-05f1-23ea-1cd2ddb60c41@intel.com> (raw)
In-Reply-To: <DM5PR0101MB2954D8F49E8BB0BF093D911587F60@DM5PR0101MB2954.prod.exchangelabs.com>

On 08-Jul-19 4:00 PM, Shubhachint, Chaitanya wrote:
> Hello,
> 
> I run my dpdk applications with "file-prefix" option, so I can run them concurrently. I see that it creates a runtime directory under /var/run/dpdk. This directory still persists after the application has terminated. The code calls rte_eal_cleanup before exiting but that doesn't seem to remove the directory and its content. In my setup I have to consistently bring my applications up, run then for short period and terminate them, each application run picks a new file-prefix, thus creating new directory under /var/run/dpdk. After enough number of runs the tempfs partition fills up and results into rte_eal_init failure.
> Is there a cleanup routine or sequence I need to implement to unlink this directory? Your help is appreciated.
> 
> Chaitanya.
> 

This is a natural consequence of how our multiprocessing works. Running 
a secondary process *after* primary has already exited is a supported 
use-case (meaning, primary won't clean up *everything* after itself - 
only things that are not shared), and secondary processes may be running 
as well (meaning, we cannot remove shared data because it may be used by 
other processes).

I don't think it's possible to do this from within DPDK. Of course, you 
could always use --in-memory mode if you don't use secondary processes.

-- 
Thanks,
Anatoly

      parent reply	other threads:[~2019-07-09  9:58 UTC|newest]

Thread overview: 3+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-07-08 15:00 Shubhachint, Chaitanya
2019-07-08 15:41 ` Stephen Hemminger
2019-07-09  9:58 ` Burakov, Anatoly [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=9e415b49-9b4a-05f1-23ea-1cd2ddb60c41@intel.com \
    --to=anatoly.burakov@intel.com \
    --cc=Chaitanya.Shubhachint@netscout.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).