DPDK patches and discussions
 help / color / mirror / Atom feed
From: "Van Haaren, Harry" <harry.van.haaren@intel.com>
To: "Qiu, Michael" <michael.qiu@intel.com>,
	"david.marchand@6wind.com" <david.marchand@6wind.com>
Cc: "dev@dpdk.org" <dev@dpdk.org>
Subject: Re: [dpdk-dev] [PATCH] eal: add function to check if primary proc alive
Date: Tue, 26 Jan 2016 11:19:19 +0000	[thread overview]
Message-ID: <E923DB57A917B54B9182A2E928D00FA6128624A1@IRSMSX102.ger.corp.intel.com> (raw)
In-Reply-To: <533710CFB86FA344BFBF2D6802E6028622F22C3C@SHSMSX101.ccr.corp.intel.com>

> From: Qiu, Michael
> > Whatever work the secondary was performing (in its own address space)
> > won't be directly changed by the primary being killed, because the
> > shared config and hugepages stay (EAL "cleans up" when the primary
> > is re-launched, not on quit).
> 
> OK,  when primary quit or be killed, the queues will be freed, it will
> be a potential issue when secondary try to access, maybe I'm wrong.

The use-case for this patch is monitoring statistics and fault-detection.
That involves reading registers directly from the NIC, and the NIC
rx/tx queues are not used. I think you are right that using the rx/tx
queues from a secondary process when they have been cleaned-up by the
primary process will indeed cause issues.

If there is a valid use-case where both primary and secondary processes
will be forwarding packets on the same NIC, this issue should be discussed
in more detail.

In its current state, this patch solves a problem for the use case of a
primary process forwarding packets, and a secondary process monitoring
and providing fault-detection.

-Harry

  reply	other threads:[~2016-01-26 11:19 UTC|newest]

Thread overview: 43+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-01-20 13:25 Harry van Haaren
2016-01-21  6:14 ` Qiu, Michael
2016-01-21  6:19   ` Matthew Hall
2016-01-21  9:02   ` Van Haaren, Harry
2016-01-22 17:37     ` Bruce Richardson
2016-01-25  8:06       ` Qiu, Michael
2016-01-25 11:44       ` Van Haaren, Harry
2016-01-26 19:13         ` Bruce Richardson
2016-01-27 10:35           ` Van Haaren, Harry
2016-01-25  8:11 ` Qiu, Michael
2016-01-25 11:51   ` Van Haaren, Harry
2016-01-26  2:25     ` Qiu, Michael
2016-01-26  9:04       ` Van Haaren, Harry
2016-01-26 11:07         ` Qiu, Michael
2016-01-26 11:19           ` Van Haaren, Harry [this message]
2016-01-27 10:31 ` [dpdk-dev] [PATCH v2] " Harry van Haaren
2016-02-02 14:11   ` [dpdk-dev] [PATCH v3] " Harry van Haaren
2016-02-23 14:10     ` [dpdk-dev] [PATCH v4] " Harry van Haaren
2016-02-24 13:50       ` Tahhan, Maryam
2016-03-04 18:07       ` Thomas Monjalon
2016-03-07 11:37       ` [dpdk-dev] [PATCH v5] " Harry van Haaren
2016-03-07 12:02         ` [dpdk-dev] [PATCH v6] " Harry van Haaren
2016-03-08  8:42           ` David Marchand
2016-03-08  9:58             ` Van Haaren, Harry
2016-03-08 11:13               ` Thomas Monjalon
2016-03-08 11:19                 ` David Marchand
2016-03-08 13:57                   ` Van Haaren, Harry
2016-03-08 14:40                     ` David Marchand
2016-03-08 17:07           ` [dpdk-dev] [PATCH v7 0/2] eal: add function to check primary alive Harry van Haaren
2016-03-08 17:07             ` [dpdk-dev] [PATCH v7 1/2] eal: fix race-condition in pri/sec proc startup Harry van Haaren
2016-03-08 17:07             ` [dpdk-dev] [PATCH v7 2/2] eal: add function to check if primary proc alive Harry van Haaren
2016-03-09 10:12             ` [dpdk-dev] [PATCH v8 0/2] eal: add function to check primary alive Harry van Haaren
2016-03-09 10:12               ` [dpdk-dev] [PATCH v8 1/2] eal: fix race-condition in pri/sec proc startup Harry van Haaren
2016-03-09 13:23                 ` Sergio Gonzalez Monroy
2016-03-09 10:12               ` [dpdk-dev] [PATCH v8 2/2] eal: add function to check if primary proc alive Harry van Haaren
2016-03-09 11:07               ` [dpdk-dev] [PATCH v8 0/2] eal: add function to check primary alive David Marchand
2016-03-09 12:59                 ` Sergio Gonzalez Monroy
2016-03-09 13:37               ` [dpdk-dev] [PATCH v9 " Harry van Haaren
2016-03-09 13:37                 ` [dpdk-dev] [PATCH v9 1/2] eal: fix race-condition in pri/sec proc startup Harry van Haaren
2016-03-09 14:27                   ` Sergio Gonzalez Monroy
2016-03-09 13:37                 ` [dpdk-dev] [PATCH v9 2/2] eal: add function to check if primary proc alive Harry van Haaren
2016-03-09 15:02                   ` Thomas Monjalon
2016-03-09 15:17                 ` [dpdk-dev] [PATCH v9 0/2] eal: add function to check primary alive Thomas Monjalon

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=E923DB57A917B54B9182A2E928D00FA6128624A1@IRSMSX102.ger.corp.intel.com \
    --to=harry.van.haaren@intel.com \
    --cc=david.marchand@6wind.com \
    --cc=dev@dpdk.org \
    --cc=michael.qiu@intel.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).