From: David Miller <davem@davemloft.net>
To: or.gerlitz@gmail.com
Cc: rdreier@cisco.com, cl@linux-foundation.org,
netdev@vger.kernel.org, yosefe@voltaire.com
Subject: Re: IPoIB: Fix multicast packet drops before join is complete
Date: Wed, 10 Jun 2009 05:01:22 -0700 (PDT) [thread overview]
Message-ID: <20090610.050122.261415364.davem@davemloft.net> (raw)
In-Reply-To: <15ddcffd0906100318u2a61b7d8g991fe52439e07928@mail.gmail.com>
From: Or Gerlitz <or.gerlitz@gmail.com>
Date: Wed, 10 Jun 2009 13:18:29 +0300
> If there's no app level flow control around, UDP senders will just
> send... so for --unicast-- the same problem of injecting tons of
> packets which can get dropped will come into play under both
> Ethernet and IB, so the user is limited by the socket buffer len and
> the neigh unres_qlen systcl.
But this generally does not cause problems via ARP, why might that
be? Because resolution is 1) rare 2) quick. Both of which do not
apply to this IPoIB case.
> Why not apply a similar systcl mechanism for the IB/mcast case so
> the ipoib driver level (under the user directive) will have control
> on how many packets would be queued before starting to drop.
Sure, but that's just pushing the problem around instead of
solving it.
next prev parent reply other threads:[~2009-06-10 12:01 UTC|newest]
Thread overview: 29+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-06-02 14:49 IPoIB: Fix multicast packet drops before join is complete Christoph Lameter
2009-06-04 5:41 ` David Miller
2009-06-04 14:28 ` Or Gerlitz
2009-06-04 15:52 ` Christoph Lameter
2009-06-04 22:30 ` David Miller
2009-06-05 14:18 ` Christoph Lameter
2009-06-05 16:56 ` Roland Dreier
2009-06-05 19:17 ` Christoph Lameter
2009-06-05 21:12 ` Roland Dreier
2009-06-06 1:17 ` David Miller
2009-06-05 21:13 ` Roland Dreier
2009-06-08 15:16 ` Christoph Lameter
2009-06-06 1:16 ` David Miller
2009-06-08 15:20 ` Christoph Lameter
2009-06-08 21:29 ` David Miller
2009-06-09 20:52 ` Roland Dreier
2009-06-10 0:45 ` David Miller
2009-06-10 3:55 ` Roland Dreier
2009-06-10 4:57 ` David Miller
2009-06-10 5:04 ` Roland Dreier
2009-06-10 5:12 ` David Miller
2009-06-10 10:18 ` Or Gerlitz
2009-06-10 12:01 ` David Miller [this message]
2009-06-11 11:45 ` Or Gerlitz
2009-06-11 11:57 ` David Miller
2009-06-11 15:07 ` Christoph Lameter
2009-06-11 23:58 ` David Miller
2009-06-12 14:17 ` Christoph Lameter
2009-06-05 16:54 ` Roland Dreier
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=20090610.050122.261415364.davem@davemloft.net \
--to=davem@davemloft.net \
--cc=cl@linux-foundation.org \
--cc=netdev@vger.kernel.org \
--cc=or.gerlitz@gmail.com \
--cc=rdreier@cisco.com \
--cc=yosefe@voltaire.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).