From: Stephen Hemminger <shemminger@vyatta.com>
To: "John A. Sullivan III" <jsullivan@opensourcedevel.com>
Cc: David Laight <David.Laight@ACULAB.COM>,
netdev@vger.kernel.org, Rick Jones <rick.jones2@hp.com>,
Dave Taht <dave.taht@gmail.com>,
Eric Dumazet <eric.dumazet@gmail.com>
Subject: Re: Latency difference between fifo and pfifo_fast
Date: Wed, 7 Dec 2011 15:27:09 -0800 [thread overview]
Message-ID: <20111207152709.37b5798d@nehalam.linuxnetplumber.net> (raw)
In-Reply-To: <b6a68bd3-eec7-47f3-bc46-2781b08d8815@jasiiieee>
> <grin> Sorry to have kicked up a storm! We really don't have a problem - just trying to optimize our environment. We have been told by our SAN vendor that, because of the 4KB limit on block size in Linux file systems, iSCSI connections for Linux file services are latency bound and not bandwidth bound. I'm not sure if I believe that based upon our traces where tag queueing seems to coalesce SCSI commands into larger blocks and we are able to achieve network saturation. I was just wondering, since it is all the same traffic and hence no need to separate into bands, if I should change the qdisc on those connections from pfifo_fast (which I assume needs to look at the TOS bits, sort into bands, and poll the separate bands) to fifo which I assume simply dumps packets on the wire. Thanks -
John
Is this a shared network? TOS won't matter if it is only your traffic.
There are number of route metrics that you can tweak to that can reduce TCP slow
start effects, like increasing the initial cwnd, etc.
next prev parent reply other threads:[~2011-12-07 23:27 UTC|newest]
Thread overview: 16+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <8f05fdb0-6e4c-4adf-b8d1-bd67a0dc114f@jasiiieee>
2011-12-06 4:10 ` Latency difference between fifo and pfifo_fast John A. Sullivan III
2011-12-06 6:02 ` Eric Dumazet
2011-12-06 6:29 ` Eric Dumazet
2011-12-06 8:39 ` John A. Sullivan III
2011-12-06 8:51 ` Eric Dumazet
2011-12-06 18:20 ` Rick Jones
2011-12-06 18:39 ` Dave Taht
2011-12-06 19:44 ` John A. Sullivan III
2011-12-07 13:04 ` Eric Dumazet
2011-12-07 13:27 ` Dave Taht
2011-12-07 14:08 ` David Laight
2011-12-08 0:05 ` John A. Sullivan III
2011-12-07 23:27 ` Stephen Hemminger [this message]
2011-12-08 0:34 ` John A. Sullivan III
2011-12-07 23:49 ` Stephen Hemminger
2011-12-08 3:20 ` John A. Sullivan III
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=20111207152709.37b5798d@nehalam.linuxnetplumber.net \
--to=shemminger@vyatta.com \
--cc=David.Laight@ACULAB.COM \
--cc=dave.taht@gmail.com \
--cc=eric.dumazet@gmail.com \
--cc=jsullivan@opensourcedevel.com \
--cc=netdev@vger.kernel.org \
--cc=rick.jones2@hp.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).