From: "Steinar H. Gunderson" <sgunderson@bigfoot.com>
To: bloat@lists.bufferbloat.net
Subject: Re: [Bloat] Hardware upticks
Date: Wed, 6 Jan 2016 00:17:59 +0100 [thread overview]
Message-ID: <20160105231759.GA8545@sesse.net> (raw)
In-Reply-To: <568C1B5E.1070008@taht.net>
On Tue, Jan 05, 2016 at 11:37:02AM -0800, Dave Täht wrote:
>> Anyway, the biggest cost of a context switch isn't necessarily the time used
>> to set up registers and such. It's increased L1 pressure; your CPU is now
>> running different code and looking at (largely) different data.
> A L1/L2 Icache dedicated to interrupt processing code could make a great
> deal of difference, if only cpu makers and benchmarkers would make
> CS time something we valued.
>
> Dcache, not so much, except for the intel architectures which are now
> doing DMA direct to cache. (any arms doing that?)
Note that I'm saying L1 pressure, not “bad choice of what to keep in L1”.
If you dedicate L1i space to interrupt processing code (which includes,
presumably, large parts of your TCP/IP stack?), you will have less for
your normal userspace, and I'd like to see some very hard data on that being
a win before I'll believe it at face value.
In a sense, if you tie your interrupts to a dedicated core, you get exactly
this, though.
/* Steinar */
--
Homepage: https://www.sesse.net/
next prev parent reply other threads:[~2016-01-05 23:18 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-01-05 6:37 Jonathan Morton
2016-01-05 17:42 ` Aaron Wood
2016-01-05 18:27 ` Jonathan Morton
2016-01-05 18:57 ` Dave Täht
2016-01-05 19:29 ` Steinar H. Gunderson
2016-01-05 19:37 ` Dave Täht
2016-01-05 20:13 ` David Collier-Brown
2016-01-05 20:27 ` Stephen Hemminger
2016-01-05 21:10 ` Jonathan Morton
2016-01-05 23:20 ` Steinar H. Gunderson
2016-01-05 23:17 ` Steinar H. Gunderson [this message]
2016-01-05 21:36 ` Benjamin Cronce
2016-01-06 0:01 ` Steinar H. Gunderson
2016-01-06 0:06 ` Stephen Hemminger
2016-01-06 0:22 ` Steinar H. Gunderson
2016-01-06 0:53 ` Stephen Hemminger
2016-01-06 0:55 ` Steinar H. Gunderson
2016-01-06 1:22 ` Stephen Hemminger
2016-01-06 6:18 ` Jonathan Morton
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
List information: https://lists.bufferbloat.net/postorius/lists/bloat.lists.bufferbloat.net/
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20160105231759.GA8545@sesse.net \
--to=sgunderson@bigfoot.com \
--cc=bloat@lists.bufferbloat.net \
/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