netdev - Re: [RFC] napi: adding an administrative state & priority

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [day] [month] [year] [list]

Date:	Wed, 23 Jul 2008 20:01:47 -0700 (PDT)
From:	David Miller <davem@...emloft.net>
To:	nhorman@...driver.com
Cc:	netdev@...r.kernel.org, jgarzik@...ox.com
Subject: Re: [RFC] napi: adding an administrative state & priority

From: Neil Horman <nhorman@...driver.com>
Date: Wed, 23 Jul 2008 21:21:15 -0400

> And what are your thoughts regarding the creation of a napi instance priority
> scheme?  I understand your arguments for not disabling napi entirely, but it
> doesn't speak to prioritization.  I can still see a benefit to instructing the
> kernel to serve a interface first handling high priority traffic.

The weight assigned to each NAPI instance to some extent already
behaves much like a priority.

We could also do something like, knowing how many NAPI contexts
are scheduled, create a total work budget for an entire pass.

Each "weight" (you say "priority") assigned to the NAPI context
determines how big a slice of the pie that NAPI context gets.

But, two points:

1) True prioritization is the antithesis of what NAPI is trying
   to achieve.  It wants fairness and to avoid starvation.

2) %99.999999 of the time only a single NAPI context is scheduled
   on a cpu at a time, making this whole idea quite moot in my
   opinion :-)
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html