This is the mail archive of the
ecos-devel@sources.redhat.com
mailing list for the eCos project.
Re: Ecos API's are deterministic?
- From: Jonathan Larmour <jifl at eCosCentric dot com>
- To: giri at jntu dot net
- Cc: ecos-devel at sources dot redhat dot com
- Date: Thu, 30 Oct 2003 20:49:57 +0000
- Subject: Re: Ecos API's are deterministic?
- References: <2903.203.200.40.199.1067517113.squirrel@www.jntu.net>
Guntipalli Giribabu wrote:
Hai,
The intrrupt and thread API's provided by the Ecos are determinstic?
is there any mesured statics that tells worst case execution time of
interrupt and thread API's
It's configuration dependent, hardware dependent, and dependent on how you
use the APIs (if an application disables interrupts, then naturally all
bets are off re real-time performance!). So no, it's impractical for us to
determine worst case times. Note that eCos is soft real-time, not hard
real-time.
You can get some help though from running the tm_basic kernel test. The
"max" figure there isn't the true max, but a statistical measurement over
a number of executions. This is all discussed in the documentation, which
you should read.
Jifl
--
eCosCentric http://www.eCosCentric.com/ The eCos and RedBoot experts
--["No sense being pessimistic, it wouldn't work anyway"]-- Opinions==mine