Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]
Groups > comp.arch.embedded > #25484
| Path | csiph.com!feeder.erje.net!2.us.feeder.erje.net!nntp.club.cc.cmu.edu!micro-heart-of-gold.mit.edu!bloom-beacon.mit.edu!bloom-beacon.mit.edu!panix!not-for-mail |
|---|---|
| From | Grant Edwards <invalid@invalid.invalid> |
| Newsgroups | comp.arch.embedded |
| Subject | Re: soft real-time on linux |
| Date | Sat, 12 Nov 2016 17:16:16 +0000 (UTC) |
| Organization | PANIX Public Access Internet and UNIX, NYC |
| Lines | 30 |
| Message-ID | <o07ip0$tp$1@reader2.panix.com> (permalink) |
| References | <87eg2gerei.fsf@digitalsignallabs.com> |
| NNTP-Posting-Host | 67-130-15-94.dia.static.qwest.net |
| X-Trace | reader2.panix.com 1478970976 953 67.130.15.94 (12 Nov 2016 17:16:16 GMT) |
| X-Complaints-To | abuse@panix.com |
| NNTP-Posting-Date | Sat, 12 Nov 2016 17:16:16 +0000 (UTC) |
| User-Agent | slrn/1.0.2 (Linux) |
| Xref | csiph.com comp.arch.embedded:25484 |
Show key headers only | View raw
On 2016-11-12, Randy Yates <yates@digitalsignallabs.com> wrote:
> I was told by someone on the ##kernel channel that if the kernel is
> compiled with "preemptive" enabled, there is a way to set a thread's
> priority to "real-time" and it will not only have priority over other
> user-land threads but also will preempt much of the kernel's internal
> threads. This sounds promising.
In my experience (on a 400MHz ARM9), if you build the kernel with all
the pre-emptable options, and run your task at the highest real-time
priority then latency between an external event that causes an
interrupt and your user task waking up and running is going to be
somwhere in the 100-300 microsecond range. [Assuming the interrupt
routine and device driver require minimal processing.]
That, of course, depends on the exact set of drivers you have enabled.
All it takes is one long critical section in a poorly written driver
to run that into many hundreds of microseconds.
I would be shocked if it ever got up to 1ms.
Unless you disable the rx FIFO, I would guess that the vast majority
of the latency is going to be in the UART itself. With the rxFIFO
enabled, there's often a delay of several tens of bit-times between
the last data byte and the receive interrupt.
--
Grant Edwards grant.b.edwards Yow! Zippy's brain cells
at are straining to bridge
gmail.com synapses ...
Back to comp.arch.embedded | Previous | Next — Previous in thread | Next in thread | Find similar | Unroll thread
soft real-time on linux Randy Yates <yates@digitalsignallabs.com> - 2016-11-12 08:53 -0500
Re: soft real-time on linux Grant Edwards <invalid@invalid.invalid> - 2016-11-12 17:16 +0000
Re: soft real-time on linux Mel Wilson <mwilson@the-wire.com> - 2016-11-12 17:33 +0000
Re: soft real-time on linux upsidedown@downunder.com - 2016-11-12 20:34 +0200
Re: soft real-time on linux Don Y <blockedofcourse@foo.invalid> - 2016-11-12 13:53 -0700
Re: soft real-time on linux sbattazzo@gmail.com - 2017-02-09 11:06 -0800
Re: soft real-time on linux Paul Rubin <no.email@nospam.invalid> - 2016-11-12 14:12 -0800
Re: soft real-time on linux Phil Hobbs <pcdhSpamMeSenseless@electrooptical.net> - 2017-02-08 21:17 -0500
Re: soft real-time on linux Jack <jack4747@gmail.com> - 2017-02-09 00:16 -0800
Re: soft real-time on linux David Brown <david.brown@hesbynett.no> - 2017-02-09 10:00 +0100
Re: soft real-time on linux Phil Hobbs <pcdhSpamMeSenseless@electrooptical.net> - 2017-02-10 11:12 -0500
Re: soft real-time on linux George Neuner <gneuner2@comcast.net> - 2017-02-11 01:33 -0500
Re: soft real-time on linux Phil Hobbs <pcdhSpamMeSenseless@electrooptical.net> - 2017-02-10 22:10 -0500
csiph-web