Thread (33 messages) 33 messages, 10 authors, 2016-11-09

Re: [PATCH] sched/rt: RT_RUNTIME_GREED sched feature

From: Clark Williams <hidden>
Date: 2016-11-07 18:50:13
Also in: lkml

On Mon, 7 Nov 2016 13:30:46 -0500
Steven Rostedt [off-list ref] wrote:
On Mon, 7 Nov 2016 12:22:21 -0600
Clark Williams [off-list ref] wrote:
quoted
I'm still reviewing the patch, but I have to wonder why bother with making it a scheduler feature?

The SCHED_FIFO definition allows a fifo thread to starve others
because a fifo task will run until it yields. Throttling was added as
a safety valve to allow starved SCHED_OTHER tasks to get some cpu
time.  Adding this unconditionally gets us a safety valve for
throttling a badly written fifo task, but allows the fifo task to
continue to consume cpu cycles if it's not starving anyone. 

Or am I missing something that's blazingly obvious?  
Or I say make it the default. If people want the old behavior, they can
modify SCHED_FEATURES to do so.
Ok, I can see wanting the previous behavior. 

Clark

Attachments

  • (unnamed) [application/pgp-signature] 801 bytes
Keyboard shortcuts
hback out one level
jnext message in thread
kprevious message in thread
ldrill in
Escclose help / fold thread tree
?toggle this help