Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]


Groups > comp.os.linux.hardware > #2808

Re: bfs scheduler run queue

From ruben safir <ruben@mrbrklyn.com>
Newsgroups comp.os.linux.hardware
Subject Re: bfs scheduler run queue
Date 2015-05-06 05:12 -0400
Organization PANIX Public Access Internet and UNIX, NYC
Message-ID <miclum$rmg$2@reader1.panix.com> (permalink)
References <mi39fd$bt4$1@reader1.panix.com>

Show all headers | View raw


On 05/02/2015 03:44 PM, ruben safir wrote:
> I'm confused by the documentation of the BFS scheduler.  it say that is has 
> a single run queue for the entire system as a double linked list and then 
> later it says:
> 
> BFS has 103 priority queues. 100 of these are dedicated to the static priority
> of realtime tasks, and the remaining 3 are, in order of best to worst priority,
> SCHED_ISO (isochronous), SCHED_NORMAL, and SCHED_IDLEPRIO (idle priority
> scheduling). When a task of these priorities is queued, a bitmap of running
> priorities is set showing which of these priorities has tasks waiting for CPU
> time. When a CPU is made to reschedule, the lookup for the next task to get
> CPU time is performed in the following way:
> 
> 
> 
> This seems like a contradiction.  where is the linked list in the code for BFS?
> 
> Ruben 
> 


wow - you know I've seen dozens of papers on this but none analyzed the
code.  They all test the scheduler, but nobody every explains it.  I've
looked it over with some intensity, and it does not seem to be at al
simpler than the CFS...

Back to comp.os.linux.hardware | Previous | NextPrevious in thread | Find similar | Unroll thread


Thread

bfs scheduler run queue ruben safir <ruben@mrbrklyn.com> - 2015-05-02 15:44 -0400
  Re: bfs scheduler run queue ruben safir <ruben@mrbrklyn.com> - 2015-05-06 05:12 -0400

csiph-web