Re: Blocking read() policy?

From: David Schwartz (davids_at_webmaster.com)
Date: 07/20/05 

Date: Wed, 20 Jul 2005 12:33:31 -0700

"Robert Redelmeier" <redelm@ev1.net.invalid> wrote in message
news:u9wDe.655$LF.600@newssvr27.news.prodigy.net...

> David Schwartz <davids@webmaster.com> wrote:

>> I don't understand what you're asking. What do you mean by
>> "bypass blocks"?

> An app can open a fd with O_NONBLOCK. I'm suggesting
> the kernel treat that both POSIXly _and_ as a suggestion
> to the scheduler that too many null returns should cause
> rescheduling in spite of O_NONBLOCK.

    Eww, no, that's horrible. Unexpected blocking is something we work very,
very hard to avoid.

    DS

Relevant Pages

  • Re: [patch 00/13] Syslets, "Threadlets", generic AIO support, v3
    ... With rescheduling there are _too_ many things to ... request in the future too]'. ... I did not run reschedulingtests with kernel thread, ... We do user-space register saving not in the scheduler ...
    (Linux-Kernel)
  • Re: question about SYSINTR_RESCHED and scheduler
    ... suppose that I have three thread, two of them running in kernel process, and ... responsibility to resume a suspended thread using a call to ResumeThread ... I have a question about SYSINTR_RESCHED and scheduler, ... but what will scheduler do in case of rescheduling? ...
    (microsoft.public.windowsce.platbuilder)
  • Re: Blocking read() policy?
    ... and the rescheduling check ... In 2.6.9 a call to the scheduler is ... may call the scheduler on return to user mode, ... > Linux' responsiveness has improved substantially. ...
    (comp.os.linux.development.system)
  • Re: Goodbye to Xbox Live!
    ... spite your face. ... You cannot avoid it unless you stay offline forever so ... what is the point of ruining your gaming for a few weeks. ...
    (uk.games.video.misc)
  • Re: [PATCH 3/7] x86: make 32bit support per_cpu vector fix #1
    ... unrelated sidenote - shouldnt the scheduler define cpu_online_map to ... to avoid such ugly #ifdefs? ...
    (Linux-Kernel)