Re: Self-scheduling threading
Re: Self-scheduling threading
- Subject: Re: Self-scheduling threading
- From: Shaun Wexler <email@hidden>
- Date: Thu, 17 Mar 2005 16:07:04 -0800
On Mar 17, 2005, at 3:51 PM, I typoed:
He won't do any better than the default granularity of 1 ms,
regardless. For each type of duty (realtime-driven, low-latency,
rendering, etc). MacFOH spawns up to one worker thread per CPU, and
each services their common work queue during its cycle. Bloody
efficient. I also strive to LOWER the priority of threads rather than
raise them, and making them RR/fixed keeps the important background
tasks churning along without disrupting the user experience such as
when many raised-priority threads are in competition.
He won't do any better than the default granularity of 10 ms,
regardless. For each type of duty (realtime-driven, low-latency,
rendering, etc), MacFOH spawns up to one worker thread per CPU, and
each services their common work queue during its timeslice. Bloody
efficient. I also strive to LOWER the priority of threads rather than
raise them, and making them RR/fixed keeps the important background
tasks churning along without disrupting the user experience such as
when many raised-priority threads are in competition.
--
Shaun Wexler
MacFOH
http://www.macfoh.com
Attachment:
smime.p7s
Description: S/MIME cryptographic signature
_______________________________________________
Do not post admin requests to the list. They will be ignored.
Cocoa-dev mailing list (email@hidden)
Help/Unsubscribe/Update your Subscription:
This email sent to email@hidden