Linked by Kasra Yousefi on Fri 7th Jan 2005 17:44 UTC
Editorial Problem: Even the most powerful PC's become non responsive during resource-intensive computations, such as graphic design, media, image rendering and manipulating. The traditional solution has been to upgrade to a faster computer and throw more computing power at the problem to lessen the wait-time. But there's a simple solution that utilizes multiple machines, but without using grid/clustering. For now, this involves a hack, but how hard would it be for an OS vendor to streamline this process?
Permalink for comment
To read all comments associated with this story, please click here.
There is another way...
by ASHLB on Fri 7th Jan 2005 19:01 UTC

If the Operating Systems we were using had decent schedulers then this would not be a problem. Let me explain.

If the OS detects that a process is really compute bound and interactive users/processes were suffering from lengthening I/O response times(eg keyboard clicks) it would dynamically reduce the priority of the CPU hog to let other users get a slot. This is not rocket sciene. I learnt this 30 years ago when studying realt time compute operating systems. One great example at the time was the RSTS-E Operating System that ran on PDP-11's. Hawker Siddley Aviation(Home of the Harrier VTOL aircraft) was using a RSTS system in the aerodynamics lab. They had many users doing lots of CPU intensive work. They all got a response. The OS limited CPUS from taking too much CPU. The O/S would switch from a timeslice based scheduler to a priority based schedule at time of high CPU Usage.(That was how a top guy at DEC explained it to me at the time).
Naturally, this sort of thing could never be included in any Microsoft OS as IMHO, they don't know the meaning of the word Scheduler but, that as I say is MHO.
Enough of the history remeniscing. Its Friday night and I'm off down the pub.