Messages in this thread | | | Date | Sun, 20 Jan 2002 07:34:32 -0700 | From | yodaiken@fsmlabs ... | Subject | Re: [2.4.17/18pre] VM and swap - it's really unusable |
| |
On Sun, Jan 20, 2002 at 02:31:51AM -0800, george anzinger wrote: > yodaiken@fsmlabs.com wrote: > > What I think we need is a kind of interval real-time scheduling. > > Something like: > > The system has a basic timing period of N milliseconds where > > N is at lease 500 and probably more. > > > > Over a N millisecond period each process gets a full scheduling quantum > > and, if it requests, a full I/O quantum. > > For a niced process there is some calculated interval greater than > > N. An I/O quantum should correspond somehow to a rate of I/0. > > > > RTLIMIT is used to set the max number of processes allowed to start > > and this determines the computation length of "one quantum" > > Have you looked at SCHED_SPORADIC (see 1003.1d-1999)?
Yes, but I don't think it does much - although its description is quite long and complex. - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
| |