On Thu, Mar 03, 2011 at 08:46:40AM -0800, Nathan Froyd wrote: > On Thu, Mar 03, 2011 at 06:15:49PM +0200, Riku Voipio wrote: > > QEMU linux-user calls glibc functions which, while usually very conservative > > with memory usage, are not guaranteed not take less than 10KB (at do_syscall > > we are already around 5 functions deep). > Bleh. OK, so it needs to be increased. Could we get by with somewhat > less (256K?), to try and maximize the number of threads we can > potentially run? Maybe it doesn't matter (people creating thousands of > simultaneous threads inside QEMU have other problems...), but not > gratuitously wasting memory would be good.
I believe 256K should be enough for everone now, then again we know what happened when someone suggested same about 640K.. In this case however, if the limit is ever hit, increasing the limit again is easy. Originally I did put the limit much higher, as I assume due to lazy memory allocation from kernel it doesn't matter if we ask for 256K or 8M, as unused pages will never be allocated. But I'll do some testing with lots of threads and see if stack size has an impact on how many threads we can run. Riku