On Mon, Oct 22, 2012 at 6:29 PM, Andi Kleen <ak@xxxxxxxxxxxxxxx> wrote: >> Since PowerPC already allows 16GB page sizes, doesn't there need to be >> allowance for the possibility of future expansion? Choosing a larger >> minimum size (like 2^16) would allow that. Does the minimum size need >> to be 16k? (Surely, if you want a HUGEPAGE, you want a bigger page >> than that? I am not sure.) > > Some architectures have configurable huge page sizes, so it depends on > the user. I thought 16K is reasonable. Can make it larger too. > > But I personally consider even 16GB pages somewhat too big. I do not know the answer course ;-). Just thought that it was worth emphasizing that some system already allows the upper limit you propose. It seems inevitable that some other system will allow something even bigger. Anyway, I got distracted from my earlier more important point. This proposed change will chew up most (all?) of the remaining bit-space in 'flags'. This seems like a mistake from a future extensibility point of view... It sounds a lot like you'll force someone else to write and deploy mmap3()... -- Michael Kerrisk Linux man-pages maintainer; http://www.kernel.org/doc/man-pages/ Author of "The Linux Programming Interface"; http://man7.org/tlpi/ -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@xxxxxxxxx. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>