This is the mail archive of the
libc-alpha@sourceware.org
mailing list for the glibc project.
Re: Fixed size of thread stacks in the nptl pthread implementation
Richard,
> Indeed, the single largest problem with growing stacks is the
> reservation of the VM space.
Do you have a pointer to a discussion on the problem?
When you say "reservation of the VM space" are you talking about VM
layout and how you ensure the thread stacks have space to grow?
> Which of course led Google to invent the split-stack feature
> in gcc, allowing the stack to grow a couple of pages at a time.
Thanks! I'd not read [1] and it was informative and interesting. I've
added Ian to the CC to ask him directly since he's probably already
thought of the answer.
Ian,
Is there any reason, when looking at split-stack, that it was not an
intermediate option to reduce default thread sizes and grow the thread
stacks dynamically (in the traditional manner)? While such a solution
is not as good as split-stack, it would have been a short-term
solution to reduce thread stack size to the approximately required
size (as opposed to the large static stack sizes used by glibc today).
Cheers,
Carlos.
[1] http://gcc.gnu.org/wiki/SplitStacks