Messages in this thread | | | From | (Alan Cox) | Subject | Re: 2.1.125 Show stopper list: Draft | Date | Wed, 14 Oct 1998 12:42:19 +0100 (BST) |
| |
> > to reclaim memory urgently they simply blow the CPU page tables away > > and give the task a new empty page table set to page everything back > > into. > > > > Since there are caches these faults don't go to disk but just to the cache > > and rapidly recover the page tables for the current working set. > > But surely with enough small segments I could overflow these caches too? > Doesn't sound like a complete solution to me.
Since the cache in question is in Linux terms the page cache anyway then no you can't overflow it and cause a problem. If the page cache isnt holding all your pages then they were swapped to disk anyway so the behaviour hasnt changed.
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/
| |