> Hmm, stupid question: what happens when 16K is not enough too, do we > increase again? When do we stop increasing? 1M, 2M... ?
It's not a stupid question, it's IMHO the most important question > Sounds like we want to make it a config option with a couple of sizes > for everyone to be happy. :-) At the moment it goes bang if you freakily get three layers of recursion through allocations. But show me the proof we can't already hit four, or five, or six .... We don't *need* to allocate tons of stack memory to each task just because we might recursively allocate. We don't solve the problem by doing so either. We at best fudge over it. Why is *any* recursive memory allocation not ending up waiting for other kernel worker threads to free up memory (beyond it being rather hard to go and retrofit) ? -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
