Messages in this thread | | | Date | Sat, 22 Sep 2001 14:36:24 -0700 (PDT) | Subject | Re: Purpose of the mm/slab.c changes | From | "David S. Miller" <> |
| |
From: Davide Libenzi <davidel@xmailserver.org> Date: Sat, 22 Sep 2001 14:03:02 -0700 (PDT)
Besides this, i don't get how a LIFO could help you.
Actually, there is a school of thought which says that if you make the time between the free and re-alloc of a piece of memory as long as possible you increase the likelyhood that any dirty cache lines of that memory can be sent back to memory "quietly" during natural L2 cache line replacement.
I don't necessarily subscribe to these ideas, but I do see the potential benefits. For one thing, it does have the potential to lead to more repeatable timings, at least in theory.
Later, David S. Miller davem@redhat.com - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
| |