From: "Richard Henderson" <rth@twiddle.net>
> Any reason we couldn't vmalloc the in-kernel array when it gets too big?
>
vmalloc is sloww, especially on SMP computer because it must unconditionally
flush all tlb's on all cpu's. I'd prefer a linked list, each entry up to
PAGE_SIZE. Either kmalloc'ed(), or kmalloc + gfp().
And: move the lock_kernel() calls as near a possible to the actual do_poll()
calls. You don't need the big kernel lock for the memory allocations or the
copy_from_user() calls.
--
Manfred
-
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/
This archive was generated by hypermail 2b29 : Sat Jan 15 2000 - 21:00:13 EST