Messages in this thread | | | Date | Thu, 20 Jan 2000 16:01:20 +0000 (GMT) | From | Tigran Aivazian <> | Subject | Re: [patch-2.3.40-pre6] nfds limit for poll() raised to 131 million (is that enough?) |
| |
On Thu, 20 Jan 2000, Jamie Lokier wrote: > Excellent idea!
hmmm, you think so? I felt a bit embarrased after posting it because I thought it was not such a good idea because one would have to reorganize the way we pass parameters to do_poll() completely. Well, do_poll() only walks through one element at a time so it can walk through the (say, linked list?) of slab'd pollfd objects one at a time.
> - No fd limit, for free yes, true.
> To keep it scalable on SMP, you'd want a per-processor slab cache.
I know - we had lots of chats with Mark Hemment about this stuff and I gradually moved from understanding 0.1% to about 78% of what he is talking about :)
Regards, ------ Tigran A. Aivazian | http://www.sco.com Escalations Research Group | tel: +44-(0)1923-813796 Santa Cruz Operation Ltd | http://www.ocston.org/~tigran
- 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/
| |