Re: [patch - v3] epoll ready set loops diet ...
- From: Davide Libenzi <davidel@xxxxxxxxxxxxxxx>
- Date: Wed, 28 Feb 2007 11:23:37 -0800 (PST)
On Wed, 28 Feb 2007, Eric Dumazet wrote:
On Wednesday 28 February 2007 19:37, Davide Libenzi wrote:
+ list_del(&epi->rdllink);
+ if (!(epi->event.events & EPOLLET) && (revents & epi->event.events))
+ list_add_tail(&epi->rdllink, &injlist);
+ else {
Is the ( ... & epi->event.events) really necessary ? (It seems already done)
Yes, look here:
if (epi->event.events & EPOLLONESHOT)
epi->event.events &= EP_PRIVATE_BITS;
Oneshot events should not be requeued.
I was wrong about the size of epitem : it is now 68 bytes instead of 72.
At least we now use/dirty one cache line instead of two per epitem.
Do you have another brilliant idea to shrink 4 more bytes ? :)
I don't think we can cleanly shove more stuff out of it.
- Davide
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
- References:
- [patch - v3] epoll ready set loops diet ...
- From: Davide Libenzi
- Re: [patch - v3] epoll ready set loops diet ...
- From: Eric Dumazet
- [patch - v3] epoll ready set loops diet ...
- Prev by Date: Re: PROBLEM: null pointer dereference in cfq_dispatch_requests (2.6.21-rc2 and 2.6.20)
- Next by Date: [PATCH] SLUB The unqueued slab allocator V3
- Previous by thread: Re: [patch - v3] epoll ready set loops diet ...
- Next by thread: [PATCH]: __init to __cpuinit in mtrr code
- Index(es):