Re: [PATCH v9 net-next 5/7] net: simple poll/select low latency socketpoll

From: Eliezer Tamir
Date: Wed Jun 05 2013 - 11:47:26 EST


On 05/06/2013 18:20, Eric Dumazet wrote:
On Wed, 2013-06-05 at 16:41 +0300, Eliezer Tamir wrote:
On 05/06/2013 16:30, Eric Dumazet wrote:

I am a bit uneasy with this one, because an applicatio polling() on one
thousand file descriptors using select()/poll(), will call sk_poll_ll()
one thousand times.

But we call sk_poll_ll() with nonblock set, so it will only test once
for each socket and not loop.

I think this is not as bad as it sounds.
We still honor the time limit on how long to poll.

We still call ndo_ll_poll() a thousand times, and probably do a
spinlock/unlock a thousand times in the driver.

I would definitely be convinced if you give us some performance numbers
of a poll() on a thousand tcp sockets for example.

So with 1000 sockets this is defiantly not a win
sockperf with 1000 udp sockets

sysctl 50 0
select 178.5 us / 130.0 us
poll 188.6 us / 130.0 us

--
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/