[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <alpine.DEB.1.10.0904231803550.28139@qirst.com>
Date: Thu, 23 Apr 2009 18:06:43 -0400 (EDT)
From: Christoph Lameter <cl@...ux.com>
To: Eric Dumazet <dada1@...mosbay.com>
cc: "David S. Miller" <davem@...emloft.net>,
Linux Netdev List <netdev@...r.kernel.org>,
Michael Chan <mchan@...adcom.com>,
Ben Hutchings <bhutchings@...arflare.com>
Subject: Re: about latencies
On Fri, 24 Apr 2009, Eric Dumazet wrote:
> sock_wfree()
> -> sock_def_write_space()
> -> _read_lock()
> -> __wake_up_sync_key()
> and lot of functions calls to wakeup the task, for nothing since it
> will just schedule again. Lot of cache lines dirtied...
Right.
> We could improve this.
>
> 1) dst_release at xmit time, should save a cache line ping-pong on general case
> 2) sock_wfree() in advance, done at transmit time (generally the thread/cpu doing the send)
> 3) changing bnx2_poll_work() to first call bnx2_rx_int(), then bnx2_tx_int() to consume tx.
Good idea that would get rid of the IRQ delay if the process is asking for
data. We'd only be batching if no one is asking for data?
> What do you think ?
Sounds good.
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists