[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <4B0C4624.9080607@gmail.com>
Date: Tue, 24 Nov 2009 21:46:28 +0100
From: Eric Dumazet <eric.dumazet@...il.com>
To: Andi Kleen <andi@...stfloor.org>
CC: David Miller <davem@...emloft.net>,
peter.p.waskiewicz.jr@...el.com, peterz@...radead.org,
arjan@...ux.intel.com, yong.zhang0@...il.com,
linux-kernel@...r.kernel.org, arjan@...ux.jf.intel.com,
netdev@...r.kernel.org
Subject: Re: [PATCH] irq: Add node_affinity CPU masks for smarter irqbalance
hints
Andi Kleen a écrit :
> They are typically allocated with dma_alloc_coherent(), which does
> allocate a continuous area. In theory you could do interleaving
> with IOMMus, but just putting it on the same node as the device
> is probably better.
There are two parts, biggest one allocated with vmalloc()
(to hold struct ixgbe_rx_buffer array, 32 bytes or more per entry),
only used by driver (not adapter)
and one allocated with pci_alloc_consistent()
(to hold ixgbe_adv_tx_desc array, 16 bytes per entry)
vmalloc() one could be spreaded on many nodes.
I am not speaking about the pci_alloc_consistent() one :)
--
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