Re: [PATCH 0/4] skb paged fragment destructors

Le mercredi 21 décembre 2011 à 13:48 +0000, Ian Campbell a écrit :

On Wed, 2011-12-21 at 12:30 +0000, Eric Dumazet wrote:

quoted

Le mercredi 21 décembre 2011 à 11:18 +0000, Ian Campbell a écrit :

quoted

An order 1 allocation is in multiples of PAGE_SIZE, isn't it, even
though they happen to be contiguous?

Really an order-1 allocation allocates one page, a compound one.

Oh, right, I see what you mean.

You snipped the question about the + 2, I take it you have no idea what
it is all about either?

No idea on this +2 point.

I know some hardwares have limits on a fragment length (for example IGB
uses IGB_MAX_DATA_PER_TXD limit), but I dont know why we add extra frags
in generic skb.