[lkml]   [1996]   [Jun]   [8]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
Messages in this thread
    SubjectRe: Speed of memcpy, csum_partial and csum_partial_copy

    >>>>> "me" == Pedro Roque Marques <> writes:
    >>>>> "Alan" == Alan Cox <> writes:

    Alan> There are three for TCP loopback unless someone has fiddled
    Alan> recently. We copy:

    sk_buff [with csum]
    sk_buff to sk_buff
    sk_buff-> user [skip csum]

    Alan> While it seems a really dumb thing to do it makes sense as
    Alan> there may be retransmissions and thus the receiver cannot go
    Alan> using the queue pointers of the senders buffer copy. Its a
    Alan> bad case solely applicable to loopback, and if we are going
    Alan> to optimise loopback tcp we should do the solaris trick and
    Alan> dump everything. In the mean time thats what AF_UNIX was
    Alan> invented for.

    me> On the TCP i've been seting up for 2.1 there is no need for
    me> copy number 2 since the skb is cloned (the copy is restricted
    me> to the skb header).

    Well, i've been looking at the code and loopback does a clone of the
    skb (the right thing to do) so there are really 2 data copies
    only. There is the memcpy of the skb header but that does not seam
    to show on Linus profile trace (it's 30-40 bytes for each 3k).


     \ /
      Last update: 2005-03-22 13:37    [W:0.018 / U:70.480 seconds]
    ©2003-2016 Jasper Spaans. hosted at Digital OceanAdvertise on this site