Andrew Morton writes: > The box has 130 mbyte/sec memory write bandwidth, so saving > a copy should save 10% of this. (Wanders away, scratching > head...) Are you sure your measurment program will account properly for all system cycles spent in softnet processing? This is where the bulk of the cpu cycle savings will occur. Later, David S. Miller [EMAIL PROTECTED] - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [EMAIL PROTECTED] Please read the FAQ at http://www.tux.org/lkml/
- sendfile+zerocopy: fairly sexy (nothing to do with ECN) Andrew Morton
- Re: sendfile+zerocopy: fairly sexy (nothing to do wi... Aaron Lehmann
- Re: sendfile+zerocopy: fairly sexy (nothing to d... Andrew Morton
- Re: sendfile+zerocopy: fairly sexy (nothing ... Ion Badulescu
- Re: sendfile+zerocopy: fairly sexy (noth... Andrew Morton
- Re: sendfile+zerocopy: fairly sexy (nothing ... David S. Miller
- Re: sendfile+zerocopy: fairly sexy (noth... David S. Miller
- Re: sendfile+zerocopy: fairly sexy ... David S. Miller
- Re: sendfile+zerocopy: fairly s... David S. Miller
- Re: sendfile+zerocopy: fairly sexy ... David S. Miller
- Re: sendfile+zerocopy: fairly sexy (noth... Andrew Morton
- Re: sendfile+zerocopy: fairly sexy ... Trond Myklebust
- Re: sendfile+zerocopy: fairly sexy ... David Lang
- Re: sendfile+zerocopy: fairly s... David S. Miller
- Re: sendfile+zerocopy: fair... David Lang
- Re: sendfile+zerocopy: fair... David S. Miller
- Re: sendfile+zerocopy: fair... David Lang
- Re: sendfile+zerocopy: fair... Jeff Barrow
- Re: sendfile+zerocopy: fair... David S. Miller
- Re: sendfile+zerocopy: fair... James Sutherland