Nice work Ian! | Signed-off-by: Ian McDonald <ian.mcdonald@xxxxxxxxxxx> Signed-off-by: Gerrit Renker <gerrit@xxxxxxxxxxxxxx> | + unsigned long delay; With regard to the delay, I think we are now fairly on the safe side. Although schedule_timeout takes `signed long', the value of delay can not be large: as per earlier discussion (regarding the return type of dccp_hc_tx_send_packet), the delay is bounded by sending one packet in 64 seconds, hence the maximum delay is 1/64 sec = 15.625 milliseconds (I am not suggesting to use `u8' :) Have signed off and uploaded as 10a onto http://www.erg.abdn.ac.uk/users/gerrit/dccp/patch-backlog/ I did some performance testing which ended asking my boss for a faster computer, since on this one the figures get strange as soon as system load increases. I think we need something other than iperf to do the profiling - at the moment it does not at all act in a reproducible or predictable way. - To unsubscribe from this list: send the line "unsubscribe dccp" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
