Messages in this thread | | | Date | Wed, 17 Feb 1999 09:13:27 -0800 | From | <> | Subject | Re: TCP/IP Kernel Code modifications |
| |
> What I would like to know is if it is a big undertaking to have the > kernel TCP/IP Code stall the packets for say between 10ms to 500ms?
Interesting application. This could be done in user space with raw sockets, I think; perhaps something like
raw_stamp in_if | raw_transmit out_if
where raw_stamp prepends a timestamp (from gettimeofday()) to each relevant packet before writing to the pipe, and raw_transmit uses a timer to schedule the outgoing packets based on the stamps.
If user space is unacceptable for some reason, I guess the network driver could be hacked: instead of immediately netif_rx(skb), you'd want to append to a timer_list to defer the netif_rx() until after some number of jiffies.
Cheers, Peter Monta pmonta@imedia.com Imedia Corp.
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/
| |