| To: | Lennert Buytenhek <buytenh@xxxxxxxxxxxxxx> |
|---|---|
| Subject: | Re: inter-packet gap in pktgen |
| From: | Robert Olsson <Robert.Olsson@xxxxxxxxxxx> |
| Date: | Wed, 8 Dec 2004 11:21:54 +0100 |
| Cc: | Ben Greear <greearb@xxxxxxxxxxxxxxx>, Robert Olsson <Robert.Olsson@xxxxxxxxxxx>, hadi@xxxxxxxxxx, netdev@xxxxxxxxxxx |
| In-reply-to: | <20041208073858.GA4027@xxxxxxxxxxxxxxxxx> |
| References: | <20041207222522.GA30266@xxxxxxxxxxxxxxxxx> <41B632F3.1090104@xxxxxxxxxxxxxxx> <20041208073858.GA4027@xxxxxxxxxxxxxxxxx> |
| Sender: | netdev-bounce@xxxxxxxxxxx |
Lennert Buytenhek writes:
>
> Another option is:
>
> next_tx = get_time_in_ns();
> while (--count) {
> tx_packet();
> next_tx += 1e9/intended_pps;
> nanospin(next_tx - get_time_in_ns());
> }
Hello!
I think this what Ben is doing with his userland app. Ev. adjusting
the ipg delay in runtime? A kind of control system. Even the device
stats could possible be read.
> This should be relatively independent of system load. OK, I know,
> time to show some code.
Also an idea might be to have some kind of option to use pktgen w.
existent qdisc/tc infrastructure for this type of tests. Ben did
you try this?
--ro
|
| <Prev in Thread] | Current Thread | [Next in Thread> |
|---|---|---|
| ||
| Previous by Date: | [PATCH] [IPV6]: Fix check if we're router., YOSHIFUJI Hideaki / 吉藤英明 |
|---|---|
| Next by Date: | [PATCH 0/5] sis900 printk and stack usage audit, Daniele Venzano |
| Previous by Thread: | Re: inter-packet gap in pktgen, Lennert Buytenhek |
| Next by Thread: | Re: inter-packet gap in pktgen, Lennert Buytenhek |
| Indexes: | [Date] [Thread] [Top] [All Lists] |