* [PATCH 4/4][NEW]: More to see in dccp_probe
@ 2007-01-03 13:58 Gerrit Renker
0 siblings, 0 replies; 3+ messages in thread
From: Gerrit Renker @ 2007-01-03 13:58 UTC (permalink / raw)
To: dccp
[CCID 3]: More to see in dccp_probe
This removes the `size' field from output (which would report the constant buffer size),
and adds a few more fields of interest to /proc/net/dccpprobe, the following output ensues:
sec.usec src:sport dst:dport s rtt p X_calc X_recv X t_ipi
1 2 3 4 5 6 7 8 9 10
Scripts that go with this can be downloaded from http://139.133.210.30/users/gerrit/dccp/dccp_probe/
Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk>
---
net/dccp/probe.c | 8 +++++---
1 file changed, 5 insertions(+), 3 deletions(-)
--- a/net/dccp/probe.c
+++ b/net/dccp/probe.c
@@ -90,11 +90,13 @@ static int jdccp_sendmsg(struct kiocb *i
if (port = 0 || ntohs(inet->dport) = port ||
ntohs(inet->sport) = port) {
if (hctx)
- printl("%d.%d.%d.%d:%u %d.%d.%d.%d:%u %d %d %d %d %d\n",
+ printl("%d.%d.%d.%d:%u %d.%d.%d.%d:%u %d %d %d %u %llu %llu %d\n",
NIPQUAD(inet->saddr), ntohs(inet->sport),
- NIPQUAD(inet->daddr), ntohs(inet->dport), size,
+ NIPQUAD(inet->daddr), ntohs(inet->dport),
hctx->ccid3hctx_s, hctx->ccid3hctx_rtt,
- hctx->ccid3hctx_p, hctx->ccid3hctx_t_ipi);
+ hctx->ccid3hctx_p,
+ hctx->ccid3hctx_x_calc, hctx->ccid3hctx_x_recv >> 6,
+ hctx->ccid3hctx_x >> 6, hctx->ccid3hctx_t_ipi);
else
printl("%d.%d.%d.%d:%u %d.%d.%d.%d:%u %d\n",
NIPQUAD(inet->saddr), ntohs(inet->sport),
^ permalink raw reply [flat|nested] 3+ messages in thread
* Re: [PATCH 4/4][NEW]: More to see in dccp_probe
@ 2007-01-03 21:39 Ian McDonald
2007-01-04 3:04 `
0 siblings, 1 reply; 3+ messages in thread
From: Ian McDonald @ 2007-01-03 21:39 UTC (permalink / raw)
To: dccp
On 1/4/07, Gerrit Renker <gerrit@erg.abdn.ac.uk> wrote:
> [CCID 3]: More to see in dccp_probe
>
> This removes the `size' field from output (which would report the constant buffer size),
> and adds a few more fields of interest to /proc/net/dccpprobe, the following output ensues:
>
I would like the size field kept. This is not constant if you are
sending different size packets like I am :-) It is only constant if
you are using something like iperf/ttcp.
Ian
--
Web: http://wand.net.nz/~iam4
Blog: http://imcdnzl.blogspot.com
WAND Network Research Group
^ permalink raw reply [flat|nested] 3+ messages in thread
* Re: [PATCH 4/4][NEW]: More to see in dccp_probe
2007-01-03 21:39 Ian McDonald
@ 2007-01-04 3:04 `
0 siblings, 0 replies; 3+ messages in thread
From: @ 2007-01-04 3:04 UTC (permalink / raw)
To: dccp
In article <5640c7e00701031339u20f7ad2hf416821257f44214@mail.gmail.com> (at Thu, 4 Jan 2007 10:39:18 +1300), "Ian McDonald" <ian.mcdonald@jandi.co.nz> says:
> On 1/4/07, Gerrit Renker <gerrit@erg.abdn.ac.uk> wrote:
> > [CCID 3]: More to see in dccp_probe
> >
> > This removes the `size' field from output (which would report the constant buffer size),
> > and adds a few more fields of interest to /proc/net/dccpprobe, the following output ensues:
> >
> I would like the size field kept. This is not constant if you are
> sending different size packets like I am :-) It is only constant if
> you are using something like iperf/ttcp.
I agree, and please do not insert new fields
but add them to the tail of old fields.
--yoshfuji
^ permalink raw reply [flat|nested] 3+ messages in thread
end of thread, other threads:[~2007-01-04 3:04 UTC | newest]
Thread overview: 3+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2007-01-03 13:58 [PATCH 4/4][NEW]: More to see in dccp_probe Gerrit Renker
-- strict thread matches above, loose matches on Subject: below --
2007-01-03 21:39 Ian McDonald
2007-01-04 3:04 `
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.