| To: | "David S. Miller" <davem@xxxxxxxxxx> |
|---|---|
| Subject: | Re: fix TCP roundtrip time update code |
| From: | David Mosberger <davidm@xxxxxxxxxxxxxxxxx> |
| Date: | Tue, 3 Jun 2003 23:12:47 -0700 |
| Cc: | davidm@xxxxxxxxxx, davidm@xxxxxxxxxxxxxxxxx, niv@xxxxxxxxxx, kuznet@xxxxxxxxxxxxx, jmorris@xxxxxxxxxxxxxxxx, gandalf@xxxxxxxxxxxxxx, linux-kernel@xxxxxxxxxxxxxxx, linux-ia64@xxxxxxxxxxxxx, netdev@xxxxxxxxxxx, akpm@xxxxxxxxx |
| In-reply-to: | <20030603.225245.55753285.davem@xxxxxxxxxx> |
| References: | <16093.30507.661714.676184@xxxxxxxxxxxxxxxxx> <3EDD7832.7010804@xxxxxxxxxx> <16093.34022.445246.52398@xxxxxxxxxxxxxxxxx> <20030603.225245.55753285.davem@xxxxxxxxxx> |
| Reply-to: | davidm@xxxxxxxxxx |
| Sender: | netdev-bounce@xxxxxxxxxxx |
>>>>> On Tue, 03 Jun 2003 22:52:45 -0700 (PDT), "David S. Miller"
>>>>> <davem@xxxxxxxxxx> said:
David> From: David Mosberger <davidm@xxxxxxxxxxxxxxxxx> Date:
David> Tue, 3 Jun 2003 22:34:30 -0700
David> You can't go higher than 1000 conn/sec per client (IP
David> address) because otherwise you run out of port space (due to
David> TIME_WAIT).
DaveM> echo "1" >/proc/sys/net/ipv4/tcp_tw_recycle
DaveM> It should eliminate this limit. Unfortunately we can't
DaveM> enable this by default because of NAT :(
Ah, yes, provided PAWS is enabled, this would give you a time_wait
timeout of 3.5*RTO. Nice.
--david
|
| <Prev in Thread] | Current Thread | [Next in Thread> |
|---|---|---|
| ||
| Previous by Date: | Re: [PATCH] IPV6: typo, unrequired #undef and killing warning, David S. Miller |
|---|---|
| Next by Date: | Re: fix TCP roundtrip time update code, Nivedita Singhvi |
| Previous by Thread: | Re: fix TCP roundtrip time update code, David S. Miller |
| Next by Thread: | Re: fix TCP roundtrip time update code, Nivedita Singhvi |
| Indexes: | [Date] [Thread] [Top] [All Lists] |