[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <54F002A8.307@gmail.com>
Date: Fri, 27 Feb 2015 13:37:44 +0800
From: Fan Du <fengyuleidian0615@...il.com>
To: David Laight <David.Laight@...LAB.COM>
CC: 'Fan Du' <fan.du@...el.com>,
"johnwheffner@...il.com" <johnwheffner@...il.com>,
"edumazet@...gle.com" <edumazet@...gle.com>,
"davem@...emloft.net" <davem@...emloft.net>,
"netdev@...r.kernel.org" <netdev@...r.kernel.org>
Subject: Re: [PATCHv2 net-next 0/4] Small fix for TCP PMTU
于 2015年02月26日 21:40, David Laight 写道:
> From: Fan Du
>> >This patchset performs some small fix and enhancement
>> >for current TCP PMTU as per RFC4821 with below changes:
>> >
>> >Patch1/4: Set probe mss base to 1024 Bytes per RFC4821
>> >Patch2/4: Do not double probe_size for each probing,
>> > use a simple binary search to gain maximum performance.
>> >Patch3/4: When it comes to blackhole detection, shrink current
>> > mss for next probing.
>> >Patch4/4: Create a probe timer to detect enlarged path MTU.
> Isn't the most likely problem PPPoE blackholes?
No.
It's used to probe a optimal pmtu value for vxlan tunnel when ICMP message
is not available. Refer patch2/4 for test summary.
> Where a reduction of the PMTU from 1500 to (IIRC) 1492 is
> all that is required?
>
> Would seem appropriate to test that value reasonable quickly.
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists