netdev - Re: [PATCH net-next 3/4] ipv4: Use probe_size to check write queue data length

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:	Wed, 18 Mar 2015 08:41:58 -0400
From:	John Heffner <johnwheffner@...il.com>
To:	Fan Du <fengyuleidian0615@...il.com>
Cc:	Fan Du <fan.du@...el.com>, David Miller <davem@...emloft.net>,
	Netdev <netdev@...r.kernel.org>
Subject: Re: [PATCH net-next 3/4] ipv4: Use probe_size to check write queue
 data length

On Tue, Mar 17, 2015 at 9:37 PM, Fan Du <fengyuleidian0615@...il.com> wrote:
> 于 2015年03月10日 20:26, John Heffner 写道:
>>
>> NACK.  From RFC4821:
>>
>>     In addition, the timely loss detection algorithms in most protocols
>>     have pre-conditions that SHOULD be satisfied before sending a probe.
>>     For example, TCP Fast Retransmit is not robust unless there are
>>     sufficient segments following a probe; that is, the sender SHOULD
>>     have enough data queued and sufficient receiver window to send the
>>     probe plus at least Tcprexmtthresh [RFC2760] additional segments.
>>     This restriction may inhibit probing in some protocol states, such as
>>     too close to the end of a connection, or when the window is too
>>     small.
>>
>
> Thanks for pointing this out for me.
>
> My limit understanding is the extra segments is used to trigger fast
> retransmit,
> and the conditions is the count of duplicate ack. Then why needs an extra
> one more
> segment here besides 'reordering' segment to trigger this?
>
> size_needed = probe_size + (tp->reordering + 1) * tp->mss_cache;
>                                             ^^^

I can't recall a particular reason for the plus one.  It may be
unnecessarily conservative.
--
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