netdev - Re: [PATCH net-next 2/4] net: bcmgenet: add support for ethtool tx-frames

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] [day] [month] [year] [list]

Message-Id: <20140421.155952.1239791110163851437.davem@davemloft.net>
Date:	Mon, 21 Apr 2014 15:59:52 -0400 (EDT)
From:	David Miller <davem@...emloft.net>
To:	f.fainelli@...il.com
Cc:	netdev@...r.kernel.org
Subject: Re: [PATCH net-next 2/4] net: bcmgenet: add support for ethtool
 tx-frames

From: Florian Fainelli <f.fainelli@...il.com>
Date: Mon, 21 Apr 2014 12:55:12 -0700

> 2014-04-21 12:17 GMT-07:00 David Miller <davem@...emloft.net>:
>> From: Florian Fainelli <f.fainelli@...il.com>
>> Date: Mon, 21 Apr 2014 08:45:22 -0700
>>
>>> Configuring the ethtool tx-frames property, which translates into N
>>> packets before a TX interrupt is the simplest configuration scheme
>>> because it requires no locking neither at the softare nor hardware
>>> level, and is completely indepedent from the link speed. Since ethtool
>>> does not allow per-tx queue coalescing parameters, we apply the same
>>> setting to any transmit queue.
>>>
>>> We can no longer enable the BDONE/PDONE interrupts as those would fire
>>> for each packet/buffer received, which would defeat the MBDONE interrupt
>>> purpose. The MBDONE interrupt is guaranteed to correspond to a
>>> PDONE/BDONE interrupt when the threshold is set to 1.
>>>
>>> Signed-off-by: Florian Fainelli <f.fainelli@...il.com>
>>
>> Does the MBDONE scheme have a timeout?
>>
>> For example if you ask for a MBDONE setting where N=4, if only 2 packets
>> arrive will you get an interrupt or will it wait for 2 more to arrive
>> no matter what?
> 
> There is no configurable timeout for the transmit DMA engine (receive
> does have one), but we do get a ring empty interrupt as soon as the
> transmit path has completed the packets, so the MBDONE interrupt cause
> always makes us run the TX reclaim logic.

This latency may be too large for TCP.

In particular things like TCP Small Queues need timely feedback for
transmitted packets.
--
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