Skip site navigation (1)Skip section navigation (2)
Date:      Mon, 22 Mar 2010 12:03:21 +0300
From:      Alexander Bubnov <alexander.bubnov@gmail.com>
To:        freebsd-net@freebsd.org
Subject:   Re: why zero-copy sockets(9) are not popular?
Message-ID:  <c3e287ff1003220203n7bec914dqefd1cb81eb6a2cf3@mail.gmail.com>
In-Reply-To: <c3e287ff1003202221p15fe6da8gce813c5889e095e0@mail.gmail.com>
References:  <c3e287ff1003200306l162800bfgfc0eecec04401917@mail.gmail.com> <4BA50BA1.5060401@incunabulum.net> <c3e287ff1003202221p15fe6da8gce813c5889e095e0@mail.gmail.com>

next in thread | previous in thread | raw e-mail | index | archive | help
Hi, everybody!
I have found some Intel NICs which supports "header splitting". Does FreeBSD
support them for zero-copy receive?
One more question please... is there a way to determine whether or not
zero-copy receive is working, for example by kernel log or something else?

Thank you in advance.

2010/3/21 Alexander Bubnov <alexander.bubnov@gmail.com>

> Bruce, many thanks for comprehensive answer!
>
> 2010/3/20 Bruce Simpson <bms@incunabulum.net>
>
> On 03/20/10 10:06, Alexander Bubnov wrote:
>>
>>> Hello, all!
>>> Anybody knows why zero copy is not popular although this technique
>>>  allows
>>> to increase performance of servers? It is very hard to find any examples
>>> of
>>> zero-copy for FreeBSD.
>>>
>>>
>>
>> Transmit is easy. Receive is hard.
>>
>> The whole concept of zero-copy revolves around being able to use
>> page-flipping to map buffers in user and kernel space, to amortize the cost
>> of copies across that system boundary.
>>
>> The compromise usually taken is to use the sendfile() API, or rely on TCP
>> Segmentation Offload (TSO), much like Microsoft's Chimney stack does in
>> Windows 7. Unfortunately, sendfile() only covers transmit. TSO only offloads
>> up to the point where sockets hit the card; TSO can offload TCP stream
>> reassembly, but you still have to copy from the kernel buffers into
>> userland.
>>
>> True zero-copy sockets generally require scatter/gather DMA engine
>> support, and TCP/IP header splitting, to do zero-copy recieve.
>>
>> S/G PCI DMA cores are often custom designed, and you tend not to find them
>> in off-the-shelf VHDL libraries. That IP (as in intellectual property) still
>> has cost.
>>
>> Historically the only cards in FreeBSD which supported this, were the
>> Tigon-II, which got bought by Broadcom (bge is the Tigon-III). Modified
>> firmware was required to do this.
>>
>>
>> _______________________________________________
>> freebsd-net@freebsd.org mailing list
>> http://lists.freebsd.org/mailman/listinfo/freebsd-net
>> To unsubscribe, send any mail to "freebsd-net-unsubscribe@freebsd.org"
>>
>
>
>
> --
> /BR, Alexander
>



-- 
/BR, Alexander



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?c3e287ff1003220203n7bec914dqefd1cb81eb6a2cf3>