interconnect working group that already tried to push idiocies like RNICPI
onto us. I already told them that they're on crack but they don't care.
It's never going to appear in Linux.
ES-API has relatively little to do with memory registration or the RDMA
world view per se. It is primarily a generic API
On Mon, Mar 13, 2006 at 02:25:08PM -0800, Zach Brown ([EMAIL PROTECTED]) wrote:
Hi guys,
Hello Zach.
I'm hearing noise about the 'Extended Sockets' API in Oracle. It's an
extension to the socket API put together by an industry group that calls
itself the Interconnect Software Consortium and
On Mon, Mar 13, 2006 at 02:25:08PM -0800, Zach Brown wrote:
Hi guys,
I'm hearing noise about the 'Extended Sockets' API in Oracle. It's an
extension to the socket API put together by an industry group that calls
itself the Interconnect Software Consortium and is working in
partnership with
Evgeniy,
There are some stuff already implemented and presented in netdev@,
unfortunately it did not get much attention and feedback.
Queue of events used for socket operations:
http://tservice.net.ru/~s0mbre/old/?section=projectsitem=kevent
http://lwn.net/Articles/171317/
On Tue, Mar 14, 2006 at 05:48:41PM +0200, Robert Iakobashvili ([EMAIL
PROTECTED]) wrote:
Evgeniy,
There are some stuff already implemented and presented in netdev@,
unfortunately it did not get much attention and feedback.
Queue of events used for socket operations:
See the links below.
On 3/14/06, Evgeniy Polyakov [EMAIL PROTECTED] wrote:
So, while commercial Unix vendors create rocket-science-capable API,
Linux just implements the core.
Your patches have been recently discussed on ACE mail list
regarding future support of linux kernel to
Ugh...
So people can find the ways to connect kernelspace event queue and
asynchronous networking operations with object-oriented design patterns?
It's time to me to have a step forward from stone age...
yep ;-).
Could you please provide a link, it would be nice to read this
discussion.
Here
On Tue, Mar 14, 2006 at 04:51:42PM +, [EMAIL PROTECTED] ([EMAIL PROTECTED])
wrote:
Ugh...
So people can find the ways to connect kernelspace event queue and
asynchronous networking operations with object-oriented design patterns?
It's time to me to have a step forward from stone age...
From: Zach Brown [EMAIL PROTECTED]
Date: Mon, 13 Mar 2006 14:25:08 -0800
The API adds support for things like memory registration, async
operations completed through event queues, standard sendfile() and
async poll(), etc.
Yes, this is how these standard groups try to force a particular
Yes, this is how these standard groups try to force a particular
approach to high speed networking down everyone's throats.
Yeah, from what I understand there's a lot of RDMA/IB people involved in
that ``ICSC'' thing.
I think we'll pass on this stuff.
OK, so noted. Thanks.
- z
-
To
Also, the following scares me:
This specification has not been verified for avoidance of possible
third-party proprietary rights. In implementing this specification,
usual procedures to ensure the respect of possible third-party
intellectual property rights should be followed.
Scary,
11 matches
Mail list logo