<html>
<body>
<font size=3><br>
Why not just leverage the SDP port mapper protocol already defined in the
RDMAC version and avoid having to provide a new address family? The
port mapper protocol is interconnect independent and will enable sockets
applications to more easily be executed transparently. It seems
counterproductive to continue to pursue a new address family.<br><br>
BTW, the new port mapper protocol will also work with the new async
sockets and memory management API that is nearly complete (should be
approved soon within the OpenGroup). This would greatly enhance
socket application design and provide greater performance when operating
over a RDMA interconnect than traditional BSD sockets.<br><br>
Mike<br><br>
<br>
At 03:17 PM 10/14/2004, Yaron Haviv wrote:<br>
<blockquote type=cite class=cite cite="">There seems to be a conflict
between the currently used SDP socket address family number (26) and the
current linux kernel. Linux allocates this address family number (26) for
'LLC' protocol.<br><br>
Any ideas if we should change it from 26, and to what ?<br>
<br>
Below are some related header-file snippets:<br>
<br>
SuSE-9.1 /usr/include/linux/socket.h:<br>
-------------------------------------------------------------------<br>
#define AF_IRDA
23 /* IRDA
sockets
*/<br>
#define AF_PPPOX
24 /* PPPoX
sockets
*/<br>
#define AF_WANPIPE
25 /* Wanpipe API Sockets */<br>
#define AF_LLC
26 /* Linux
LLC
*/<br>
#define AF_BLUETOOTH 31
/* Bluetooth
sockets
*/<br>
#define AF_MAX
32 /* For now.. */<br>
<br><br>
Voltaire's sdp/sdp-sockets/sdp-sockets.h:<br>
-------------------------------------------------------------------<br>
# define AF_IBT 26<br>
<br><br>
TopSpin's infiniband/ulp/sdp/sdp_inet.h:<br>
-------------------------------------------------------------------<br>
/*<br>
* constants shared between user and kernel space.<br>
*/<br>
#define AF_INET_SDP
26
/* SDP socket protocol family */<br>
#define AF_INET_STR "AF_INET_SDP" /* SDP enabled
enviroment variable */<br>
<br>
Yaron<br><br>
_______________________________________________<br>
openib-general mailing list<br>
openib-general@openib.org<br>
<a href="http://openib.org/mailman/listinfo/openib-general" eudora="autourl">http://openib.org/mailman/listinfo/openib-general</a><br><br>
To unsubscribe, please visit
<a href="http://openib.org/mailman/listinfo/openib-general" eudora="autourl">http://openib.org/mailman/listinfo/openib-general</a>
</font></blockquote></body>
</html>