<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN">
<html>
<head>
<meta content="text/html;charset=ISO-8859-1" http-equiv="Content-Type">
</head>
<body bgcolor="#ffffff" text="#000000">
Talpey, Thomas wrote:
<blockquote
cite="mid:RTPCLUEXC1-PRD51Eeo0000010a@RTPMVEXC1-PRD.hq.netapp.com"
type="cite">
<pre wrap="">At 09:40 AM 5/19/2008, Steve Wise wrote:
</pre>
<blockquote type="cite">
<blockquote type="cite">
<pre wrap="">I suggest to use a "page_shift" notation and not "page_size" to comply
with the kernel semantics of other APIs.
</pre>
</blockquote>
<pre wrap="">Ok, I wondered about that. It will also ensure a power of two.
</pre>
</blockquote>
<pre wrap=""><!---->
Does it have to be ^2? In the iWARP spec development, we envisioned
the possibility of arbitrary page sizes. I don't recall any such dependency
in the protocol architecture.
</pre>
</blockquote>
<br>
I didn't add block mode support since its not available anywhere in the
Linux RDMA API. I'd rather _not_ introduce that at this point.<br>
<br>
<blockquote
cite="mid:RTPCLUEXC1-PRD51Eeo0000010a@RTPMVEXC1-PRD.hq.netapp.com"
type="cite">
<pre wrap="">Storage has been known to adopt non ^2 blocks, for instance including
block checksums in sectors, etc. If transferred, these will become quite
inefficient on ^2 hardware.
</pre>
</blockquote>
Is this true today for any of the existing RDMA ULPs that will utilize
fastreg?<br>
<br>
Steve.<br>
<br>
</body>
</html>