[openib-general] Re: [PATCH][RFC][0/4] InfiniBand userspace v erbs implementation

Diego Crupnicoff Diego at Mellanox.com
Thu Apr 28 09:30:51 PDT 2005


> The userspace library should be able to track the tree and
> the overlaps, etc.  Things might become interesting when the 
> memory is MAP_SHARED pagecache and multiple independent 
> processes are involved, although I guess that'd work OK.
> 
> But afaict the problem wherein part of a page needs
> VM_DONTCOPY and the other part does not cannot be solved.

Not sure it was such a good idea, but at some point we thought of forcing
the copy of (***only***) such pages at fork time (leaving of course the
original one for the parent). This eliminates the COW that would have messed
the parent's mapping, and still allows the child process to access the
"un-registered" portions of the page.

BTW: We did try to "motivate" applications to do whole page registrations
only so to avoid this issue altogether. But that did not work. Some (hard to
ignore) applications want byte granularity.







-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.openfabrics.org/pipermail/general/attachments/20050428/d70374ae/attachment.html>


More information about the general mailing list