> Another possibility we could consider would be modify the VFS where
> needed to treat sockets differently. There is a flag saying whether an
> inode belongs to a socket, and in some cases is may make more sense to
> process the socket inode differently rather than set up fields that have
> no use for sockets.
I'm not sure that will be faster than a memcpy over the offending parts.
And it will get you back to the problems before: This won't be fixed in a
timely manner, leading to further bugs down the line.
Just curious: How come this inode clearing is performance critical? My gut
tells me this shouldn't be exactly the most frequent operation around...
-- Dr. Horst H. von Brand mailto:vonbrand@inf.utfsm.cl Departamento de Informatica Fono: +56 32 654431 Universidad Tecnica Federico Santa Maria +56 32 654239 Casilla 110-V, Valparaiso, Chile Fax: +56 32 797513
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.altern.org/andrebalsa/doc/lkml-faq.html