I checked out the sparc64 PTE structure. It's not a bozo-design which I
thought it was (like some PPC's). If you can select powers of 2 sizes my
concern is meaningless there since you can pick the appropriate
granularity.
A genuine Bershad-esque superpages design would be perfect there.
} Large PTE's aren't free either, though. Cheap enough to implement but
} there's some fragmentation that isn't easy to deal with in some
} pathological cases. The virtual space is pretty tight on some archs
} already.
}
} A lot of stock distributions load most drivers as modules so a machine well
} stocked with devices may run into trouble.
}
} } Modules can be mapped using a large PTE mapping.
} } I've been meaning to do this on sparc64 for a long
} } time.
} }
} } So this TLB argument alone is not sufficient :-)
} } I do concur on the "ipv4 as module is difficult to
} } get correct" argument however.
} } -
} } To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
} } the body of a message to majordomo@vger.kernel.org
} } More majordomo info at http://vger.kernel.org/majordomo-info.html
} } Please read the FAQ at http://www.tux.org/lkml/
} -
} To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
} the body of a message to majordomo@vger.kernel.org
} More majordomo info at http://vger.kernel.org/majordomo-info.html
} Please read the FAQ at http://www.tux.org/lkml/
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
This archive was generated by hypermail 2b29 : Mon Jul 15 2002 - 22:00:19 EST