Re: NFS locking bug -- limited mtime resolution means nfs_lock() does not provide coherency guarantee

From: Andi Kleen (ak@suse.de)
Date: Wed Sep 13 2000 - 06:41:07 EST


On Wed, Sep 13, 2000 at 12:42:15PM +0200, Trond Myklebust wrote:
> >>>>> " " == Andi Kleen <ak@suse.de> writes:
>
> > On Tue, Sep 12, 2000 at 09:10:56PM +0200, Trond Myklebust
> > wrote:
> >> Making mtime a true 64-bit cookie on Linux servers would be a
> >> solution that works on all clients.
>
> > Making mtime 64bit would also be useful for local parallel make
> > runs, the current second resolution leads to race conditions on
> > bigger SMP boxes.
>
> > Unfortunately the only FS that supports <s on disk timestamps
> > currently is XFS afaik, and there is no VFS interface for it.
>
>
> You'd have to fix make as well: 'stat' & friends alway return the
> timestamp in seconds.

struct stat64 leaves enough padding for micro or nanosecond fields.

>
> Is there any 'standard' function for reading the microseconds fields
> in userland? I couldn't find anything with a brief search in the
> X/Open docs.

Solaris seems to support it in newer releases, and GNU make 3.79 already does
on Solaris. They seem to use a st_mtime_nsec.

-Andi
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
Please read the FAQ at http://www.tux.org/lkml/



This archive was generated by hypermail 2b29 : Fri Sep 15 2000 - 21:00:20 EST