Messages in this thread |  | | Date | Wed, 13 Sep 2000 13:41:07 +0200 | From | "Andi Kleen" <> | Subject | Re: NFS locking bug -- limited mtime resolution means nfs_lock() does not provide coherency guarantee |
| |
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/
|  |