We should get O_SYNC as fast as possible then, which means optimizing
the FS's and cleaning up the performance holes.
Jeff
Andi Kleen wrote:
>
> On Mon, May 15, 2000 at 06:57:57PM -0600, Jeff V. Merkey wrote:
> > Van and I worked together for several years on Oracle for NetWare (I
> > guess this part was obvious). He is getting together some info for us
> > on what would be the most ideal. A block oriented version of fsync() is
> > probably the way to go the get Oracle the highest numbers possible on
> > Linux rather then force a flush of every dirty block for a file each
> > time an Oracle data table is written to.
>
> There are other databases than just Oracle too which run on Linux ;)
> iirc the slow fsync problem was mostly reported with Solid servers.
>
> For example mail servers use fsync extensively too.
>
> >
> > We should probably add (int block, int blocks) to fsync() to give
> > callers the ability to selectively push blocks out of cache. IMHO.
>
> That's msync(MS_INVALIDATE) when you it mmaped().
> If you don't want to flush you can also use madvise(MADV_DONTNEED)
> (that was even added at the request of some big database vendor)
>
> I guess Oracle will use POSIX aio with O_SYNC anyways.
>
> -Andi
>
> -
> 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.tux.org/lkml/
-
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.tux.org/lkml/
This archive was generated by hypermail 2b29 : Tue May 23 2000 - 21:00:11 EST