On Thu, 5 Oct 2000, Neil Brown wrote:
> 2/ Arrange your filesystem so that you write new data to an otherwise
> unused stripe a whole stripe at a time, and store some sort of
> chechksum in the stripe so that corruption can be detected. This
> implies a log structured filesystem (though possibly you could come
> close enough with a journalling or similar filesystem, I'm not
> sure).
This will hose your performance if you're doing random read/writes of
small chunks of data. Its better in that case to have the size that your
app/fs writes be the same as the blocksize on a single disk, so that you
don't have to seek all the drives to the same cylinder every time you do a
read/write.
-
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 : Mon Oct 23 2000 - 21:00:12 EST