The tiobench threaded read phase is very sensitive to the
interworking between readahead and the disk scheduler. 2.4
gets this right, and 2.5 does not.
2.5 seeks between the files with a granularity equal to the
readahead window size. 2.4 seeks betwen the files at a
granularity equal to the elevator request expiry count.
So yup, it's known. Haven't investigated it yet.
-
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/