Изменения

== Copy kernel source (from SSD with warm cache) ==

* xfs 1 thread: 12.348s

* xfs 4 threads: 65.883s

* HDD: WD Scorpio Black 2.5" 750GB 7200rpm

* fs_mark is a write-only test and it does fsync(), so there should be no skew caused by page cache

* HDD: WD Scorpio Black 2.5" 750GB 7200rpm

* sysbench was ran with O_DIRECT, so the page cache should also have no impact.

* It’s not a filesystem benchmark at all! It tests disk performance because it holds ALL prepared files open during the test. It only shows us that XFS isn’t slowing down the direct access to the underlying device (which is also good, of course)…

== sysbench random read/write 16K in 16K files ==

<plot>

* HDD: WD VelociRaptor WD6000HLHX, 10000rpm

* fileserver test is read whole file + append + write whole file test ran on 10000 files in X threads

* filebench fails to run fileserver test with O_DIRECT, so I tried to "disable" page cache using dirty_ratio=1% and ran tests like this:

* HDD: WD VelociRaptor WD6000HLHX, 10000rpm

* Same test but ran with default 20% dirty_ratio setting. It's clearly seen that the system was using page cache extensively - ext4 was permanently gaining an unreal result in the single-thread test...