Re: stochastic fair queueing in the elevator [Re: [BENCHMARK] 2.4.20-ck3

Hans Reiser (reiser@namesys.com)
Mon, 10 Feb 2003 13:39:54 +0300


Andrew Morton wrote:

>Hans Reiser <reiser@namesys.com> wrote:
>
>
>>reiser4 does directory readahead. It gets a lot of gain from it.
>>
>>
>
>What is "a lot"?
>
>
>
>
Vladimir Saveliev had the numbers ready at hand after all, and said:

The most noticeable gain is found in the folowing test (not sure that it
can be considered as effective readahead though): ls -l over directory
containing 30000 files (named numerically) created in random order :
4.87 with no readahead
2.99 with readahead (which is limited by 25% of ram or by directory and
all its stat data)

-- 
Hans

- 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/