Re: [RFC] cfq: adapt slice to number of processes doing I/O

[Jeff Moyer]

Corrado Zoccolo <czoccolo@xxxxxxxxx> writes:

> Hi Jeff,
>
>> How did you come to this magic number of 3, both for the number of
>> competing tasks and the multiplier for the slice time? ÂDid you
>> experiment with this number at all?
>
> The number is quickly explained. The base slice is 100ms, and on the
> mailing list it was mentioned that the latency becomes annoing for an
> user when it is above 300ms.  This means that, up to 3 processes, the
> current thresholds are good, and for more we have to scale.  This is
> good, because we don't change the behaviour unless we have many
> competing processes.

OK, then in your next patch, could you make this more clear?  Maybe
define a LATENCY_MAX and derive the number of processes from that,
instead of assuming that the base slice will always and forever be
100ms?

Cheers,
Jeff
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/