[tahoe-dev] atlasgrid performance testing results

Zooko O'Whielacronx zooko at zooko.com
Fri Sep 23 21:57:45 UTC 2011


On Fri, Sep 23, 2011 at 12:36 AM, Brian Warner <warner at lothar.com> wrote:
>
>  * MDMF is nice and fast: 4MBps over LAN connections
>
>  * my new CHK downloader (which appeared in 1.8.0) is not as fast
>   (2.6MBps) as the old downloader (from 1.7.1) (4.4MBps)
>
>  * high values of "k" really hurt the new CHK downloader (but not MDMF)

> This analysis reveals a number of fixes that we should experiment with.
> The first big one is to implement a scatter/gather readv() method for
> immutable-share downloads, to bring them more in line with mutable
> retrievals.

Perhaps this should be obvious, but why are MDMF retrievals and
immutable ("CHK") retrievals currently different in this regard? As
far as I understand they each proceed (in the main part of the process
where they are downloading the bulk data) by sequentially requesting
one block and then the next. Don't they?

Regards,

Zooko



More information about the tahoe-dev mailing list