Poor performance in test grid

[Lukas Pirl]

Hello Zooko,

now, what do I learn? "Cumulative Pushing" is the bottleneck? :)

I did:
     $ tahoe put -u http://localhost:3456 ../1Gfile.bin

And the stats looked like:
     * Shares Pushed: 1
     * Shares Already Present: 0
     * Sharemap:
          + 0 -> placed on [c2sji7rg]
     * Servermap:
          + [c2sji7rg] got share: #0
     * Timings:
     * File Size: 1073741824 bytes
     * Total: 7 minutes (2.32MBps)
     * Storage Index: 47 seconds (22.84MBps)
     * [Contacting Helper]:
     * [Upload Ciphertext To Helper]: ()
     * Peer Selection: 6.12s
     * Encode And Push: 6 minutes (2.65MBps)
     * Cumulative Encoding: 55 seconds (19.47MBps)
     * Cumulative Pushing: 5 minutes (3.07MBps)
     * Send Hashes And Close: 980ms

The gateway is configured with shares.needed, shares.happy,
shares.total set to 1.

Note: using rsync, duplication of the 1GFile worked with ~32MB/sec
(just to verify the I/O performance).

Is this common? Is there a way to "fix" this?

Thanks in advance & best regards!

Lukas

On 12/26/2013 01:07 AM, Zooko O'Whielacronx wrote:
> Hello, Lukas Purl:
>
> Thanks for the note! Could you please look at the timing
> measurements, from the Recent Uploads and Downloads page when doing
> this experiment, and post here what you learn? Thanks!
>
> https://tahoe-lafs.org/trac/tahoe-lafs/ticket/1375# the
> performance stats for each upload or download are really well
> hidden
>
> Regards,
>
> Zooko _______________________________________________ tahoe-dev
> mailing list tahoe-dev at tahoe-lafs.org
> https://tahoe-lafs.org/cgi-bin/mailman/listinfo/tahoe-dev
>

-- 
+49 174 940 74 71