[tahoe-dev] dynamic ip

Daira Hopwood (formerly David-Sarah) davidsarah at leastauthority.com
Tue Jun 18 01:14:02 UTC 2013


On 16/06/13 23:28, Greg Troxel wrote:
> "erpo41 at gmail.com" <erpo41 at gmail.com> writes:
> 
>> This makes sense when all of the storage nodes and upload helpers are
>> connected together with a fast ethernet switch: an uploading node
>> would saturate its own interface to the switch while sending a single
>> chunk to a single switch, requiring no optimization. On the Internet,
>> if the connection between my node and a friend's node is poor, my node
>> is going to leave most of my most precious resource (upstream
>> bandwidth) unused while taking a long time to finish uploading that
>> chunk.
> 
> I suspect any seralization is accidental and a result of simple code
> rather than an intentional design decision.

Upload should already use pipelining of blocks
(https://tahoe-lafs.org/trac/tahoe-lafs/browser/trunk/src/allmydata/immutable/layout.py?rev=3668cb3d#L120).

I seem to remember that increasing the pipeline depth didn't help much,
so the performance problem is probably elsewhere. (Debugging this is
hampered by the fact that there's no timing visualization for uploads,
unlike downloads.)

-- 
Daira Hopwood ⚥

-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 555 bytes
Desc: OpenPGP digital signature
URL: <http://tahoe-lafs.org/pipermail/tahoe-dev/attachments/20130618/997218e4/attachment.asc>


More information about the tahoe-dev mailing list