[svn.haxx.se] · SVN Dev · SVN Users · SVN Org · TSVN Dev · TSVN Users · Subclipse Dev · Subclipse Users · this month's index

Re: Doubts in Accessing information from cache

From: Stefan Fuhrmann <stefanfuhrmann_at_alice-dsl.de>
Date: Mon, 11 Jan 2010 11:58:33 +0100

SVram <malsam.v2_at_gmail.com
<mailto:malsam.v2_at_gmail.com?Subject=Re:%20Doubts%20in%20Accessing%20information%20from%20cache>>
wrote on Sat, 9 Jan 2010 19:45:24:
> />>Req 1: Cache access must be faster than repo access /
> />>-> cache must load in 1 second or less /
> />>-> about 100MB max can be loaded in that time /
> /> /
> />>Execution overhead was the main concern during the implementation. /
> />>That is why some data structures and access methods look unusual. /
> /> /
> /> -- Stefan^2. /
> /> /
> /> /
>
> Thanks for your excellent explanation. I got whats happening in and out.
>
> When coming reducing the access time further , Are we following any
> *parallelization* or any concurrent reading techniques while
> retrieving the
> cache info ? If not, introducing that will further reduce the access time
> rite ? ?
Currently, TSVN does not parallelize the read process.
The data structures, however, allow for parallel read.
I already do that in another project with 10+GB files and
get 500+MB/sec read speeds.

Due to the hash tables used in the data model, the speedup
is limited however to about 3x on a Quad-core and
max 5x on a 8+ core machine. To properly test the
parallelized version, I need access to my workstation.
Therefore, it won't happen before March.

-- Stefan^2.

------------------------------------------------------
http://tortoisesvn.tigris.org/ds/viewMessage.do?dsForumId=757&dsMessageId=2436253

To unsubscribe from this discussion, e-mail: [dev-unsubscribe_at_tortoisesvn.tigris.org].
Received on 2010-01-11 11:58:53 CET

This is an archived mail posted to the TortoiseSVN Dev mailing list.

This site is subject to the Apache Privacy Policy and the Apache Public Forum Archive Policy.