Store whole database in memory

Michael McClain michael.c.mcclain at gmail.com
Sat May 28 12:56:33 EDT 2011


Thank you.

That's what I'm looking for.
I have stopped my 3 nodes (the ones from the Fast Track Tutorial) and set
the storage to *riak_kv_ets_backend*.
Then I started the 3 nodes again and tried some bulk insert operations with
the java client (the one optimized for the api buffer).

 I can't see any speed improvement.
 Should I delete the databases in the 3 nodes and start the whole thing from
scratch?

 Do you know the improvement I could get in the number of writes?
 I'm trying to achieve a 100,000 writes per second, where the data being
inserted is just 12 bytes and I do a bulk insert of a thousand keys at a
time (12 bytes).

Thank you,
Michael
2011/5/28 Greg Nelson <grourk at dropcam.com>

>  Michael,
>
> You might want to check out riak_kv_ets_backend, riak_kv_gb_trees_backend,
> and riak_kv_cache_backend.
>
> http://wiki.basho.com/Configuration-Files.html
>
> <http://wiki.basho.com/Configuration-Files.html>-Greg
>
> On Friday, May 27, 2011 at 10:35 PM, Michael McClain wrote:
>
> Hi,
>
>  Is it possible to store the whole database in memory?
>  In a similar way as Redis does.
>
>  I'm really interested in the distributed map reduce done by riak ("bring
> processing to the data, instead of data to processors), but I need faster
> writes/reads that a memory-only database could provide.
>  In case you don't support memory-only storage (no disk touched / all keys
> and data fitting the memory in all nodes) yet, do you plan on implementing
> it?
>
> Thank you,
> Michael
> _______________________________________________
> riak-users mailing list
> riak-users at lists.basho.com
> http://lists.basho.com/mailman/listinfo/riak-users_lists.basho.com
>
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.basho.com/pipermail/riak-users_lists.basho.com/attachments/20110528/54d628cb/attachment.html>


More information about the riak-users mailing list