Hi Gavin!
On Mon, Jun 29, 2015 at 11:27 AM, Gavin Li wrote:
> Hi Roman,
>
> I've taken a brief look at Geode. Pistachio and Geode both can support
> similar in-memory consistent HA distributed storage, and the data aware
> function routing idea is also similar. Here are what I think are different
Hi
I can for sure follow the argument that different design ideas around a
problem complex
leads to different implementations.
My concern is a little bit different. I assume that the developers are in
general more
interested in the problem complex than the design. If I am correct such
projects
wi
Hi Andrew,
I agree with you. I've updated the proposal to include a little bit more
explanations about the difference with Hadoop.
Purely pursuing novelty is never our interest. Instead I believe even for
the same problem different design and implementation ideas can make big
difference. I think
Hi Roman,
I've taken a brief look at Geode. Pistachio and Geode both can support
similar in-memory consistent HA distributed storage, and the data aware
function routing idea is also similar. Here are what I think are different:
1. Pistachio actually uses a very different approach to resolve the
Thanks Gavin.
Please let me suggest that novelty is not a requirement for incubation, and
a proposal doesn't need to make claims of novelty to be accepted.
Should the proposal be accepted for incubation, you may find your new
neighbors at Apache can do X where you weren't aware of it. It will be
Thank you, Amareshwari.
On Friday, June 26, 2015, Jake Farrell wrote:
> Hi Amareshwari
> Thanks for catching the incorrect wording for removing the dependency
> before graduation, should have been before first incubating release,
> updated. Glad to have you on board as a mentor
>
> Updated propo
Hi Amareshwari
Thanks for catching the incorrect wording for removing the dependency
before graduation, should have been before first incubating release,
updated. Glad to have you on board as a mentor
Updated proposal is now available on the wiki at
https://wiki.apache.org/incubator/PistachioProp
Hello Gavin,
I would like to volunteer as mentor. I'm first time mentor, hope you will
bare with me.
>> Kytoto cabinet is under GNU GPL, but it is not a hard necessary
dependency to Pistachio, it’s an optional pluggable storage engine. It’s
designed in the way that it’s totally pluggable and very
We need more mentors. Please let me know if you are interested.
THanks,
Gavin Li
On Mon, Jun 22, 2015 at 8:25 PM, Gavin Li wrote:
> Roman,
>
> I think Pistachio is similar to Ignite in the sense that they both try to
> distribute the computation to storage to co-locate the data and
> computatio
Roman,
I think Pistachio is similar to Ignite in the sense that they both try to
distribute the computation to storage to co-locate the data and
computation. One difference might be Pistachio also supports other storage
options like disk based storage to support longer term durability. Actually
Pi
On Mon, Jun 22, 2015 at 7:54 PM, Gavin Li wrote:
> The other difference is in Pistachio we can do computation based on
> in-memory storage with data replication. Different from the in-memory
> computation in Spark, the storage can be in-memory here.
Have you guys looked at in-memory computation l
Hi Andrew,
As we described more in
http://yahooeng.tumblr.com/post/116291838351/pistachio-co-locate-the-data-and-compute-for,
a very common problem we saw in Hadoop use cases is we often need to
persist the previous result of one map reduce job onto HDFS, then the next
day we process the new data
On Mon, Jun 22, 2015 at 7:45 PM, John D. Ament wrote:
> On Mon, Jun 22, 2015 at 10:26 PM Andrew Purtell wrote:
>
>> > Pistachio can easily embed computation to the storage layer to achieve
>> the
>> > best data locality to improve the computation performance significantly
>> > which is an innovat
It was a simple question, and not meant to suggest anything one way or
other regarding my opinion of this proposal.
On Monday, June 22, 2015, John D. Ament wrote:
> On Mon, Jun 22, 2015 at 10:26 PM Andrew Purtell > wrote:
>
> > > Pistachio can easily embed computation to the storage layer to ac
On Mon, Jun 22, 2015 at 10:26 PM Andrew Purtell wrote:
> > Pistachio can easily embed computation to the storage layer to achieve
> the
> > best data locality to improve the computation performance significantly
> > which is an innovative model comparing with the normal ways where the
> > storage
> Pistachio can easily embed computation to the storage layer to achieve the
> best data locality to improve the computation performance significantly
> which is an innovative model comparing with the normal ways where the
> storage and compute are independent to each other.
Have you heard of some
Wiki has been created for the proposal:
https://wiki.apache.org/incubator/PistachioProposal.
The comments here has been addressed and reflected in the wiki.
Thanks,
Gavin Li
On Fri, Jun 19, 2015 at 11:30 AM, Gavin Li wrote:
> Henry,
>
> Thanks for the suggestion.
>
> We agree that at early sta
Henry,
Thanks for the suggestion.
We agree that at early stage we'd better shunt the user discussion to dev
list to help developing the community. I'll update the proposal on the wiki
once I have write access on wiki.
THanks,
Gavin Li
On Fri, Jun 19, 2015 at 10:51 AM, Henry Saputra
wrote:
> S
Since it is mostly used in Yahoo do you need pistachio-user list for now?
Usually incubator project should focus all communications in dev@ list
to avoid distractions of emails.
- Henry
On Thu, Jun 18, 2015 at 10:17 AM, Gavin Li wrote:
> Hi,
>
> I want to propose project Pistachio to enter Apa
19 matches
Mail list logo
