[jira] [Commented] (PHOENIX-3148) Reduce size of PTable so that more tables can be cached in the metada cache.

["James Taylor (JIRA)" <ji...@apache.org>]

    [ https://issues.apache.org/jira/browse/PHOENIX-3148?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15408575#comment-15408575 ] 

James Taylor commented on PHOENIX-3148:
---------------------------------------

FYI, stats are now cached outside of PTable, so having stats on or off should have no impact.  Here are some potential things to do:
- figure out what we think the size of a PTable should be. 7KB seems high. Can we get a breakdown on this?
- have a "small memory footprint" option for PTable without any of the maps.
- don't store both byte[] and String representation in PName.
- use a different cache representation which gets translated into the full PTable form on the way out. For example, call PTableImpl.toProto() as a PTable comes into the cache and only cache the bytes; then call PTableImpl.createFromProto() on the way out of the cache to reconstitute the PTable. Let's compare the size of the protobuf bytes with the memory size of a PTableImpl to get an idea of how much this would help.
- given the particular data set of Argus, there may be a way to cache it much more efficiently given the commonality across all the metrics. The trick here would be to do it in a general enough way that it can go into Phoenix.


> Reduce size of PTable so that more tables can be cached in the metada cache.
> ----------------------------------------------------------------------------
>
>                 Key: PHOENIX-3148
>                 URL: https://issues.apache.org/jira/browse/PHOENIX-3148
>             Project: Phoenix
>          Issue Type: Bug
>            Reporter: Thomas D'Silva
>              Labels: argus
>             Fix For: 4.9.0
>
>
> According to PHOENIX-2995, the current size is 7KB per PTable which works out to enabling 140K PTables per 1GB.



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)