You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@phoenix.apache.org by "Tanuj Khurana (Jira)" <ji...@apache.org> on 2026/09/25 20:43:00 UTC

[jira] [Commented] (PHOENIX-8007) Index metadata lookup on the server creates a new Server connection on every commit

    [ https://issues.apache.org/jira/browse/PHOENIX-8007?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=18119541#comment-18119541 ] 

Tanuj Khurana commented on PHOENIX-8007:
----------------------------------------

*Wall* decomposition of *getIndexMetaDataCacheFromPTable* (async-profiler `-e wall`, 6,891 samples):
 
{code:java}
 | sub-path | % of path wall |
 |---|---|
 | `PhoenixConnection.getTable` → `getTableNoCache` (SYSTEM.CATALOG RPC) | **58.5%** |
 | `DriverManager.getConnection` (per-batch `PhoenixConnection` build) | **27.2%** |
 | `getConnectionUrl` (config resolution) | 6.0% |
 | `combineProperties` (`Configuration.iterator`) | 4.9% |
 {code}

*Lock*
the shared-`Configuration` monitor (`getConnectionUrl` + `combineProperties`) is 49–57% of all lock contention

> Index metadata lookup on the server creates a new Server connection on every commit
> -----------------------------------------------------------------------------------
>
>                 Key: PHOENIX-8007
>                 URL: https://issues.apache.org/jira/browse/PHOENIX-8007
>             Project: Phoenix
>          Issue Type: Improvement
>    Affects Versions: 5.4.0, 5.3.1
>            Reporter: Tanuj Khurana
>            Assignee: Viraj Jasani
>            Priority: Major
>         Attachments: 7727-server-lock-flamegraph.html, 7727-server-wall-flamegraph.html
>
>
> PHOENIX-7727 added _phoenix.index.useServerMetadata_ (default true) to eliminate the client _addServerCache_ RPC by having the region server rebuild the I{_}ndexMaintainer{_} from its PTable cache per batch {_}PhoenixIndexMetaDataBuilder.getIndexMetaDataCacheFromPTable{_}.  It builds a fresh PhoenixConnection per batch which contributes to wall latency and under concurrent load has lock contention. I have attached both wall and lock flamegraphs which show the contribution of new connection. I think we can create the connection lazily per region but we have to be careful if the connection is reaped and closed for example when cqsi closes.



--
This message was sent by Atlassian Jira
(v8.20.10#820010)