[
https://issues.apache.org/jira/browse/PHOENIX-4008?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16620004#comment-16620004
]
ASF GitHub Bot commented on PHOENIX-4008:
-----------------------------------------
Github user karanmehta93 commented on a diff in the pull request:
https://github.com/apache/phoenix/pull/351#discussion_r218652492
--- Diff:
phoenix-core/src/it/java/org/apache/phoenix/schema/stats/StatsCollectorIT.java
---
@@ -736,6 +737,71 @@ public void
testEmptyGuidePostGeneratedWhenDataSizeLessThanGPWidth() throws Exce
}
}
+ @Test
+ public void testCollectingAllVersionsOfCells() throws Exception {
+ String tableName = generateUniqueName();
+ try (Connection conn = DriverManager.getConnection(getUrl())) {
+ long guidePostWidth = 70;
+ String ddl =
+ "CREATE TABLE " + tableName + " (k INTEGER PRIMARY
KEY, c1.a bigint, c2.b bigint)"
+ + " GUIDE_POSTS_WIDTH=" + guidePostWidth
+ + ", USE_STATS_FOR_PARALLELIZATION=true" + ",
VERSIONS=3";
+ conn.createStatement().execute(ddl);
+ conn.createStatement().execute("upsert into " + tableName + "
values (100,100,3)");
+ conn.commit();
+ conn.createStatement().execute("UPDATE STATISTICS " +
tableName);
+
+ ConnectionQueryServices queryServices =
+
conn.unwrap(PhoenixConnection.class).getQueryServices();
+
+ // The table only has one row. All cells just has one version,
and the data size of the row
+ // is less than the guide post width, so we generate empty
guide post.
+ try (Table statsHTable =
--- End diff --
nit: Extract out similar looking pieces of test code into a method
> UPDATE STATISTIC should collect all versions of cells
> -----------------------------------------------------
>
> Key: PHOENIX-4008
> URL: https://issues.apache.org/jira/browse/PHOENIX-4008
> Project: Phoenix
> Issue Type: Bug
> Reporter: Samarth Jain
> Assignee: Bin Shi
> Priority: Major
> Attachments: PHOENIX-4008_0918.patch
>
>
> In order to truly measure the size of data when calculating guide posts,
> UPDATE STATISTIC should taken into account all versions of cells. We should
> also be setting the max versions on the scan.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
