Github user JamesRTaylor commented on a diff in the pull request:
https://github.com/apache/phoenix/pull/12#discussion_r17747869
--- Diff:
phoenix-core/src/main/java/org/apache/phoenix/schema/MetaDataClient.java ---
@@ -462,6 +470,54 @@ public MutationState createTable(CreateTableStatement
statement, byte[][] splits
return connection.getQueryServices().updateData(plan);
}
+ public MutationState updateStatistics(UpdateStatisticsStatement
updateStatisticsStmt) throws SQLException {
+ // Check before updating the stats if we have reached the
configured time to reupdate the stats once again
+ long minTimeForStatsUpdate =
connection.getQueryServices().getProps()
+ .getLong(QueryServices.STATS_UPDATE_FREQ_MS_ATTRIB,
QueryServicesOptions.DEFAULT_STATS_UPDATE_FREQ_MS);
+ ColumnResolver resolver =
FromCompiler.getResolver(updateStatisticsStmt, connection);
+ PTable table = resolver.getTables().get(0).getTable();
+ PName physicalName = table.getPhysicalName();
+ byte[] tenantIdBytes = ByteUtil.EMPTY_BYTE_ARRAY;
+ KeyRange analyzeRange = KeyRange.EVERYTHING_RANGE;
+ if (connection.getTenantId() != null && table.isMultiTenant()) {
+ if (table.getBucketNum() == null && table.getIndexType() !=
IndexType.LOCAL) {
+ tenantIdBytes = connection.getTenantId().getBytes();
+ List<List<KeyRange>> tenantIdKeyRanges =
Collections.singletonList(Collections.singletonList(KeyRange
+ .getKeyRange(tenantIdBytes)));
+ byte[] lowerRange =
ScanUtil.getMinKey(table.getRowKeySchema(), tenantIdKeyRanges,
+ ScanUtil.SINGLE_COLUMN_SLOT_SPAN);
+ byte[] upperRange =
ScanUtil.getMaxKey(table.getRowKeySchema(), tenantIdKeyRanges,
+ ScanUtil.SINGLE_COLUMN_SLOT_SPAN);
+ analyzeRange = KeyRange.getKeyRange(lowerRange,
upperRange);
+ }
+ }
+ Long scn = connection.getSCN();
+ // Always invalidate the cache
+ long clientTS = connection.getSCN() == null ?
HConstants.LATEST_TIMESTAMP : scn;
+ connection.getQueryServices().clearCacheForTable(tenantIdBytes,
table.getSchemaName().getBytes(),
+ table.getTableName().getBytes(), clientTS);
+ // Clear the cache also. So that for cases like major compaction
also we would be able to use the stats
+ updateCache(table.getSchemaName().getString(),
table.getTableName().getString(), true);
+ String query = "SELECT CURRENT_DATE(),"+ LAST_STATS_UPDATE_TIME +
" FROM " + SYSTEM_CATALOG_SCHEMA
+ + "." + SYSTEM_STATS_TABLE + " WHERE " + PHYSICAL_NAME +
"='" + physicalName.getString() + "' AND " + COLUMN_FAMILY
+ + " IS NULL AND " + REGION_NAME + " IS NULL";
+ ResultSet rs = connection.createStatement().executeQuery(query);
+ long lastUpdatedTime = 0;
+ if (rs.next()) {
--- End diff --
This needs to be if (rs.next() && rs.getDate(2) != null) to prevent NPE if
analyze hasn't been called
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
