ramitg254 commented on code in PR #6089:
URL: https://github.com/apache/hive/pull/6089#discussion_r2583757083
##########
standalone-metastore/metastore-server/src/main/java/org/apache/hadoop/hive/metastore/MetaStoreDirectSql.java:
##########
@@ -2098,29 +2121,39 @@ private List<ColumnStatisticsObj> aggrStatsUseDB(String
catName, String dbName,
}
// get sum for all columns to reduce the number of queries
Map<String, Map<Integer, Object>> sumMap = new HashMap<String,
Map<Integer, Object>>();
- queryText = "select \"COLUMN_NAME\", sum(\"NUM_NULLS\"),
sum(\"NUM_TRUES\"), sum(\"NUM_FALSES\"), sum(\"NUM_DISTINCTS\")"
- + " from " + PART_COL_STATS
- + " inner join " + PARTITIONS + " on " + PART_COL_STATS +
".\"PART_ID\" = " + PARTITIONS + ".\"PART_ID\""
- + " inner join " + TBLS + " on " + PARTITIONS + ".\"TBL_ID\" = " +
TBLS + ".\"TBL_ID\""
- + " inner join " + DBS + " on " + TBLS + ".\"DB_ID\" = " + DBS +
".\"DB_ID\""
- + " where " + DBS + ".\"CTLG_NAME\" = ? and " + DBS + ".\"NAME\" =
? and " + TBLS + ".\"TBL_NAME\" = ? "
- + " and " + PART_COL_STATS + ".\"COLUMN_NAME\" in (" +
makeParams(extraColumnNameTypeParts.size()) + ")"
- + " and " + PARTITIONS + ".\"PART_NAME\" in (" +
makeParams(partNames.size()) + ")"
- + " and " + PART_COL_STATS + ".\"ENGINE\" = ? "
- + " group by " + PART_COL_STATS + ".\"COLUMN_NAME\"";
- start = doTrace ? System.nanoTime() : 0;
- try (QueryWrapper query = new
QueryWrapper(pm.newQuery("javax.jdo.query.SQL", queryText))) {
+ queryText =
+ "select \"COLUMN_NAME\", sum(\"NUM_NULLS\"), sum(\"NUM_TRUES\"),
sum(\"NUM_FALSES\"), sum(\"NUM_DISTINCTS\")"
+ + " from " + PART_COL_STATS + " inner join " + PARTITIONS + "
on " + PART_COL_STATS + ".\"PART_ID\" = "
+ + PARTITIONS + ".\"PART_ID\"" + " inner join " + TBLS + " on "
+ PARTITIONS + ".\"TBL_ID\" = " + TBLS
+ + ".\"TBL_ID\"" + " inner join " + DBS + " on " + TBLS +
".\"DB_ID\" = " + DBS + ".\"DB_ID\""
+ + " where " + DBS + ".\"CTLG_NAME\" = ? and " + DBS +
".\"NAME\" = ? and " + TBLS + ".\"TBL_NAME\" = ? "
+ + " and " + PART_COL_STATS + ".\"COLUMN_NAME\" in (" +
makeParams(extraColumnNameTypeParts.size()) + ")"
+ + " and " + PARTITIONS + ".\"PART_NAME\" in (" +
makeParams(partNames.size()) + ")" + " and "
+ + PART_COL_STATS + ".\"ENGINE\" = ? " + " group by " +
PART_COL_STATS + ".\"COLUMN_NAME\"";
+
+ b = jobsBatching(queryText, catName, dbName, tableName, partNames,
engine, doTrace);
+ try {
List<String> extraColumnNames = new ArrayList<String>();
extraColumnNames.addAll(extraColumnNameTypeParts.keySet());
- Object qResult = executeWithArray(query.getInnerQuery(),
- prepareParams(catName, dbName, tableName, partNames,
- extraColumnNames, engine), queryText);
- if (qResult == null) {
- return Collections.emptyList();
+ List<Object[]> unmergedList = Batchable.runBatched(batchSize,
extraColumnNames, b);
+ Map<String, List<Object[]>> colSubList =
columnWiseSubList(unmergedList);
+ List<Object[]> mergedList = new ArrayList<>();
+ for (Map.Entry<String, List<Object[]>> entry :
colSubList.entrySet()) {
Review Comment:
I don't think it can be avoided same as the above mentioned reason
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
