[
https://issues.apache.org/jira/browse/PHOENIX-4010?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16099311#comment-16099311
]
ASF GitHub Bot commented on PHOENIX-4010:
-----------------------------------------
Github user JamesRTaylor commented on a diff in the pull request:
https://github.com/apache/phoenix/pull/268#discussion_r129186906
--- Diff:
phoenix-core/src/main/java/org/apache/phoenix/cache/ServerCacheClient.java ---
@@ -303,73 +318,84 @@ public TaskExecutionMetricsHolder
getTaskExecutionMetric() {
* @throws SQLException
* @throws IllegalStateException if hashed table cannot be removed on
any region server on which it was added
*/
- private void removeServerCache(final byte[] cacheId,
Set<HRegionLocation> servers) throws SQLException {
- ConnectionQueryServices services =
connection.getQueryServices();
- Throwable lastThrowable = null;
- TableRef cacheUsingTableRef =
cacheUsingTableRefMap.get(Bytes.mapKey(cacheId));
- final PTable cacheUsingTable = cacheUsingTableRef.getTable();
- byte[] tableName =
cacheUsingTableRef.getTable().getPhysicalName().getBytes();
- HTableInterface iterateOverTable = services.getTable(tableName);
- try {
- List<HRegionLocation> locations =
services.getAllTableRegions(tableName);
- Set<HRegionLocation> remainingOnServers = new
HashSet<HRegionLocation>(servers);
- /**
- * Allow for the possibility that the region we based
where to send our cache has split and been
- * relocated to another region server *after* we sent
it, but before we removed it. To accommodate
- * this, we iterate through the current metadata
boundaries and remove the cache once for each
- * server that we originally sent to.
- */
- if (LOG.isDebugEnabled())
{LOG.debug(addCustomAnnotations("Removing Cache " + cacheId + " from servers.",
connection));}
- for (HRegionLocation entry : locations) {
- if (remainingOnServers.contains(entry)) { //
Call once per server
- try {
+ private void removeServerCache(final ServerCache cache,
Set<HRegionLocation> servers) throws SQLException {
+ HTableInterface iterateOverTable = null;
+ final byte[] cacheId = cache.getId();
+ try {
+ List<byte[]> keys = cache.getKeys();
+ ConnectionQueryServices services =
connection.getQueryServices();
+ Throwable lastThrowable = null;
+ TableRef cacheUsingTableRef =
cacheUsingTableRefMap.get(Bytes.mapKey(cacheId));
+ final PTable cacheUsingTable = cacheUsingTableRef.getTable();
+ byte[] tableName =
cacheUsingTableRef.getTable().getPhysicalName().getBytes();
+ iterateOverTable = services.getTable(tableName);
+
+ List<HRegionLocation> locations =
services.getAllTableRegions(tableName);
+ Set<HRegionLocation> remainingOnServers = new
HashSet<HRegionLocation>(servers);
--- End diff --
Instead of Set<HRegionLocation> can we change this to Set<ServerName>? It'd
make it more clear IMHO
> Hash Join cache may not be send to all regionservers when we have stale HBase
> meta cache
> ----------------------------------------------------------------------------------------
>
> Key: PHOENIX-4010
> URL: https://issues.apache.org/jira/browse/PHOENIX-4010
> Project: Phoenix
> Issue Type: Bug
> Reporter: Ankit Singhal
> Assignee: Ankit Singhal
> Fix For: 4.12.0
>
> Attachments: PHOENIX-4010.patch, PHOENIX-4010_v1.patch,
> PHOENIX-4010_v2.patch, PHOENIX-4010_v2_rebased_1.patch,
> PHOENIX-4010_v2_rebased.patch
>
>
> If the region locations changed and our HBase meta cache is not updated then
> we might not be sending hash join cache to all region servers hosting the
> regions.
> ConnectionQueryServicesImpl#getAllTableRegions
> {code}
> boolean reload =false;
> while (true) {
> try {
> // We could surface the package projected
> HConnectionImplementation.getNumberOfCachedRegionLocations
> // to get the sizing info we need, but this would require a
> new class in the same package and a cast
> // to this implementation class, so it's probably not worth
> it.
> List<HRegionLocation> locations = Lists.newArrayList();
> byte[] currentKey = HConstants.EMPTY_START_ROW;
> do {
> HRegionLocation regionLocation =
> connection.getRegionLocation(
> TableName.valueOf(tableName), currentKey, reload);
> locations.add(regionLocation);
> currentKey = regionLocation.getRegionInfo().getEndKey();
> } while (!Bytes.equals(currentKey, HConstants.EMPTY_END_ROW));
> return locations;
> {code}
> Skipping duplicate servers in ServerCacheClient#addServerCache
> {code}
> List<HRegionLocation> locations =
> services.getAllTableRegions(cacheUsingTable.getPhysicalName().getBytes());
> int nRegions = locations.size();
>
> .....
> if ( ! servers.contains(entry) &&
> keyRanges.intersectRegion(regionStartKey,
> regionEndKey,
> cacheUsingTable.getIndexType() ==
> IndexType.LOCAL)) {
> // Call RPC once per server
> servers.add(entry);
> {code}
> For eg:- Table âTâ has two regions R1 and R2 originally hosted on
> regionserver RS1.
> while Phoenix/Hbase connection is still active, R2 is transitioned to RS2 ,
> but stale meta cache will still give old region locations i.e R1 and R2 on
> RS1 and when we start copying hash table, we copy for R1 and skip R2 as they
> are hosted on same regionserver. so, the query on a table will fail as it
> will unable to find hash table cache on RS2 for processing regions R2.
--
This message was sent by Atlassian JIRA
(v6.4.14#64029)
