keith-turner commented on a change in pull request #2422:
URL: https://github.com/apache/accumulo/pull/2422#discussion_r791085150
##########
File path:
core/src/main/java/org/apache/accumulo/core/clientImpl/TabletServerBatchReaderIterator.java
##########
@@ -497,26 +499,44 @@ private void
doLookups(Map<String,Map<KeyExtent,List<Range>>> binnedRanges,
for (final String tsLocation : locations) {
final Map<KeyExtent,List<Range>> tabletsRanges =
binnedRanges.get(tsLocation);
- if (maxTabletsPerRequest == Integer.MAX_VALUE || tabletsRanges.size() ==
1) {
- QueryTask queryTask = new QueryTask(tsLocation, tabletsRanges,
failures, receiver, columns);
- queryTasks.add(queryTask);
+ if (options.isUseScanServer()) {
+ // Ignore the tablets location and find a scan server to use
+ ScanServerLocator ssl = context.getScanServerLocator();
+ tabletsRanges.forEach((k, v) -> {
+ try {
+ String location = ssl.reserveScanServer(new TabletIdImpl(k));
Review comment:
Not sure if it achievable but it would be nice if we could have
information about scan servers from ZK that is cacheable on the client side (so
clients do not have to go to ZK frequently), a busy signal from scan servers,
and the previous two bits of information available to client side plugin that
makes decisions about which scan servers to use. If that is workable it could
avoid any single bottleneck processes in the cluster hopefully allowing this to
scale up to many thousands of scan servers and thousands of clients.
--
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]
