Github user sohami commented on a diff in the pull request: https://github.com/apache/drill/pull/639#discussion_r86060309 --- Diff: exec/java-exec/src/main/java/org/apache/drill/exec/store/parquet/ParquetGroupScan.java --- @@ -822,10 +838,103 @@ private void getFiles(String path, List<FileStatus> fileStatuses) throws IOExcep } } + /* + * Figure out the best node to scan each of the rowGroups and update the preferredEndpoint. + * Based on this, update the total work units assigned to the endpoint in the endpointAffinity. + */ + private void computeRowGroupAssignment() { + Map<DrillbitEndpoint, Integer> numEndpointAssignments = Maps.newHashMap(); + Map<DrillbitEndpoint, Long> numAssignedBytes = Maps.newHashMap(); + + // Do this for 2 iterations to adjust node assignments after first iteration. + int numIterartions = 2; + + while (numIterartions-- > 0) { + + for (RowGroupInfo rowGroupInfo : rowGroupInfos) { + EndpointByteMap endpointByteMap = rowGroupInfo.getByteMap(); + + // This can be empty for local file system or if drilbit is not running + // on hosts which have data. + if (endpointByteMap.isEmpty()) { + continue; + } + + // Get the list of endpoints which have maximum (equal) data. + List<DrillbitEndpoint> topEndpoints = endpointByteMap.getTopEndpoints(); + + long minBytes = 0, numBytes = 0; + DrillbitEndpoint nodePicked = rowGroupInfo.preferredEndpoint; + if (nodePicked != null && numAssignedBytes.containsKey(nodePicked)) { + minBytes = numAssignedBytes.get(nodePicked); + } + + DrillbitEndpoint previousNodePicked = nodePicked; + + for (DrillbitEndpoint endpoint : topEndpoints) { + if (nodePicked == null) { + nodePicked = endpoint; + if (numAssignedBytes.containsKey(nodePicked)) { + minBytes = numAssignedBytes.get(nodePicked); + } + } + + if (numAssignedBytes.containsKey(endpoint)) { + numBytes = numAssignedBytes.get(endpoint); + } else { + numBytes = 0; + } + + if (numBytes < minBytes) { + nodePicked = endpoint; + minBytes = numBytes; + } + } + + if (nodePicked != null && nodePicked != previousNodePicked) { + numAssignedBytes.put(nodePicked, minBytes + endpointByteMap.get(nodePicked)); + if (numEndpointAssignments.containsKey(nodePicked)) { + numEndpointAssignments.put(nodePicked, numEndpointAssignments.get(nodePicked) + 1); + } else { + numEndpointAssignments.put(nodePicked, 1); + } + + // If a different node is picked in second iteration, update. + if (previousNodePicked != null) { + numAssignedBytes.put(previousNodePicked, + numAssignedBytes.get(previousNodePicked) - endpointByteMap.get(previousNodePicked)); + numEndpointAssignments.put(previousNodePicked, numEndpointAssignments.get(previousNodePicked) - 1); + } + } + rowGroupInfo.preferredEndpoint = nodePicked; + } + } + + // Set the number of local work units for each endpoint in the endpointAffinity. + for (EndpointAffinity epAff : endpointAffinities) { + DrillbitEndpoint endpoint = epAff.getEndpoint(); + if (numEndpointAssignments.containsKey(endpoint)) { + epAff.setNumLocalWorkUnits(numEndpointAssignments.get(endpoint)); + } else { + epAff.setNumLocalWorkUnits(0); --- End diff -- "else" condition is not required since by default it will be set to 0
--- 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 infrastruct...@apache.org or file a JIRA ticket with INFRA. ---