keith-turner commented on a change in pull request #1187: Log busy tablets by
ingest and query at a configurable time duration
URL: https://github.com/apache/accumulo/pull/1187#discussion_r292053660
##########
File path:
server/tserver/src/main/java/org/apache/accumulo/tserver/TabletServer.java
##########
@@ -358,6 +364,77 @@ public TabletServer(ServerConfigurationFactory
confFactory, VolumeManager fs) th
this.logSorter = new LogSorter(instance, fs, aconf);
this.replWorker = new ReplicationWorker(this, fs);
this.statsKeeper = new TabletStatsKeeper();
+ final int numBusyTabletsToLog =
aconf.getCount(Property.TSERV_LOG_BUSY_TABLETS_COUNT);
+ final long logBusyTabletsDelay =
+ aconf.getTimeInMillis(Property.TSERV_LOG_BUSY_TABLETS_INTERVAL);
+
+ // This thread will calculate and log out the busiest tablets based on
ingest count and
+ // query count every #{logBusiestTabletsDelay}
+ if (numBusyTabletsToLog > 0) {
+ SimpleTimer.getInstance(aconf).schedule(new Runnable() {
+ @Override
+ public void run() {
+ Comparator<Pair<String,Double>> busiestTabletComparator =
+ new Comparator<Pair<String,Double>>() {
+ @Override
+ public int compare(Pair<String,Double> first,
Pair<String,Double> second) {
+ return second.getSecond().compareTo(first.getSecond());
+ }
+ };
+ Map<String,PriorityQueue<Pair<String,Double>>> busyTabletMap = new
HashMap<>();
+ busyTabletMap.put(INGEST_COUNT,
+ new PriorityQueue<>(numBusyTabletsToLog,
busiestTabletComparator));
+ busyTabletMap.put(INGEST_RATE,
+ new PriorityQueue<>(numBusyTabletsToLog,
busiestTabletComparator));
+ busyTabletMap.put(QUERY_COUNT,
+ new PriorityQueue<>(numBusyTabletsToLog,
busiestTabletComparator));
+ busyTabletMap.put(QUERY_RATE,
+ new PriorityQueue<>(numBusyTabletsToLog,
busiestTabletComparator));
+ List<Tablet> tablets;
+ synchronized (onlineTablets) {
+ tablets = new ArrayList<>(onlineTablets.values());
+ }
+ for (Tablet tablet : tablets) {
+ String extentString = tablet.getExtent().toString();
+ addToBusiestTablets(extentString, tablet.totalQueries(),
busyTabletMap.get(QUERY_COUNT),
+ numBusyTabletsToLog);
+ addToBusiestTablets(extentString, tablet.queryRate(),
busyTabletMap.get(QUERY_RATE),
+ numBusyTabletsToLog);
+ addToBusiestTablets(extentString, tablet.totalIngest(),
busyTabletMap.get(INGEST_COUNT),
+ numBusyTabletsToLog);
+ addToBusiestTablets(extentString, tablet.ingestRate(),
busyTabletMap.get(INGEST_RATE),
+ numBusyTabletsToLog);
+ }
+
+ logBusyTablets(busyTabletMap, QUERY_COUNT, numBusyTabletsToLog);
+ logBusyTablets(busyTabletMap, QUERY_RATE, numBusyTabletsToLog);
+ logBusyTablets(busyTabletMap, INGEST_COUNT, numBusyTabletsToLog);
+ logBusyTablets(busyTabletMap, INGEST_RATE, numBusyTabletsToLog);
+ }
+
+ private void addToBusiestTablets(String extent, double count,
+ PriorityQueue<Pair<String,Double>> busiestTabletsQueue, int
numBusiestTabletsToLog) {
+ if (busiestTabletsQueue.size() < numBusiestTabletsToLog
+ || busiestTabletsQueue.peek().getSecond() < count) {
+ if (busiestTabletsQueue.size() == numBusiestTabletsToLog) {
+ busiestTabletsQueue.remove();
+ }
+ busiestTabletsQueue.add(new Pair<String,Double>(extent, count));
+ }
+ }
+
+ private void
logBusyTablets(Map<String,PriorityQueue<Pair<String,Double>>> busyTabletsMap,
+ String label, int numBusiestTabletsToLog) {
+ PriorityQueue<Pair<String,Double>> busyTabletsQueue =
busyTabletsMap.get(label);
+ for (int i = 0; i < numBusiestTabletsToLog; i++) {
Review comment:
I think the expectation is that this code empties the queue. If it did not
empty the queue for some reason it could lead to odd situations like the same
tablet being on the queue multiple times. To make this expectation more clear
and to decouple this code from how the queue is created, could do the following
instead of the for loop.
```java
int i = 0;
while(!busyTabletsQueue.isEmpty()) {
Pair<String,Double> pair = busyTabletsQueue.poll();
log.debug("{} busiest tablet by {} -- extent: {} count: {}", i++, label,
pair.getFirst(),
 pair.getSecond());
}
```
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
[email protected]
With regards,
Apache Git Services
