anmolanmol1234 commented on code in PR #8056:
URL: https://github.com/apache/hadoop/pull/8056#discussion_r2556297999


##########
hadoop-tools/hadoop-azure/src/main/java/org/apache/hadoop/fs/azurebfs/services/ReadBufferManagerV2.java:
##########
@@ -831,41 +861,79 @@ private boolean manualEviction(final ReadBuffer buf) {
    */
   private void adjustThreadPool() {
     int currentPoolSize = workerRefs.size();
-    double cpuLoad = getCpuLoad();
+    double cpuLoad = getJvmCpuLoad();
+    if (cpuLoad > maxCpuUtilization) {
+      maxCpuUtilization = cpuLoad;
+    }
     int requiredPoolSize = getRequiredThreadPoolSize();
     int newThreadPoolSize;
     printTraceLog(
         "Current CPU load: {}, Current worker pool size: {}, Current queue 
size: {}",
         cpuLoad, currentPoolSize, requiredPoolSize);
     if (currentPoolSize < requiredPoolSize && cpuLoad < cpuThreshold) {
+      lastScaleDirection = "I";
       // Submit more background tasks.
       newThreadPoolSize = Math.min(maxThreadPoolSize,
           (int) Math.ceil(
               (currentPoolSize * (HUNDRED_D + threadPoolUpscalePercentage))
                   / HUNDRED_D));
+      if (newThreadPoolSize == maxThreadPoolSize) {
+        lastScaleDirection = "+F";   // Already full, cannot scale up
+      } else {
+        lastScaleDirection = "I";    // Normal scale-up
+      }
       // Create new Worker Threads
-      for (int i = currentPoolSize; i < newThreadPoolSize; i++) {
-        ReadBufferWorker worker = new ReadBufferWorker(i, getBufferManager());
-        workerRefs.add(worker);
-        workerPool.submit(worker);
+      if ("I".equals(lastScaleDirection)) {
+        for (int i = currentPoolSize; i < newThreadPoolSize; i++) {
+          ReadBufferWorker worker = new ReadBufferWorker(i,
+              getBufferManager(abfsClient));
+          workerRefs.add(worker);
+          workerPool.submit(worker);
+        }
       }
+      // Capture the latest thread pool statistics (pool size, CPU, memory, 
etc.)
+      ReadThreadPoolStats stats = getCurrentStats(cpuLoad, maxCpuUtilization);

Review Comment:
   these are needed only when we are scaling up or down not always hence added 
in blocks where scale up or down is happening



-- 
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]

Reply via email to