zddr commented on code in PR #47370:
URL: https://github.com/apache/doris/pull/47370#discussion_r1926714853
##########
fe/fe-core/src/main/java/org/apache/doris/job/extensions/mtmv/MTMVTask.java:
##########
@@ -240,6 +247,39 @@ public void run() throws JobException {
}
}
+ private void executeWithRetry(Set<String> execPartitionNames, Map<TableIf,
String> tableWithPartKey)
+ throws Exception {
+ int retryCount = 0;
+ int retryTime = Config.max_query_retry_time;
+ retryTime = retryTime <= 0 ? 1 : retryTime + 1;
+ while (retryCount < retryTime) {
+ try {
+ exec(execPartitionNames, tableWithPartKey);
+ break; // Exit loop if execution is successful
+ } catch (Exception e) {
+ if (!(Config.isCloudMode() &&
e.getMessage().contains(FeConstants.CLOUD_RETRY_E230))) {
+ throw e; // Re-throw if it's not a retryable exception
+ }
+
+ int randomMillis = 10 + (int) (Math.random() * 10);
+ if (retryCount > retryTime / 2) {
+ randomMillis = 20 + (int) (Math.random() * 10);
+ }
+ if (DebugPointUtil.isEnable("MTMVTask.retry.longtime")) {
+ randomMillis = 1000;
+ }
+
+ retryCount++;
+ LOG.warn("Retrying execution due to exception: {}. Attempt
{}/{}, lastQueryId {}, randomMillis {}",
Review Comment:
add taskId and execPartitionNames
##########
fe/fe-core/src/main/java/org/apache/doris/job/extensions/mtmv/MTMVTask.java:
##########
@@ -225,7 +227,12 @@ public void run() throws JobException {
// need get names before exec
Map<String, MTMVRefreshPartitionSnapshot>
execPartitionSnapshots = MTMVPartitionUtil
.generatePartitionSnapshots(context,
relation.getBaseTablesOneLevel(), execPartitionNames);
- exec(execPartitionNames, tableWithPartKey);
+ try {
+ executeWithRetry(execPartitionNames, tableWithPartKey);
+ } catch (Exception e) {
Review Comment:
not need?
##########
fe/fe-core/src/main/java/org/apache/doris/job/extensions/mtmv/MTMVTask.java:
##########
@@ -240,6 +247,39 @@ public void run() throws JobException {
}
}
+ private void executeWithRetry(Set<String> execPartitionNames, Map<TableIf,
String> tableWithPartKey)
+ throws Exception {
+ int retryCount = 0;
+ int retryTime = Config.max_query_retry_time;
+ retryTime = retryTime <= 0 ? 1 : retryTime + 1;
+ while (retryCount < retryTime) {
+ try {
+ exec(execPartitionNames, tableWithPartKey);
+ break; // Exit loop if execution is successful
+ } catch (Exception e) {
+ if (!(Config.isCloudMode() &&
e.getMessage().contains(FeConstants.CLOUD_RETRY_E230))) {
+ throw e; // Re-throw if it's not a retryable exception
+ }
+
+ int randomMillis = 10 + (int) (Math.random() * 10);
+ if (retryCount > retryTime / 2) {
+ randomMillis = 20 + (int) (Math.random() * 10);
+ }
+ if (DebugPointUtil.isEnable("MTMVTask.retry.longtime")) {
+ randomMillis = 1000;
+ }
+
+ retryCount++;
+ LOG.warn("Retrying execution due to exception: {}. Attempt
{}/{}, lastQueryId {}, randomMillis {}",
+ e.getMessage(), retryCount, retryTime, lastQueryId,
randomMillis);
+ Thread.sleep(randomMillis);
+ }
+ }
+ if (retryCount == retryTime) {
+ throw new Exception("Max retry attempts reached");
Review Comment:
if need add original exception?
--
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]
