RussellSpitzer commented on code in PR #4687:
URL: https://github.com/apache/iceberg/pull/4687#discussion_r867251585
##########
spark/v3.2/spark/src/main/java/org/apache/iceberg/spark/source/SparkWrite.java:
##########
@@ -196,24 +199,33 @@ private void commitOperation(SnapshotUpdate<?> operation,
String description) {
}
long start = System.currentTimeMillis();
- operation.commit(); // abort is automatically called if this fails
- long duration = System.currentTimeMillis() - start;
- LOG.info("Committed in {} ms", duration);
+ try {
+ operation.commit(); // abort is automatically called if this fails
+ long duration = System.currentTimeMillis() - start;
+ LOG.info("Committed in {} ms", duration);
+ } catch (CommitStateUnknownException commitStateUnknownException) {
+ cleanupOnAbort = false;
+ throw commitStateUnknownException;
+ }
}
private void abort(WriterCommitMessage[] messages) {
- Map<String, String> props = table.properties();
- Tasks.foreach(files(messages))
- .retry(PropertyUtil.propertyAsInt(props, COMMIT_NUM_RETRIES,
COMMIT_NUM_RETRIES_DEFAULT))
- .exponentialBackoff(
- PropertyUtil.propertyAsInt(props, COMMIT_MIN_RETRY_WAIT_MS,
COMMIT_MIN_RETRY_WAIT_MS_DEFAULT),
- PropertyUtil.propertyAsInt(props, COMMIT_MAX_RETRY_WAIT_MS,
COMMIT_MAX_RETRY_WAIT_MS_DEFAULT),
- PropertyUtil.propertyAsInt(props, COMMIT_TOTAL_RETRY_TIME_MS,
COMMIT_TOTAL_RETRY_TIME_MS_DEFAULT),
- 2.0 /* exponential */)
- .throwFailureWhenFinished()
- .run(file -> {
- table.io().deleteFile(file.path().toString());
- });
+ if (cleanupOnAbort) {
+ Map<String, String> props = table.properties();
+ Tasks.foreach(files(messages))
+ .retry(PropertyUtil.propertyAsInt(props, COMMIT_NUM_RETRIES,
COMMIT_NUM_RETRIES_DEFAULT))
+ .exponentialBackoff(
+ PropertyUtil.propertyAsInt(props, COMMIT_MIN_RETRY_WAIT_MS,
COMMIT_MIN_RETRY_WAIT_MS_DEFAULT),
+ PropertyUtil.propertyAsInt(props, COMMIT_MAX_RETRY_WAIT_MS,
COMMIT_MAX_RETRY_WAIT_MS_DEFAULT),
+ PropertyUtil.propertyAsInt(props, COMMIT_TOTAL_RETRY_TIME_MS,
COMMIT_TOTAL_RETRY_TIME_MS_DEFAULT),
+ 2.0 /* exponential */)
+ .throwFailureWhenFinished()
+ .run(file -> {
+ table.io().deleteFile(file.path().toString());
+ });
+ } else {
+ LOG.error("Skipping cleaning up of data files because Iceberg was unable
to determine the final commit state");
Review Comment:
We are about to abort, so I was mixed ... something is going wrong and we
will be failing
##########
spark/v3.2/spark/src/main/java/org/apache/iceberg/spark/source/SparkWrite.java:
##########
@@ -196,24 +199,33 @@ private void commitOperation(SnapshotUpdate<?> operation,
String description) {
}
long start = System.currentTimeMillis();
- operation.commit(); // abort is automatically called if this fails
- long duration = System.currentTimeMillis() - start;
- LOG.info("Committed in {} ms", duration);
+ try {
+ operation.commit(); // abort is automatically called if this fails
+ long duration = System.currentTimeMillis() - start;
+ LOG.info("Committed in {} ms", duration);
+ } catch (CommitStateUnknownException commitStateUnknownException) {
+ cleanupOnAbort = false;
+ throw commitStateUnknownException;
+ }
}
private void abort(WriterCommitMessage[] messages) {
- Map<String, String> props = table.properties();
- Tasks.foreach(files(messages))
- .retry(PropertyUtil.propertyAsInt(props, COMMIT_NUM_RETRIES,
COMMIT_NUM_RETRIES_DEFAULT))
- .exponentialBackoff(
- PropertyUtil.propertyAsInt(props, COMMIT_MIN_RETRY_WAIT_MS,
COMMIT_MIN_RETRY_WAIT_MS_DEFAULT),
- PropertyUtil.propertyAsInt(props, COMMIT_MAX_RETRY_WAIT_MS,
COMMIT_MAX_RETRY_WAIT_MS_DEFAULT),
- PropertyUtil.propertyAsInt(props, COMMIT_TOTAL_RETRY_TIME_MS,
COMMIT_TOTAL_RETRY_TIME_MS_DEFAULT),
- 2.0 /* exponential */)
- .throwFailureWhenFinished()
- .run(file -> {
- table.io().deleteFile(file.path().toString());
- });
+ if (cleanupOnAbort) {
+ Map<String, String> props = table.properties();
+ Tasks.foreach(files(messages))
+ .retry(PropertyUtil.propertyAsInt(props, COMMIT_NUM_RETRIES,
COMMIT_NUM_RETRIES_DEFAULT))
+ .exponentialBackoff(
+ PropertyUtil.propertyAsInt(props, COMMIT_MIN_RETRY_WAIT_MS,
COMMIT_MIN_RETRY_WAIT_MS_DEFAULT),
+ PropertyUtil.propertyAsInt(props, COMMIT_MAX_RETRY_WAIT_MS,
COMMIT_MAX_RETRY_WAIT_MS_DEFAULT),
+ PropertyUtil.propertyAsInt(props, COMMIT_TOTAL_RETRY_TIME_MS,
COMMIT_TOTAL_RETRY_TIME_MS_DEFAULT),
+ 2.0 /* exponential */)
+ .throwFailureWhenFinished()
+ .run(file -> {
+ table.io().deleteFile(file.path().toString());
+ });
+ } else {
+ LOG.error("Skipping cleaning up of data files because Iceberg was unable
to determine the final commit state");
Review Comment:
We are about to abort, so I was mixed ... something is going wrong and we
will be failing. I can do warn
--
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]
