Github user TomasHofman commented on a diff in the pull request:
https://github.com/apache/activemq-artemis/pull/2287#discussion_r231878791
--- Diff:
artemis-server/src/main/java/org/apache/activemq/artemis/core/server/impl/FileLockNodeManager.java
---
@@ -299,44 +303,52 @@ protected FileLock tryLock(final long lockPos) throws
IOException {
protected FileLock lock(final long lockPosition) throws Exception {
long start = System.currentTimeMillis();
+ boolean isRecurringFailure = false;
while (!interrupted) {
- FileLock lock = tryLock(lockPosition);
-
- if (lock == null) {
- try {
- Thread.sleep(500);
- } catch (InterruptedException e) {
- return null;
+ try {
+ FileLock lock = tryLock(lockPosition);
+ isRecurringFailure = false;
+
+ if (lock == null) {
+ try {
+ Thread.sleep(500);
+ } catch (InterruptedException e) {
+ return null;
+ }
+
+ if (lockAcquisitionTimeout != -1 &&
(System.currentTimeMillis() - start) > lockAcquisitionTimeout) {
+ throw new Exception("timed out waiting for lock");
+ }
+ } else {
+ return lock;
}
-
- if (lockAcquisitionTimeout != -1 &&
(System.currentTimeMillis() - start) > lockAcquisitionTimeout) {
- throw new Exception("timed out waiting for lock");
+ } catch (IOException e) {
+ // IOException during trylock() may be a temporary issue, e.g.
NFS volume not being accessible
+
+ logger.log(isRecurringFailure ? Logger.Level.DEBUG :
Logger.Level.WARN,
+ "Failure when accessing a lock file", e);
+ isRecurringFailure = true;
+
+ long waitTime = LOCK_ACCESS_FAILURE_WAIT_TIME;
+ if (lockAcquisitionTimeout != -1) {
+ final long remainingTime = lockAcquisitionTimeout -
(System.currentTimeMillis() - start);
+ if (remainingTime <= 0) {
+ throw new Exception("timed out waiting for lock");
+ }
+ waitTime = Collections.min(Arrays.asList(waitTime,
remainingTime));
--- End diff --
Good point, updated.
---
