sodonnel commented on code in PR #11800:
URL: https://github.com/apache/ozone/pull/11800#discussion_r4442469714
##########
hadoop-hdds/server-scm/src/test/java/org/apache/hadoop/hdds/scm/upgrade/TestScmStartupInvalidApparentVersion.java:
##########
@@ -59,8 +68,91 @@ public void
testStartupFailsWhenApparentVersionBeyondLastKnownComponentVersion()
assertStartupFailsWithComponentVersionMessage(SOFTWARE_VERSION.serialize()
+ 1);
}
+ /**
+ * An SCM that stops after replacing its DB with a finalized checkpoint, but
before updating its VERSION file, cannot
+ * replay the finalization from the Raft log, so it should finalize up to
the version in its DB on restart.
+ */
+ @Test
+ public void testStartupFinalizesToApparentVersionInDB() throws Exception {
+ OzoneConfiguration conf = createScmStorage(INITIAL_VERSION.serialize());
+ StorageContainerManager scm = HddsTestUtils.getScm(conf, new
SCMConfigurator());
+ try {
+ // Without a version in the DB, startup leaves the SCM pre-finalized.
+
assertThat(scm.getScmMetadataStore().getMetaTable().get(APPARENT_VERSION_KEY)).isNull();
+
assertThat(scm.getVersionManager().getApparentVersion()).isEqualTo(INITIAL_VERSION);
+
+ // The DB is ahead of the VERSION file, as the interrupted install
leaves it. The SCM finalizes to the
+ // software version
+ scm = restartWithDBVersion(scm, SOFTWARE_VERSION);
+ assertVersions(scm, SOFTWARE_VERSION, SOFTWARE_VERSION);
+ assertThat(scm.getVersionManager().needsFinalization()).isFalse();
+ } finally {
+ scm.stop();
+ scm.join();
+ }
+ }
+
+ /**
+ * The VERSION file is ahead of the DB. This can happen if finalization
wrote the VERSION file (inside Ratis
+ * applyTransaction) but the process crashed before the Ratis transaction
buffer was flushed to RocksDB.
+ * Ratis log replay should correct this, but finalizeFromSnapshotIfRequired
also updates the DB as a safety net.
+ */
+ @Test
+ public void testStartupUpdatesDBWhenVersionFileAheadOfDB() throws Exception {
+ // Create an SCM whose VERSION file is already at SOFTWARE_VERSION
(simulates the crash scenario where the
+ // VERSION file was written during finalization but the DB was not yet
flushed).
Review Comment:
I think the comment above the test method already says that this is added as
a safety net.
--
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]
