This is an automated email from the ASF dual-hosted git repository. huaxiangsun pushed a commit to branch master in repository https://gitbox.apache.org/repos/asf/hbase.git
The following commit(s) were added to refs/heads/master by this push: new 597098ebba HBASE-26984 Chaos Monkey thread dies in ITBLL Chaos GracefulRollingRestartRsAction (#4383) 597098ebba is described below commit 597098ebbafb0705662699f1cd573982d97aaca1 Author: huaxiangsun <huaxiang...@apache.org> AuthorDate: Thu May 5 09:37:41 2022 -0500 HBASE-26984 Chaos Monkey thread dies in ITBLL Chaos GracefulRollingRestartRsAction (#4383) There are two cases here: 1. Chaos Monkey thread died and there is no chaos after that. 2. Sometimes, regions are being moved back too quick that region server has not finished its initliazation yet. wait sometime to make sure that region server finishes its initialization. Signed-off-by: Wellington Chevreuil <wellington.chevre...@gmail.com> --- .../hadoop/hbase/chaos/actions/GracefulRollingRestartRsAction.java | 2 ++ .../org/apache/hadoop/hbase/chaos/actions/RestartActionBaseAction.java | 2 ++ 2 files changed, 4 insertions(+) diff --git a/hbase-it/src/test/java/org/apache/hadoop/hbase/chaos/actions/GracefulRollingRestartRsAction.java b/hbase-it/src/test/java/org/apache/hadoop/hbase/chaos/actions/GracefulRollingRestartRsAction.java index 236ed21290..6fe6332813 100644 --- a/hbase-it/src/test/java/org/apache/hadoop/hbase/chaos/actions/GracefulRollingRestartRsAction.java +++ b/hbase-it/src/test/java/org/apache/hadoop/hbase/chaos/actions/GracefulRollingRestartRsAction.java @@ -63,6 +63,8 @@ public class GracefulRollingRestartRsAction extends RestartActionBaseAction { rm.load(); } catch (Shell.ExitCodeException e) { getLogger().info("Problem restarting but presume successful; code={}", e.getExitCode(), e); + } catch (Exception e) { + getLogger().info("Exception but continuing...", e); } sleep(rand.nextInt((int) sleepTime)); } diff --git a/hbase-it/src/test/java/org/apache/hadoop/hbase/chaos/actions/RestartActionBaseAction.java b/hbase-it/src/test/java/org/apache/hadoop/hbase/chaos/actions/RestartActionBaseAction.java index 31e9f578b9..3edb1fabdd 100644 --- a/hbase-it/src/test/java/org/apache/hadoop/hbase/chaos/actions/RestartActionBaseAction.java +++ b/hbase-it/src/test/java/org/apache/hadoop/hbase/chaos/actions/RestartActionBaseAction.java @@ -80,6 +80,8 @@ public abstract class RestartActionBaseAction extends Action { sleep(sleepTime); getLogger().info("Starting region server: {}", server); startRs(server); + // Sleep some time to make sure RS is online. + sleep(sleepTime); } void restartZKNode(ServerName server, long sleepTime) throws IOException {