[
https://issues.apache.org/jira/browse/TRAFODION-2883?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16380731#comment-16380731
]
ASF GitHub Bot commented on TRAFODION-2883:
-------------------------------------------
Github user DaveBirdsall commented on a diff in the pull request:
https://github.com/apache/trafodion/pull/1457#discussion_r171324209
--- Diff: core/sqf/monitor/linux/zclient.cxx ---
@@ -799,6 +896,67 @@ bool CZClient::IsZNodeExpired( const char *nodeName,
int &zerr )
return( expired );
}
+int CZClient::CreateMasterZNode( const char *nodeName )
+{
+ const char method_name[] = "CZClient::CreateMasterZNode";
+ TRACE_ENTRY;
+
+ int rc;
+ int retries = 0;
+
+ stringstream masterpath;
+ masterpath.str( "" );
+ masterpath << zkRootNode_.c_str()
+ << zkRootNodeInstance_.c_str()
+ << ZCLIENT_MASTER_ZNODE<< "/"
+ << nodeName;
+
+ string monZnode = masterpath.str( );
+
+ stringstream ss;
+ ss.str( "" );
+ ss <<nodeName << ":" << MyPNID;
+ string monData = ss.str( );
+
+ if (trace_settings & (TRACE_INIT | TRACE_RECOVERY))
+ {
+ trace_printf( "%s@%d RegisterZNode(%s:%s)\n"
+ , method_name, __LINE__
+ , monZnode.c_str()
+ , monData.c_str() );
+ }
+
+ rc = RegisterZNode( monZnode.c_str(), monData.c_str(), ZOO_EPHEMERAL );
+ while ( ((rc == ZCONNECTIONLOSS) || (rc == ZOPERATIONTIMEOUT)) &&
retries < ZOOKEEPER_RETRY_COUNT)
+ {
+ sleep(ZOOKEEPER_RETRY_WAIT);
+ retries++;
+ rc = RegisterZNode( monZnode.c_str(), monData.c_str(),
ZOO_EPHEMERAL );
+ }
+
+ if (rc != ZOK)
+ {
+ if (trace_settings & (TRACE_INIT | TRACE_RECOVERY))
+ {
+ trace_printf( "%s@%d Error (MasterMonitor) Create master node
for %s with rc = %d)\n"
+ , method_name, __LINE__, monZnode.c_str( ), rc);
+ }
+ char buf[MON_STRING_BUF_SIZE];
+ snprintf( buf, sizeof(buf)
+ , "[%s], RegisterZNode(%s) failed with error %s\n"
+ , method_name, monData.c_str(), zerror(rc) );
+ mon_log_write(MON_ZCLIENT_CREATEMASTERZNODE, SQ_LOG_ERR, buf);
+ return(rc); // Return the error
--- End diff --
Should there be a TRACE_EXIT before this return statement?
> Preliminary Trafodion Foundation Scalability Enhancements
> ---------------------------------------------------------
>
> Key: TRAFODION-2883
> URL: https://issues.apache.org/jira/browse/TRAFODION-2883
> Project: Apache Trafodion
> Issue Type: Improvement
> Components: dtm, foundation, installer
> Affects Versions: 2.3
> Reporter: Gonzalo E Correa
> Assignee: Gonzalo E Correa
> Priority: Major
> Fix For: 2.3
>
>
> Initial changes required to:
> - AGENT mode monitor
> o Preliminary change to remove dependency on OpenMPI during
> initialization of operational cluster by creating a cluster
> of one node (MASTER monitor) where other remote nodes (SLAVE
> monitors) join the cluster through the MASTER
> - MASTER monitor selection
> - Scale bug fixes found when creating clusters greater than 120 nodes
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
