FazBrowse GitHub Viewer | Trending |
URL:
| Home
Tools: [Download Repo ZIP]   [Original HTTPS Page]

CLOUDSTACK-10310 Fix KVM reboot on storage issue by Slair1 · Pull Request #2722 · apache/cloudstack · GitHub

Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension .java  (2) .sh  (1) All 2 file types selected
Viewed files
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Unified
Split
Hide whitespace
Diff view
Unified
Split
Hide whitespace
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters. Learn more about bidirectional Unicode characters
Original file line number Diff line number Diff line change
Expand Up @@ -34,7 +34,8 @@ public class KVMHABase {
protected static String s_heartBeatPath;
protected long _heartBeatUpdateTimeout = 60000;
protected long _heartBeatUpdateFreq = 60000;
protected long _heartBeatUpdateMaxRetry = 3;
protected long _heartBeatUpdateMaxTries = 5;
protected long _heartBeatUpdateRetrySleep = 15000;

public static enum PoolType {
PrimaryStorage, SecondaryStorage
Expand Down
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters. Learn more about bidirectional Unicode characters
Original file line number Diff line number Diff line change
Expand Up @@ -119,22 +119,30 @@ protected void runInContext() {
}

String result = null;
for (int i = 0; i < 5; i++) {
// Try multiple times, but sleep in between tries to ensure it isn't a short lived transient error
for (int i = 1; i <= _heartBeatUpdateMaxTries; i++) {
Script cmd = new Script(s_heartBeatPath, _heartBeatUpdateTimeout, s_logger);
cmd.add("-i", primaryStoragePool._poolIp);
cmd.add("-p", primaryStoragePool._poolMountSourcePath);
cmd.add("-m", primaryStoragePool._mountDestPath);
cmd.add("-h", _hostIP);
result = cmd.execute();
if (result != null) {
s_logger.warn("write heartbeat failed: " + result + ", retry: " + i);
s_logger.warn("write heartbeat failed: " + result + ", try: " + i + " of " + _heartBeatUpdateMaxTries);
try {
Thread.sleep(_heartBeatUpdateRetrySleep);
} catch (InterruptedException e) {
s_logger.debug("[ignored] interupted between heartbeat retries.");
}
} else {
break;
}
}

if (result != null) {
s_logger.warn("write heartbeat failed: " + result + "; reboot the host");
// Stop cloudstack-agent if can't write to heartbeat file.
// This will raise an alert on the mgmt server
s_logger.warn("write heartbeat failed: " + result + "; stopping cloudstack-agent");
Script cmd = new Script(s_heartBeatPath, _heartBeatUpdateTimeout, s_logger);
cmd.add("-i", primaryStoragePool._poolIp);
cmd.add("-p", primaryStoragePool._poolMountSourcePath);
Expand Down
4 changes: 2 additions & 2 deletions scripts/vm/hypervisor/kvm/kvmheartbeat.sh
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters. Learn more about bidirectional Unicode characters
Original file line number Diff line number Diff line change
Expand Up @@ -155,10 +155,10 @@ then
exit 0
elif [ "$cflag" == "1" ]
then
/usr/bin/logger -t heartbeat "kvmheartbeat.sh rebooted system because it was unable to write the heartbeat to the storage."
/usr/bin/logger -t heartbeat "kvmheartbeat.sh stopped cloudstack-agent because it was unable to write the heartbeat to the storage."
sync &
sleep 5
echo b > /proc/sysrq-trigger
service cloudstack-agent stop
exit $?
else
write_hbLog
Expand Down

Back | FazBrowse Home | New Git URL