Linstor fix migration while node offline (#8610)

* linstor: Add util method getBestErrorMessage from main

* linstor: failed remove of allow-two-primaries is no fatal error

* linstor: Fix failure if a Linstor node is down while migrating

If a Linstor node is down while migrating resource, allow-two-primaries
setting will fail because we can't reach the downed node. But it will
still set the property on the other nodes and migration should work.
We now just report an error instead of completely failing.
This commit is contained in:
Rene Peinthor 2024-02-08 19:27:38 +01:00 committed by GitHub
parent 3fa052c1f5
commit 56f0448f0d
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 30 additions and 9 deletions

View File

@ -269,27 +269,35 @@ public class LinstorStorageAdaptor implements StorageAdaptor {
}
final DevelopersApi api = getLinstorAPI(pool);
String rscName;
try
{
final String rscName = getLinstorRscName(volumePath);
rscName = getLinstorRscName(volumePath);
ResourceMakeAvailable rma = new ResourceMakeAvailable();
ApiCallRcList answers = api.resourceMakeAvailableOnNode(rscName, localNodeName, rma);
checkLinstorAnswersThrow(answers);
} catch (ApiException apiEx) {
s_logger.error(apiEx);
throw new CloudRuntimeException(apiEx.getBestMessage(), apiEx);
}
try
{
// allow 2 primaries for live migration, should be removed by disconnect on the other end
ResourceDefinitionModify rdm = new ResourceDefinitionModify();
Properties props = new Properties();
props.put("DrbdOptions/Net/allow-two-primaries", "yes");
rdm.setOverrideProps(props);
answers = api.resourceDefinitionModify(rscName, rdm);
ApiCallRcList answers = api.resourceDefinitionModify(rscName, rdm);
if (answers.hasError()) {
s_logger.error("Unable to set 'allow-two-primaries' on " + rscName);
throw new CloudRuntimeException(answers.get(0).getMessage());
// do not fail here as adding allow-two-primaries property is only a problem while live migrating
}
} catch (ApiException apiEx) {
s_logger.error(apiEx);
throw new CloudRuntimeException(apiEx.getBestMessage(), apiEx);
// do not fail here as adding allow-two-primaries property is only a problem while live migrating
}
return true;
}
@ -353,19 +361,21 @@ public class LinstorStorageAdaptor implements StorageAdaptor {
ApiCallRcList answers = api.resourceDefinitionModify(rsc.get().getName(), rdm);
if (answers.hasError())
{
s_logger.error("Failed to remove 'allow-two-primaries' on " + rsc.get().getName());
throw new CloudRuntimeException(answers.get(0).getMessage());
s_logger.error(
String.format("Failed to remove 'allow-two-primaries' on %s: %s",
rsc.get().getName(), LinstorUtil.getBestErrorMessage(answers)));
// do not fail here as removing allow-two-primaries property isn't fatal
}
return true;
}
s_logger.warn("Linstor: Couldn't find resource for this path: " + localPath);
} catch (ApiException apiEx) {
s_logger.error(apiEx);
throw new CloudRuntimeException(apiEx.getBestMessage(), apiEx);
s_logger.error(apiEx.getBestMessage());
// do not fail here as removing allow-two-primaries property isn't fatal
}
}
return false;
return true;
}
@Override

View File

@ -20,6 +20,8 @@ import com.linbit.linstor.api.ApiClient;
import com.linbit.linstor.api.ApiException;
import com.linbit.linstor.api.Configuration;
import com.linbit.linstor.api.DevelopersApi;
import com.linbit.linstor.api.model.ApiCallRc;
import com.linbit.linstor.api.model.ApiCallRcList;
import com.linbit.linstor.api.model.ProviderKind;
import com.linbit.linstor.api.model.ResourceGroup;
import com.linbit.linstor.api.model.StoragePool;
@ -47,6 +49,15 @@ public class LinstorUtil {
return new DevelopersApi(client);
}
public static String getBestErrorMessage(ApiCallRcList answers) {
return answers != null && !answers.isEmpty() ?
answers.stream()
.filter(ApiCallRc::isError)
.findFirst()
.map(ApiCallRc::getMessage)
.orElse((answers.get(0)).getMessage()) : null;
}
public static long getCapacityBytes(String linstorUrl, String rscGroupName) {
DevelopersApi linstorApi = getLinstorAPI(linstorUrl);
try {