HDDS-14990. Show failed volumes in ozone admin datanode list output and SCM metrics
#10058
There are no files selected for viewing
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
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
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
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
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 |
|---|---|---|
|
|
@@ -19,6 +19,7 @@ | |
|
|
||
| import com.google.common.base.Strings; | ||
| import java.io.IOException; | ||
| import java.util.ArrayList; | ||
| import java.util.Collections; | ||
| import java.util.Comparator; | ||
| import java.util.List; | ||
|
|
@@ -65,6 +66,11 @@ public class ListInfoSubcommand extends ScmSubcommand { | |
| defaultValue = "false") | ||
| private boolean json; | ||
|
|
||
| @CommandLine.Option(names = {"--failed-volumes"}, | ||
| description = "Only show datanodes that have at least one failed volume.", | ||
| defaultValue = "false") | ||
| private boolean failedVolumesOnly; | ||
|
|
||
|
Comment on lines
+68
to
+72
Contributor
There was a problem hiding this comment. The --nodes-with-failed-volumes filter is silently ignored when --node-id is used. |
||
| @CommandLine.ArgGroup(exclusive = true, multiplicity = "0..1") | ||
| private ExclusiveNodeOptions exclusiveNodeOptions; | ||
|
|
||
|
|
@@ -92,7 +98,8 @@ public void execute(ScmClient scmClient) throws IOException { | |
| Integer healthyVolumeCount = node.hasHealthyVolumeCount() ? node.getHealthyVolumeCount() : null; | ||
| BasicDatanodeInfo singleNodeInfo = new BasicDatanodeInfo.Builder( | ||
| DatanodeDetails.getFromProtoBuf(node.getNodeID()), node.getNodeOperationalStates(0), | ||
| node.getNodeStates(0)).withVolumeCounts(totalVolumeCount, healthyVolumeCount) | ||
| .withFailedVolumes(getFailedVolumes(node)).build(); | ||
|
||
| if (json) { | ||
| List<BasicDatanodeInfo> dtoList = Collections.singletonList(singleNodeInfo); | ||
| System.out.println(JsonUtils.toJsonStringWithDefaultPrettyPrinter(dtoList)); | ||
|
|
@@ -118,6 +125,10 @@ public void execute(ScmClient scmClient) throws IOException { | |
| allNodes = allNodes.filter(p -> p.getHealthState().toString() | ||
| .compareToIgnoreCase(nodeState) == 0); | ||
| } | ||
| if (failedVolumesOnly) { | ||
| allNodes = allNodes.filter(p -> | ||
| p.getFailedVolumes() != null && !p.getFailedVolumes().isEmpty()); | ||
| } | ||
|
|
||
| if (!listLimitOptions.isAll()) { | ||
| allNodes = allNodes.limit(listLimitOptions.getLimit()); | ||
|
|
@@ -160,7 +171,8 @@ private List<BasicDatanodeInfo> getAllNodes(ScmClient scmClient) | |
| DatanodeDetails.getFromProtoBuf(node.getNodeID()), | ||
| node.getNodeOperationalStates(0), node.getNodeStates(0)) | ||
| .withUsageInfo(used, capacity, percentUsed) | ||
| .withVolumeCounts(totalVolumeCount, healthyVolumeCount) | ||
| .withFailedVolumes(getFailedVolumes(node)).build(); | ||
| } catch (Exception e) { | ||
| String reason = "Could not process info for an unknown datanode"; | ||
| if (p != null && p.getNode() != null && !Strings.isNullOrEmpty(p.getNode().getUuid())) { | ||
|
|
@@ -182,11 +194,24 @@ private List<BasicDatanodeInfo> getAllNodes(ScmClient scmClient) | |
| Integer healthyVolumeCount = p.hasHealthyVolumeCount() ? p.getHealthyVolumeCount() : null; | ||
| return new BasicDatanodeInfo.Builder( | ||
| DatanodeDetails.getFromProtoBuf(p.getNodeID()), p.getNodeOperationalStates(0), p.getNodeStates(0)) | ||
| .withVolumeCounts(totalVolumeCount, healthyVolumeCount) | ||
| .withFailedVolumes(getFailedVolumes(p)).build(); }) | ||
| .sorted(Comparator.comparing(BasicDatanodeInfo::getHealthState)) | ||
| .collect(Collectors.toList()); | ||
| } | ||
|
|
||
| private static List<String> getFailedVolumes(HddsProtos.Node node) { | ||
| int count = node.getFailedVolumesCount(); | ||
| if (count == 0) { | ||
| return Collections.emptyList(); | ||
| } | ||
| List<String> result = new ArrayList<>(count); | ||
| for (int i = 0; i < count; i++) { | ||
| result.add(node.getFailedVolumes(i)); | ||
| } | ||
| return result; | ||
| } | ||
|
|
||
| private void printDatanodeInfo(BasicDatanodeInfo dn) { | ||
| StringBuilder pipelineListInfo = new StringBuilder(); | ||
| DatanodeDetails datanode = dn.getDatanodeDetails(); | ||
|
|
@@ -210,6 +235,7 @@ private void printDatanodeInfo(BasicDatanodeInfo dn) { | |
| } | ||
| } else { | ||
| pipelineListInfo.append("No pipelines in cluster."); | ||
| pipelineListInfo.append(System.getProperty("line.separator")); | ||
|
||
| } | ||
| System.out.println("Datanode: " + datanode.getUuid().toString() + | ||
| " (" + datanode.getNetworkLocation() + "/" + datanode.getIpAddress() | ||
|
|
@@ -221,6 +247,12 @@ private void printDatanodeInfo(BasicDatanodeInfo dn) { | |
| System.out.println("Total volume count: " + dn.getTotalVolumeCount() + "\n" + | ||
| "Healthy volume count: " + dn.getHealthyVolumeCount()); | ||
| } | ||
| if (dn.getFailedVolumes() != null && !dn.getFailedVolumes().isEmpty()) { | ||
| System.out.println("Failed volumes:"); | ||
| for (String vol : dn.getFailedVolumes()) { | ||
| System.out.println(" " + vol); | ||
| } | ||
| } | ||
| System.out.println("Related pipelines:\n" + pipelineListInfo); | ||
|
|
||
| if (dn.getUsed() != null && dn.getCapacity() != null && dn.getUsed() >= 0 && dn.getCapacity() > 0) { | ||
|
|
||
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 |
|---|---|---|
|
|
@@ -357,6 +357,50 @@ public void testVolumeCounters() throws Exception { | |
| assertTrue(output.contains("Healthy volume count:"), "Should display healthy volume count"); | ||
| } | ||
|
|
||
| @Test | ||
| public void testFailedVolumesFilter() throws Exception { | ||
| ScmClient scmClient = mock(ScmClient.class); | ||
| List<HddsProtos.Node> baseNodes = getNodeDetails(); | ||
|
|
||
| List<HddsProtos.Node> nodes = new ArrayList<>(); | ||
| // node 0: 1 failed volume | ||
| nodes.add(HddsProtos.Node.newBuilder(baseNodes.get(0)) | ||
| .setTotalVolumeCount(4).setHealthyVolumeCount(3) | ||
| .addFailedVolumes("/data/disk2").build()); | ||
| // node 1: healthy, no failed volumes | ||
| nodes.add(HddsProtos.Node.newBuilder(baseNodes.get(1)) | ||
| .setTotalVolumeCount(4).setHealthyVolumeCount(4).build()); | ||
| // node 2: 2 failed volumes | ||
| nodes.add(HddsProtos.Node.newBuilder(baseNodes.get(2)) | ||
| .setTotalVolumeCount(6).setHealthyVolumeCount(4) | ||
| .addFailedVolumes("/data/disk1") | ||
| .addFailedVolumes("/data/disk5").build()); | ||
| // node 3: healthy, no failed volumes | ||
| nodes.add(HddsProtos.Node.newBuilder(baseNodes.get(3)) | ||
| .setTotalVolumeCount(4).setHealthyVolumeCount(4).build()); | ||
|
|
||
| when(scmClient.queryNode(any(), any(), any(), any())).thenReturn(nodes); | ||
| when(scmClient.listPipelines()).thenReturn(new ArrayList<>()); | ||
|
|
||
| CommandLine c = new CommandLine(cmd); | ||
| c.parseArgs("--failed-volumes"); | ||
| cmd.execute(scmClient); | ||
| String output = outContent.toString(DEFAULT_ENCODING); | ||
|
|
||
| // Only 2 datanodes (those with failed volumes) should appear | ||
| Matcher m = Pattern.compile("^Datanode:", Pattern.MULTILINE) | ||
| .matcher(output); | ||
| int count = 0; | ||
| while (m.find()) { | ||
| count++; | ||
| } | ||
| assertEquals(2, count, "Only datanodes with failed volumes should be listed"); | ||
| assertTrue(output.contains("Failed volume")); | ||
| assertTrue(output.contains("/data/disk2")); | ||
| assertTrue(output.contains("/data/disk1")); | ||
| assertTrue(output.contains("/data/disk5")); | ||
|
||
| } | ||
|
|
||
| private void validateOrdering(JsonNode root, String orderDirection) { | ||
| for (int i = 0; i < root.size() - 1; i++) { | ||
| long usedCurrent = root.get(i).get("used").asLong(); | ||
|
|
||
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Would
--with-failed-volumebe better?There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
how about
--show-failed-volumes? --with-failed-volume seems mean that "display along with bad disk information".There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
--show-failed-volumesimplies failed volumes are normally hidden, and included in the output only if this flag is used.I think the command
reads better.
If we want to be extra clear, it can be
--nodes-with-failed-volume.There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Update to
--nodes-with-failed-volume