Skip to content

HDFS-15934: Make DirectoryScanner reconcile blocks batch size and int… #2833

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
ayushtkn merged 1 commit into from
May 5, 2021
Merged

HDFS-15934: Make DirectoryScanner reconcile blocks batch size and int… #2833

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 8 additions & 0 deletions hadoop-hdfs-project/hadoop-hdfs/src/main/java/org/apache/hadoop/hdfs/DFSConfigKeys.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -836,6 +836,14 @@ public class DFSConfigKeys extends CommonConfigurationKeys {
public static final int DFS_DATANODE_DIRECTORYSCAN_INTERVAL_DEFAULT = 21600;
public static final String DFS_DATANODE_DIRECTORYSCAN_THREADS_KEY = "dfs.datanode.directoryscan.threads";
public static final int DFS_DATANODE_DIRECTORYSCAN_THREADS_DEFAULT = 1;
public static final String DFS_DATANODE_RECONCILE_BLOCKS_BATCH_SIZE =
"dfs.datanode.reconcile.blocks.batch.size";
public static final int
DFS_DATANODE_RECONCILE_BLOCKS_BATCH_SIZE_DEFAULT = 1000;
public static final String DFS_DATANODE_RECONCILE_BLOCKS_BATCH_INTERVAL
= "dfs.datanode.reconcile.blocks.batch.interval";
public static final long
DFS_DATANODE_RECONCILE_BLOCKS_BATCH_INTERVAL_DEFAULT = 2000;

public static final String DFS_DATANODE_DISK_CHECK_MIN_GAP_KEY =
"dfs.datanode.disk.check.min.gap";
Expand Down
44 changes: 40 additions & 4 deletions ...ct/hadoop-hdfs/src/main/java/org/apache/hadoop/hdfs/server/datanode/DirectoryScanner.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -65,7 +65,8 @@ public class DirectoryScanner implements Runnable {
LoggerFactory.getLogger(DirectoryScanner.class);

private static final int DEFAULT_MAP_SIZE = 32768;
private static final int RECONCILE_BLOCKS_BATCH_SIZE = 1000;
private final int reconcileBlocksBatchSize;
private final long reconcileBlocksBatchInterval;
private final FsDatasetSpi<?> dataset;
private final ExecutorService reportCompileThreadPool;
private final ScheduledExecutorService masterThread;
Expand Down Expand Up @@ -315,6 +316,41 @@ public DirectoryScanner(FsDatasetSpi<?> dataset, Configuration conf) {

masterThread =
new ScheduledThreadPoolExecutor(1, new Daemon.DaemonFactory());

int reconcileBatchSize =
conf.getInt(DFSConfigKeys.
DFS_DATANODE_RECONCILE_BLOCKS_BATCH_SIZE,
DFSConfigKeys.
DFS_DATANODE_RECONCILE_BLOCKS_BATCH_SIZE_DEFAULT);

if (reconcileBatchSize <= 0) {
LOG.warn("Invalid value configured for " +
"dfs.datanode.reconcile.blocks.batch.size, " +
"should be greater than 0, Using default.");
reconcileBatchSize =
DFSConfigKeys.
DFS_DATANODE_RECONCILE_BLOCKS_BATCH_SIZE_DEFAULT;
}

reconcileBlocksBatchSize = reconcileBatchSize;

long reconcileBatchInterval =
conf.getTimeDuration(DFSConfigKeys.
DFS_DATANODE_RECONCILE_BLOCKS_BATCH_INTERVAL,
DFSConfigKeys.
DFS_DATANODE_RECONCILE_BLOCKS_BATCH_INTERVAL_DEFAULT,
TimeUnit.MILLISECONDS);

if (reconcileBatchInterval <= 0) {
LOG.warn("Invalid value configured for " +
"dfs.datanode.reconcile.blocks.batch.interval, " +
"should be greater than 0, Using default.");
reconcileBatchInterval =
DFSConfigKeys.
DFS_DATANODE_RECONCILE_BLOCKS_BATCH_INTERVAL_DEFAULT;
}

reconcileBlocksBatchInterval = reconcileBatchInterval;
}

/**
Expand Down Expand Up @@ -428,16 +464,16 @@ public void reconcile() throws IOException {
LOG.debug("reconcile start DirectoryScanning");
scan();

// HDFS-14476: run checkAndUpadte with batch to avoid holding the lock too
// HDFS-14476: run checkAndUpdate with batch to avoid holding the lock too
// long
int loopCount = 0;
synchronized (diffs) {
for (final Map.Entry<String, ScanInfo> entry : diffs.getEntries()) {
dataset.checkAndUpdate(entry.getKey(), entry.getValue());

if (loopCount % RECONCILE_BLOCKS_BATCH_SIZE == 0) {
if (loopCount % reconcileBlocksBatchSize == 0) {
try {
Thread.sleep(2000);
Thread.sleep(reconcileBlocksBatchInterval);
} catch (InterruptedException e) {
// do nothing
}
Expand Down
12 changes: 12 additions & 0 deletions hadoop-hdfs-project/hadoop-hdfs/src/main/resources/hdfs-default.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -873,6 +873,18 @@
</description>
</property>

<property>
<name>dfs.datanode.reconcile.blocks.batch.size</name>
<value>1000</value>
<description>Setting this to define reconcile batch size.</description>
</property>

<property>
<name>dfs.datanode.reconcile.blocks.batch.interval</name>
<value>2000</value>
<description>Setting this to define interval between batches.</description>
</property>

<property>
<name>dfs.heartbeat.interval</name>
<value>3s</value>
Expand Down