Skip to content

HDDS-12134. Implement Snapshot Cache lock for OM Bootstrap #7745

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

Closed
swamirishi wants to merge 3 commits into from
Closed

HDDS-12134. Implement Snapshot Cache lock for OM Bootstrap #7745

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
ead32f2
HDDS-12134. Implement Snapshot Cache lock for OM Bootstrap
swamirishi Jan 24, 2025
84c5c91
HDDS-12134. fix locking
swamirishi Jan 24, 2025
c1f911b
Merge remote-tracking branch 'origin/master' into HDDS-12134
adoroszlai Feb 18, 2025
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
10 changes: 10 additions & 0 deletions hadoop-hdds/common/src/main/resources/ozone-default.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4449,6 +4449,16 @@
</description>
</property>

<property>
<name>ozone.om.snapshot.cache.lock.timeout</name>
<value>5s</value>
<tag>OZONE, OM</tag>
<description>
Wait Timeout for snapshot cache lock.
Uses milliseconds by default when no time unit is specified.
</description>
</property>

<property>
<name>ozone.om.snapshot.load.native.lib</name>
<value>true</value>
Expand Down
6 changes: 6 additions & 0 deletions hadoop-ozone/common/src/main/java/org/apache/hadoop/ozone/om/OMConfigKeys.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -591,6 +591,12 @@ private OMConfigKeys() {
public static final long
OZONE_OM_SNAPSHOT_DIFF_CLEANUP_SERVICE_RUN_INTERVAL_DEFAULT
= TimeUnit.MINUTES.toMillis(1);
public static final String
OZONE_OM_SNAPSHOT_CACHE_LOCK_TIMEOUT
= "ozone.om.snapshot.cache.lock.timeout";
public static final long
OZONE_OM_SNAPSHOT_CACHE_LOCK_TIMEOUT_DEFAULT
= TimeUnit.SECONDS.toMillis(5);
public static final long
OZONE_OM_SNAPSHOT_CACHE_CLEANUP_SERVICE_RUN_INTERVAL_DEFAULT
= TimeUnit.MINUTES.toMillis(1);
Expand Down
8 changes: 7 additions & 1 deletion hadoop-ozone/ozone-manager/src/main/java/org/apache/hadoop/ozone/om/OmSnapshotManager.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,6 +26,8 @@
import static org.apache.hadoop.ozone.OzoneConsts.OM_SNAPSHOT_INDICATOR;
import static org.apache.hadoop.ozone.om.OMConfigKeys.OZONE_OM_SNAPSHOT_CACHE_CLEANUP_SERVICE_RUN_INTERVAL;
import static org.apache.hadoop.ozone.om.OMConfigKeys.OZONE_OM_SNAPSHOT_CACHE_CLEANUP_SERVICE_RUN_INTERVAL_DEFAULT;
import static org.apache.hadoop.ozone.om.OMConfigKeys.OZONE_OM_SNAPSHOT_CACHE_LOCK_TIMEOUT;
import static org.apache.hadoop.ozone.om.OMConfigKeys.OZONE_OM_SNAPSHOT_CACHE_LOCK_TIMEOUT_DEFAULT;
import static org.apache.hadoop.ozone.om.OMConfigKeys.OZONE_OM_SNAPSHOT_CACHE_MAX_SIZE;
import static org.apache.hadoop.ozone.om.OMConfigKeys.OZONE_OM_SNAPSHOT_CACHE_MAX_SIZE_DEFAULT;
import static org.apache.hadoop.ozone.om.OMConfigKeys.OZONE_OM_SNAPSHOT_DB_MAX_OPEN_FILES;
Expand Down Expand Up @@ -279,8 +281,12 @@ public OmSnapshotManager(OzoneManager ozoneManager) {
.getTimeDuration(OZONE_OM_SNAPSHOT_CACHE_CLEANUP_SERVICE_RUN_INTERVAL,
OZONE_OM_SNAPSHOT_CACHE_CLEANUP_SERVICE_RUN_INTERVAL_DEFAULT,
TimeUnit.MILLISECONDS);
long cacheLockTimeout = ozoneManager.getConfiguration()
.getTimeDuration(OZONE_OM_SNAPSHOT_CACHE_LOCK_TIMEOUT,
OZONE_OM_SNAPSHOT_CACHE_LOCK_TIMEOUT_DEFAULT,
TimeUnit.MILLISECONDS);
this.snapshotCache = new SnapshotCache(loader, softCacheSize, ozoneManager.getMetrics(),
cacheCleanupServiceInterval);
cacheCleanupServiceInterval, cacheLockTimeout);

this.snapshotDiffManager = new SnapshotDiffManager(snapshotDiffDb, differ,
ozoneManager, snapDiffJobCf, snapDiffReportCf,
Expand Down
14 changes: 9 additions & 5 deletions ...one/ozone-manager/src/main/java/org/apache/hadoop/ozone/om/snapshot/ReferenceCounted.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,6 +18,8 @@
package org.apache.hadoop.ozone.om.snapshot;

import com.google.common.base.Preconditions;
import com.google.common.collect.ImmutableMap;
import java.util.Map;
import java.util.concurrent.ConcurrentHashMap;
import java.util.concurrent.atomic.AtomicLong;

Expand Down Expand Up @@ -50,10 +52,10 @@ public class ReferenceCounted<T>
/**
* Parent instance whose callback will be triggered upon this RC closure.
*/
private final ReferenceCountedCallback parentWithCallback;
private final ReferenceCountedCallback<T> parentWithCallback;

public ReferenceCounted(T obj, boolean disableCounter,
ReferenceCountedCallback parentWithCallback) {
ReferenceCountedCallback<T> parentWithCallback) {
// A param to allow disabling ref counting to reduce active DB
// access penalties due to AtomicLong operations.
this.obj = obj;
Expand Down Expand Up @@ -125,9 +127,7 @@ public long decrementRefCount() {
Preconditions.checkState(newValTotal >= 0L,
"Total reference count underflow");
}
if (refCount.get() == 0) {
this.parentWithCallback.callback(this);
}
this.parentWithCallback.callback(this);
return refCount.get();
}

Expand Down Expand Up @@ -160,4 +160,8 @@ public void close() {
// so it is eligible to be used with try-with-resources.
decrementRefCount();
}

public Map<Long, Long> getThreadCntMap() {
return ImmutableMap.copyOf(threadMap);
Copy link
Contributor

@jojochuang jojochuang May 2, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

will this be expensive?

Copy link
Contributor Author

@swamirishi swamirishi May 6, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This shouldn't be very expensive as the reference to a snapshot shouldn't be held by a lot of threads.

}
}
4 changes: 2 additions & 2 deletions ...e-manager/src/main/java/org/apache/hadoop/ozone/om/snapshot/ReferenceCountedCallback.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,6 +20,6 @@
/**
* Callback interface for ReferenceCounted.
*/
public interface ReferenceCountedCallback {
void callback(ReferenceCounted referenceCounted);
public interface ReferenceCountedCallback<T> {
void callback(ReferenceCounted<T> referenceCounted);
}
Loading