Skip to content

[fix](checkpoint) fix checkpoint failure when reloading new image #9262

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
morningman merged 2 commits into from
Apr 28, 2022
Merged

[fix](checkpoint) fix checkpoint failure when reloading new image #9262

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
a4ce5e0
[fix](checkpoint) fix checkpoint failure when reload new image
morningman-cmy Apr 27, 2022
740d637
add ut
morningman Apr 27, 2022
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
16 changes: 10 additions & 6 deletions fe/fe-core/src/main/java/org/apache/doris/master/Checkpoint.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,11 +32,11 @@
import org.apache.doris.qe.VariableMgr;
import org.apache.doris.system.Frontend;

import com.google.common.base.Strings;

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;

import com.google.common.base.Strings;

import java.io.IOException;
import java.io.OutputStream;
import java.net.HttpURLConnection;
Expand Down Expand Up @@ -73,12 +73,16 @@ public void write(int b) throws IOException {

@Override
protected void runAfterCatalogReady() {
doCheckpoint();
try {
doCheckpoint();
} catch (CheckpointException e) {
LOG.warn("failed to do checkpoint.", e);
}
}

// public for unit test, so that we can trigger checkpoint manually.
// DO NOT call it manually outside the unit test.
public synchronized void doCheckpoint() {
public synchronized void doCheckpoint() throws CheckpointException {
long imageVersion = 0;
long checkPointVersion = 0;
Storage storage = null;
Expand Down Expand Up @@ -135,19 +139,19 @@ public synchronized void doCheckpoint() {
// If success, do all the following jobs
// If failed, just return
catalog = Catalog.getCurrentCatalog();
createStaticFieldForCkpt();
catalog.loadImage(imageDir);
if (MetricRepo.isInit) {
MetricRepo.COUNTER_IMAGE_WRITE_SUCCESS.increase(1L);
}
LOG.info("checkpoint finished save image.{}", replayedJournalId);
} catch (Throwable e) {
exceptionCaught = true;
e.printStackTrace();
LOG.error("Exception when generate new image file", e);
if (MetricRepo.isInit) {
MetricRepo.COUNTER_IMAGE_WRITE_FAILED.increase(1L);
}
return;
throw new CheckpointException(e.getMessage(), e);
} finally {
// destroy checkpoint catalog, reclaim memory
catalog = null;
Expand Down
2 changes: 2 additions & 0 deletions fe/fe-core/src/test/java/org/apache/doris/qe/VariableMgrTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -179,6 +179,8 @@ public void testGlobalVariablePersist() throws Exception {
// the Catalog.isCheckpointThread() will return true.
Deencapsulation.setField(Catalog.class, "checkpointThreadId", Thread.currentThread().getId());
currentCatalog.getCheckpointer().doCheckpoint();
} catch (Throwable e) {
Assert.fail(e.getMessage());
} finally {
// Restore the ckptThreadId
Deencapsulation.setField(Catalog.class, "checkpointThreadId", ckptThreadId);
Expand Down