Skip to content
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

HBASE-26945 Quotas causes too much load on meta for large clusters #4567

Merged
merged 1 commit into from
Jun 23, 2022
Merged

HBASE-26945 Quotas causes too much load on meta for large clusters #4567

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
28 changes: 17 additions & 11 deletions hbase-server/src/main/java/org/apache/hadoop/hbase/quotas/QuotaCache.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,12 +28,13 @@
import java.util.concurrent.ConcurrentHashMap;
import java.util.concurrent.ConcurrentMap;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.ClusterMetrics;
import org.apache.hadoop.hbase.ClusterMetrics.Option;
import org.apache.hadoop.hbase.MetaTableAccessor;
import org.apache.hadoop.hbase.ScheduledChore;
import org.apache.hadoop.hbase.Stoppable;
import org.apache.hadoop.hbase.TableName;
import org.apache.hadoop.hbase.client.Get;
import org.apache.hadoop.hbase.client.RegionStatesCount;
import org.apache.hadoop.hbase.regionserver.HRegionServer;
import org.apache.hadoop.hbase.regionserver.RegionServerServices;
import org.apache.hadoop.hbase.util.EnvironmentEdgeManager;
Expand Down Expand Up @@ -350,24 +351,29 @@ private <K, V extends QuotaState> void fetch(final String type,
*/
private void updateQuotaFactors() {
// Update machine quota factor
ClusterMetrics clusterMetrics;
try {
int rsSize = rsServices.getConnection().getAdmin()
.getClusterMetrics(EnumSet.of(Option.SERVERS_NAME)).getServersName().size();
if (rsSize != 0) {
// TODO if use rs group, the cluster limit should be shared by the rs group
machineQuotaFactor = 1.0 / rsSize;
}
clusterMetrics = rsServices.getConnection().getAdmin()
.getClusterMetrics(EnumSet.of(Option.SERVERS_NAME, Option.TABLE_TO_REGIONS_COUNT));
} catch (IOException e) {
LOG.warn("Get live region servers failed", e);
LOG.warn("Failed to get cluster metrics needed for updating quotas", e);
return;
}

int rsSize = clusterMetrics.getServersName().size();
if (rsSize != 0) {
// TODO if use rs group, the cluster limit should be shared by the rs group
machineQuotaFactor = 1.0 / rsSize;
}

Map<TableName, RegionStatesCount> tableRegionStatesCount =
clusterMetrics.getTableRegionStatesCount();

// Update table machine quota factors
for (TableName tableName : tableQuotaCache.keySet()) {
double factor = 1;
try {
long regionSize =
MetaTableAccessor.getTableRegions(rsServices.getConnection(), tableName, true).stream()
.filter(regionInfo -> !regionInfo.isOffline()).count();
long regionSize = tableRegionStatesCount.get(tableName).getOpenRegions();
if (regionSize == 0) {
factor = 0;
} else {
Expand Down