-
Notifications
You must be signed in to change notification settings - Fork 24.9k
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Fail restore when the shard allocations max retries count is reached (#…
…27493) This commit changes the RestoreService so that it now fails the snapshot restore if one of the shards to restore has failed to be allocated. It also adds a new RestoreInProgressAllocationDecider that forbids such shards to be allocated again. This way, when a restore is impossible or failed too many times, the user is forced to take a manual action (like deleting the index which failed shards) in order to try to restore it again. This behaviour has been implemented because when the allocation of a shard has been retried too many times, the MaxRetryDecider is engaged to prevent any future allocation of the failed shard. If it happens while restoring a snapshot, the restore hanged and was never completed because it stayed around waiting for the shards to be assigned (and that won't happen). It also blocked future attempts to restore the snapshot again. With this commit, the restore does not hang and is marked as failed, leaving failed shards around for investigation. This is the second part of the #26865 issue. Closes #26865
- Loading branch information
Showing
8 changed files
with
541 additions
and
28 deletions.
There are no files selected for viewing
This file contains 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 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
86 changes: 86 additions & 0 deletions
86
.../elasticsearch/cluster/routing/allocation/decider/RestoreInProgressAllocationDecider.java
This file contains 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 |
|---|---|---|
| @@ -0,0 +1,86 @@ | ||
| /* | ||
| * Licensed to Elasticsearch under one or more contributor | ||
| * license agreements. See the NOTICE file distributed with | ||
| * this work for additional information regarding copyright | ||
| * ownership. Elasticsearch licenses this file to you under | ||
| * the Apache License, Version 2.0 (the "License"); you may | ||
| * not use this file except in compliance with the License. | ||
| * You may obtain a copy of the License at | ||
| * | ||
| * http://www.apache.org/licenses/LICENSE-2.0 | ||
| * | ||
| * Unless required by applicable law or agreed to in writing, | ||
| * software distributed under the License is distributed on an | ||
| * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY | ||
| * KIND, either express or implied. See the License for the | ||
| * specific language governing permissions and limitations | ||
| * under the License. | ||
| */ | ||
|
|
||
| package org.elasticsearch.cluster.routing.allocation.decider; | ||
|
|
||
| import org.elasticsearch.cluster.RestoreInProgress; | ||
| import org.elasticsearch.cluster.routing.RecoverySource; | ||
| import org.elasticsearch.cluster.routing.RoutingNode; | ||
| import org.elasticsearch.cluster.routing.ShardRouting; | ||
| import org.elasticsearch.cluster.routing.allocation.RoutingAllocation; | ||
| import org.elasticsearch.common.settings.Settings; | ||
| import org.elasticsearch.snapshots.Snapshot; | ||
|
|
||
| /** | ||
| * This {@link AllocationDecider} prevents shards that have failed to be | ||
| * restored from a snapshot to be allocated. | ||
| */ | ||
| public class RestoreInProgressAllocationDecider extends AllocationDecider { | ||
|
|
||
| public static final String NAME = "restore_in_progress"; | ||
|
|
||
| /** | ||
| * Creates a new {@link RestoreInProgressAllocationDecider} instance from | ||
| * given settings | ||
| * | ||
| * @param settings {@link Settings} to use | ||
| */ | ||
| public RestoreInProgressAllocationDecider(Settings settings) { | ||
| super(settings); | ||
| } | ||
|
|
||
| @Override | ||
| public Decision canAllocate(final ShardRouting shardRouting, final RoutingNode node, final RoutingAllocation allocation) { | ||
| return canAllocate(shardRouting, allocation); | ||
| } | ||
|
|
||
| @Override | ||
| public Decision canAllocate(final ShardRouting shardRouting, final RoutingAllocation allocation) { | ||
| final RecoverySource recoverySource = shardRouting.recoverySource(); | ||
| if (recoverySource == null || recoverySource.getType() != RecoverySource.Type.SNAPSHOT) { | ||
| return allocation.decision(Decision.YES, NAME, "ignored as shard is not being recovered from a snapshot"); | ||
| } | ||
|
|
||
| final Snapshot snapshot = ((RecoverySource.SnapshotRecoverySource) recoverySource).snapshot(); | ||
| final RestoreInProgress restoresInProgress = allocation.custom(RestoreInProgress.TYPE); | ||
|
|
||
| if (restoresInProgress != null) { | ||
| for (RestoreInProgress.Entry restoreInProgress : restoresInProgress.entries()) { | ||
| if (restoreInProgress.snapshot().equals(snapshot)) { | ||
| RestoreInProgress.ShardRestoreStatus shardRestoreStatus = restoreInProgress.shards().get(shardRouting.shardId()); | ||
| if (shardRestoreStatus != null && shardRestoreStatus.state().completed() == false) { | ||
| assert shardRestoreStatus.state() != RestoreInProgress.State.SUCCESS : "expected shard [" + shardRouting | ||
| + "] to be in initializing state but got [" + shardRestoreStatus.state() + "]"; | ||
| return allocation.decision(Decision.YES, NAME, "shard is currently being restored"); | ||
| } | ||
| break; | ||
| } | ||
| } | ||
| } | ||
| return allocation.decision(Decision.NO, NAME, "shard has failed to be restored from the snapshot [%s] because of [%s] - " + | ||
| "manually close or delete the index [%s] in order to retry to restore the snapshot again or use the reroute API to force the " + | ||
| "allocation of an empty primary shard", snapshot, shardRouting.unassignedInfo().getDetails(), shardRouting.getIndexName()); | ||
| } | ||
|
|
||
| @Override | ||
| public Decision canForceAllocatePrimary(ShardRouting shardRouting, RoutingNode node, RoutingAllocation allocation) { | ||
| assert shardRouting.primary() : "must not call canForceAllocatePrimary on a non-primary shard " + shardRouting; | ||
| return canAllocate(shardRouting, node, allocation); | ||
| } | ||
| } |
This file contains 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 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 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
Oops, something went wrong.