1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
|
/*
* 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;
import org.elasticsearch.cluster.ClusterChangedEvent;
import org.elasticsearch.cluster.ClusterService;
import org.elasticsearch.cluster.ClusterState;
import org.elasticsearch.cluster.ClusterStateListener;
import org.elasticsearch.cluster.ClusterStateUpdateTask;
import org.elasticsearch.cluster.routing.allocation.AllocationService;
import org.elasticsearch.cluster.routing.allocation.RoutingAllocation;
import org.elasticsearch.common.Priority;
import org.elasticsearch.common.component.AbstractLifecycleComponent;
import org.elasticsearch.common.inject.Inject;
import org.elasticsearch.common.settings.Settings;
import org.elasticsearch.common.unit.TimeValue;
import org.elasticsearch.common.util.concurrent.AbstractRunnable;
import org.elasticsearch.common.util.concurrent.FutureUtils;
import org.elasticsearch.threadpool.ThreadPool;
import java.util.concurrent.ScheduledFuture;
import java.util.concurrent.atomic.AtomicBoolean;
/**
* A {@link RoutingService} listens to clusters state. When this service
* receives a {@link ClusterChangedEvent} the cluster state will be verified and
* the routing tables might be updated.
* <p>
* Note: The {@link RoutingService} is responsible for cluster wide operations
* that include modifications to the cluster state. Such an operation can only
* be performed on the clusters master node. Unless the local node this service
* is running on is the clusters master node this service will not perform any
* actions.
* </p>
*/
public class RoutingService extends AbstractLifecycleComponent<RoutingService> implements ClusterStateListener {
private static final String CLUSTER_UPDATE_TASK_SOURCE = "cluster_reroute";
final ThreadPool threadPool;
private final ClusterService clusterService;
private final AllocationService allocationService;
private AtomicBoolean rerouting = new AtomicBoolean();
private volatile long minDelaySettingAtLastSchedulingNanos = Long.MAX_VALUE;
private volatile ScheduledFuture registeredNextDelayFuture;
@Inject
public RoutingService(Settings settings, ThreadPool threadPool, ClusterService clusterService, AllocationService allocationService) {
super(settings);
this.threadPool = threadPool;
this.clusterService = clusterService;
this.allocationService = allocationService;
if (clusterService != null) {
clusterService.addFirst(this);
}
}
@Override
protected void doStart() {
}
@Override
protected void doStop() {
}
@Override
protected void doClose() {
FutureUtils.cancel(registeredNextDelayFuture);
clusterService.remove(this);
}
public AllocationService getAllocationService() {
return this.allocationService;
}
/**
* Initiates a reroute.
*/
public final void reroute(String reason) {
performReroute(reason);
}
@Override
public void clusterChanged(ClusterChangedEvent event) {
if (event.state().nodes().localNodeMaster()) {
// Figure out if an existing scheduled reroute is good enough or whether we need to cancel and reschedule.
// If the minimum of the currently relevant delay settings is larger than something we scheduled in the past,
// we are guaranteed that the planned schedule will happen before any of the current shard delays are expired.
long minDelaySetting = UnassignedInfo.findSmallestDelayedAllocationSettingNanos(settings, event.state());
if (minDelaySetting <= 0) {
logger.trace("no need to schedule reroute - no delayed unassigned shards, minDelaySetting [{}], scheduled [{}]", minDelaySetting, minDelaySettingAtLastSchedulingNanos);
minDelaySettingAtLastSchedulingNanos = Long.MAX_VALUE;
FutureUtils.cancel(registeredNextDelayFuture);
} else if (minDelaySetting < minDelaySettingAtLastSchedulingNanos) {
FutureUtils.cancel(registeredNextDelayFuture);
minDelaySettingAtLastSchedulingNanos = minDelaySetting;
TimeValue nextDelay = TimeValue.timeValueNanos(UnassignedInfo.findNextDelayedAllocationIn(event.state()));
assert nextDelay.nanos() > 0 : "next delay must be non 0 as minDelaySetting is [" + minDelaySetting + "]";
logger.info("delaying allocation for [{}] unassigned shards, next check in [{}]",
UnassignedInfo.getNumberOfDelayedUnassigned(event.state()), nextDelay);
registeredNextDelayFuture = threadPool.schedule(nextDelay, ThreadPool.Names.SAME, new AbstractRunnable() {
@Override
protected void doRun() throws Exception {
minDelaySettingAtLastSchedulingNanos = Long.MAX_VALUE;
reroute("assign delayed unassigned shards");
}
@Override
public void onFailure(Throwable t) {
logger.warn("failed to schedule/execute reroute post unassigned shard", t);
minDelaySettingAtLastSchedulingNanos = Long.MAX_VALUE;
}
});
} else {
logger.trace("no need to schedule reroute - current schedule reroute is enough. minDelaySetting [{}], scheduled [{}]", minDelaySetting, minDelaySettingAtLastSchedulingNanos);
}
}
}
// visible for testing
long getMinDelaySettingAtLastSchedulingNanos() {
return this.minDelaySettingAtLastSchedulingNanos;
}
// visible for testing
protected void performReroute(String reason) {
try {
if (lifecycle.stopped()) {
return;
}
if (rerouting.compareAndSet(false, true) == false) {
logger.trace("already has pending reroute, ignoring {}", reason);
return;
}
logger.trace("rerouting {}", reason);
clusterService.submitStateUpdateTask(CLUSTER_UPDATE_TASK_SOURCE + "(" + reason + ")", new ClusterStateUpdateTask(Priority.HIGH) {
@Override
public ClusterState execute(ClusterState currentState) {
rerouting.set(false);
RoutingAllocation.Result routingResult = allocationService.reroute(currentState, reason);
if (!routingResult.changed()) {
// no state changed
return currentState;
}
return ClusterState.builder(currentState).routingResult(routingResult).build();
}
@Override
public void onNoLongerMaster(String source) {
rerouting.set(false);
// no biggie
}
@Override
public void onFailure(String source, Throwable t) {
rerouting.set(false);
ClusterState state = clusterService.state();
if (logger.isTraceEnabled()) {
logger.error("unexpected failure during [{}], current state:\n{}", t, source, state.prettyPrint());
} else {
logger.error("unexpected failure during [{}], current state version [{}]", t, source, state.version());
}
}
});
} catch (Throwable e) {
rerouting.set(false);
ClusterState state = clusterService.state();
logger.warn("failed to reroute routing table, current state:\n{}", e, state.prettyPrint());
}
}
}
|
