From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001 From: Aikar Date: Sun, 12 Apr 2020 15:50:48 -0400 Subject: [PATCH] Improved Watchdog Support Forced Watchdog Crash support and Improve Async Shutdown If the request to shut down the server is received while we are in a watchdog hang, immediately treat it as a crash and begin the shutdown process. Shutdown process is now improved to also shutdown cleanly when not using restart scripts either. If a server is deadlocked, a server owner can send SIGUP (or any other signal the JVM understands to shut down as it currently does) and the watchdog will no longer need to wait until the full timeout, allowing you to trigger a close process and try to shut the server down gracefully, saving player and world data. Previously there was no way to trigger this outside of waiting for a full watchdog timeout, which may be set to a really long time... Additionally, fix everything to do with shutting the server down asynchronously. Previously, nearly everything about the process was fragile and unsafe. Main might not have actually been frozen, and might still be manipulating state. Or, some reuest might ask main to do something in the shutdown but main is dead. Or worse, other things might start closing down items such as the Console or Thread Pool before we are fully shutdown. This change tries to resolve all of these issues by moving everything into the stop method and guaranteeing only one thread is stopping the server. We then issue Thread Death to the main thread of another thread initiates the stop process. We have to ensure Thread Death propagates correctly though to stop main completely. This is to ensure that if main isn't truely stuck, it's not manipulating state we are trying to save. This also moves all plugins who register "delayed init" tasks to occur just before "Done" so they are properly accounted for and wont trip watchdog on init. diff --git a/src/main/java/com/destroystokyo/paper/Metrics.java b/src/main/java/com/destroystokyo/paper/Metrics.java index 6aaed8e8bf8c721fc834da5c76ac72a4c3e92458..4b002e8b75d117b726b0de274a76d3596fce015b 100644 --- a/src/main/java/com/destroystokyo/paper/Metrics.java +++ b/src/main/java/com/destroystokyo/paper/Metrics.java @@ -92,7 +92,12 @@ public class Metrics { * Starts the Scheduler which submits our data every 30 minutes. */ private void startSubmitting() { - final Runnable submitTask = this::submitData; + final Runnable submitTask = () -> { + if (MinecraftServer.getServer().hasStopped()) { + return; + } + submitData(); + }; // Many servers tend to restart at a fixed time at xx:00 which causes an uneven distribution of requests on the // bStats backend. To circumvent this problem, we introduce some randomness into the initial and second delay. diff --git a/src/main/java/net/minecraft/CrashReport.java b/src/main/java/net/minecraft/CrashReport.java index 336795dff742b7c6957fbd3476aff31d25a5e659..30a58229aa6dac5039511d0c0df5f2912ea7de9f 100644 --- a/src/main/java/net/minecraft/CrashReport.java +++ b/src/main/java/net/minecraft/CrashReport.java @@ -230,6 +230,7 @@ public class CrashReport { } public static CrashReport forThrowable(Throwable cause, String title) { + if (cause instanceof ThreadDeath) com.destroystokyo.paper.util.SneakyThrow.sneaky(cause); // Paper while (cause instanceof CompletionException && cause.getCause() != null) { cause = cause.getCause(); } diff --git a/src/main/java/net/minecraft/server/MinecraftServer.java b/src/main/java/net/minecraft/server/MinecraftServer.java index 8dcbeeae50afe23aa7e2a083239f0a315424574f..d406df9626d29ee257b8eedcbea2af09ed4b6baf 100644 --- a/src/main/java/net/minecraft/server/MinecraftServer.java +++ b/src/main/java/net/minecraft/server/MinecraftServer.java @@ -295,7 +295,7 @@ public abstract class MinecraftServer extends ReentrantBlockableEventLoop processQueue = new java.util.concurrent.ConcurrentLinkedQueue(); public int autosavePeriod; public Commands vanillaCommandDispatcher; - private boolean forceTicks; + public boolean forceTicks; // Paper // CraftBukkit end // Spigot start public static final int TPS = 20; @@ -306,6 +306,9 @@ public abstract class MinecraftServer extends ReentrantBlockableEventLoop S spin(Function serverFactory) { AtomicReference atomicreference = new AtomicReference(); Thread thread = new io.papermc.paper.util.TickThread(() -> { // Paper - rewrite chunk system @@ -885,6 +888,7 @@ public abstract class MinecraftServer extends ReentrantBlockableEventLoop {}; + } + // Paper end return new TickTask(this.tickCount, runnable); } @@ -1453,6 +1506,7 @@ public abstract class MinecraftServer extends ReentrantBlockableEventLoop implements Profiler try { task.run(); } catch (Exception var3) { + if (var3.getCause() instanceof ThreadDeath) throw var3; // Paper LOGGER.error(LogUtils.FATAL_MARKER, "Error executing task on {}", this.name(), var3); } diff --git a/src/main/java/net/minecraft/world/level/Level.java b/src/main/java/net/minecraft/world/level/Level.java index c53fa2902c6572c65f42a07be987a7da096a8aee..d9842447d7ae840bf9541bbe7c99b032c83d0039 100644 --- a/src/main/java/net/minecraft/world/level/Level.java +++ b/src/main/java/net/minecraft/world/level/Level.java @@ -821,6 +821,7 @@ public abstract class Level implements LevelAccessor, AutoCloseable { try { tickConsumer.accept(entity); } catch (Throwable throwable) { + if (throwable instanceof ThreadDeath) throw throwable; // Paper // Paper start - Prevent tile entity and entity crashes final String msg = String.format("Entity threw exception at %s:%s,%s,%s", entity.level.getWorld().getName(), entity.getX(), entity.getY(), entity.getZ()); MinecraftServer.LOGGER.error(msg, throwable); diff --git a/src/main/java/net/minecraft/world/level/chunk/LevelChunk.java b/src/main/java/net/minecraft/world/level/chunk/LevelChunk.java index 1c618cfb63561f4557f8ec71254b6397eb9cc485..6e95a98727322106d2c418de80f5f0aad2ea1953 100644 --- a/src/main/java/net/minecraft/world/level/chunk/LevelChunk.java +++ b/src/main/java/net/minecraft/world/level/chunk/LevelChunk.java @@ -1218,6 +1218,7 @@ public class LevelChunk extends ChunkAccess { gameprofilerfiller.pop(); } catch (Throwable throwable) { + if (throwable instanceof ThreadDeath) throw throwable; // Paper // Paper start - Prevent tile entity and entity crashes final String msg = String.format("BlockEntity threw exception at %s:%s,%s,%s", LevelChunk.this.getLevel().getWorld().getName(), this.getPos().getX(), this.getPos().getY(), this.getPos().getZ()); net.minecraft.server.MinecraftServer.LOGGER.error(msg, throwable); diff --git a/src/main/java/org/bukkit/craftbukkit/Main.java b/src/main/java/org/bukkit/craftbukkit/Main.java index 4f666a16a46d86cd0919bbe8f8b918a7f451d254..f7c8d25830ed701e72f828fa73066a6e9188253b 100644 --- a/src/main/java/org/bukkit/craftbukkit/Main.java +++ b/src/main/java/org/bukkit/craftbukkit/Main.java @@ -12,6 +12,8 @@ import java.util.logging.Level; import java.util.logging.Logger; import joptsimple.OptionParser; import joptsimple.OptionSet; +import net.minecraft.util.ExceptionCollector; +import net.minecraft.world.level.lighting.LayerLightEventListener; import net.minecrell.terminalconsole.TerminalConsoleAppender; // Paper public class Main { @@ -169,6 +171,36 @@ public class Main { OptionSet options = null; + // Paper start - preload logger classes to avoid plugins mixing versions + tryPreloadClass("org.apache.logging.log4j.core.Core"); + tryPreloadClass("org.apache.logging.log4j.core.appender.AsyncAppender"); + tryPreloadClass("org.apache.logging.log4j.core.Appender"); + tryPreloadClass("org.apache.logging.log4j.core.ContextDataInjector"); + tryPreloadClass("org.apache.logging.log4j.core.Filter"); + tryPreloadClass("org.apache.logging.log4j.core.ErrorHandler"); + tryPreloadClass("org.apache.logging.log4j.core.LogEvent"); + tryPreloadClass("org.apache.logging.log4j.core.Logger"); + tryPreloadClass("org.apache.logging.log4j.core.LoggerContext"); + tryPreloadClass("org.apache.logging.log4j.core.LogEventListener"); + tryPreloadClass("org.apache.logging.log4j.core.AbstractLogEvent"); + tryPreloadClass("org.apache.logging.log4j.message.AsynchronouslyFormattable"); + tryPreloadClass("org.apache.logging.log4j.message.FormattedMessage"); + tryPreloadClass("org.apache.logging.log4j.message.ParameterizedMessage"); + tryPreloadClass("org.apache.logging.log4j.message.Message"); + tryPreloadClass("org.apache.logging.log4j.message.MessageFactory"); + tryPreloadClass("org.apache.logging.log4j.message.TimestampMessage"); + tryPreloadClass("org.apache.logging.log4j.message.SimpleMessage"); + tryPreloadClass("org.apache.logging.log4j.core.async.AsyncLogger"); + tryPreloadClass("org.apache.logging.log4j.core.async.AsyncLoggerContext"); + tryPreloadClass("org.apache.logging.log4j.core.async.AsyncQueueFullPolicy"); + tryPreloadClass("org.apache.logging.log4j.core.async.AsyncLoggerDisruptor"); + tryPreloadClass("org.apache.logging.log4j.core.async.RingBufferLogEvent"); + tryPreloadClass("org.apache.logging.log4j.core.async.DisruptorUtil"); + tryPreloadClass("org.apache.logging.log4j.core.async.RingBufferLogEventHandler"); + tryPreloadClass("org.apache.logging.log4j.core.impl.ThrowableProxy"); + tryPreloadClass("org.apache.logging.log4j.core.impl.ExtendedClassInfo"); + tryPreloadClass("org.apache.logging.log4j.core.impl.ExtendedStackTraceElement"); + // Paper end try { options = parser.parse(args); } catch (joptsimple.OptionException ex) { @@ -264,8 +296,64 @@ public class Main { } catch (Throwable t) { t.printStackTrace(); } + // Paper start + // load some required classes to avoid errors during shutdown if jar is replaced + // also to guarantee our version loads over plugins + tryPreloadClass("com.destroystokyo.paper.util.SneakyThrow"); + tryPreloadClass("com.google.common.collect.Iterators$PeekingImpl"); + tryPreloadClass("com.google.common.collect.MapMakerInternalMap$Values"); + tryPreloadClass("com.google.common.collect.MapMakerInternalMap$ValueIterator"); + tryPreloadClass("com.google.common.collect.MapMakerInternalMap$WriteThroughEntry"); + tryPreloadClass("com.google.common.collect.Iterables"); + for (int i = 1; i <= 15; i++) { + tryPreloadClass("com.google.common.collect.Iterables$" + i, false); + } + tryPreloadClass("org.apache.commons.lang3.mutable.MutableBoolean"); + tryPreloadClass("org.apache.commons.lang3.mutable.MutableInt"); + tryPreloadClass("org.jline.terminal.impl.MouseSupport"); + tryPreloadClass("org.jline.terminal.impl.MouseSupport$1"); + tryPreloadClass("org.jline.terminal.Terminal$MouseTracking"); + tryPreloadClass("co.aikar.timings.TimingHistory"); + tryPreloadClass("co.aikar.timings.TimingHistory$MinuteReport"); + tryPreloadClass("io.netty.channel.AbstractChannelHandlerContext"); + tryPreloadClass("io.netty.channel.AbstractChannelHandlerContext$11"); + tryPreloadClass("io.netty.channel.AbstractChannelHandlerContext$12"); + tryPreloadClass("io.netty.channel.AbstractChannel$AbstractUnsafe$8"); + tryPreloadClass("io.netty.util.concurrent.DefaultPromise"); + tryPreloadClass("io.netty.util.concurrent.DefaultPromise$1"); + tryPreloadClass("io.netty.util.internal.PromiseNotificationUtil"); + tryPreloadClass("io.netty.util.internal.SystemPropertyUtil"); + tryPreloadClass("org.bukkit.craftbukkit.scheduler.CraftScheduler"); + tryPreloadClass("org.bukkit.craftbukkit.scheduler.CraftScheduler$1"); + tryPreloadClass("org.bukkit.craftbukkit.scheduler.CraftScheduler$2"); + tryPreloadClass("org.bukkit.craftbukkit.scheduler.CraftScheduler$3"); + tryPreloadClass("org.bukkit.craftbukkit.scheduler.CraftScheduler$4"); + tryPreloadClass("org.slf4j.helpers.MessageFormatter"); + tryPreloadClass("org.slf4j.helpers.FormattingTuple"); + tryPreloadClass("org.slf4j.helpers.BasicMarker"); + tryPreloadClass("org.slf4j.helpers.Util"); + tryPreloadClass("com.destroystokyo.paper.event.player.PlayerConnectionCloseEvent"); + tryPreloadClass("com.destroystokyo.paper.event.entity.EntityRemoveFromWorldEvent"); + // Minecraft, seen during saving + tryPreloadClass(LayerLightEventListener.DummyLightLayerEventListener.class.getName()); + tryPreloadClass(LayerLightEventListener.class.getName()); + tryPreloadClass(ExceptionCollector.class.getName()); + // Paper end + } + } + + // Paper start + private static void tryPreloadClass(String className) { + tryPreloadClass(className, true); + } + private static void tryPreloadClass(String className, boolean printError) { + try { + Class.forName(className); + } catch (ClassNotFoundException e) { + if (printError) System.err.println("An expected class " + className + " was not found for preloading: " + e.getMessage()); } } + // Paper end private static List asList(String... params) { return Arrays.asList(params); diff --git a/src/main/java/org/bukkit/craftbukkit/util/ServerShutdownThread.java b/src/main/java/org/bukkit/craftbukkit/util/ServerShutdownThread.java index b4a19d80bbf71591f25729fd0e98590350cb31d0..e948ec5a573b22645664eb53bc3e9932246544e4 100644 --- a/src/main/java/org/bukkit/craftbukkit/util/ServerShutdownThread.java +++ b/src/main/java/org/bukkit/craftbukkit/util/ServerShutdownThread.java @@ -12,12 +12,28 @@ public class ServerShutdownThread extends Thread { @Override public void run() { try { + // Paper start - try to shutdown on main + server.safeShutdown(false, false); + for (int i = 1000; i > 0 && !server.hasStopped(); i -= 100) { + Thread.sleep(100); + } + if (server.hasStopped()) { + while (!server.hasFullyShutdown) Thread.sleep(1000); + return; + } + // Looks stalled, close async org.spigotmc.AsyncCatcher.enabled = false; // Spigot org.spigotmc.AsyncCatcher.shuttingDown = true; // Paper + server.forceTicks = true; this.server.close(); + while (!server.hasFullyShutdown) Thread.sleep(1000); + } catch (InterruptedException e) { + e.printStackTrace(); + // Paper end } finally { + org.apache.logging.log4j.LogManager.shutdown(); // Paper try { - net.minecrell.terminalconsole.TerminalConsoleAppender.close(); // Paper - Use TerminalConsoleAppender + //net.minecrell.terminalconsole.TerminalConsoleAppender.close(); // Paper - Move into stop } catch (Exception e) { } } diff --git a/src/main/java/org/spigotmc/RestartCommand.java b/src/main/java/org/spigotmc/RestartCommand.java index a142a56a920e153ed84c08cece993f10d76f7793..92d97a5810a379b427a99b4c63fb9844d823a84f 100644 --- a/src/main/java/org/spigotmc/RestartCommand.java +++ b/src/main/java/org/spigotmc/RestartCommand.java @@ -139,7 +139,7 @@ public class RestartCommand extends Command // Paper end // Paper start - copied from above and modified to return if the hook registered - private static boolean addShutdownHook(String restartScript) + public static boolean addShutdownHook(String restartScript) { String[] split = restartScript.split( " " ); if ( split.length > 0 && new File( split[0] ).isFile() ) diff --git a/src/main/java/org/spigotmc/WatchdogThread.java b/src/main/java/org/spigotmc/WatchdogThread.java index b47d043144c499b1499f6b4be5a16a3f75c9fcb8..383c52c62f49b17db2fbf58009d6ea132d124bea 100644 --- a/src/main/java/org/spigotmc/WatchdogThread.java +++ b/src/main/java/org/spigotmc/WatchdogThread.java @@ -11,6 +11,7 @@ import org.bukkit.Bukkit; public final class WatchdogThread extends io.papermc.paper.util.TickThread // Paper - rewrite chunk system { + public static final boolean DISABLE_WATCHDOG = Boolean.getBoolean("disable.watchdog"); // Paper private static WatchdogThread instance; private long timeoutTime; private boolean restart; @@ -39,6 +40,7 @@ public final class WatchdogThread extends io.papermc.paper.util.TickThread // Pa { if ( WatchdogThread.instance == null ) { + if (timeoutTime <= 0) timeoutTime = 300; // Paper WatchdogThread.instance = new WatchdogThread( timeoutTime * 1000L, restart ); WatchdogThread.instance.start(); } else @@ -70,12 +72,13 @@ public final class WatchdogThread extends io.papermc.paper.util.TickThread // Pa // Paper start Logger log = Bukkit.getServer().getLogger(); long currentTime = WatchdogThread.monotonicMillis(); - if ( this.lastTick != 0 && this.timeoutTime > 0 && currentTime > this.lastTick + this.earlyWarningEvery && !Boolean.getBoolean("disable.watchdog")) // Paper - Add property to disable + MinecraftServer server = MinecraftServer.getServer(); + if ( this.lastTick != 0 && this.timeoutTime > 0 && WatchdogThread.hasStarted && (!server.isRunning() || (currentTime > this.lastTick + this.earlyWarningEvery && !DISABLE_WATCHDOG) )) // Paper - add property to disable { - boolean isLongTimeout = currentTime > lastTick + timeoutTime; + boolean isLongTimeout = currentTime > lastTick + timeoutTime || (!server.isRunning() && !server.hasStopped() && currentTime > lastTick + 1000); // Don't spam early warning dumps if ( !isLongTimeout && (earlyWarningEvery <= 0 || !hasStarted || currentTime < lastEarlyWarning + earlyWarningEvery || currentTime < lastTick + earlyWarningDelay)) continue; - if ( !isLongTimeout && MinecraftServer.getServer().hasStopped()) continue; // Don't spam early watchdog warnings during shutdown, we'll come back to this... + if ( !isLongTimeout && server.hasStopped()) continue; // Don't spam early watchdog warnings during shutdown, we'll come back to this... lastEarlyWarning = currentTime; if (isLongTimeout) { // Paper end @@ -137,9 +140,25 @@ public final class WatchdogThread extends io.papermc.paper.util.TickThread // Pa if ( isLongTimeout ) { - if ( this.restart && !MinecraftServer.getServer().hasStopped() ) + if ( !server.hasStopped() ) { - RestartCommand.restart(); + AsyncCatcher.enabled = false; // Disable async catcher incase it interferes with us + AsyncCatcher.shuttingDown = true; + server.forceTicks = true; + if (restart) { + RestartCommand.addShutdownHook( SpigotConfig.restartScript ); + } + // try one last chance to safe shutdown on main incase it 'comes back' + server.abnormalExit = true; + server.safeShutdown(false, restart); + try { + Thread.sleep(1000); + } catch (InterruptedException e) { + e.printStackTrace(); + } + if (!server.hasStopped()) { + server.close(); + } } break; } // Paper end diff --git a/src/main/resources/log4j2.xml b/src/main/resources/log4j2.xml index 3dc317e466e1b93dff030794dd7f29ca1b266778..d285dbec16272db6b8a71865e05924ad66087407 100644 --- a/src/main/resources/log4j2.xml +++ b/src/main/resources/log4j2.xml @@ -1,5 +1,5 @@ - +