Paper/patches/server/0698-Consolidate-flush-calls-for-entity-tracker-packets.patch

53 lines
2.5 KiB
Diff
Raw Normal View History

From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
Rewrite chunk system (#8177) Patch documentation to come Issues with the old system that are fixed now: - World generation does not scale with cpu cores effectively. - Relies on the main thread for scheduling and maintaining chunk state, dropping chunk load/generate rates at lower tps. - Unreliable prioritisation of chunk gen/load calls that block the main thread. - Shutdown logic is utterly unreliable, as it has to wait for all chunks to unload - is it guaranteed that the chunk system is in a state on shutdown that it can reliably do this? Watchdog shutdown also typically failed due to thread checks, which is now resolved. - Saving of data is not unified (i.e can save chunk data without saving entity data, poses problems for desync if shutdown is really abnormal. - Entities are not loaded with chunks. This caused quite a bit of headache for Chunk#getEntities API, but now the new chunk system loads entities with chunks so that they are ready whenever the chunk loads in. Effectively brings the behavior back to 1.16 era, but still storing entities in their own separate regionfiles. The above list is not complete. The patch documentation will complete it. New chunk system hard relies on starlight and dataconverter, and most importantly the new concurrent utilities in ConcurrentUtil. Some of the old async chunk i/o interface (i.e the old file io thread reroutes _some_ calls to the new file io thread) is kept for plugin compat reasons. It will be removed in the next major version of minecraft. The old legacy chunk system patches have been moved to the removed folder in case we need them again.
2022-09-26 10:02:51 +02:00
From: Spottedleaf <Spottedleaf@users.noreply.github.com>
Date: Sat, 4 Apr 2020 17:00:20 -0700
Subject: [PATCH] Consolidate flush calls for entity tracker packets
Most server packets seem to be sent from here, so try to avoid
expensive flush calls from them.
This change was motivated due to local testing:
- My server spawn has 130 cows in it (for testing a prev. patch)
- Try to let 200 players join spawn
Without this change, I could only get 20 players on before they
all started timing out due to the load put on the Netty I/O threads.
With this change I could get all 200 on at 0ms ping.
(one of the primary issues is that my CPU is kinda trash, and having
4 extra threads at 100% is just too much for it).
So in general this patch should reduce Netty I/O thread load.
diff --git a/src/main/java/net/minecraft/server/level/ServerChunkCache.java b/src/main/java/net/minecraft/server/level/ServerChunkCache.java
index 2a31265ac49b7a6e32105530d00952ee0c0d4331..488a253e218409b5f0b4a872cee0928578fa7582 100644
--- a/src/main/java/net/minecraft/server/level/ServerChunkCache.java
+++ b/src/main/java/net/minecraft/server/level/ServerChunkCache.java
@@ -656,7 +656,24 @@ public class ServerChunkCache extends ChunkSource {
this.level.timings.broadcastChunkUpdates.stopTiming(); // Paper - timing
gameprofilerfiller.pop();
// Paper end - use set of chunks requiring updates, rather than iterating every single one loaded
+ // Paper start - controlled flush for entity tracker packets
+ List<net.minecraft.network.Connection> disabledFlushes = new java.util.ArrayList<>(this.level.players.size());
+ for (ServerPlayer player : this.level.players) {
+ net.minecraft.server.network.ServerGamePacketListenerImpl connection = player.connection;
+ if (connection != null) {
+ connection.connection.disableAutomaticFlush();
+ disabledFlushes.add(connection.connection);
+ }
+ }
+ try { // Paper end - controlled flush for entity tracker packets
this.chunkMap.tick();
+ // Paper start - controlled flush for entity tracker packets
+ } finally {
+ for (net.minecraft.network.Connection networkManager : disabledFlushes) {
+ networkManager.enableAutomaticFlush();
+ }
+ }
+ // Paper end - controlled flush for entity tracker packets
}
}