Start a benchmark setup, then improve start times

benchmark/.dockerignore

@@ -0,0 +1,5 @@
+*
+!target/*-runner
+!target/*-runner.jar
+!target/lib/*
+!target/quarkus-app/*

benchmark/.gitignore

@@ -0,0 +1,42 @@
+#Maven
+target/
+pom.xml.tag
+pom.xml.releaseBackup
+pom.xml.versionsBackup
+release.properties
+
+# Eclipse
+.project
+.classpath
+.settings/
+bin/
+
+# IntelliJ
+.idea
+*.ipr
+*.iml
+*.iws
+
+# NetBeans
+nb-configuration.xml
+
+# Visual Studio Code
+.vscode
+.factorypath
+
+# OSX
+.DS_Store
+
+# Vim
+*.swp
+*.swo
+
+# patch
+*.orig
+*.rej
+
+# Local environment
+.env
+
+# non-quarkus
+kubeconfig

benchmark/benchmark.sh

@@ -0,0 +1,44 @@
+#!/usr/bin/env bash
+[ -z "$DEBUG" ] || set -x
+set -eo pipefail
+WORKDIR="$(dirname $0)"
+[ "$WORKDIR" != "." ] || WORKDIR="$PWD"
+
+# NS=kkv-benchmark
+
+# export KUBECONFIG="$WORKDIR/kubeconfig"
+# echo "Hint: y-kubie ctx -f '$WORKDIR/kubeconfig'" -n $NS
+
+# y-k3d cluster create kkv-benchmark || echo "Cluster already exists?"
+
+# kubectl create namespace $NS
+# kubectl config set-context --current --namespace=$NS
+
+# kubectl -n $NS apply -k github.com/Yolean/kubernetes-kafka/variants/dev-small?ref=kafka-2.8.0
+
+# skaffold dev --tail=true --port-forward=true --status-check=false
+
+docker rm -f kkv-benchmark-kafka || true
+docker build -t kafka-kraft:local kafka-kraft/
+docker run -p 9094:9094 --name kkv-benchmark-kafka --rm -d kafka-kraft:local
+
+echo "Running benchmark prepare"
+# quarkus:dev with a main-class that terminates ends up here:
+# https://github.com/quarkusio/quarkus/blob/c87b6fae3db21b10e225f81936d848eb05c09fec/core/deployment/src/main/java/io/quarkus/deployment/dev/IsolatedDevModeMain.java#L114
+#mvn compile quarkus:dev -Dquarkus.package.main-class=prepare
+mvn package -Dmaven.test.skip=true
+java -jar target/quarkus-app/quarkus-run.jar
+
+echo "Kafka starting..."
+echo ""
+echo "Starting kkv in dev mode ..."
+echo "(the benchmark app can be started in a new shell using: mvn quarkus:dev -Dquarkus.package.main-class=)"
+echo ""
+(cd ../; mvn quarkus:dev \
+  -Dquarkus.http.port=8090 \
+  -Dkafka_bootstrap=localhost:9094 \
+  -Dtopic=kkv-benchmark \
+  -Dkafka_group_id=kkv1 \
+  -Dkafka_offset_reset=earliest \
+  -Dtarget=http://localhost:8080/kkv-benchmark/onupdate \
+  )

benchmark/kafka-kraft/Dockerfile

@@ -0,0 +1,7 @@
+FROM solsson/kafka:2.8.0-nonroot@sha256:a4a6d0d6fe723ec838d3c26ccb402ec0356e4b7016193ef620b11daa2c789a35
+
+COPY server.properties config/
+
+COPY start-dev.sh .
+
+ENTRYPOINT ["./start-dev.sh"]

benchmark/kafka-kraft/server.properties

@@ -0,0 +1,131 @@
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements.  See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF 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.
+
+#
+# This configuration file is intended for use in KRaft mode, where
+# Apache ZooKeeper is not present.  See config/kraft/README.md for details.
+#
+
+# only for dev
+auto.create.topics=true
+
+############################# Server Basics #############################
+
+# The role of this server. Setting this puts us in KRaft mode
+process.roles=broker,controller
+
+# The node id associated with this instance's roles
+node.id=1
+
+# The connect string for the controller quorum
+controller.quorum.voters=1@localhost:9093
+
+############################# Socket Server Settings #############################
+
+# The address the socket server listens on. It will get the value returned from
+# java.net.InetAddress.getCanonicalHostName() if not configured.
+#   FORMAT:
+#     listeners = listener_name://host_name:port
+#   EXAMPLE:
+#     listeners = PLAINTEXT://your.host.name:9092
+listeners=PLAINTEXT://:9094,CONTROLLER://:9093
+inter.broker.listener.name=PLAINTEXT
+
+# Hostname and port the broker will advertise to producers and consumers. If not set,
+# it uses the value for "listeners" if configured.  Otherwise, it will use the value
+# returned from java.net.InetAddress.getCanonicalHostName().
+advertised.listeners=PLAINTEXT://localhost:9094
+
+# Listener, host name, and port for the controller to advertise to the brokers. If
+# this server is a controller, this listener must be configured.
+controller.listener.names=CONTROLLER
+
+# Maps listener names to security protocols, the default is for them to be the same. See the config documentation for more details
+listener.security.protocol.map=CONTROLLER:PLAINTEXT,PLAINTEXT:PLAINTEXT
+
+# The number of threads that the server uses for receiving requests from the network and sending responses to the network
+num.network.threads=3
+
+# The number of threads that the server uses for processing requests, which may include disk I/O
+num.io.threads=8
+
+# The send buffer (SO_SNDBUF) used by the socket server
+socket.send.buffer.bytes=102400
+
+# The receive buffer (SO_RCVBUF) used by the socket server
+socket.receive.buffer.bytes=102400
+
+# The maximum size of a request that the socket server will accept (protection against OOM)
+socket.request.max.bytes=104857600
+
+
+############################# Log Basics #############################
+
+# A comma separated list of directories under which to store log files
+log.dirs=/home/nonroot/kafka-data
+
+# The default number of log partitions per topic. More partitions allow greater
+# parallelism for consumption, but this will also result in more files across
+# the brokers.
+num.partitions=1
+
+# The number of threads per data directory to be used for log recovery at startup and flushing at shutdown.
+# This value is recommended to be increased for installations with data dirs located in RAID array.
+num.recovery.threads.per.data.dir=1
+
+############################# Internal Topic Settings  #############################
+# The replication factor for the group metadata internal topics "__consumer_offsets" and "__transaction_state"
+# For anything other than development testing, a value greater than 1 is recommended to ensure availability such as 3.
+offsets.topic.replication.factor=1
+transaction.state.log.replication.factor=1
+transaction.state.log.min.isr=1
+
+############################# Log Flush Policy #############################
+
+# Messages are immediately written to the filesystem but by default we only fsync() to sync
+# the OS cache lazily. The following configurations control the flush of data to disk.
+# There are a few important trade-offs here:
+#    1. Durability: Unflushed data may be lost if you are not using replication.
+#    2. Latency: Very large flush intervals may lead to latency spikes when the flush does occur as there will be a lot of data to flush.
+#    3. Throughput: The flush is generally the most expensive operation, and a small flush interval may lead to excessive seeks.
+# The settings below allow one to configure the flush policy to flush data after a period of time or
+# every N messages (or both). This can be done globally and overridden on a per-topic basis.
+
+# The number of messages to accept before forcing a flush of data to disk
+#log.flush.interval.messages=10000
+
+# The maximum amount of time a message can sit in a log before we force a flush
+#log.flush.interval.ms=1000
+
+############################# Log Retention Policy #############################
+
+# The following configurations control the disposal of log segments. The policy can
+# be set to delete segments after a period of time, or after a given size has accumulated.
+# A segment will be deleted whenever *either* of these criteria are met. Deletion always happens
+# from the end of the log.
+
+# The minimum age of a log file to be eligible for deletion due to age
+log.retention.hours=-1
+
+# A size-based retention policy for logs. Segments are pruned from the log unless the remaining
+# segments drop below log.retention.bytes. Functions independently of log.retention.hours.
+#log.retention.bytes=1073741824
+
+# The maximum size of a log segment file. When this size is reached a new log segment will be created.
+log.segment.bytes=1073741824
+
+# The interval at which log segments are checked to see if they can be deleted according
+# to the retention policies
+log.retention.check.interval.ms=300000

benchmark/kafka-kraft/start-dev.sh

@@ -0,0 +1,8 @@
+#!/usr/bin/env bash
+set -x
+
+ID=$(./bin/kafka-storage.sh random-uuid | tail -n 1)
+
+./bin/kafka-storage.sh format -t $ID -c ./config/server.properties
+
+./bin/kafka-server-start.sh ./config/server.properties

benchmark/kafkaproxy/Dockerfile

@@ -0,0 +1,3 @@
+FROM envoyproxy/envoy:v1.18.2@sha256:e8b37c1d75787dd1e712ff389b0d37337dc8a174a63bed9c34ba73359dc67da7
+
+COPY envoy.yaml /etc/envoy/envoy.yaml

benchmark/kafkaproxy/envoy.yaml

@@ -0,0 +1,38 @@
+admin:
+  access_log_path: /dev/null
+  address:
+    socket_address:
+      address: 0.0.0.0
+      port_value: 9091
+static_resources:
+  listeners:
+  - address:
+      socket_address:
+        #address: 127.0.0.1
+        address: 0.0.0.0 # for port-forward
+        port_value: 9094
+    filter_chains:
+    - filters:
+      - name: envoy.filters.network.kafka_broker
+        typed_config:
+          "@type": type.googleapis.com/envoy.extensions.filters.network.kafka_broker.v3.KafkaBroker
+          stat_prefix: exampleprefix
+      - name: envoy.filters.network.tcp_proxy
+        typed_config:
+          "@type": type.googleapis.com/envoy.extensions.filters.network.tcp_proxy.v3.TcpProxy
+          stat_prefix: tcp
+          cluster: localkafka
+  clusters:
+  - name: localkafka
+    connect_timeout: 0.25s
+    type: strict_dns
+    lb_policy: round_robin
+    load_assignment:
+      cluster_name: some_service
+      endpoints:
+        - lb_endpoints:
+          - endpoint:
+              address:
+                socket_address:
+                  address: bootstrap
+                  port_value: 9092

benchmark/kustomize/kkv-benchmark-app.yaml

@@ -0,0 +1,62 @@
+# apiVersion: apps/v1
+# kind: StatefulSet
+# metadata:
+#   name: kkv
+#   labels: &labels
+#     app: kkv
+# spec:
+#   replicas: 1
+#   serviceName: kkv-example
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: kkv
+  labels: &labels
+    app: kkv
+spec:
+  replicas: 1
+  selector:
+    matchLabels: *labels
+  template:
+    metadata:
+      labels: *labels
+      annotations:
+        prometheus.io/scrape: "true"
+        prometheus.io/port: "8081"
+        prometheus.io/path: "/stats/prometheus"
+    spec:
+      containers:
+      - name: kafkaproxy
+        image: builds-registry.ystack.svc.cluster.local/yolean/kkv-benchmark-kafkaproxy
+        ports:
+        - containerPort: 9094
+          name: kafka-localhost
+      - name: kkv
+        image: builds-registry.ystack.svc.cluster.local/yolean/kafka-keyvalue
+        ports:
+        - containerPort: 8090
+          name: api
+        - containerPort: 5005
+          name: debugger
+        env:
+        - name: kafka_bootstrap
+          value: localhost:9094
+        - name: kafka_group_id
+          valueFrom:
+            fieldRef:
+              fieldPath: metadata.name
+        - name: topic
+          value: kkv-benchmark
+        - name: kafka_offset_reset
+          value: earliest
+        - name: target
+          value: http://127.0.0.1:8080/204/__TOPIC__
+        readinessProbe:
+          httpGet:
+            path: /q/health/ready
+            port: api
+        livenessProbe:
+          httpGet:
+            path: /q/health/live
+            port: api
+          initialDelaySeconds: 30

benchmark/kustomize/kustomization.yaml

@@ -0,0 +1,3 @@
+namespace: kkv-benchmark
+resources:
+- kkv-benchmark-app.yaml