THREESCALE-12133 optimize configuration reload

[tkan145]

What

Fix THREESCALE-12133

NOTE:

• Try to download the flamegraph file and and open the it in your browser (interactive graph).
• Latency was measured by reloading the static file, adding 2-3 seconds to the result if loading from a portal.
• JSON encoding/decoding still consumes a significant portion of the CPU, but latency has decreased to an acceptable level, and it requires more extensive changes, so I decided to defer the refactor to the next PR.

Before:

File read

bash-5.2# accessed-files -p `pgrep -f 'nginx: worker'` -t 60        
Neither -r nor -w options are specified.                            
bash-5.2# accessed-files -p `pgrep -f 'nginx: worker'` -r -t 60     
Tracing 3599829 (/usr/local/openresty/nginx/sbin/nginx)...          
Please wait for 60 seconds.                                         
                                                                    
=== Top 10 file reads ===                                           
#1: 117280 times, 233684323 bytes reads in file apicast-policy.json.
#2: 44 times, 31357920 bytes reads in file config.json.             

Latency

HTTP                                                                                
http_req_duration..............: med=42.46ms p(95)=48.14ms p(99)=2.37s p(99.9)=2.76s
  { expected_response:true }...: med=42.46ms p(95)=48.14ms p(99)=2.37s p(99.9)=2.76s
http_req_failed................: 0.00%  0 out of 9000                               
http_reqs......................: 9000   47.464397/s

Flamegraph

After:

File read

bash-5.2# accessed-files -p `pgrep -f 'nginx: worker'` -r -t 60
Tracing 3605605 (/usr/local/openresty/nginx/sbin/nginx)...     
Please wait for 60 seconds.                                    
                                                               
=== Top 10 file reads ===                                      
#1: 44 times, 31357920 bytes reads in file config.json.        

Latency

HTTP                                                                                
http_req_duration..............: med=42.66ms p(95)=44.6ms p(99)=68.14ms p(99.9)=205.02ms
  { expected_response:true }...: med=42.66ms p(95)=44.6ms p(99)=68.14ms p(99.9)=205.02ms
http_req_failed................: 0.00%  0 out of 9147                                   
http_reqs......................: 9147   49.677724/s  

Flamegraph

Verification steps

• Install 3scale
• Setup products, applications, backend, etc...

Details

#!/bin/bash

# Get the ADMIN_URL and ADMIN_ACCESS_TOKEN from apimanager and system-seed secret
DOMAIN=$(oc get routes console -n openshift-console -o json | jq -r '.status.ingress[0].routerCanonicalHostname' | sed 's/router-default.//')
ADMIN_ACCESS_TOKEN=$(oc get secret system-seed -n 3scale-test -o jsonpath="{.data.ADMIN_ACCESS_TOKEN}"| base64 --decode)
oc project 3scale-test
# Create the required secrets for Accounts, products and backends. 
oc apply -f - <<EOF
---
apiVersion: v1
kind: Secret
metadata:
  name: mytenant
type: Opaque
stringData:
  adminURL: https://3scale-admin.$DOMAIN
  token: $ADMIN_ACCESS_TOKEN
EOF
# user secret
oc apply -f - <<EOF
---
apiVersion: v1
kind: Secret
metadata:
  name: myusername01
stringData:
  password: "123456"
EOF
# Developer User
oc apply -f - <<EOF
---
apiVersion: capabilities.3scale.net/v1beta1
kind: DeveloperUser
metadata:
  name: developeruser01
  namespace: 3scale-test
  annotations:
    "insecure_skip_verify": "true"
spec:
  developerAccountRef:
    name: developeraccount01
  email: myusername01@example.com
  passwordCredentialsRef:
    name: myusername01
  providerAccountRef:
    name: mytenant
  role: admin
  username: myusername01
EOF
sleep 30
# TODO check for developer user completed
oc apply -f - <<EOF
---
apiVersion: capabilities.3scale.net/v1beta1
kind: DeveloperAccount
metadata:
  name: developeraccount01
  namespace: 3scale-test
  annotations:
    "insecure_skip_verify": "true"
spec:
  orgName: 3scale-test
  providerAccountRef:
    name: mytenant
EOF
deploy httpbin and use it as the backend
oc new-project httpbin
oc new-app quay.io/trepel/httpbin
oc get svc
oc scale deployment/httpbin --namespace httpbin --replicas=1 
oc project 3scale-test

# create backend
oc apply -f - <<EOF
---
apiVersion: capabilities.3scale.net/v1beta1
kind: Backend
metadata:
  name: backend1-cr
  namespace: 3scale-test
  annotations:
    "insecure_skip_verify": "true"
spec:
  mappingRules:
    - httpMethod: GET
      increment: 1
      last: true
      metricMethodRef: hits
      pattern: /
    - httpMethod: POST
      pattern : "/"
      metricMethodRef: hits
      increment: 1    
  name: backend1
  privateBaseURL: 'http://httpbin.httpbin.svc:8080'
  systemName: backend1
EOF

TOTAL_PRODUCTS=600

for ((n=1; n<=$TOTAL_PRODUCTS; n++))
do
# Product
oc apply -f - <<EOF
---
apiVersion: capabilities.3scale.net/v1beta1
kind: Product
metadata:
  name: product$n-cr
  namespace: 3scale-test
  annotations:
    "insecure_skip_verify": "true"
spec:
  applicationPlans:
    plan01:
      name: "My Plan 01"
  deployment:
    apicastHosted:
      authentication:
        userkey:
          authUserKey: token
  name: product$n
  backendUsages:
    backend1:
      path: /
  mappingRules:
    - httpMethod: GET
      pattern : "/"
      metricMethodRef: hits
      increment: 1
    - httpMethod: POST
      pattern : "/"
      metricMethodRef: hits
      increment: 1
  policies:
    - name: headers
      version: builtin
      enabled: true
      configuration:
        set_headers:
          - name: "echo1"
            value: "test"
            value_type: "plain"
    - name: headers
      version: builtin
      enabled: true
      configuration:
        set_headers:
          - name: "echo2"
            value: "test"
            value_type: "plain"
    - name: headers
      version: builtin
      enabled: true
      configuration:
        set_headers:
          - name: "echo3"
            value: "test"
            value_type: "plain"
    - name: logging
      version: builtin
      enabled: true
      configuration:
        custom_logging: "[{{time_local}}] {{host}}:{{server_port}} {{remote_addr}}:{{remote_port}} \"{{request}}\" {{status}} {{body_bytes_sent}} ({{request_time}}) {{post_action_impact}} AND {{upstream_response_time}}"
    - name: headers
      version: builtin
      enabled: true
      configuration:
        set_headers:
          - name: "echo4"
            value: "test"
            value_type: "plain"
    - name: headers
      version: builtin
      enabled: true
      configuration:
        set_headers:
          - name: "echo5"
            value: "test"
            value_type: "plain"
    - name: apicast
      version: builtin
      enabled: true
      configuration: {}
EOF

# application
oc apply -f - <<EOF
---
apiVersion: capabilities.3scale.net/v1beta1
kind: Application
metadata:
  name: application$n-cr
  namespace: 3scale-test
  annotations:
    "insecure_skip_verify": "true"
spec:
  accountCR: 
    name: developeraccount01
  applicationPlanName: plan01
  productCR: 
    name: product$n-cr
  name: testApp
  description: further testing
EOF
# TODO proxy promote
oc apply -f - <<EOF
---
apiVersion: capabilities.3scale.net/v1beta1
kind: ProxyConfigPromote
metadata:
  name: product$n-v1-production
  namespace: 3scale-test
  annotations:
    "insecure_skip_verify": "true"
spec:
  productCRName: product$n-cr
  production: true
  deleteCR: true
EOF
done


sleep 30
echo Product Route: 
echo "https://$(oc get routes | grep product1 |grep production| awk '{print $2}')" 
echo
echo User_key: 
echo $(curl -s -X 'GET' "https://3scale-admin.$DOMAIN/admin/api/applications.xml?access_token=$ADMIN_ACCESS_TOKEN&page=1&per_page=500&service_id=3" -H 'accept: */*' | grep -oP '<user_key>\K[^<]+' | sed 's/\s//g')

• Once the script finish, visit the admin portal and wait for all products to be populated (going to take a while)
• Create an token
• Inside APIcast repo, move into dev-environments folder

▲ lib/3scale/APIcast cd dev-environments/http-proxy-plain-http-upstream/

• Update the docker-compose.yml file as follow. Update <token> and <3scale_admin_portal> to match values from previous step.

diff --git a/dev-environments/http-proxy-plain-http-upstream/docker-compose.yml b/dev-environments/http-proxy-plain-http-upstream/docker-compose.yml
index f7b311a5..5032bc13 100644                                                                                                                     
--- a/dev-environments/http-proxy-plain-http-upstream/docker-compose.yml                                                                            
+++ b/dev-environments/http-proxy-plain-http-upstream/docker-compose.yml                                                                            
@@ -12,11 +12,12 @@ services:                                                                                                                       
     - two.upstream                                                                                                                                 
     environment:                                                                                                                                   
       THREESCALE_CONFIG_FILE: /tmp/config.json                                                                                                     
-      THREESCALE_DEPLOYMENT_ENV: staging                                                                                                           
-      APICAST_CONFIGURATION_LOADER: lazy                                                                                                           
+      THREESCALE_PORTAL_ENDPOINT: "https://<token>:<3scale_admin_portal>"                                                                          
+      THREESCALE_DEPLOYMENT_ENV: production                                                                                                        
+      APICAST_CONFIGURATION_LOADER: boot                                                                                                           
       APICAST_WORKERS: 1                                                                                                                           
-      APICAST_LOG_LEVEL: debug                                                                                                                     
-      APICAST_CONFIGURATION_CACHE: "0"                                                                                                             
+      APICAST_LOG_LEVEL: notice                                                                                                                    
+      APICAST_CONFIGURATION_CACHE: "15"                                                                                                            
     expose:                                                                                                                                        
       - "8080"                                                                                                                                     
       - "8090"                                                                                                                                     

• Start the gateway

make gateway IMAGE_NAME=quay.io/3scale/apicast:latest 

• Get the gateway's IP

 ▲ lib/3scale/3scale-operator docker inspect \                                                         
  -f '{{range.NetworkSettings.Networks}}{{.IPAddress}}{{end}}' http-proxy-plain-http-upstream-gateway-1

• In another terminal, create k6 script with the following content

import http from 'k6/http';
import { check, sleep } from 'k6';

export const options = {
  stages: [
    { duration: '3m', target: 100 },
    { duration: '6m', target: 200 },
    { duration: '2m', target: 0 },
  ],
  thresholds: {
    http_req_duration: ['p(95)<500'], 
    http_req_failed: ['rate<0.01'], 
  },
};

export function setup() {
  // This runs once for the whole test run, after the init context and before default
  const msg = `[${new Date().toISOString()}] Starting load test`;
  console.log(msg);
}

export default function () {
  const url = 'http://<APICast_gateway_IP>:8080/echo?user_key=<user_key>'
  const params = {
    headers: {
      'Host': '<hostname>'
      'Content-Type': 'application/json',
    },
  };

  const res = http.get(url, params);
  if(res.timings.duration > 1000) {
    const msg = `[${new Date().toISOString()}] Response time above 1s: ${String(res.timings.duration)} ms`;
    console.log(msg);
  }

  check(res, {
    'status 200': (r) => r.status === 200
  });

  sleep(1);
}

Replace:

• APICast_gateway_IP, user_key with value from previous steps

• Visit the admin portal and replace the hostname with the hostname of one product of your choice

• Start k6 test

k6 run --summary-trend-stats="med,p(95),p(99),p(99.9)" script.js 

• Once the test is finish, stop the gateway

CTRL-C

• Checkout this branch and build a new runtime-image

make runtime-image IMAGE_NAME=quay.io/3scale/apicast:reload-patch

• Start the gateway again with new image

make gateway IMAGE_NAME=quay.io/3scale/apicast:reload-patch 

• Start the test again, you should see the delay drop to sub 1s

k6 run --summary-trend-stats="med,p(95),p(99),p(99.9)" script.js