Can you show me the performance improvement?

[WillemJiang]

Can you show me the performance improvement?

[jiuang]

Refer to the Performance Testing Document.
And there is also the latest result:

[jiuang]

And the latest result will be updated later.

[jiuang]

We updated the Performance Testing Document.

[WillemJiang]

Can you show me the jmeter scripts? I cannot tell what kind of invocation are you send to the alpha server.
Did you simulate the saga rollback scenario?

并发为1250是， 在平均耗时降低一个数量级的时候，总耗时还增加了一个数量级， 让我感觉小数点发生的漂移。
于是我做了一个简单的计算，看了一下吞吐率变化不大，假设测量计算没有问题， 那在事务处理量总数不变的情况，并发数越大，总耗时时间越少， 但是这和测量结果不一致。 于是我假设了你们测试是一个并发跑100000个事务， 总事务 = 吞吐* 耗时 = 并发数 * 事务量， 结果发现计算结果发现差了两个数量级，这不由让我怀疑起来这个性能测试的真实性。

[asiroliu]

@WillemJiang
是我的失误导致1250-2000并发的平均耗时和总耗时的数据填反了，现在已更新。感谢你的指正~

以下是我用的jmeter script，使用5台虚拟机采用jmeter分布式的方式制造压力。
每次测试的总事务数为100000
业务端的逻辑，你可以在demo： https://github.com/actiontech/txle/tree/master/examples/sample-txle-springboot 中找到

<jmeterTestPlan version="1.2" properties="5.0" jmeter="5.1.1 r1855137">
  <hashTree>
    <TestPlan guiclass="TestPlanGui" testclass="TestPlan" testname="TXLE_long_hp" enabled="true">
      <stringProp name="TestPlan.comments"></stringProp>
      <boolProp name="TestPlan.functional_mode">false</boolProp>
      <boolProp name="TestPlan.tearDown_on_shutdown">true</boolProp>
      <boolProp name="TestPlan.serialize_threadgroups">false</boolProp>
      <elementProp name="TestPlan.user_defined_variables" elementType="Arguments" guiclass="ArgumentsPanel" testclass="Arguments" testname="User Defined Variables" enabled="true">
        <collectionProp name="Arguments.arguments"/>
      </elementProp>
      <stringProp name="TestPlan.user_define_classpath"></stringProp>
    </TestPlan>
    <hashTree>
      <ThreadGroup guiclass="ThreadGroupGui" testclass="ThreadGroup" testname="HIGH_PERFORMANCE" enabled="true">
        <stringProp name="ThreadGroup.on_sample_error">continue</stringProp>
        <elementProp name="ThreadGroup.main_controller" elementType="LoopController" guiclass="LoopControlPanel" testclass="LoopController" testname="Loop Controller" enabled="true">
          <boolProp name="LoopController.continue_forever">false</boolProp>
          <stringProp name="LoopController.loops">50</stringProp>
        </elementProp>
        <stringProp name="ThreadGroup.num_threads">400</stringProp>
        <stringProp name="ThreadGroup.ramp_time">1</stringProp>
        <boolProp name="ThreadGroup.scheduler">false</boolProp>
        <stringProp name="ThreadGroup.duration">200</stringProp>
        <stringProp name="ThreadGroup.delay"></stringProp>
      </ThreadGroup>
      <hashTree>
        <HTTPSamplerProxy guiclass="HttpTestSampleGui" testclass="HTTPSamplerProxy" testname="HIGH_PERFORMANCE" enabled="true">
          <elementProp name="HTTPsampler.Arguments" elementType="Arguments" guiclass="HTTPArgumentsPanel" testclass="Arguments" testname="User Defined Variables" enabled="true">
            <collectionProp name="Arguments.arguments"/>
          </elementProp>
          <stringProp name="HTTPSampler.domain">10.186.18.127</stringProp>
          <stringProp name="HTTPSampler.port">8000</stringProp>
          <stringProp name="HTTPSampler.protocol">http</stringProp>
          <stringProp name="HTTPSampler.contentEncoding"></stringProp>
          <stringProp name="HTTPSampler.path">/highPerformance</stringProp>
          <stringProp name="HTTPSampler.method">GET</stringProp>
          <boolProp name="HTTPSampler.follow_redirects">true</boolProp>
          <boolProp name="HTTPSampler.auto_redirects">false</boolProp>
          <boolProp name="HTTPSampler.use_keepalive">true</boolProp>
          <boolProp name="HTTPSampler.DO_MULTIPART_POST">false</boolProp>
          <stringProp name="HTTPSampler.embedded_url_re"></stringProp>
          <stringProp name="HTTPSampler.connect_timeout"></stringProp>
          <stringProp name="HTTPSampler.response_timeout"></stringProp>
        </HTTPSamplerProxy>
        <hashTree/>
      </hashTree>
    </hashTree>
  </hashTree>
</jmeterTestPlan>