JBoss：32 位与 64 位性能差异？
我知道这是一个相当模糊的问题，但我希望得到一些关于在哪里查看的想法，因为这对我来说有点令人困惑。
我有一个 Web 应用程序，可以计算一些值并将其返回给客户端（EJB 远程调用）。当我从 main() 测试循环调用 localhost 10 次时，它会在大约 100 毫秒内返回。当我按照相同的流程调用 DEV 机器时，它有时很快，有时很慢，比如 4 秒，这是一个巨大的差异。
奇怪的是，我的本地主机是 32 位 1GB Jboss 配置，但我的 DEV 机器是 64 位 6GB Jboss 配置，所以如果有的话，我希望我的本地主机挂起......而不是 DEV 机器。
您建议从哪里开始故障排除过程？
I know that it is a pretty vague question but I was hoping to get some ideas about where to look as it is a little puzzling to me.
I have a web app that computes some value and returns it to the client (EJB remote calls). When I call my localhost from a main() test looping 10 times, it comes back within about 100 milliseconds. When I call the DEV machine following the same process, it is sometimes fast and sometimes really slow, like 4 seconds, which is a huge difference.
The weird thing is that my localhost is a 32 bit 1GB Jboss config but my DEV machine is a 64 bit 6GB Jboss config so if anything, I would expect my localhost to hang... not the the DEV machine.
Where would you suggest starting the troubleshooting process?
如果你对这篇内容有疑问，欢迎到本站社区发帖提问 参与讨论，获取更多帮助，或者扫码二维码加入 Web 技术交流群。
绑定邮箱获取回复消息
由于您还没有绑定你的真实邮箱，如果其他用户或者作者回复了您的评论，将不能在第一时间通知您！
发布评论
评论（3）
如果我没理解错的话，这两个电话都是从同一台计算机上拨打的吗？如果是这种情况，则与 32 位和 64 位相比，网络之间的响应时间差异更有可能产生。
如果情况并非如此，则监视开发并检查“快速”和“4 秒”情况之间的上下文（其他应用程序等）有什么区别。无论如何，响应时间的差异很可能与 32 位/64 位之间的差异无关。
If I understood right, both calls are made from same computer? If that is the case, network between is much more likely source for response time differences than 32 vs. 64 bit.
If that is not the case, then monitor dev and check what is the difference in context (other applications etc.) between "fast" and "4 seconds" cases. Anyway, most likely difference in response times have nothing to with difference between 32 bit / 64 bit.
前一段时间，我开发了一个应用程序，该应用程序部署在两台硬件配置完全相同的服务器上的 JBoss 上。第一个服务器安装了 CentOS，第二个服务器安装了 FreeBSD。完全相同的硬件、相同的网络、相似的负载。根据我的观察，应用程序在 FreeBSD 上运行时的响应速度大约快 1.5 - 2 倍。乍一看，这对我来说很奇怪，但经过一周的测试，响应时间的差异得到了证实。
从那时起，我并不认为硬件配置像我之前想象的那么重要;)
Some time ago I worked on application which was deployed on JBoss on two servers with exactly the same hardware configuration. The first server had CentOS and the second FreeBSD. Exactly the same hardware, the same network, similar load. From what I observed, application responses when it was running on FreeBSD was about 1.5 - 2 times faster. On the first sight, it was strange for me, but after week of tests differences in response times was confirmed.
Since that time I do not consider hardware configuration as so important as I thought before ;)
我们发现 Linux 计算机上的安装实际上在虚拟机上运行了两个不同的 JBoss 实例，因此导致了不可预测的行为，因此解决了该问题。消耗的资源是巨大的，这对于部署的应用程序来说没有任何意义......
We resolved the issue after finding out that the install on the linux machine actually had two different instances of JBoss running on the VM therefore resulting in unpredictable behavior. The resources that were consumed were enormous, which did not make any sense based on the app that was deployed...