英文:
Calculating the RAM required for Apache to respond to a large number of requests
问题
我想调查当Apache处于负载状态时，单个进程消耗多少RAM。并且我需要知道可以响应10,000个并发的HTTP请求而没有延迟的RAM量。
我正在使用以下版本的Apache：
httpd -VServer version: Apache/2.4.37 (Red Hat Enterprise Linux)Server built: Jun 15 2022 08:27:14Server's Module Magic Number: xxxxxxxx:xxServer loaded: APR 1.6.3, APR-UTIL 1.6.1Compiled using: APR 1.6.3, APR-UTIL 1.6.1Architecture: 64-bitServer MPM: eventthreaded: yes (fixed thread count)forked: yes (variable process count)
我有以下设置：
<IfModule mpm_event_module>StartServers 3ServerLimit 3ThreadsPerChild 25MaxRequestWorkers 75</IfModule>
根据上述设置，我预期会有4个进程（1个父进程+3个子进程）。
但出于某种原因，父进程1和子进程5启动。
ps -ylC httpdS UID PID PPID C PRI NI RSS SZ WCHAN TTY TIME CMDS 0 877361 1 1 80 0 62512 85183 - ? 00:00:00 httpd # 父进程S 48 877362 877361 0 80 0 56156 88418 - ? 00:00:00 httpd # 子进程1S 48 877363 877361 0 80 0 56228 88762 - ? 00:00:00 httpd # 子进程2S 48 877364 877361 0 80 0 66152 713989 - ? 00:00:00 httpd # 子进程3S 48 877365 877361 0 80 0 64104 648435 - ? 00:00:00 httpd # 子进程4S 48 877366 877361 0 80 0 64104 664819 - ? 00:00:00 httpd # 子进程5
当发送大量HTTP请求并施加负载时，只有子进程3、4和5的RSS增加。
ps -ylC httpdS UID PID PPID C PRI NI RSS SZ WCHAN TTY TIME CMDS 0 877361 1 0 80 0 62512 85183 - ? 00:00:00 httpd # 父进程S 48 877362 877361 0 80 0 56164 88418 - ? 00:00:00 httpd # 子进程1S 48 877363 877361 0 80 0 56236 88762 - ? 00:00:00 httpd # 子进程2S 48 877364 877361 0 80 0 86996 713989 - ? 00:00:02 httpd # 子进程3：RSS增加S 48 877365 877361 0 80 0 83868 648435 - ? 00:00:02 httpd # 子进程4：RSS增加S 48 877366 877361 0 80 0 85908 664819 - ? 00:00:02 httpd # 子进程5：RSS增加
Child1和Child2进程在做什么？
Child3、4和5的平均RSS：（86996KB+83868KB+85908KB）/ 3 ≈ 85MB
从上面的信息来看，当因大量访问而负载较高时，每个进程会使用25个线程进行处理，此时每个进程会消耗85MB。
10000/25*85MB = 34GB
这是否意味着我需要大约34GB的RAM才能在没有延迟的情况下响应10,000个并发请求？
（当然，这不是严格的，但一个粗略的值是可以的。并且假设内存是瓶颈，流量、RDBMS和其他资源如CPU都足够。）
提前感谢您。
英文:
I want to investigate how much RAM a single process consumes when apahce is under load.
And I need to know the amount of RAM that can respond to 10,000 concurrent HTTP requests without delay.
I am using the following versions of Apache:
httpd -VServer version: Apache/2.4.37 (Red Hat Enterprise Linux)Server built: Jun 15 2022 08:27:14Server's Module Magic Number: xxxxxxxx:xxServer loaded: APR 1.6.3, APR-UTIL 1.6.1Compiled using: APR 1.6.3, APR-UTIL 1.6.1Architecture: 64-bitServer MPM: eventthreaded: yes (fixed thread count)forked: yes (variable process count)
I have the following settings:
<IfModule mpm_event_module>StartServers 3ServerLimit 3ThreadsPerChild 25MaxRequestWorkers 75</IfModule>
With the above settings, I expect 4 processes (1 parent + 3 child).
But for some reason parent process 1 + child process 5 start.
ps -ylC httpdS UID PID PPID C PRI NI RSS SZ WCHAN TTY TIME CMDS 0 877361 1 1 80 0 62512 85183 - ? 00:00:00 httpd # ParentS 48 877362 877361 0 80 0 56156 88418 - ? 00:00:00 httpd # Child1S 48 877363 877361 0 80 0 56228 88762 - ? 00:00:00 httpd # Child2S 48 877364 877361 0 80 0 66152 713989 - ? 00:00:00 httpd # Child3S 48 877365 877361 0 80 0 64104 648435 - ? 00:00:00 httpd # Child4S 48 877366 877361 0 80 0 64104 664819 - ? 00:00:00 httpd # Child5
When a large number of Http requests are sent and load is applied, only Child3, 4, 5 RSS increases.
ps -ylC httpdS UID PID PPID C PRI NI RSS SZ WCHAN TTY TIME CMDS 0 877361 1 0 80 0 62512 85183 - ? 00:00:00 httpd # ParentS 48 877362 877361 0 80 0 56164 88418 - ? 00:00:00 httpd # Child1S 48 877363 877361 0 80 0 56236 88762 - ? 00:00:00 httpd # Child2S 48 877364 877361 0 80 0 86996 713989 - ? 00:00:02 httpd # Child3 : RSS increasedS 48 877365 877361 0 80 0 83868 648435 - ? 00:00:02 httpd # Child4 : RSS increasedS 48 877366 877361 0 80 0 85908 664819 - ? 00:00:02 httpd # Child5 : RSS increased
What are the Child1 and Child2 processes doing?
Child3,4,5 RSS average: (86996KB+83868KB+85908KB)/3≒85MB
From the above, when the load is high due to a large number of accesses at once, processing is performed with 25 threads per process, and 85 MB is consumed per process at that time.
10000/25*85MB=34GB
Does that mean I need roughly 34GB of RAM to respond to 10000 concurrent requests without delay?
(Of course, it's not strict, but a rough value is OK.And assume that memory is the bottleneck and traffic, RDBMS, and other resources like CPU are all sufficient.)
Thanks in advance.
- reference : <https://stackoverflow.com/questions/18317735/how-to-know-the-number-of-core-and-ram-required>
答案1
得分: 0
以下网站已经让我确信我走在正确的道路上。
<https://kb.vmware.com/s/article/1036729>
> 例子：假设你使用 worker，设置了 ThreadsPerChild 为 25 和 MaxClients 为 50，而两个子进程在满负荷下分别使用 128MB 的 RAM 和 5% 的 CPU。你大致可以期望 8 个子进程（MaxClients 200 = 25 x 8）在满负荷下使用 1GB 的 RAM 和 40% 的 CPU。
英文:
The following website has convinced me that I am on the right track.
<https://kb.vmware.com/s/article/1036729>
> Example: Suppose using worker you have set ThreadsPerChild 25 and MaxClients 50, and the two child processes each use 128MB of RAM and 5% of CPU under full load. You can roughly expect 8 children (MaxClients 200 = 25 x 8) to use 1GB of RAM and 40% of CPU under full load.
通过集体智慧和协作来改善编程学习和解决问题的方式。致力于成为全球开发者共同参与的知识库，让每个人都能够通过互相帮助和分享经验来进步。
评论