1 |
> So with KeepAlive on, the same apache2 process serves the page itself |
2 |
> and all associated files? |
3 |
|
4 |
That's my understanding, but i'm not sure if its what i've read over |
5 |
the years or just assumed. |
6 |
|
7 |
The way I think it worked is; |
8 |
- one apache process running as root, listening on port 80; |
9 |
- once a connection is made to port 80, the root apache process hands |
10 |
the connection off to a user apache process that handles all the |
11 |
action associated with that TCP connection. |
12 |
- so when using persistence, the same user apache process handles all |
13 |
the gets until it hits a client or user imposed limit, when the TCP |
14 |
connection is torn down and re-established. |
15 |
|
16 |
The tear down and re-establishment has a minor cpu cost both ends, and |
17 |
a latency cost, which is exacerbated by TCP slow start. |