|
I'm running a load balancer with ipvsadm with 10 lighttpd servers.
Serving more than 6 million pages per day.
Sometimes i have 3 (or 9) seconds of delay load balancer is serving pages.
If i request a page directly to the lighttpd server, i haven't any problem.
but if i request using load balancer sometimes i have exactly 3 seconds
of delay
example:
Direct request to a server:
_________________________________________________________
ab -n10000 -c100 192.168.20.147/img/logo.gif
Document Path: /img/logo.gif
Document Length: 3303 bytes
Concurrency Level: 100
Time taken for tests: 0.43075 seconds
Complete requests: 1000
Failed requests: 0
Write errors: 0
Total transferred: 3590486 bytes
HTML transferred: 3362454 bytes
Requests per second: 23215.32 [#/sec] (mean)
Time per request: 4.307 [ms] (mean)
Time per request: 0.043 [ms] (mean, across all concurrent requests)
Transfer rate: 81392.92 [Kbytes/sec] received
Connection Times (ms)
min mean[+/-sd] median max
Connect: 0 1 0.2 1 2
Processing: 1 2 1.0 3 7
Waiting: 0 1 0.6 1 5
Total: 2 3 1.0 4 8
WARNING: The median and mean for the processing time are not within a
normal deviation
These results are probably not that reliable.
WARNING: The median and mean for the total time are not within a normal
deviation
These results are probably not that reliable.
Percentage of the requests served within a certain time (ms)
50% 4
66% 4
75% 4
80% 4
90% 4
95% 4
98% 5
99% 7
100% 8 (longest request)
_________________________________________________________
Using load balancer:
http://x.x.x.x:3147/img/logo.gif
Percentage of the requests served within a certain time (ms)
50% 4
66% 4
75% 4
80% 4
90% 4
95% 7
98% 3025
99% 3017
100% 3038 (longest request)
_________________________________________________________
Using debian etch 2.6.19 with default configuration of kernel.
Any idea?
Best regards
|
