-
-
Save denen99/2258857 to your computer and use it in GitHub Desktop.
This is against the sample route_match_example.rb vertx.io vertical in a single instance on my macbook air (Quad Core, 4GB Ram) | |
# httperf --server=localhost --port=8080 --uri=/ --num-conns=100 --num-calls=100 | |
httperf --client=0/1 --server=localhost --port=8080 --uri=/ --send-buffer=4096 --recv-buffer=16384 --num-conns=100 --num-calls=100 | |
httperf: warning: open file limit > FD_SETSIZE; limiting max. # of open files to FD_SETSIZE | |
Maximum connect burst length: 1 | |
Total: connections 100 requests 10000 replies 10000 test-duration 1.420 s | |
Connection rate: 70.4 conn/s (14.2 ms/conn, <=1 concurrent connections) | |
Connection time [ms]: min 12.8 avg 14.2 max 18.4 median 14.5 stddev 0.9 | |
Connection time [ms]: connect 0.1 | |
Connection length [replies/conn]: 100.000 | |
Request rate: 7041.6 req/s (0.1 ms/req) | |
Request size [B]: 62.0 | |
Reply rate [replies/s]: min 0.0 avg 0.0 max 0.0 stddev 0.0 (0 samples) | |
Reply time [ms]: response 0.1 transfer 0.0 | |
Reply size [B]: header 39.0 content 78.0 footer 0.0 (total 117.0) | |
Reply status: 1xx=0 2xx=10000 3xx=0 4xx=0 5xx=0 | |
CPU time [s]: user 0.22 system 1.20 (user 15.1% system 84.4% total 99.5%) | |
Net I/O: 1230.9 KB/s (10.1*10^6 bps) | |
Errors: total 0 client-timo 0 socket-timo 0 connrefused 0 connreset 0 | |
Errors: fd-unavail 0 addrunavail 0 ftab-full 0 other 0 |
./vertx run route_match_example.rb -instances 4
now getting 10,000 req/sec
bash-3.2# httperf --client=0/1 --server=localhost --port=8080 --uri=/ --num-conns=100 --num-calls=100
httperf --client=0/1 --server=localhost --port=8080 --uri=/ --send-buffer=4096 --recv-buffer=16384 --num-conns=100 --num-calls=100
httperf: warning: open file limit > FD_SETSIZE; limiting max. # of open files to FD_SETSIZE
Maximum connect burst length: 1
Total: connections 100 requests 10000 replies 10000 test-duration 0.954 s
Connection rate: 104.8 conn/s (9.5 ms/conn, <=1 concurrent connections)
Connection time [ms]: min 8.0 avg 9.5 max 13.6 median 9.5 stddev 1.0
Connection time [ms]: connect 0.1
Connection length [replies/conn]: 100.000
Request rate: 10479.0 req/s (0.1 ms/req)
Request size [B]: 62.0
Reply rate [replies/s]: min 0.0 avg 0.0 max 0.0 stddev 0.0 (0 samples)
Reply time [ms]: response 0.1 transfer 0.0
Reply size [B]: header 39.0 content 12.0 footer 0.0 (total 51.0)
Reply status: 1xx=0 2xx=10000 3xx=0 4xx=0 5xx=0
CPU time [s]: user 0.15 system 0.80 (user 15.8% system 83.3% total 99.2%)
Net I/O: 1156.4 KB/s (9.5*10^6 bps)
Errors: total 0 client-timo 0 socket-timo 0 connrefused 0
Cool :)
I did a little test a couple of weeks ago on my desktop, and managed to get around 70k req/s with a simple page. This was with my own test client not httperf - not sure if httperf does pipelining well.
up to 21k :-)
httperf --client=0/1 --server=localhost --port=8080 --uri=/ --burst-len=50 --num-calls=100 --num-conns=100
httperf --client=0/1 --server=localhost --port=8080 --uri=/ --send-buffer=4096 --recv-buffer=16384 --num-conns=100 --num-calls=100 --burst-length=50
httperf: warning: open file limit > FD_SETSIZE; limiting max. # of open files to FD_SETSIZE
Maximum connect burst length: 1
Total: connections 100 requests 10000 replies 10000 test-duration 0.492 s
Connection rate: 203.4 conn/s (4.9 ms/conn, <=1 concurrent connections)
Connection time [ms]: min 3.6 avg 4.9 max 8.5 median 4.5 stddev 0.9
Connection time [ms]: connect 0.1
Connection length [replies/conn]: 100.000
Request rate: 20344.2 req/s (0.0 ms/req)
Request size [B]: 62.0
Reply rate [replies/s]: min 0.0 avg 0.0 max 0.0 stddev 0.0 (0 samples)
Reply time [ms]: response 1.3 transfer 0.0
Reply size [B]: header 39.0 content 12.0 footer 0.0 (total 51.0)
Reply status: 1xx=0 2xx=10000 3xx=0 4xx=0 5xx=0
CPU time [s]: user 0.08 system 0.41 (user 16.4% system 83.1% total 99.4%)
Net I/O: 2245.0 KB/s (18.4*10^6 bps)
Errors: total 0 client-timo 0 socket-timo 0 connrefused 0 connreset 0
Errors: fd-unavail 0 addrunavail 0 ftab-full 0 other 0
How are you running the server? (can you paste the command line?)