This is an old revision of the document!
Test Droplet with no load on CPU
Digital Ocean Sick $5/month droplet
john@mqtt1604testb:~$ sysbench --test=cpu run
sysbench 0.4.12: multi-threaded system evaluation benchmark
Running the test with following options:
Number of threads: 1
Doing CPU performance benchmark
Threads started!
Done.
Maximum prime number checked in CPU test: 10000
Test execution summary:
total time: 524.5674s
total number of events: 10000
total time taken by event execution: 524.0836
per-request statistics:
min: 6.48ms
avg: 52.41ms
max: 613.14ms
approx. 95 percentile: 125.51ms
Threads fairness:
events (avg/stddev): 10000.0000/0.00
execution time (avg/stddev): 524.0836/0.00
Digital Ocean Healthy $5/month droplet
john@mqtt1604C:~/mosBridge$ sysbench --test=cpu run
sysbench 0.4.12: multi-threaded system evaluation benchmark
Running the test with following options:
Number of threads: 1
Doing CPU performance benchmark
Threads started!
Done.
Maximum prime number checked in CPU test: 10000
Test execution summary:
total time: 12.8076s
total number of events: 10000
total time taken by event execution: 12.8054
per-request statistics:
min: 1.20ms
avg: 1.28ms
max: 2.52ms
approx. 95 percentile: 1.37ms
Threads fairness:
events (avg/stddev): 10000.0000/0.00
execution time (avg/stddev): 12.8054/0.00
Note: Jan 5, 2019 healthy $5/month droplet performance (verified on 6 droplets):
- execution time (avg/stddev): 15.3699/0.00
Measure CPU load on all Droplets:
./sshToServer.sh john all “top -bn1 | grep 'Cpu(s)' | sed 's/.*, *\([0-9.]*\)%* id.*/\1/' | awk '{print 100 - \$1}'”
it seems more accurate (or at least lines up better with DO usage stats) if a bit slower to catch the 2nd iteration of top instead of the first:
./sshToServer.sh john all “top -bn2 | grep 'Cpu(s)' | sed 's/.*, *\([0-9.]*\)%* id.*/\1/' | awk '{print 100 - \$1}' | tail -n 1”