I just got myself one of their 256MB “droplets” and started it up running 64bit Ubuntu 12.10.
Here is the sysbench CPU result for that:
[email protected]:/tmp/bench# 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
Maximum prime number checked in CPU test: 10000
Test execution summary:
total time: 15.4407s
total number of events: 10000
total time taken by event execution: 15.4372
approx. 95 percentile: 2.75ms
events (avg/stddev): 10000.0000/0.00
execution time (avg/stddev): 15.4372/0.00
The file IO results:
sysbench --test=fileio --file-total-size=10G prepare
sysbench --test=fileio --file-total-size=10G --file-test-mode=rndrw --init-rng=on --max-time=300 --max-requests=0 ru
[email protected]:/tmp/bench# sysbench --test=fileio --file-total-size=10G --file-test-mode=rndrw --init-rng=on --max-time=300 --max-requests=0 run sysbench 0.4.12: multi-threaded system evaluation benchmark Running the test with following options: Number of threads: 1 Initializing random number generator from timer. Extra file open flags: 0 128 files, 80Mb each 10Gb total file size Block size 16Kb Number of random requests for random IO: 0 Read/Write ratio for combined random IO test: 1.50 Periodic FSYNC enabled, calling fsync() each 100 requests. Calling fsync() at the end of test, Enabled. Using synchronous I/O mode Doing random r/w test Threads started! Time limit exceeded, exiting... Done. Operations performed: 302779 Read, 201852 Write, 645888 Other = 1150519 Total Read 4.62Gb Written 3.08Gb Total transferred 7.7001Gb (26.283Mb/sec) 1682.09 Requests/sec executed Test execution summary: total time: 300.0015s total number of events: 504631 total time taken by event execution: 160.7107 per-request statistics: min: 0.00ms avg: 0.32ms max: 8.96ms approx. 95 percentile: 0.63ms Threads fairness: events (avg/stddev): 504631.0000/0.00 execution time (avg/stddev): 160.7107/0.00
Hoogli Gallery App Running on Digital Ocean 512MB, $5/mo VPS “Droplet” Servers [Update]
I deployed an app on them and so far so good. I have two NodeJS processes, each requiring 900MB+ and a Varnish Cache master/slave process pair, all sharing a 512MB Digital Ocean Droplet VPS which I have given a 8GB swapfile and it seems to be hanging together okay. The key point is that the working set of each process is small (tens of MB) and the SSD saves the day when you would expect to fall into a classic swap thrashing scenario where performance would fall off a cliff when the working set of hot memory pages changes: that doesn’t seem to happen.
- Before (a github forum thread), After (a cool loltastic image gallery with no long boring words to ruin the images 😉 ).
- Before (a 4chan.org thread), After (all the images from that thread, sized close to a one to one pixel mapping, or shrunk to fit if very large).
- Before (A thumbnail gallery strip), After (all the thumbs exploded out to full-size images).
- Before (another thumbnail image gallery), After (The thumbnail image gallery) exploded to the full-sized images.
- Before (one-at-a-time image slideshow), After (the image slideshow opened-out into a scrolling column of full-size images).