So you have purchased a new VPS (whether it is with Binary Lane or another provider), logged in with SSH and are now staring at your root shell. For many of us, the first question that comes to mind is How fast is my server?; followed quickly by How do I measure its performance?

In this article I will look at some specific methods of measuring the disk performance of your VPS.

What not to do

Chances are, you have seen this test before; perhaps even used it yourself. It is the obligatory dd test - here is one popular variety:

dd if=/dev/zero of=test bs=64k count=16k conv=fdatasync

This test is popular because dd is pre-installed on almost all Linux servers. While it is a simple way of seeing if something is broken (for example, if you see 10MB/sec than your server is overloaded) it has a number of problems:

• This is a single-threaded, sequential-write test. If you are running the typical web+database server on your VPS, the number is meaningless because typical services do not do long-running sequential writes.
• The amount of data written (1GB) is small; and hence can be strongly influenced by caching on the host server, or the host's RAID controller. (The conv=fdatasync only applies to the VPS, not the host).
• It executes for a very short period of time; just a few seconds on faster I/O subsystems. This isn't enough to get a consistant result.
• There's no read performance testing at all.

Measuring random IOPS with FIO

cd /root
yum install -y make gcc libaio-devel || ( apt-get update && apt-get install -y make gcc libaio-dev  </dev/null )
wget https://github.com/Crowd9/Benchmark/raw/master/fio-2.0.9.tar.gz ; tar xf fio*
cd fio*
make

./fio --randrepeat=1 --ioengine=libaio --direct=1 --gtod_reduce=1 --name=test --filename=test --bs=4k --iodepth=64 --size=4G --readwrite=randrw --rwmixread=75

Jobs: 1 (f=1): [m] [65.4% done] [161.5M/55417K /s] [41.4K/13.9K iops] [eta 00m:09s]

To measure random reads, use slightly altered FIO command:

./fio --randrepeat=1 --ioengine=libaio --direct=1 --gtod_reduce=1 --name=test --filename=test --bs=4k --iodepth=64 --size=4G --readwrite=randread

Again, we pull the iops from the result:

fio-2.0.9

Starting 1 process

Jobs: 1 (f=1): [r] [100.0% done] [336.5M/0K /s] [86.2K/0  iops] [eta 00m:00s]

test: (groupid=0, jobs=1): err= 0: pid=32172: Wed Mar 13 16:11:11 2019

  read : io=4096.0MB, bw=342980KB/s, iops=85745 , runt= 12229msec

  cpu          : usr=21.43%, sys=76.05%, ctx=5387, majf=0, minf=68

  IO depths    : 1=0.1%, 2=0.1%, 4=0.1%, 8=0.1%, 16=0.1%, 32=0.1%, >=64=100.0%

     submit    : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=0.0%, >=64=0.0%

     complete  : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=0.1%, >=64=0.0%

     issued    : total=r=1048576/w=0/d=0, short=r=0/w=0/d=0

Run status group 0 (all jobs):

   READ: io=4096.0MB, aggrb=342980KB/s, minb=342980KB/s, maxb=342980KB/s, mint=12229msec, maxt=12229msec

Disk stats (read/write):

  vda: ios=1043901/20, merge=0/11, ticks=166560/4, in_queue=159628, util=96.92%

This tests shows Binary Lane's storage scoring 85745 read operations per second, a typical result for SATA SSD.  This is higher than our mixed read/write result because writes are not being performed, freeing up disk resources to execute the reads being tested.

Random write performance

./fio --randrepeat=1 --ioengine=libaio --direct=1 --gtod_reduce=1 --name=test --filename=test --bs=4k --iodepth=64 --size=4G --readwrite=randwrite

cd /root
yum install -y make gcc libaio-devel || ( apt-get update && apt-get install -y make gcc libaio-dev  </dev/null )
wget https://ioping.googlecode.com/files/ioping-0.6.tar.gz ; tar xf ioping*
cd ioping*
make

./ioping -c 10 .

I hope this article has added a few more tools to your toolbelt and if nothing else, helped to dispell the idea that dd should be used for benchmarking.