Server benchmark 2011: Hetzner VQ 19 VPS

  • 2011
  • Hetzner VQ 19 VPS
  • Single Core
  • 2 GB RAM
  • 80 GB HD on some sort of RAID
  • no backup space
  • 4 TB traffic/mo
  • Debian 6.0 64 bit
  • Tests run 2011-07-26
UnixBench 5.1.2
./Run dhry2reg whetstone-double syscall pipe context1 spawn execl shell1 shell8 shell16

========================================================================
   BYTE UNIX Benchmarks (Version 5.1.2)

   System: Debian-60-squeeze-64-minimal: GNU/Linux
   OS: GNU/Linux -- 2.6.32-5-amd64 -- #1 SMP Tue Jun 14 09:42:28 UTC 2011
   Machine: x86_64 (unknown)
   Language: en_US.utf8 (charmap="UTF-8", collate="UTF-8")
   CPU 0: QEMU Virtual CPU version 0.12.3 (5614.1 bogomips)
          x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
   21:58:33 up 1 min,  1 user,  load average: 0.37, 0.10, 0.03; runlevel 2

------------------------------------------------------------------------
Benchmark Run: Tue Jul 26 2011 21:58:33 - 22:22:39
1 CPU in system; running 1 parallel copy of tests

Dhrystone 2 using register variables       24231683.1 lps   (10.0 s, 7 samples)
Double-Precision Whetstone                     3385.5 MWIPS (9.7 s, 7 samples)
Execl Throughput                               4053.9 lps   (29.8 s, 2 samples)
Pipe Throughput                             2070396.2 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                 388304.2 lps   (10.0 s, 7 samples)
Process Creation                              14303.5 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                   5484.8 lpm   (60.0 s, 2 samples)
Shell Scripts (16 concurrent)                   401.0 lpm   (60.1 s, 2 samples)
Shell Scripts (8 concurrent)                    848.0 lpm   (60.1 s, 2 samples)
System Call Overhead                        4054643.4 lps   (10.0 s, 7 samples)

System Benchmarks Partial Index              BASELINE       RESULT    INDEX
Dhrystone 2 using register variables         116700.0   24231683.1   2076.4
Double-Precision Whetstone                       55.0       3385.5    615.5
Execl Throughput                                 43.0       4053.9    942.8
Pipe Throughput                               12440.0    2070396.2   1664.3
Pipe-based Context Switching                   4000.0     388304.2    970.8
Process Creation                                126.0      14303.5   1135.2
Shell Scripts (1 concurrent)                     42.4       5484.8   1293.6
Shell Scripts (16 concurrent)                     ---        401.0      ---
Shell Scripts (8 concurrent)                      6.0        848.0   1413.4
System Call Overhead                          15000.0    4054643.4   2703.1
                                                                   ========
System Benchmarks Index Score (Partial Only)                         1304.3

the best of three subsequent test runs of

dd if=/dev/zero of=test bs=64k count=16k conv=fdatasync
1073741824 bytes (1.1 GB) copied, 30.9888 s, 34.6 MB/s

the best of three subsequent test runs of

hdparm -t dev
Timing buffered disk reads: 606 MB in  3.01 seconds = 201.37 MB/sec

Disclaimer: based on my experience disk performance testing with dd and hdparm are crude methods. The real-life disk load of a web service cannot be emulated with dd or hdparm.