Server benchmark 2019: Hetzner EX42-NVMe Dedicated Server
- 2019
- Intel® Core™ i7-6700 Quad-Core incl. Hyper-Threading Technology
- 64 GB DDR4 RAM
- 2 x 512 GB NVMe SSD (software-RAID 1)
- Connection 1 Gbit/s-Port
- Guaranteed Bandwidth 1 GBit/s
- Backup Space 100 GB
- Unlimited Traffic
- Debian 10.1 64 bit
- Tests run 2019-09-24
Full test
========================================================================
BYTE UNIX Benchmarks (Version 5.1.3)
System: ******: GNU/Linux
OS: GNU/Linux -- 4.19.0-6-amd64 -- #1 SMP Debian 4.19.67-2 (2019-08-28)
Machine: x86_64 (unknown)
Language: en_US.utf8 (charmap="UTF-8", collate="UTF-8")
CPU 0: Intel(R) Core(TM) i7-6700 CPU @ 3.40GHz (6816.0 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
CPU 1: Intel(R) Core(TM) i7-6700 CPU @ 3.40GHz (6816.0 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
CPU 2: Intel(R) Core(TM) i7-6700 CPU @ 3.40GHz (6816.0 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
CPU 3: Intel(R) Core(TM) i7-6700 CPU @ 3.40GHz (6816.0 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
CPU 4: Intel(R) Core(TM) i7-6700 CPU @ 3.40GHz (6816.0 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
CPU 5: Intel(R) Core(TM) i7-6700 CPU @ 3.40GHz (6816.0 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
CPU 6: Intel(R) Core(TM) i7-6700 CPU @ 3.40GHz (6816.0 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
CPU 7: Intel(R) Core(TM) i7-6700 CPU @ 3.40GHz (6816.0 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
21:20:27 up 17 min, 1 user, load average: 0.12, 0.05, 0.02; runlevel
------------------------------------------------------------------------
Benchmark Run: Tue Sep 24 2019 21:20:27 - 21:48:23
8 CPUs in system; running 1 parallel copy of tests
Dhrystone 2 using register variables 51611568.9 lps (10.0 s, 7 samples)
Double-Precision Whetstone 8023.1 MWIPS (9.0 s, 7 samples)
Execl Throughput 6582.0 lps (29.9 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 805249.5 KBps (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 207208.8 KBps (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 2314506.6 KBps (30.0 s, 2 samples)
Pipe Throughput 1048405.7 lps (10.0 s, 7 samples)
Pipe-based Context Switching 238813.8 lps (10.0 s, 7 samples)
Process Creation 6999.8 lps (30.0 s, 2 samples)
Shell Scripts (1 concurrent) 6698.9 lpm (60.0 s, 2 samples)
Shell Scripts (8 concurrent) 4827.3 lpm (60.1 s, 2 samples)
System Call Overhead 618071.5 lps (10.0 s, 7 samples)
System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 51611568.9 4422.6
Double-Precision Whetstone 55.0 8023.1 1458.7
Execl Throughput 43.0 6582.0 1530.7
File Copy 1024 bufsize 2000 maxblocks 3960.0 805249.5 2033.5
File Copy 256 bufsize 500 maxblocks 1655.0 207208.8 1252.0
File Copy 4096 bufsize 8000 maxblocks 5800.0 2314506.6 3990.5
Pipe Throughput 12440.0 1048405.7 842.8
Pipe-based Context Switching 4000.0 238813.8 597.0
Process Creation 126.0 6999.8 555.5
Shell Scripts (1 concurrent) 42.4 6698.9 1579.9
Shell Scripts (8 concurrent) 6.0 4827.3 8045.4
System Call Overhead 15000.0 618071.5 412.0
========
System Benchmarks Index Score 1515.6
------------------------------------------------------------------------
Benchmark Run: Tue Sep 24 2019 21:48:23 - 22:16:22
8 CPUs in system; running 8 parallel copies of tests
Dhrystone 2 using register variables 274609385.7 lps (10.0 s, 7 samples)
Double-Precision Whetstone 53119.1 MWIPS (9.1 s, 7 samples)
Execl Throughput 31522.3 lps (29.6 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 1347766.8 KBps (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 349278.9 KBps (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 4204030.3 KBps (30.0 s, 2 samples)
Pipe Throughput 5134966.5 lps (10.0 s, 7 samples)
Pipe-based Context Switching 1461778.0 lps (10.0 s, 7 samples)
Process Creation 65984.4 lps (30.0 s, 2 samples)
Shell Scripts (1 concurrent) 53131.9 lpm (60.0 s, 2 samples)
Shell Scripts (8 concurrent) 7974.1 lpm (60.0 s, 2 samples)
System Call Overhead 2906387.3 lps (10.0 s, 7 samples)
System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 274609385.7 23531.2
Double-Precision Whetstone 55.0 53119.1 9658.0
Execl Throughput 43.0 31522.3 7330.8
File Copy 1024 bufsize 2000 maxblocks 3960.0 1347766.8 3403.5
File Copy 256 bufsize 500 maxblocks 1655.0 349278.9 2110.4
File Copy 4096 bufsize 8000 maxblocks 5800.0 4204030.3 7248.3
Pipe Throughput 12440.0 5134966.5 4127.8
Pipe-based Context Switching 4000.0 1461778.0 3654.4
Process Creation 126.0 65984.4 5236.9
Shell Scripts (1 concurrent) 42.4 53131.9 12531.1
Shell Scripts (8 concurrent) 6.0 7974.1 13290.1
System Call Overhead 15000.0 2906387.3 1937.6
========
System Benchmarks Index Score 6007.8
Partial test excluding disk
./Run dhry2reg whetstone-double syscall pipe context1 spawn execl shell1 shell8 shell16
========================================================================
BYTE UNIX Benchmarks (Version 5.1.3)
System: ******: GNU/Linux
OS: GNU/Linux -- 4.19.0-6-amd64 -- #1 SMP Debian 4.19.67-2 (2019-08-28)
Machine: x86_64 (unknown)
Language: en_US.utf8 (charmap="UTF-8", collate="UTF-8")
CPU 0: Intel(R) Core(TM) i7-6700 CPU @ 3.40GHz (6816.0 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
CPU 1: Intel(R) Core(TM) i7-6700 CPU @ 3.40GHz (6816.0 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
CPU 2: Intel(R) Core(TM) i7-6700 CPU @ 3.40GHz (6816.0 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
CPU 3: Intel(R) Core(TM) i7-6700 CPU @ 3.40GHz (6816.0 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
CPU 4: Intel(R) Core(TM) i7-6700 CPU @ 3.40GHz (6816.0 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
CPU 5: Intel(R) Core(TM) i7-6700 CPU @ 3.40GHz (6816.0 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
CPU 6: Intel(R) Core(TM) i7-6700 CPU @ 3.40GHz (6816.0 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
CPU 7: Intel(R) Core(TM) i7-6700 CPU @ 3.40GHz (6816.0 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
22:19:47 up 1:16, 1 user, load average: 1.42, 12.62, 10.63; runlevel
------------------------------------------------------------------------
Benchmark Run: Tue Sep 24 2019 22:19:47 - 22:43:38
8 CPUs in system; running 1 parallel copy of tests
Dhrystone 2 using register variables 51594817.8 lps (10.0 s, 7 samples)
Double-Precision Whetstone 8022.8 MWIPS (9.0 s, 7 samples)
Execl Throughput 6615.8 lps (29.9 s, 2 samples)
Pipe Throughput 1048083.3 lps (10.0 s, 7 samples)
Pipe-based Context Switching 239225.3 lps (10.0 s, 7 samples)
Process Creation 6128.4 lps (30.0 s, 2 samples)
Shell Scripts (1 concurrent) 6691.5 lpm (60.0 s, 2 samples)
Shell Scripts (16 concurrent) 3035.8 lpm (60.1 s, 2 samples)
Shell Scripts (8 concurrent) 4903.6 lpm (60.0 s, 2 samples)
System Call Overhead 618631.5 lps (10.0 s, 7 samples)
System Benchmarks Partial Index BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 51594817.8 4421.1
Double-Precision Whetstone 55.0 8022.8 1458.7
Execl Throughput 43.0 6615.8 1538.6
Pipe Throughput 12440.0 1048083.3 842.5
Pipe-based Context Switching 4000.0 239225.3 598.1
Process Creation 126.0 6128.4 486.4
Shell Scripts (1 concurrent) 42.4 6691.5 1578.2
Shell Scripts (16 concurrent) --- 3035.8 ---
Shell Scripts (8 concurrent) 6.0 4903.6 8172.7
System Call Overhead 15000.0 618631.5 412.4
========
System Benchmarks Index Score (Partial Only) 1329.0
------------------------------------------------------------------------
Benchmark Run: Tue Sep 24 2019 22:43:38 - 23:07:32
8 CPUs in system; running 8 parallel copies of tests
Dhrystone 2 using register variables 276194818.5 lps (10.0 s, 7 samples)
Double-Precision Whetstone 53138.2 MWIPS (9.1 s, 7 samples)
Execl Throughput 31506.4 lps (29.9 s, 2 samples)
Pipe Throughput 5126389.7 lps (10.0 s, 7 samples)
Pipe-based Context Switching 1467891.3 lps (10.0 s, 7 samples)
Process Creation 66514.7 lps (30.0 s, 2 samples)
Shell Scripts (1 concurrent) 53160.3 lpm (60.0 s, 2 samples)
Shell Scripts (16 concurrent) 3997.9 lpm (60.1 s, 2 samples)
Shell Scripts (8 concurrent) 7976.6 lpm (60.0 s, 2 samples)
System Call Overhead 2905927.5 lps (10.0 s, 7 samples)
System Benchmarks Partial Index BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 276194818.5 23667.1
Double-Precision Whetstone 55.0 53138.2 9661.5
Execl Throughput 43.0 31506.4 7327.1
Pipe Throughput 12440.0 5126389.7 4120.9
Pipe-based Context Switching 4000.0 1467891.3 3669.7
Process Creation 126.0 66514.7 5278.9
Shell Scripts (1 concurrent) 42.4 53160.3 12537.8
Shell Scripts (16 concurrent) --- 3997.9 ---
Shell Scripts (8 concurrent) 6.0 7976.6 13294.4
System Call Overhead 15000.0 2905927.5 1937.3
========
System Benchmarks Index Score (Partial Only) 7053.0
Disk tests
disk write without caching
dd if=/dev/zero of=dummytest bs=8k count=128k conv=fdatasync 131072+0 records in 131072+0 records out 1073741824 bytes (1.1 GB, 1.0 GiB) copied, 1.25311 s, 857 MB/s dd if=/dev/zero of=dummytest bs=16k count=64k conv=fdatasync 65536+0 records in 65536+0 records out 1073741824 bytes (1.1 GB, 1.0 GiB) copied, 1.23056 s, 873 MB/s dd if=/dev/zero of=dummytest bs=32k count=32k conv=fdatasync 32768+0 records in 32768+0 records out 1073741824 bytes (1.1 GB, 1.0 GiB) copied, 1.18862 s, 903 MB/s dd if=/dev/zero of=dummytest bs=64k count=16k conv=fdatasync 16384+0 records in 16384+0 records out 1073741824 bytes (1.1 GB, 1.0 GiB) copied, 1.1489 s, 935 MB/s
disk read without caching
hdparm -t /dev/md* Timing buffered disk reads: 6760 MB in 3.00 seconds = 2253.21 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.