UnixBench Archives - David Yin's Blog

VPS performance benchmark – Vultr Intel High Fequency

David Yin — Wed, 18 May 2022 19:29:32 +0000

It is a brand new VPS, just created on Vultr.com yesterday. It is a High-Frequency CPU, Intel Xeon with NVMe SSD, 1vCPU, 1GB memory, 32GB NVMe storage, including 1TB transfer.

The monthly cost of this VPS is $6.

I just change the TCP Congestion Control Algorithms to BBR.

Yet-Another-Bench-Script (YABS)

It includes three parts.

Disk Speed tests – fio;
iperf3 Network speed test IPv4 and IPv6;
Geekbench 4 test.

root@Hemlock:~# curl -sL yabs.sh | bash -s -- -4
# ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## #
# Yet-Another-Bench-Script #
# v2022-05-06 #
# https://github.com/masonr/yet-another-bench-script #
# ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## #

Wed May 18 07:13:10 AM UTC 2022

Basic System Information:
---------------------------------
Uptime : 0 days, 0 hours, 7 minutes
Processor : Intel Core Processor (Skylake, IBRS)
CPU cores : 1 @ 3695.996 MHz
AES-NI : ✔ Enabled
VM-x/AMD-V : ❌ Disabled
RAM : 971.1 MiB
Swap : 3.1 GiB
Disk : 31.4 GiB
Distro : Ubuntu 22.04 LTS
Kernel : 5.15.0-30-generic

fio Disk Speed Tests (Mixed R/W 50/50):
---------------------------------
Block Size | 4k (IOPS) | 64k (IOPS)
------ | --- ---- | ---- ----
Read | 401.53 MB/s (100.3k) | 617.73 MB/s (9.6k)
Write | 402.59 MB/s (100.6k) | 620.98 MB/s (9.7k)
Total | 804.12 MB/s (201.0k) | 1.23 GB/s (19.3k)
| |
Block Size | 512k (IOPS) | 1m (IOPS)
------ | --- ---- | ---- ----
Read | 673.55 MB/s (1.3k) | 701.05 MB/s (684)
Write | 709.33 MB/s (1.3k) | 747.74 MB/s (730)
Total | 1.38 GB/s (2.7k) | 1.44 GB/s (1.4k)

iperf3 Network Speed Tests (IPv4):
---------------------------------
Provider | Location (Link) | Send Speed | Recv Speed
| | |
Clouvider | London, UK (10G) | 1.32 Gbits/sec | 185 Mbits/sec
Online.net | Paris, FR (10G) | 1.90 Gbits/sec | 2.59 Gbits/sec
Hybula | The Netherlands (40G) | 1.23 Gbits/sec | 1.42 Gbits/sec
Clouvider | NYC, NY, US (10G) | 3.05 Gbits/sec | 1.69 Gbits/sec
Velocity Online | Tallahassee, FL, US (10G) | 4.09 Gbits/sec | 3.73 Gbits/sec
Clouvider | Los Angeles, CA, US (10G) | 3.61 Gbits/sec | 3.03 Gbits/sec

iperf3 Network Speed Tests (IPv6):
---------------------------------
Provider | Location (Link) | Send Speed | Recv Speed
| | |
Clouvider | London, UK (10G) | 1.31 Gbits/sec | 609 Mbits/sec
Online.net | Paris, FR (10G) | 1.35 Gbits/sec | 2.25 Gbits/sec
Hybula | The Netherlands (40G) | 1.26 Gbits/sec | 1.37 Gbits/sec
Clouvider | NYC, NY, US (10G) | 3.04 Gbits/sec | 1.47 Gbits/sec
Clouvider | Los Angeles, CA, US (10G) | 7.67 Gbits/sec | 4.15 Gbits/sec

Geekbench 4 Benchmark Test:
---------------------------------
Test | Value
|
Single Core | 5759
Multi Core | 5587
Full Test | https://browser.geekbench.com/v4/cpu/16554174

Bench.sh

It has following testing portions.

I/O test
Network Speed test

wget -qO- bench.sh | bash

-------------------- A Bench.sh Script By Teddysun -------------------
Version : v2022-02-22
Usage : wget -qO- bench.sh | bash
----------------------------------------------------------------------
CPU Model : Intel Core Processor (Skylake, IBRS)
CPU Cores : 1 @ 3695.996 MHz
CPU Cache : 16384 KB
AES-NI : Enabled
VM-x/AMD-V : Disabled
Total Disk : 31.4 GB (8.7 GB Used)
Total Mem : 971.2 MB (162.2 MB Used)
Total Swap : 3.1 GB (0 Used)
System uptime : 0 days, 0 hour 15 min
Load average : 0.11, 0.17, 0.08
OS : Ubuntu 22.04 LTS
Arch : x86_64 (64 Bit)
Kernel : 5.15.0-30-generic
TCP CC : bbr
Virtualization : KVM
Organization : AS20473 The Constant Company, LLC
Location : San Jose / US
Region : California
----------------------------------------------------------------------
I/O Speed(1st run) : 1.1 GB/s
I/O Speed(2nd run) : 1.1 GB/s
I/O Speed(3rd run) : 1.1 GB/s
I/O Speed(average) : 1126.4 MB/s
----------------------------------------------------------------------
Node Name Upload Speed Download Speed Latency
Speedtest.net 3224.41 Mbps 4988.86 Mbps 0.70 ms
Los Angeles, US 5571.45 Mbps 5136.65 Mbps 9.11 ms
Dallas, US 2303.21 Mbps 6641.83 Mbps 37.06 ms
Montreal, CA 587.18 Mbps 935.36 Mbps 76.01 ms
Paris, FR 1047.59 Mbps 1792.98 Mbps 160.88 ms
Amsterdam, NL 609.99 Mbps 4889.86 Mbps 141.00 ms
Shanghai, CN 1710.91 Mbps 2161.45 Mbps 132.80 ms
Nanjing, CN 537.43 Mbps 4011.27 Mbps 146.25 ms
Guangzhou, CN 3.95 Mbps 18.67 Mbps 393.72 ms
Hongkong, CN 1118.23 Mbps 2177.47 Mbps 158.45 ms
Seoul, KR 609.97 Mbps 845.70 Mbps 132.52 ms
Singapore, SG 487.68 Mbps 1564.76 Mbps 172.04 ms
Tokyo, JP 595.09 Mbps 7219.81 Mbps 152.04 ms
----------------------------------------------------------------------
Finished in : 6 min 38 sec
Timestamp : 2022-05-18 07:28:25 UTC
----------------------------------------------------------------------

UnixBench

First I need to clone the project, then install the build-essential software, build the software. At last run the test.

root@Hemlock:~/byte-unixbench/UnixBench# ./Run
make all
make[1]: Entering directory '/root/byte-unixbench/UnixBench'
make distr
make[2]: Entering directory '/root/byte-unixbench/UnixBench'
Checking distribution of files
./pgms exists
./src exists
./testdir exists
./tmp exists
./results exists
make[2]: Leaving directory '/root/byte-unixbench/UnixBench'
make programs
make[2]: Entering directory '/root/byte-unixbench/UnixBench'
make[2]: Nothing to be done for 'programs'.
make[2]: Leaving directory '/root/byte-unixbench/UnixBench'
make[1]: Leaving directory '/root/byte-unixbench/UnixBench'
sh: 1: 3dinfo: not found

# # # # # # # ##### ###### # # #### # #
# # ## # # # # # # # ## # # # # #
# # # # # # ## ##### ##### # # # # ######
# # # # # # ## # # # # # # # # #
# # # ## # # # # # # # ## # # # #
#### # # # # # ##### ###### # # #### # #

Version 5.1.3 Based on the Byte Magazine Unix Benchmark

Multi-CPU version Version 5 revisions by Ian Smith,
Sunnyvale, CA, USA
January 13, 2011 johantheghost at yahoo period com

------------------------------------------------------------------------------
Use directories for:
* File I/O tests (named fs***) = /root/byte-unixbench/UnixBench/tmp
* Results = /root/byte-unixbench/UnixBench/results
------------------------------------------------------------------------------

1 x Dhrystone 2 using register variables 1 2 3 4 5 6 7 8 9 10

1 x Double-Precision Whetstone 1 2 3 4 5 6 7 8 9 10

1 x Execl Throughput 1 2 3

1 x File Copy 1024 bufsize 2000 maxblocks 1 2 3

1 x File Copy 256 bufsize 500 maxblocks 1 2 3

1 x File Copy 4096 bufsize 8000 maxblocks 1 2 3

1 x Pipe Throughput 1 2 3 4 5 6 7 8 9 10

1 x Pipe-based Context Switching 1 2 3 4 5 6 7 8 9 10

1 x Process Creation 1 2 3

1 x System Call Overhead 1 2 3 4 5 6 7 8 9 10

1 x Shell Scripts (1 concurrent) 1 2 3

1 x Shell Scripts (8 concurrent) 1 2 3

========================================================================
BYTE UNIX Benchmarks (Version 5.1.3)

System: Hemlock: GNU/Linux
OS: GNU/Linux -- 5.15.0-30-generic -- #31-Ubuntu SMP Thu May 5 10:00:34 UTC 2022
Machine: x86_64 (x86_64)
Language: en_US.utf8 (charmap="UTF-8", collate="UTF-8")
CPU 0: Intel Core Processor (Skylake, IBRS) (7392.0 bogomips)
x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
07:33:01 up 26 min, 1 user, load average: 0.07, 0.12, 0.13; runlevel 2022-05-18

------------------------------------------------------------------------
Benchmark Run: Wed May 18 2022 07:33:01 - 08:00:58
1 CPU in system; running 1 parallel copy of tests

Dhrystone 2 using register variables 57357517.0 lps (10.0 s, 7 samples)
Double-Precision Whetstone 9990.2 MWIPS (9.9 s, 7 samples)
Execl Throughput 4454.9 lps (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 882803.5 KBps (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 238186.9 KBps (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 2552321.6 KBps (30.0 s, 2 samples)
Pipe Throughput 1172961.8 lps (10.0 s, 7 samples)
Pipe-based Context Switching 256970.7 lps (10.0 s, 7 samples)
Process Creation 12920.8 lps (30.0 s, 2 samples)
Shell Scripts (1 concurrent) 11114.5 lpm (60.0 s, 2 samples)
Shell Scripts (8 concurrent) 1426.6 lpm (60.0 s, 2 samples)
System Call Overhead 628650.1 lps (10.0 s, 7 samples)

System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 57357517.0 4915.0
Double-Precision Whetstone 55.0 9990.2 1816.4
Execl Throughput 43.0 4454.9 1036.0
File Copy 1024 bufsize 2000 maxblocks 3960.0 882803.5 2229.3
File Copy 256 bufsize 500 maxblocks 1655.0 238186.9 1439.2
File Copy 4096 bufsize 8000 maxblocks 5800.0 2552321.6 4400.6
Pipe Throughput 12440.0 1172961.8 942.9
Pipe-based Context Switching 4000.0 256970.7 642.4
Process Creation 126.0 12920.8 1025.5
Shell Scripts (1 concurrent) 42.4 11114.5 2621.3
Shell Scripts (8 concurrent) 6.0 1426.6 2377.7
System Call Overhead 15000.0 628650.1 419.1
========
System Benchmarks Index Score 1562.6

The post VPS performance benchmark – Vultr Intel High Fequency appeared first on David Yin's Blog.

UnixBench test result on Raspberry Pi

David Yin — Fri, 28 Aug 2015 16:35:55 +0000

Yes, it is the Raspberry Pi I mentioned yesterday.

I let it on more than eight hours, then I start to run the UnixBench test.

Look at the result:

#    #  #    #  #  #    #          #####   ######  #    #   ####   #    #
#    #  ##   #  #   #  #           #    #  #       ##   #  #    #  #    #
#    #  # #  #  #    ##            #####   #####   # #  #  #       ######
#    #  #  # #  #    ##            #    #  #       #  # #  #       #    #
#    #  #   ##  #   #  #           #    #  #       #   ##  #    #  #    #
####   #    #  #  #    #          #####   ######  #    #   ####   #    #

Version 5.1.3                      Based on the Byte Magazine Unix Benchmark

Multi-CPU version                  Version 5 revisions by Ian Smith,
Sunnyvale, CA, USA
January 13, 2011                   johantheghost at yahoo period com

Use of uninitialized value in printf at ./Run line 1378.
Use of uninitialized value in printf at ./Run line 1380.
Use of uninitialized value in printf at ./Run line 1588.
Use of uninitialized value in printf at ./Run line 1590.

1 x Dhrystone 2 using register variables  1 2 3 4 5 6 7 8 9 10

1 x Double-Precision Whetstone  1 2 3 4 5 6 7 8 9 10

1 x Execl Throughput  1 2 3

1 x File Copy 1024 bufsize 2000 maxblocks  1 2 3

1 x File Copy 256 bufsize 500 maxblocks  1 2 3

1 x File Copy 4096 bufsize 8000 maxblocks  1 2 3

1 x Pipe Throughput  1 2 3 4 5 6 7 8 9 10

1 x Pipe-based Context Switching  1 2 3 4 5 6 7 8 9 10

1 x Process Creation  1 2 3

1 x System Call Overhead  1 2 3 4 5 6 7 8 9 10

1 x Shell Scripts (1 concurrent)  1 2 3

1 x Shell Scripts (8 concurrent)  1 2 3

========================================================================
BYTE UNIX Benchmarks (Version 5.1.3)

System: raspberrypi: GNU/Linux
OS: GNU/Linux -- 4.1.6+ -- #810 PREEMPT Tue Aug 18 15:19:58 BST 2015
Machine: armv6l (unknown)
Language: en_US.utf8 (charmap="ANSI_X3.4-1968", collate="ANSI_X3.4-1968")
CPU 0: ARMv6-compatible processor rev 7 (v6l) (0.0 bogomips)

23:01:27 up  6:57,  1 user,  load average: 0.71, 0.24, 0.11; runlevel 2

------------------------------------------------------------------------
Benchmark Run: Thu Aug 27 2015 23:01:27 - 23:31:32
1 CPU in system; running 1 parallel copy of tests

Dhrystone 2 using register variables        1666373.2 lps   (10.0 s, 7 samples)
Double-Precision Whetstone                      265.2 MWIPS (10.0 s, 7 samples)
Execl Throughput                                188.2 lps   (29.7 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks         30458.0 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks            9554.5 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks         78833.1 KBps  (30.0 s, 2 samples)
Pipe Throughput                              123181.8 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                  15379.2 lps   (10.0 s, 7 samples)
Process Creation                                485.1 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                    370.6 lpm   (60.2 s, 2 samples)
Shell Scripts (8 concurrent)                     46.9 lpm   (60.7 s, 2 samples)
System Call Overhead                         343457.1 lps   (10.0 s, 7 samples)

System Benchmarks Index Values               BASELINE       RESULT    INDEX
Dhrystone 2 using register variables         116700.0    1666373.2    142.8
Double-Precision Whetstone                       55.0        265.2     48.2
Execl Throughput                                 43.0        188.2     43.8
File Copy 1024 bufsize 2000 maxblocks          3960.0      30458.0     76.9
File Copy 256 bufsize 500 maxblocks            1655.0       9554.5     57.7
File Copy 4096 bufsize 8000 maxblocks          5800.0      78833.1    135.9
Pipe Throughput                               12440.0     123181.8     99.0
Pipe-based Context Switching                   4000.0      15379.2     38.4
Process Creation                                126.0        485.1     38.5
Shell Scripts (1 concurrent)                     42.4        370.6     87.4
Shell Scripts (8 concurrent)                      6.0         46.9     78.2
System Call Overhead                          15000.0     343457.1    229.0
========
System Benchmarks Index Score                                          76.7

I will repeat the test after a reboot. see if it is a little bit different.

The second round shown as below:

#    #  #    #  #  #    #          #####   ######  #    #   ####   #    #
#    #  ##   #  #   #  #           #    #  #       ##   #  #    #  #    #
#    #  # #  #  #    ##            #####   #####   # #  #  #       ######
#    #  #  # #  #    ##            #    #  #       #  # #  #       #    #
#    #  #   ##  #   #  #           #    #  #       #   ##  #    #  #    #
####   #    #  #  #    #          #####   ######  #    #   ####   #    #

Version 5.1.3                      Based on the Byte Magazine Unix Benchmark

Multi-CPU version                  Version 5 revisions by Ian Smith,
Sunnyvale, CA, USA
January 13, 2011                   johantheghost at yahoo period com

Use of uninitialized value in printf at ./Run line 1378.
Use of uninitialized value in printf at ./Run line 1380.
Use of uninitialized value in printf at ./Run line 1588.
Use of uninitialized value in printf at ./Run line 1590.

1 x Dhrystone 2 using register variables  1 2 3 4 5 6 7 8 9 10

1 x Double-Precision Whetstone  1 2 3 4 5 6 7 8 9 10

1 x Execl Throughput  1 2 3

1 x File Copy 1024 bufsize 2000 maxblocks  1 2 3

1 x File Copy 256 bufsize 500 maxblocks  1 2 3

1 x File Copy 4096 bufsize 8000 maxblocks  1 2 3

1 x Pipe Throughput  1 2 3 4 5 6 7 8 9 10

1 x Pipe-based Context Switching  1 2 3 4 5 6 7 8 9 10

1 x Process Creation  1 2 3

1 x System Call Overhead  1 2 3 4 5 6 7 8 9 10

1 x Shell Scripts (1 concurrent)  1 2 3

1 x Shell Scripts (8 concurrent)  1 2 3

========================================================================
BYTE UNIX Benchmarks (Version 5.1.3)

System: raspberrypi: GNU/Linux
OS: GNU/Linux -- 4.1.6+ -- #810 PREEMPT Tue Aug 18 15:19:58 BST 2015
Machine: armv6l (unknown)
Language: en_US.utf8 (charmap="ANSI_X3.4-1968", collate="ANSI_X3.4-1968")
CPU 0: ARMv6-compatible processor rev 7 (v6l) (0.0 bogomips)

23:41:37 up 1 min,  1 user,  load average: 0.66, 0.28, 0.10; runlevel 2

------------------------------------------------------------------------
Benchmark Run: Thu Aug 27 2015 23:41:37 - 00:11:38
1 CPU in system; running 1 parallel copy of tests

Dhrystone 2 using register variables        1664979.1 lps   (10.0 s, 7 samples)
Double-Precision Whetstone                      265.4 MWIPS (10.0 s, 7 samples)
Execl Throughput                                186.3 lps   (29.9 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks         30534.9 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks            9407.5 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks         78715.5 KBps  (30.0 s, 2 samples)
Pipe Throughput                              116981.5 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                  15090.0 lps   (10.0 s, 7 samples)
Process Creation                                471.3 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                    366.7 lpm   (60.1 s, 2 samples)
Shell Scripts (8 concurrent)                     46.9 lpm   (60.8 s, 2 samples)
System Call Overhead                         329852.9 lps   (10.0 s, 7 samples)

System Benchmarks Index Values               BASELINE       RESULT    INDEX
Dhrystone 2 using register variables         116700.0    1664979.1    142.7
Double-Precision Whetstone                       55.0        265.4     48.3
Execl Throughput                                 43.0        186.3     43.3
File Copy 1024 bufsize 2000 maxblocks          3960.0      30534.9     77.1
File Copy 256 bufsize 500 maxblocks            1655.0       9407.5     56.8
File Copy 4096 bufsize 8000 maxblocks          5800.0      78715.5    135.7
Pipe Throughput                               12440.0     116981.5     94.0
Pipe-based Context Switching                   4000.0      15090.0     37.7
Process Creation                                126.0        471.3     37.4
Shell Scripts (1 concurrent)                     42.4        366.7     86.5
Shell Scripts (8 concurrent)                      6.0         46.9     78.2
System Call Overhead                          15000.0     329852.9    219.9
========
System Benchmarks Index Score                                          75.6

The post UnixBench test result on Raspberry Pi appeared first on David Yin's Blog.

A new VPS service provider – Vultr

David Yin — Wed, 29 Oct 2014 19:22:16 +0000

I just ordered a new VPS from Vultr.com.

It has All SSD. Maybe the lowest price per memory. Pay $0.007/hr, you get 768MB RAM, 3GHz CPU and 15GB storage. It is about $5/month.

And more datacenters than other VPS service providers. There are 14 locations worldwide, right now.

I did following test though Benchmark Serverbear.

The simply results as below.

UnixBench score: 2242.1

I/O rate: 409.0 MB/second

Bandwidth rate: 97.4 MB/secon

CPU Info:
processor	: 0
vendor_id	: GenuineIntel
cpu family	: 6
model		: 60
model name	: Vultr Virtual CPU 2
stepping	: 1
cpu MHz		: 3599.996
cache size	: 4096 KB

Unix Bench score is 2242.1

One cool thing, it accepts Bitcoin as payment option.

It is good for user. Vultr calculate bandwidth based on the highest of either inbound traffic or outbound traffic, not inbound plus outbound.

One thing I don’t like is that Vultr utilize KVM on virtualization frame. It allows Windows Server on it. Actually I don’t like Windows Server running on the same physical server with Linux.

Now, I put two sites on the Vultr VPS. It is good choice to take your road test on SSD VPS with the lowest cost. Click here to get your own Vultr VPS.

The post A new VPS service provider – Vultr appeared first on David Yin's Blog.

Benchmark Report of 4GB Servermania VPS with SSD Cached

David Yin — Thu, 08 May 2014 18:48:59 +0000

The VPS with SSD cached is much faster than normal HDD. Servermania had a email to me last week. It said there is a upgrade of the hardware on the host of my VPS. From normal HDD storage to SSD Cached HDD.

Here is a benchmark report for the new one.

UnixBench score: 2456.6

I/O rate: 139.0 MB/second

Bandwidth rate: 37.5 MB/second

It is 4 core CPU.

The IO read with cache is faster than before.

It is double the figure of the speed.

The post Benchmark Report of 4GB Servermania VPS with SSD Cached appeared first on David Yin's Blog.

Linodes New SSD VPS performance test

David Yin — Sat, 19 Apr 2014 01:03:14 +0000

Yes, I just upgraded my VPS from old plan to new platform. Actually my old VPS at Linode is SSD cached system. They called it SSD Beta. I used it from last September. I did a performance test at that time.

SSD Cached Linode

UnixBench

UnixBench (w/ all processors) 2086.0
UnixBench (w/ one processor) 324.3

IOPS

Read IOPS 28016.0
Read Bandwidth 112.0 MB/second
Write IOPS 12494.0
Write Bandwidth 49.9 MB/second

Now, after upgrading my VPS, I did a new test through ServerBear.com

UnixBench

UnixBench (w/ all processors) 1023.3
UnixBench (w/ one processor) 559.6

IOPS

Read IOPS 83772.0
Read Bandwidth 335.0 MB/second
Write IOPS 45037.0
Write Bandwidth 180.1 MB/second

UnixBench one core scroe is much higher than before, about 72% more. It is benefited by the new CPU. But Linode reduced total core from 8 to 2, so the UnixBench with all processors is lower.

IO performance is very faster, just because of the fast SSD. And last one is Bandwidth is 166 MB/s compared with 24.3 MB/s of old setup.

It is good time to order you VPS at Linode. All SSD powered VPS for new instance. Price is still $20.00.

The post Linodes New SSD VPS performance test appeared first on David Yin's Blog.

4GB OpenVZ VPS

David Yin — Mon, 23 Sep 2013 00:32:49 +0000

Ordered a new VPS from ServerMania. I did a test two days ago through ServerBear.

The basic information about this VPS.

RAM 4 GB
Burstable 8GB
HDD 150 GB
CPU Model Intel(R) Xeon(R) CPU E3-1270 V2 @ 3.50GHz
CPU Cores 4
CPU Speed 3500 MHz
CPU Cache 8192 KB
4 TB Bandwidth
4 IP address

The testing results:

UnixBench

UnixBench (w/ all processors) 3817.1
UnixBench (w/ one processor) 1900.7

I/O rate: 234.0 MB/second

Bandwidth rate: 31.2 MB/second

This VPS is located at Buffalo, NY. Speed it OK.

The price is so amzing. Only $88/year. I saw this one on facebook side advertisement. I thought it may be a good deal. So I ordered and pay by paypal.

The customer support told me that it is the recuring amount. Even I am wondering it is true or not. At least I paid $88 for the first year.

The post 4GB OpenVZ VPS appeared first on David Yin's Blog.

UnixBench 5.1.3 testing result on Digital Ocean VPS

David Yin — Sat, 03 Aug 2013 00:51:27 +0000

Yes, I tried a new VPS. And I would like to show you how fast it is.
DigitalOcean has SSD for storage. I just ordered a 512MB VPS, with 20GB space.
Let us see the results of it.

[root@beta UnixBench]# ./Run
make all
make[1]: Entering directory `/root/UnixBench'
Checking distribution of files
./pgms  exists
./src  exists
./testdir  exists
./tmp  exists
./results  exists
make[1]: Leaving directory `/root/UnixBench'
sh: 3dinfo: command not found
#    #  #    #  #  #    #          #####   ######  #    #   ####   #    #
#    #  ##   #  #   #  #           #    #  #       ##   #  #    #  #    #
#    #  # #  #  #    ##            #####   #####   # #  #  #       ######
#    #  #  # #  #    ##            #    #  #       #  # #  #       #    #
#    #  #   ##  #   #  #           #    #  #       #   ##  #    #  #    #
####   #    #  #  #    #          #####   ######  #    #   ####   #    #
Version 5.1.3                      Based on the Byte Magazine Unix Benchmark
Multi-CPU version                  Version 5 revisions by Ian Smith,
Sunnyvale, CA, USA
January 13, 2011                   johantheghost at yahoo period com
1 x Dhrystone 2 using register variables  1 2 3 4 5 6 7 8 9 10
1 x Double-Precision Whetstone  1 2 3 4 5 6 7 8 9 10
1 x Execl Throughput  1 2 3
1 x File Copy 1024 bufsize 2000 maxblocks  1 2 3
1 x File Copy 256 bufsize 500 maxblocks  1 2 3
1 x File Copy 4096 bufsize 8000 maxblocks  1 2 3
1 x Pipe Throughput  1 2 3 4 5 6 7 8 9 10
1 x Pipe-based Context Switching  1 2 3 4 5 6 7 8 9 10
1 x Process Creation  1 2 3
1 x System Call Overhead  1 2 3 4 5 6 7 8 9 10
1 x Shell Scripts (1 concurrent)  1 2 3
1 x Shell Scripts (8 concurrent)  1 2 3
========================================================================
BYTE UNIX Benchmarks (Version 5.1.3)
System: beta.freeinoutboard.com: GNU/Linux
OS: GNU/Linux -- 2.6.32-358.6.2.el6.i686 -- #1 SMP Thu May 16 18:12:13 UTC 2013
Machine: i686 (i386)
Language: en_US.utf8 (charmap="UTF-8", collate="UTF-8")
CPU 0: QEMU Virtual CPU version 1.0 (4600.0 bogomips)
x86-64, MMX, Physical Address Ext, SYSCALL/SYSRET, Intel virtualization
07:14:46 up 1 day,  8:15,  1 user,  load average: 0.00, 0.00, 0.00; runlevel 3
------------------------------------------------------------------------
Benchmark Run: Sat Aug 03 2013 07:14:46 - 07:42:36
1 CPU in system; running 1 parallel copy of tests
Dhrystone 2 using register variables        9504205.4 lps   (10.0 s, 7 samples)
Double-Precision Whetstone                     2273.1 MWIPS (9.8 s, 7 samples)
Execl Throughput                               3473.4 lps   (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks        293547.4 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks           91489.0 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks        942026.0 KBps  (30.0 s, 2 samples)
Pipe Throughput                              685012.0 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                 120461.6 lps   (10.0 s, 7 samples)
Process Creation                               8875.8 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                   4069.1 lpm   (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                    381.8 lpm   (60.0 s, 2 samples)
System Call Overhead                         571514.4 lps   (10.0 s, 7 samples)
System Benchmarks Index Values               BASELINE       RESULT    INDEX
Dhrystone 2 using register variables         116700.0    9504205.4    814.4
Double-Precision Whetstone                       55.0       2273.1    413.3
Execl Throughput                                 43.0       3473.4    807.8
File Copy 1024 bufsize 2000 maxblocks          3960.0     293547.4    741.3
File Copy 256 bufsize 500 maxblocks            1655.0      91489.0    552.8
File Copy 4096 bufsize 8000 maxblocks          5800.0     942026.0   1624.2
Pipe Throughput                               12440.0     685012.0    550.7
Pipe-based Context Switching                   4000.0     120461.6    301.2
Process Creation                                126.0       8875.8    704.4
Shell Scripts (1 concurrent)                     42.4       4069.1    959.7
Shell Scripts (8 concurrent)                      6.0        381.8    636.3
System Call Overhead                          15000.0     571514.4    381.0
========
System Benchmarks Index Score                                         642.2

Oh, I forgot to mention it is one CPU only. So the score 642. It is higher than any other VPS tested before.
Am I mentioned it is only $5 a month? Compare with the price and performance. I do recommend Digital Ocean VPS.

The post UnixBench 5.1.3 testing result on Digital Ocean VPS appeared first on David Yin's Blog.

Three UnixBench testing results including Linode VPS

David Yin — Mon, 06 May 2013 20:42:37 +0000

UnixBench is a testing tool. I run it on two Linode VPS.
One is located at Newark, NJ, with new hardware, including CPU E5-2670.
The testing results are shown as below:

[root@servername UnixBench]# ./Run
make all
make[1]: Entering directory `/root/UnixBench'
Checking distribution of files
./pgms  exists
./src  exists
./testdir  exists
./tmp  exists
./results  exists
make[1]: Leaving directory `/root/UnixBench'
sh: 3dinfo: command not found
#    #  #    #  #  #    #          #####   ######  #    #   ####   #    #
#    #  ##   #  #   #  #           #    #  #       ##   #  #    #  #    #
#    #  # #  #  #    ##            #####   #####   # #  #  #       ######
#    #  #  # #  #    ##            #    #  #       #  # #  #       #    #
#    #  #   ##  #   #  #           #    #  #       #   ##  #    #  #    #
####   #    #  #  #    #          #####   ######  #    #   ####   #    #
Version 5.1.3                      Based on the Byte Magazine Unix Benchmark
Multi-CPU version                  Version 5 revisions by Ian Smith,
Sunnyvale, CA, USA
January 13, 2011                   johantheghost at yahoo period com
1 x Dhrystone 2 using register variables  1 2 3 4 5 6 7 8 9 10
1 x Double-Precision Whetstone  1 2 3 4 5 6 7 8 9 10
1 x Execl Throughput  1 2 3
1 x File Copy 1024 bufsize 2000 maxblocks  1 2 3
1 x File Copy 256 bufsize 500 maxblocks  1 2 3
1 x File Copy 4096 bufsize 8000 maxblocks  1 2 3
1 x Pipe Throughput  1 2 3 4 5 6 7 8 9 10
1 x Pipe-based Context Switching  1 2 3 4 5 6 7 8 9 10
1 x Process Creation  1 2 3
1 x System Call Overhead  1 2 3 4 5 6 7 8 9 10
1 x Shell Scripts (1 concurrent)  1 2 3
1 x Shell Scripts (8 concurrent)  1 2 3
8 x Dhrystone 2 using register variables  1 2 3 4 5 6 7 8 9 10
8 x Double-Precision Whetstone  1 2 3 4 5 6 7 8 9 10
8 x Execl Throughput  1 2 3
8 x File Copy 1024 bufsize 2000 maxblocks  1 2 3
8 x File Copy 256 bufsize 500 maxblocks  1 2 3
8 x File Copy 4096 bufsize 8000 maxblocks  1 2 3
8 x Pipe Throughput  1 2 3 4 5 6 7 8 9 10
8 x Pipe-based Context Switching  1 2 3 4 5 6 7 8 9 10
8 x Process Creation  1 2 3
8 x System Call Overhead  1 2 3 4 5 6 7 8 9 10
8 x Shell Scripts (1 concurrent)  1 2 3
8 x Shell Scripts (8 concurrent)  1 2 3
========================================================================
BYTE UNIX Benchmarks (Version 5.1.3)
System: worldpeaceever: GNU/Linux
OS: GNU/Linux -- 3.8.4-linode50 -- #1 SMP Mon Mar 25 15:50:29 EDT 2013
Machine: i686 (i386)
Language: en_US.utf8 (charmap="UTF-8", collate="UTF-8")
CPU 0: Intel(R) Xeon(R) CPU E5-2670 0 @ 2.60GHz (5200.1 bogomips)
Hyper-Threading, MMX, Physical Address Ext
CPU 1: Intel(R) Xeon(R) CPU E5-2670 0 @ 2.60GHz (5200.1 bogomips)
Hyper-Threading, MMX, Physical Address Ext
CPU 2: Intel(R) Xeon(R) CPU E5-2670 0 @ 2.60GHz (5200.1 bogomips)
Hyper-Threading, MMX, Physical Address Ext
CPU 3: Intel(R) Xeon(R) CPU E5-2670 0 @ 2.60GHz (5200.1 bogomips)
Hyper-Threading, MMX, Physical Address Ext
CPU 4: Intel(R) Xeon(R) CPU E5-2670 0 @ 2.60GHz (5200.1 bogomips)
Hyper-Threading, MMX, Physical Address Ext
CPU 5: Intel(R) Xeon(R) CPU E5-2670 0 @ 2.60GHz (5200.1 bogomips)
Hyper-Threading, MMX, Physical Address Ext
CPU 6: Intel(R) Xeon(R) CPU E5-2670 0 @ 2.60GHz (5200.1 bogomips)
Hyper-Threading, MMX, Physical Address Ext
CPU 7: Intel(R) Xeon(R) CPU E5-2670 0 @ 2.60GHz (5200.1 bogomips)
Hyper-Threading, MMX, Physical Address Ext
19:47:03 up 20 days, 18:07,  1 user,  load average: 0.00, 0.01, 0.05; runlevel 3
------------------------------------------------------------------------
Benchmark Run: Mon May 06 2013 19:47:03 - 20:14:59
8 CPUs in system; running 1 parallel copy of tests
Dhrystone 2 using register variables       16030487.1 lps   (10.0 s, 7 samples)
Double-Precision Whetstone                     2371.3 MWIPS (10.2 s, 7 samples)
Execl Throughput                               1370.6 lps   (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks        354802.8 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks           98594.2 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks        954149.3 KBps  (30.0 s, 2 samples)
Pipe Throughput                              509976.8 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                  23671.2 lps   (10.0 s, 7 samples)
Process Creation                               2357.2 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                   2895.0 lpm   (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                   1207.3 lpm   (60.0 s, 2 samples)
System Call Overhead                         402520.6 lps   (10.0 s, 7 samples)
System Benchmarks Index Values               BASELINE       RESULT    INDEX
Dhrystone 2 using register variables         116700.0   16030487.1   1373.6
Double-Precision Whetstone                       55.0       2371.3    431.1
Execl Throughput                                 43.0       1370.6    318.7
File Copy 1024 bufsize 2000 maxblocks          3960.0     354802.8    896.0
File Copy 256 bufsize 500 maxblocks            1655.0      98594.2    595.7
File Copy 4096 bufsize 8000 maxblocks          5800.0     954149.3   1645.1
Pipe Throughput                               12440.0     509976.8    409.9
Pipe-based Context Switching                   4000.0      23671.2     59.2
Process Creation                                126.0       2357.2    187.1
Shell Scripts (1 concurrent)                     42.4       2895.0    682.8
Shell Scripts (8 concurrent)                      6.0       1207.3   2012.2
System Call Overhead                          15000.0     402520.6    268.3
========
System Benchmarks Index Score                                         505.3
------------------------------------------------------------------------
Benchmark Run: Mon May 06 2013 20:14:59 - 20:43:01
8 CPUs in system; running 8 parallel copies of tests
Dhrystone 2 using register variables       84271128.4 lps   (10.0 s, 7 samples)
Double-Precision Whetstone                    16058.7 MWIPS (10.5 s, 7 samples)
Execl Throughput                               7123.1 lps   (29.8 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks        533181.6 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks          138475.7 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks       1660648.6 KBps  (30.0 s, 2 samples)
Pipe Throughput                             3570580.2 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                 399944.6 lps   (10.0 s, 7 samples)
Process Creation                              13403.1 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                  12387.6 lpm   (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                   1663.7 lpm   (60.1 s, 2 samples)
System Call Overhead                        2660567.5 lps   (10.0 s, 7 samples)
System Benchmarks Index Values               BASELINE       RESULT    INDEX
Dhrystone 2 using register variables         116700.0   84271128.4   7221.2
Double-Precision Whetstone                       55.0      16058.7   2919.8
Execl Throughput                                 43.0       7123.1   1656.5
File Copy 1024 bufsize 2000 maxblocks          3960.0     533181.6   1346.4
File Copy 256 bufsize 500 maxblocks            1655.0     138475.7    836.7
File Copy 4096 bufsize 8000 maxblocks          5800.0    1660648.6   2863.2
Pipe Throughput                               12440.0    3570580.2   2870.2
Pipe-based Context Switching                   4000.0     399944.6    999.9
Process Creation                                126.0      13403.1   1063.7
Shell Scripts (1 concurrent)                     42.4      12387.6   2921.6
Shell Scripts (8 concurrent)                      6.0       1663.7   2772.8
System Call Overhead                          15000.0    2660567.5   1773.7
========
System Benchmarks Index Score                                        2031.5

The other VPS is at Fremont, CA. The CPU is L5630. The score is 1186, compared with the above 2031. It is much slower.

[root@juntixiao UnixBench]# ./Run
make all
make[1]: Entering directory `/root/UnixBench'
Checking distribution of files
./pgms  exists
./src  exists
./testdir  exists
./tmp  exists
./results  exists
make[1]: Leaving directory `/root/UnixBench'
sh: 3dinfo: command not found
#    #  #    #  #  #    #          #####   ######  #    #   ####   #    #
#    #  ##   #  #   #  #           #    #  #       ##   #  #    #  #    #
#    #  # #  #  #    ##            #####   #####   # #  #  #       ######
#    #  #  # #  #    ##            #    #  #       #  # #  #       #    #
#    #  #   ##  #   #  #           #    #  #       #   ##  #    #  #    #
####   #    #  #  #    #          #####   ######  #    #   ####   #    #
Version 5.1.3                      Based on the Byte Magazine Unix Benchmark
Multi-CPU version                  Version 5 revisions by Ian Smith,
Sunnyvale, CA, USA
January 13, 2011                   johantheghost at yahoo period com
1 x Dhrystone 2 using register variables  1 2 3 4 5 6 7 8 9 10
1 x Double-Precision Whetstone  1 2 3 4 5 6 7 8 9 10
1 x Execl Throughput  1 2 3
1 x File Copy 1024 bufsize 2000 maxblocks  1 2 3
1 x File Copy 256 bufsize 500 maxblocks  1 2 3
1 x File Copy 4096 bufsize 8000 maxblocks  1 2 3
1 x Pipe Throughput  1 2 3 4 5 6 7 8 9 10
1 x Pipe-based Context Switching  1 2 3 4 5 6 7 8 9 10
1 x Process Creation  1 2 3
1 x System Call Overhead  1 2 3 4 5 6 7 8 9 10
1 x Shell Scripts (1 concurrent)  1 2 3
1 x Shell Scripts (8 concurrent)  1 2 3
8 x Dhrystone 2 using register variables  1 2 3 4 5 6 7 8 9 10
8 x Double-Precision Whetstone  1 2 3 4 5 6 7 8 9 10
8 x Execl Throughput  1 2 3
8 x File Copy 1024 bufsize 2000 maxblocks  1 2 3
8 x File Copy 256 bufsize 500 maxblocks  1 2 3
8 x File Copy 4096 bufsize 8000 maxblocks  1 2 3
8 x Pipe Throughput  1 2 3 4 5 6 7 8 9 10
8 x Pipe-based Context Switching  1 2 3 4 5 6 7 8 9 10
8 x Process Creation  1 2 3
8 x System Call Overhead  1 2 3 4 5 6 7 8 9 10
8 x Shell Scripts (1 concurrent)  1 2 3
8 x Shell Scripts (8 concurrent)  1 2 3
========================================================================
BYTE UNIX Benchmarks (Version 5.1.3)
System: juntixiao: GNU/Linux
OS: GNU/Linux -- 3.8.4-linode50 -- #1 SMP Mon Mar 25 15:50:29 EDT 2013
Machine: i686 (i386)
Language: en_US.utf8 (charmap="UTF-8", collate="UTF-8")
CPU 0: Intel(R) Xeon(R) CPU L5630 @ 2.13GHz (4266.9 bogomips)
Hyper-Threading, MMX, Physical Address Ext
CPU 1: Intel(R) Xeon(R) CPU L5630 @ 2.13GHz (4266.9 bogomips)
Hyper-Threading, MMX, Physical Address Ext
CPU 2: Intel(R) Xeon(R) CPU L5630 @ 2.13GHz (4266.9 bogomips)
Hyper-Threading, MMX, Physical Address Ext
CPU 3: Intel(R) Xeon(R) CPU L5630 @ 2.13GHz (4266.9 bogomips)
Hyper-Threading, MMX, Physical Address Ext
CPU 4: Intel(R) Xeon(R) CPU L5630 @ 2.13GHz (4266.9 bogomips)
Hyper-Threading, MMX, Physical Address Ext
CPU 5: Intel(R) Xeon(R) CPU L5630 @ 2.13GHz (4266.9 bogomips)
Hyper-Threading, MMX, Physical Address Ext
CPU 6: Intel(R) Xeon(R) CPU L5630 @ 2.13GHz (4266.9 bogomips)
Hyper-Threading, MMX, Physical Address Ext
CPU 7: Intel(R) Xeon(R) CPU L5630 @ 2.13GHz (4266.9 bogomips)
Hyper-Threading, MMX, Physical Address Ext
16:47:25 up 7 days, 15:35,  1 user,  load average: 0.01, 0.04, 0.05; runlevel 3
------------------------------------------------------------------------
Benchmark Run: Mon May 06 2013 16:47:25 - 17:15:21
8 CPUs in system; running 1 parallel copy of tests
Dhrystone 2 using register variables       12666461.0 lps   (10.0 s, 7 samples)
Double-Precision Whetstone                     2097.8 MWIPS (10.3 s, 7 samples)
Execl Throughput                               1241.3 lps   (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks        248132.0 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks           64817.5 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks        850189.9 KBps  (30.0 s, 2 samples)
Pipe Throughput                              120057.9 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                  18186.7 lps   (10.0 s, 7 samples)
Process Creation                               2003.6 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                   2497.7 lpm   (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                    688.7 lpm   (60.0 s, 2 samples)
System Call Overhead                         381542.5 lps   (10.0 s, 7 samples)
System Benchmarks Index Values               BASELINE       RESULT    INDEX
Dhrystone 2 using register variables         116700.0   12666461.0   1085.4
Double-Precision Whetstone                       55.0       2097.8    381.4
Execl Throughput                                 43.0       1241.3    288.7
File Copy 1024 bufsize 2000 maxblocks          3960.0     248132.0    626.6
File Copy 256 bufsize 500 maxblocks            1655.0      64817.5    391.6
File Copy 4096 bufsize 8000 maxblocks          5800.0     850189.9   1465.8
Pipe Throughput                               12440.0     120057.9     96.5
Pipe-based Context Switching                   4000.0      18186.7     45.5
Process Creation                                126.0       2003.6    159.0
Shell Scripts (1 concurrent)                     42.4       2497.7    589.1
Shell Scripts (8 concurrent)                      6.0        688.7   1147.9
System Call Overhead                          15000.0     381542.5    254.4
========
System Benchmarks Index Score                                         362.6
------------------------------------------------------------------------
Benchmark Run: Mon May 06 2013 17:15:21 - 17:43:45
8 CPUs in system; running 8 parallel copies of tests
Dhrystone 2 using register variables       46225008.8 lps   (10.0 s, 7 samples)
Double-Precision Whetstone                    10993.7 MWIPS (10.0 s, 7 samples)
Execl Throughput                               4335.2 lps   (29.9 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks        466791.8 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks           67770.3 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks       1315026.4 KBps  (30.0 s, 2 samples)
Pipe Throughput                             1870328.4 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                 234389.7 lps   (10.0 s, 7 samples)
Process Creation                               6680.7 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                   6638.0 lpm   (60.1 s, 2 samples)
Shell Scripts (8 concurrent)                    689.0 lpm   (60.2 s, 2 samples)
System Call Overhead                        1587949.8 lps   (10.0 s, 7 samples)
System Benchmarks Index Values               BASELINE       RESULT    INDEX
Dhrystone 2 using register variables         116700.0   46225008.8   3961.0
Double-Precision Whetstone                       55.0      10993.7   1998.8
Execl Throughput                                 43.0       4335.2   1008.2
File Copy 1024 bufsize 2000 maxblocks          3960.0     466791.8   1178.8
File Copy 256 bufsize 500 maxblocks            1655.0      67770.3    409.5
File Copy 4096 bufsize 8000 maxblocks          5800.0    1315026.4   2267.3
Pipe Throughput                               12440.0    1870328.4   1503.5
Pipe-based Context Switching                   4000.0     234389.7    586.0
Process Creation                                126.0       6680.7    530.2
Shell Scripts (1 concurrent)                     42.4       6638.0   1565.6
Shell Scripts (8 concurrent)                      6.0        689.0   1148.3
System Call Overhead                          15000.0    1587949.8   1058.6
========
System Benchmarks Index Score                                        1186.3

I have a VirtualBox on my Windows 7. The hardware is A3870K, 512MB memory for this CentOS 6 guest system.

[root@localhost UnixBench]# ./Run
make all
make[1]: Entering directory `/root/UnixBench'
Checking distribution of files
./pgms  exists
./src  exists
./testdir  exists
./tmp  exists
./results  exists
make[1]: Leaving directory `/root/UnixBench'
sh: 3dinfo: command not found
#    #  #    #  #  #    #          #####   ######  #    #   ####   #    #
#    #  ##   #  #   #  #           #    #  #       ##   #  #    #  #    #
#    #  # #  #  #    ##            #####   #####   # #  #  #       ######
#    #  #  # #  #    ##            #    #  #       #  # #  #       #    #
#    #  #   ##  #   #  #           #    #  #       #   ##  #    #  #    #
####   #    #  #  #    #          #####   ######  #    #   ####   #    #
Version 5.1.3                      Based on the Byte Magazine Unix Benchmark
Multi-CPU version                  Version 5 revisions by Ian Smith,
Sunnyvale, CA, USA
January 13, 2011                   johantheghost at yahoo period com
1 x Dhrystone 2 using register variables  1 2 3 4 5 6 7 8 9 10
1 x Double-Precision Whetstone  1 2 3 4 5 6 7 8 9 10
1 x Execl Throughput  1 2 3
1 x File Copy 1024 bufsize 2000 maxblocks  1 2 3
1 x File Copy 256 bufsize 500 maxblocks  1 2 3
1 x File Copy 4096 bufsize 8000 maxblocks  1 2 3
1 x Pipe Throughput  1 2 3 4 5 6 7 8 9 10
1 x Pipe-based Context Switching  1 2 3 4 5 6 7 8 9 10
1 x Process Creation  1 2 3
1 x System Call Overhead  1 2 3 4 5 6 7 8 9 10
1 x Shell Scripts (1 concurrent)  1 2 3
1 x Shell Scripts (8 concurrent)  1 2 3
4 x Dhrystone 2 using register variables  1 2 3 4 5 6 7 8 9 10
4 x Double-Precision Whetstone  1 2 3 4 5 6 7 8 9 10
4 x Execl Throughput  1 2 3
4 x File Copy 1024 bufsize 2000 maxblocks  1 2 3
4 x File Copy 256 bufsize 500 maxblocks  1 2 3
4 x File Copy 4096 bufsize 8000 maxblocks  1 2 3
4 x Pipe Throughput  1 2 3 4 5 6 7 8 9 10
4 x Pipe-based Context Switching  1 2 3 4 5 6 7 8 9 10
4 x Process Creation  1 2 3
4 x System Call Overhead  1 2 3 4 5 6 7 8 9 10
4 x Shell Scripts (1 concurrent)  1 2 3
4 x Shell Scripts (8 concurrent)  1 2 3
========================================================================
BYTE UNIX Benchmarks (Version 5.1.3)
System: localhost.localdomain: GNU/Linux
OS: GNU/Linux -- 2.6.32-358.2.1.el6.i686 -- #1 SMP Tue Mar 12 21:42:46 UTC 2013
Machine: i686 (i386)
Language: en_US.utf8 (charmap="UTF-8", collate="UTF-8")
CPU 0: AMD A8-3870 APU with Radeon(tm) HD Graphics (5751.0 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
CPU 1: AMD A8-3870 APU with Radeon(tm) HD Graphics (5824.3 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
CPU 2: AMD A8-3870 APU with Radeon(tm) HD Graphics (5768.3 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
CPU 3: AMD A8-3870 APU with Radeon(tm) HD Graphics (5764.0 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
17:36:12 up 32 min,  2 users,  load average: 0.10, 0.04, 0.01; runlevel 3
------------------------------------------------------------------------
Benchmark Run: Mon May 06 2013 17:36:12 - 18:04:09
4 CPUs in system; running 1 parallel copy of tests
Dhrystone 2 using register variables       12832548.0 lps   (10.0 s, 7 samples)
Double-Precision Whetstone                     1972.6 MWIPS (10.3 s, 7 samples)
Execl Throughput                                651.2 lps   (29.9 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks        436935.2 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks          167015.6 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks        740800.5 KBps  (30.0 s, 2 samples)
Pipe Throughput                             1251139.5 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                   9328.6 lps   (10.0 s, 7 samples)
Process Creation                               4598.0 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                   2813.3 lpm   (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                   1236.1 lpm   (60.0 s, 2 samples)
System Call Overhead                        1952491.6 lps   (10.0 s, 7 samples)
System Benchmarks Index Values               BASELINE       RESULT    INDEX
Dhrystone 2 using register variables         116700.0   12832548.0   1099.6
Double-Precision Whetstone                       55.0       1972.6    358.7
Execl Throughput                                 43.0        651.2    151.4
File Copy 1024 bufsize 2000 maxblocks          3960.0     436935.2   1103.4
File Copy 256 bufsize 500 maxblocks            1655.0     167015.6   1009.2
File Copy 4096 bufsize 8000 maxblocks          5800.0     740800.5   1277.2
Pipe Throughput                               12440.0    1251139.5   1005.7
Pipe-based Context Switching                   4000.0       9328.6     23.3
Process Creation                                126.0       4598.0    364.9
Shell Scripts (1 concurrent)                     42.4       2813.3    663.5
Shell Scripts (8 concurrent)                      6.0       1236.1   2060.1
System Call Overhead                          15000.0    1952491.6   1301.7
========
System Benchmarks Index Score                                         574.5
------------------------------------------------------------------------
Benchmark Run: Mon May 06 2013 18:04:09 - 18:32:04
4 CPUs in system; running 4 parallel copies of tests
Dhrystone 2 using register variables       48856746.0 lps   (10.0 s, 7 samples)
Double-Precision Whetstone                     8268.8 MWIPS (9.8 s, 7 samples)
Execl Throughput                              11202.7 lps   (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks        483796.9 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks          146739.4 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks       1200427.0 KBps  (30.0 s, 2 samples)
Pipe Throughput                             5558915.4 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                 121641.1 lps   (10.0 s, 7 samples)
Process Creation                              28685.2 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                  11394.5 lpm   (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                   1522.1 lpm   (60.1 s, 2 samples)
System Call Overhead                        2975599.7 lps   (10.0 s, 7 samples)
System Benchmarks Index Values               BASELINE       RESULT    INDEX
Dhrystone 2 using register variables         116700.0   48856746.0   4186.5
Double-Precision Whetstone                       55.0       8268.8   1503.4
Execl Throughput                                 43.0      11202.7   2605.3
File Copy 1024 bufsize 2000 maxblocks          3960.0     483796.9   1221.7
File Copy 256 bufsize 500 maxblocks            1655.0     146739.4    886.6
File Copy 4096 bufsize 8000 maxblocks          5800.0    1200427.0   2069.7
Pipe Throughput                               12440.0    5558915.4   4468.6
Pipe-based Context Switching                   4000.0     121641.1    304.1
Process Creation                                126.0      28685.2   2276.6
Shell Scripts (1 concurrent)                     42.4      11394.5   2687.4
Shell Scripts (8 concurrent)                      6.0       1522.1   2536.8
System Call Overhead                          15000.0    2975599.7   1983.7
========
System Benchmarks Index Score                                        1843.2

Based on the testing scores, it is clear that CPU plays more important role here.

The post Three UnixBench testing results including Linode VPS appeared first on David Yin's Blog.

UnixBench 5.1.3 testing result on Linode VPS

David Yin — Mon, 15 Apr 2013 10:24:04 +0000

I have a Linode VPS with 1GB RAM. To verify the performance of it, I test the VPS with UnixBench 5.1.3.
The result is amazing. The System Benchmarks Index Score is 2298.

The details of score and breakdown of it are shown as below.

I doing this test before on other VPS. Never saw any VPS with such a high score. You can search the score on Google. Most of them are below 800. Some good one may have the score just over 1000. Now, Linode VPS 1GB has 2000+.

So, if you want a powerful VPS, just go to Linode to order your own.

Let me show you how I did the test.

1) My Linode VPS is 1GB.
2) Profile is CentOS 6.2 32bit.
3) Datacenter is in Newark, NJ.
The VPS is freshly installed. No service running on it except SSH.
SSH to VPS, and enter following commands.

yum update
yum -y install gcc
wget http://byte-unixbench.googlecode.com/files/UnixBench5.1.3.tgz
tar -zxvf UnixBench5.1.3.tgz
cd UnixBench
yum install perl-Time-HiRes.i686
make
./Run

Please note that the result should be taken cautiously, as it can vary in time (depending on host activity, more precisely disk I/O).

The post UnixBench 5.1.3 testing result on Linode VPS appeared first on David Yin's Blog.

UnixBench Archives - David Yin's Blog

VPS performance benchmark – Vultr Intel High Fequency

Yet-Another-Bench-Script (YABS)

Bench.sh

UnixBench

Related posts:

UnixBench test result on Raspberry Pi

Related posts:

A new VPS service provider – Vultr

Related posts:

Benchmark Report of 4GB Servermania VPS with SSD Cached

Related posts:

Linodes New SSD VPS performance test

SSD Cached Linode

Related posts:

4GB OpenVZ VPS

UnixBench

Related posts:

UnixBench 5.1.3 testing result on Digital Ocean VPS

Related posts:

Three UnixBench testing results including Linode VPS

Related posts:

UnixBench 5.1.3 testing result on Linode VPS

Related posts: