0x01 前言

今天收到hostus的邮件,他们位于洛杉矶LAX02机房的网络增加了CN2线路,同时联通线路也在洽谈中。正好我有几台服务器在他们公司。为了测试,我将其中一台申请迁移至LAX02机房。但邮件中没表明KVM架构和Open VZ架构是否有网络区分。

在这篇文章里,我将测试位于洛杉矶数据中心的KVM和OpenVZ架构服务器。位于达拉斯数据中心的测试请留意下面的链接。

KVM架构VPS的硬盘也免费升级,其他详细内容请参考邮件内容:

Dear Terence,

Thank you for your interest in HostUS, and our KVM VPS services!

We are:

Giving FREE resource upgrades to our KVM VPS services
Upgrading networks at existing locations
Announcing NEW locations for future expansion
#1 FREE Disk Space Upgrades on KVM Plans

We have increased disk allocations on all KVM VPS plans. These upgrades are effective immediately at NO additional cost to you. You will see your increased disk space immediately after a VPS rebuild. You can also create a support ticket and ask us to grow (increase) your existing disk.

KVM-0.5 - Was 15GB, now 25GB
KVM-1 - Was 30GB, now 45GB
KVM-2 - Was 55GB, now 75GB
KVM-3 - Was 80GB, now 100GB
KVM-4 - Was 120GB, now 140GB
KVM-6 - Was 140GB, now 160GB
KVM-8 - Was 170GB, now 200GB
KVM-12 - Was 200GB, now 220GB

#2 Network Upgrades at Existing Locations

Atlanta (ATL01) - Cogent Communications (AS174) has been added to the DDoS protected bandwidth for network redundancy.
Los Angeles (LAX02) - China Telecom Next Generation Carrier Network (AS4809), commonly known as CN2, has been added. China Unicom direct connectivity is currently pending.
Washington DC (WDC01) - Zayo / Abovenet (AS6461) has been added to the bandwidth mix, view their network map here: http://www.zayo.com/solutions/global-network/

#3 New KVM Locations - Coming Soon!

London, UK - Connection to LINX (London Internet Exchange) is being finalized with a June launch date.
Hong Kong SAR, CN - Direct connections to China Telecom, China Unicom and China Mobile are under negotiation.
Sydney, AU - Negotiations under way with datacenter.

#4 Breeze Control Panel Improvements

We would like to thank our clients for reporting software bugs in the Breeze KVM control panel. Several improvements have been made to the rebuild process and IP assignment process.

在这里我将对位于LAX02机房的KVM/OpenVZ和位于达拉斯的OpenVZ进行测试。

达拉斯数据中心的测试请点击下面的链接:

美国Hostus云服务器(VPS) – OpenVZ 达拉斯数据中心

0x02 LAX02 KVM 服务器信息/性能测试

服务器配置/套餐如下:

  • vCPU:2核心
  • 内存:1GB
  • 硬盘:SSD 45GB
  • IP地址:1个IPv4
  • 网络:1000M

pachosting购买链接    conoha / z.com购买链接    hostus购买链接

这里是pachosting香港机房和conoha新加坡机房的评测:

新加坡服务器(VPS) – 日本GMO

香港云服务器(VPS) – pachosting

测试的软件和手段如下:

  • ping
  • 路由追踪
  • wget测速
  • speedtest测速
  • 基于dd的硬盘IO测试
  • 基于fio的硬盘IO测试
  • 基于RAMSpeed/SMP的内存测试
  • 基于UnixBench的系统基准测试

0x03 ping / wget / 路由追踪

–0x03.1 ping测试

--- 172.106.32.137 ping statistics ---
2050 packets transmitted, 1895 packets received, 7.6% packet loss
round-trip min/avg/max/stddev = 171.190/194.359/427.943/36.653 ms

–0x03.2 wget测试

chunqideAir:~ terence$ wget http://172.106.32.137/128m.test
--2016-05-30 01:29:45--  http://172.106.32.137/128m.test
Connecting to 172.106.32.137:80... connected.
HTTP request sent, awaiting response... 200 OK
Length: 134217728 (128M) [application/octet-stream]
Saving to: '128m.test'  

2016-05-30 01:30:16 (4.21 MB/s) - '128m.test' saved [134217728/134217728]

–0x03.3 路由追踪

0x04 speedtest 测试

8648) China Broadband Communications (Hong Kong, China) [0.00 km]
 
[root@la ~]# speedtest-cli --server 8648
Retrieving speedtest.net configuration...
Retrieving speedtest.net server list...
Testing from HostUS (172.106.32.137)...
Hosted by China Broadband Communications (Hong Kong) [11685.40 km]: 168.282 ms
Testing download speed........................................
Download: 1.68 Mbit/s
Testing upload speed..................................................
Upload: 8.44 Mbit/s
 
 
 
1536) STC (Hong Kong, China) [3.25 km]
 
[root@la ~]# speedtest-cli --server 1536
Retrieving speedtest.net configuration...
Retrieving speedtest.net server list...
Testing from HostUS (172.106.32.137)...
Hosted by STC (Hong Kong) [11683.63 km]: 569.722 ms
Testing download speed........................................
Download: 23.40 Mbit/s
Testing upload speed..................................................
Upload: 14.03 Mbit/s
 
 
 
8170) Atombase Global Datamation (Hong Kong, China) [6.53 km]
 
[root@la ~]# speedtest-cli --server 8170
Retrieving speedtest.net configuration...
Retrieving speedtest.net server list...
Testing from HostUS (172.106.32.137)...
Hosted by Atombase Global Datamation (Hong Kong) [11678.98 km]: 203.951 ms
Testing download speed........................................
Download: 28.40 Mbit/s
Testing upload speed..................................................
Upload: 17.68 Mbit/s
 
 
 
6852) FPT Telecom (Chai Wan, China) [7.86 km]
 
[root@la ~]# speedtest-cli --server 6852
Retrieving speedtest.net configuration...
Retrieving speedtest.net server list...
Testing from HostUS (172.106.32.137)...
Hosted by FPT Telecom (Chai Wan) [11678.65 km]: 300.909 ms
Testing download speed........................................
Download: 31.89 Mbit/s
Testing upload speed..................................................
Upload: 13.79 Mbit/s
 
 
 
5081) ShenZhen Telecom (Shenzhen, China) [34.06 km]
 
[root@la ~]# speedtest-cli --server 5081
Retrieving speedtest.net configuration...
Retrieving speedtest.net server list...
Testing from HostUS (172.106.32.137)...
Hosted by ShenZhen Telecom (Shenzhen) [11665.45 km]: 170.217 ms
Testing download speed........................................
Download: 12.20 Mbit/s
Testing upload speed..................................................
Upload: 6.08 Mbit/s
 
 
 
1849) CTM Internet Services (Macau, Macau) [63.72 km]
 
[root@la ~]# speedtest-cli --server 1849
Retrieving speedtest.net configuration...
Retrieving speedtest.net server list...
Testing from HostUS (172.106.32.137)...
Hosted by CTM Internet Services (Macau) [11732.32 km]: 254.144 ms
Testing download speed........................................
Download: 40.96 Mbit/s
Testing upload speed..................................................
Upload: 14.73 Mbit/s
 
 
 
3891) Unicom-GZ (Guangzhou, China) [134.80 km]
 
[root@la ~]# speedtest-cli --server 3891
Retrieving speedtest.net configuration...
Retrieving speedtest.net server list...
Testing from HostUS (172.106.32.137)...
Hosted by Unicom-GZ (Guangzhou) [11674.78 km]: 1469.16 ms
Testing download speed........................................
Download: 5.98 Mbit/s
Testing upload speed..................................................
Upload: 2.33 Mbit/s
 
 
 
5985) Hainan Unicom (Haikou, China) [466.43 km]
 
[root@la ~]# speedtest-cli --server 5985
Retrieving speedtest.net configuration...
Retrieving speedtest.net server list...
Testing from HostUS (172.106.32.137)...
Hosted by Hainan Unicom (Haikou) [12132.51 km]: 190.621 ms
Testing download speed........................................
Download: 31.88 Mbit/s
Testing upload speed..................................................
Upload: 15.44 Mbit/s
 
 
 
5506) china unicom (Xiamen, China) [468.88 km]
 
[root@la ~]# speedtest-cli --server 5506
Retrieving speedtest.net configuration...
Retrieving speedtest.net server list...
Testing from HostUS (172.106.32.137)...
Hosted by china unicom (Xiamen) [11232.31 km]: 387.545 ms
Testing download speed........................................
Download: 46.64 Mbit/s
Testing upload speed..................................................
Upload: 13.46 Mbit/s
 
 
 
6132) ChinaTelecom.Hunan (Changsha, China) [671.99 km]
 
[root@la ~]# speedtest-cli --server 6132
Retrieving speedtest.net configuration...
Retrieving speedtest.net server list...
Testing from HostUS (172.106.32.137)...
Hosted by ChinaTelecom.Hunan (Changsha) [11272.13 km]: 227.05 ms
Testing download speed........................................
Download: 45.00 Mbit/s
Testing upload speed..................................................
Upload: 9.71 Mbit/s
 
 
 
4870) Changsha, Hunan Unicom (Changsha, China) [671.99 km]
 
[root@la ~]# speedtest-cli --server 4870
Retrieving speedtest.net configuration...
Retrieving speedtest.net server list...
Testing from HostUS (172.106.32.137)...
Hosted by Changsha, Hunan Unicom (Changsha) [11272.13 km]: 493.691 ms
Testing download speed........................................
Download: 82.48 Mbit/s
Testing upload speed..................................................
Upload: 15.27 Mbit/s
 
 
 
4884) China Unicom FuJian (Fuzhou, China) [672.83 km]
 
[root@la ~]# speedtest-cli --server 4884
Retrieving speedtest.net configuration...
Retrieving speedtest.net server list...
Testing from HostUS (172.106.32.137)...
Hosted by China Unicom FuJian (Fuzhou) [11017.70 km]: 468.41 ms
Testing download speed........................................
Download: 42.31 Mbit/s
Testing upload speed..................................................
Upload: 14.57 Mbit/s
 
 
 
5204) Taiwan Fixed Network (Changhua, Taiwan) [677.49 km]
 
[root@la ~]# speedtest-cli --server 5204
Retrieving speedtest.net configuration...
Retrieving speedtest.net server list...
Testing from HostUS (172.106.32.137)...
Hosted by Taiwan Fixed Network (Changhua) [11097.39 km]: 302.588 ms
Testing download speed........................................
Download: 11.80 Mbit/s
Testing upload speed..................................................
Upload: 15.88 Mbit/s

0x05 IO测试

–0x05.1 基于dd的硬盘IO测试

[root@la ~]# dd bs=1M count=1024 if=/dev/zero of=1gb.test conv=fdatasync
记录了1024+0 的读入
记录了1024+0 的写出
1073741824字节(1.1 GB)已复制,1.2807 秒,838 MB/秒
[root@la ~]# dd bs=1M count=1024 if=/dev/zero of=1gb.test conv=fdatasync
记录了1024+0 的读入
记录了1024+0 的写出
1073741824字节(1.1 GB)已复制,1.14157 秒,941 MB/秒
[root@la ~]# dd bs=1M count=1024 if=/dev/zero of=1gb.test conv=fdatasync
记录了1024+0 的读入
记录了1024+0 的写出
1073741824字节(1.1 GB)已复制,1.03424 秒,1.0 GB/秒
[root@la ~]# dd bs=1M count=1024 if=/dev/zero of=1gb.test conv=fdatasync
记录了1024+0 的读入
记录了1024+0 的写出
1073741824字节(1.1 GB)已复制,1.16687 秒,920 MB/秒
[root@la ~]# dd bs=1M count=1024 if=/dev/zero of=1gb.test conv=fdatasync
记录了1024+0 的读入
记录了1024+0 的写出
1073741824字节(1.1 GB)已复制,0.88816 秒,1.2 GB/秒

–0x05.2 基于fio的硬盘IO测试

[root@la ~]# fio -filename=/root/bench/test.fio  -direct=1 -rw=randread -bs=4k -size 1G -numjobs=8 -runtime=30 -group_reporting -name=file
file: (g=0): rw=randread, bs=4K-4K/4K-4K/4K-4K, ioengine=psync, iodepth=1
...
fio-2.11-6-gaa7d2
Starting 8 processes
Jobs: 8 (f=8): [r(8)] [100.0% done] [458.7MB/0KB/0KB /s] [117K/0/0 iops] [eta 00m:00s]
file: (groupid=0, jobs=8): err= 0: pid=8063: Sun May 29 13:42:42 2016
  read : io=1903.4MB, bw=64953KB/s, iops=16238, runt= 30002msec
    clat (usec): min=18, max=476331, avg=491.05, stdev=4298.59
     lat (usec): min=18, max=476331, avg=491.28, stdev=4298.60
    clat percentiles (usec):
     |  1.00th=[   29],  5.00th=[   35], 10.00th=[   39], 20.00th=[   45],
     | 30.00th=[   50], 40.00th=[   55], 50.00th=[   59], 60.00th=[   64],
     | 70.00th=[   70], 80.00th=[   79], 90.00th=[   93], 95.00th=[  111],
     | 99.00th=[20864], 99.50th=[31360], 99.90th=[48896], 99.95th=[56576],
     | 99.99th=[98816]
    bw (KB  /s): min=  152, max=62624, per=12.18%, avg=7908.49, stdev=17663.85
    lat (usec) : 20=0.01%, 50=27.91%, 100=64.38%, 250=6.08%, 500=0.09%
    lat (usec) : 750=0.01%, 1000=0.01%
    lat (msec) : 2=0.01%, 4=0.01%, 10=0.09%, 20=0.38%, 50=0.96%
    lat (msec) : 100=0.08%, 250=0.01%, 500=0.01%
  cpu          : usr=0.50%, sys=1.86%, ctx=487334, majf=0, minf=273
  IO depths    : 1=100.0%, 2=0.0%, 4=0.0%, 8=0.0%, 16=0.0%, 32=0.0%, >=64=0.0%
     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=0.0%, >=64=0.0%
     issued    : total=r=487177/w=0/d=0, short=r=0/w=0/d=0, drop=r=0/w=0/d=0
     latency   : target=0, window=0, percentile=100.00%, depth=1

Run status group 0 (all jobs):
   READ: io=1903.4MB, aggrb=64952KB/s, minb=64952KB/s, maxb=64952KB/s, mint=30002msec, maxt=30002msec

Disk stats (read/write):
  vda: ios=473264/6, merge=0/18, ticks=228431/379, in_queue=228812, util=99.78%


[root@la ~]# fio -filename=/root/bench/test.fio  -direct=1 -rw=randread -bs=8k -size 1G -numjobs=8 -runtime=30 -group_reporting -name=file
file: (g=0): rw=randread, bs=8K-8K/8K-8K/8K-8K, ioengine=psync, iodepth=1
...
fio-2.11-6-gaa7d2
Starting 8 processes
Jobs: 8 (f=8): [r(8)] [100.0% done] [733.6MB/0KB/0KB /s] [93.9K/0/0 iops] [eta 00m:00s]
file: (groupid=0, jobs=8): err= 0: pid=8073: Sun May 29 13:43:10 2016
  read : io=8192.0MB, bw=813401KB/s, iops=101675, runt= 10313msec
    clat (usec): min=18, max=402090, avg=75.95, stdev=969.61
     lat (usec): min=19, max=402091, avg=76.19, stdev=969.61
    clat percentiles (usec):
     |  1.00th=[   30],  5.00th=[   36], 10.00th=[   41], 20.00th=[   47],
     | 30.00th=[   51], 40.00th=[   56], 50.00th=[   60], 60.00th=[   66],
     | 70.00th=[   72], 80.00th=[   82], 90.00th=[  102], 95.00th=[  135],
     | 99.00th=[  286], 99.50th=[  346], 99.90th=[  498], 99.95th=[  612],
     | 99.99th=[ 3600]
    bw (KB  /s): min=23744, max=126192, per=12.68%, avg=103137.26, stdev=19464.87
    lat (usec) : 20=0.01%, 50=26.02%, 100=63.05%, 250=9.44%, 500=1.38%
    lat (usec) : 750=0.06%, 1000=0.01%
    lat (msec) : 2=0.01%, 4=0.01%, 10=0.01%, 20=0.01%, 50=0.01%
    lat (msec) : 100=0.01%, 250=0.01%, 500=0.01%
  cpu          : usr=3.23%, sys=10.09%, ctx=1048882, majf=0, minf=291
  IO depths    : 1=100.0%, 2=0.0%, 4=0.0%, 8=0.0%, 16=0.0%, 32=0.0%, >=64=0.0%
     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=0.0%, >=64=0.0%
     issued    : total=r=1048576/w=0/d=0, short=r=0/w=0/d=0, drop=r=0/w=0/d=0
     latency   : target=0, window=0, percentile=100.00%, depth=1

Run status group 0 (all jobs):
   READ: io=8192.0MB, aggrb=813401KB/s, minb=813401KB/s, maxb=813401KB/s, mint=10313msec, maxt=10313msec

Disk stats (read/write):
  vda: ios=1047174/0, merge=0/0, ticks=59193/0, in_queue=59270, util=98.62%


[root@la ~]# fio -filename=/root/bench/test.fio  -direct=1 -rw=randread -bs=1m -size 1G -numjobs=8 -runtime=30 -group_reporting -name=file
file: (g=0): rw=randread, bs=1M-1M/1M-1M/1M-1M, ioengine=psync, iodepth=1
...
fio-2.11-6-gaa7d2
Starting 8 processes
Jobs: 6 (f=6)
file: (groupid=0, jobs=8): err= 0: pid=8083: Sun May 29 13:43:33 2016
  read : io=8192.0MB, bw=8569.4MB/s, iops=8569, runt=   956msec
    clat (usec): min=229, max=86747, avg=886.68, stdev=2640.32
     lat (usec): min=229, max=86748, avg=887.00, stdev=2640.32
    clat percentiles (usec):
     |  1.00th=[  294],  5.00th=[  334], 10.00th=[  370], 20.00th=[  434],
     | 30.00th=[  482], 40.00th=[  540], 50.00th=[  604], 60.00th=[  716],
     | 70.00th=[  892], 80.00th=[ 1144], 90.00th=[ 1448], 95.00th=[ 1704],
     | 99.00th=[ 2224], 99.50th=[ 2640], 99.90th=[66048], 99.95th=[66048],
     | 99.99th=[86528]
    bw (KB  /s): min=819200, max=1223054, per=11.53%, avg=1011714.25, stdev=135945.38
    lat (usec) : 250=0.04%, 500=33.25%, 750=29.13%, 1000=12.16%
    lat (msec) : 2=23.58%, 4=1.56%, 10=0.10%, 50=0.04%, 100=0.15%
  cpu          : usr=0.52%, sys=7.98%, ctx=8207, majf=0, minf=2310
  IO depths    : 1=100.0%, 2=0.0%, 4=0.0%, 8=0.0%, 16=0.0%, 32=0.0%, >=64=0.0%
     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=0.0%, >=64=0.0%
     issued    : total=r=8192/w=0/d=0, short=r=0/w=0/d=0, drop=r=0/w=0/d=0
     latency   : target=0, window=0, percentile=100.00%, depth=1

Run status group 0 (all jobs):
   READ: io=8192.0MB, aggrb=8569.4MB/s, minb=8569.4MB/s, maxb=8569.4MB/s, mint=956msec, maxt=956msec

Disk stats (read/write):
  vda: ios=23463/0, merge=0/0, ticks=19110/0, in_queue=19139, util=89.96%

0x06 基于RAMSpeed/SMP的内存测试

[root@la ramsmp-3.5.0]# ./ramsmp -b 1
RAMspeed/SMP (Linux) v3.5.0 by Rhett M. Hollander and Paul V. Bolotoff, 2002-09

8Gb per pass mode, 2 processes

INTEGER & WRITING         1 Kb block: 39087.89 MB/s
INTEGER & WRITING         2 Kb block: 39345.21 MB/s
INTEGER & WRITING         4 Kb block: 38251.48 MB/s
INTEGER & WRITING         8 Kb block: 39201.12 MB/s
INTEGER & WRITING        16 Kb block: 39244.50 MB/s
INTEGER & WRITING        32 Kb block: 38264.82 MB/s
INTEGER & WRITING        64 Kb block: 35072.09 MB/s
INTEGER & WRITING       128 Kb block: 34740.04 MB/s
INTEGER & WRITING       256 Kb block: 33507.12 MB/s
INTEGER & WRITING       512 Kb block: 30891.99 MB/s
INTEGER & WRITING      1024 Kb block: 31124.78 MB/s
INTEGER & WRITING      2048 Kb block: 30718.85 MB/s
INTEGER & WRITING      4096 Kb block: 30370.70 MB/s
INTEGER & WRITING      8192 Kb block: 23053.30 MB/s
INTEGER & WRITING     16384 Kb block: 12358.76 MB/s
INTEGER & WRITING     32768 Kb block: 10995.45 MB/s
[root@la ramsmp-3.5.0]# ./ramsmp -b 2
RAMspeed/SMP (Linux) v3.5.0 by Rhett M. Hollander and Paul V. Bolotoff, 2002-09

8Gb per pass mode, 2 processes

INTEGER & READING         1 Kb block: 78308.15 MB/s
INTEGER & READING         2 Kb block: 79676.05 MB/s
INTEGER & READING         4 Kb block: 79168.99 MB/s
INTEGER & READING         8 Kb block: 80566.45 MB/s
INTEGER & READING        16 Kb block: 80360.50 MB/s
INTEGER & READING        32 Kb block: 77453.96 MB/s
INTEGER & READING        64 Kb block: 57920.64 MB/s
INTEGER & READING       128 Kb block: 57608.81 MB/s
INTEGER & READING       256 Kb block: 50854.19 MB/s
INTEGER & READING       512 Kb block: 46841.05 MB/s
INTEGER & READING      1024 Kb block: 47809.78 MB/s
INTEGER & READING      2048 Kb block: 48277.86 MB/s
INTEGER & READING      4096 Kb block: 45638.58 MB/s
INTEGER & READING      8192 Kb block: 26506.58 MB/s
INTEGER & READING     16384 Kb block: 17031.79 MB/s
INTEGER & READING     32768 Kb block: 15238.69 MB/s
[root@la ramsmp-3.5.0]# ./ramsmp -b 3
RAMspeed/SMP (Linux) v3.5.0 by Rhett M. Hollander and Paul V. Bolotoff, 2002-09

8Gb per pass mode, 2 processes

INTEGER   Copy:      13267.47 MB/s
INTEGER   Scale:     13769.89 MB/s
INTEGER   Add:       14679.62 MB/s
INTEGER   Triad:     13380.04 MB/s
---
INTEGER   AVERAGE:   13774.26 MB/s

[root@la ramsmp-3.5.0]# ./ramsmp -b 4
RAMspeed/SMP (Linux) v3.5.0 by Rhett M. Hollander and Paul V. Bolotoff, 2002-09

8Gb per pass mode, 2 processes

FL-POINT & WRITING        1 Kb block: 38837.77 MB/s
FL-POINT & WRITING        2 Kb block: 39197.54 MB/s
FL-POINT & WRITING        4 Kb block: 38799.44 MB/s
FL-POINT & WRITING        8 Kb block: 38801.94 MB/s
FL-POINT & WRITING       16 Kb block: 39723.53 MB/s
FL-POINT & WRITING       32 Kb block: 38388.41 MB/s
FL-POINT & WRITING       64 Kb block: 34881.74 MB/s
FL-POINT & WRITING      128 Kb block: 34831.46 MB/s
FL-POINT & WRITING      256 Kb block: 34088.23 MB/s
FL-POINT & WRITING      512 Kb block: 31414.45 MB/s
FL-POINT & WRITING     1024 Kb block: 31342.23 MB/s
FL-POINT & WRITING     2048 Kb block: 31897.06 MB/s
FL-POINT & WRITING     4096 Kb block: 30761.64 MB/s
FL-POINT & WRITING     8192 Kb block: 23792.31 MB/s
FL-POINT & WRITING    16384 Kb block: 9479.26 MB/s
FL-POINT & WRITING    32768 Kb block: 11005.69 MB/s
[root@la ramsmp-3.5.0]# ./ramsmp -b 5
RAMspeed/SMP (Linux) v3.5.0 by Rhett M. Hollander and Paul V. Bolotoff, 2002-09

8Gb per pass mode, 2 processes

FL-POINT & READING        1 Kb block: 75675.74 MB/s
FL-POINT & READING        2 Kb block: 76237.23 MB/s
FL-POINT & READING        4 Kb block: 76959.71 MB/s
FL-POINT & READING        8 Kb block: 75403.05 MB/s
FL-POINT & READING       16 Kb block: 76566.47 MB/s
FL-POINT & READING       32 Kb block: 75125.59 MB/s
FL-POINT & READING       64 Kb block: 59462.58 MB/s
FL-POINT & READING      128 Kb block: 61999.14 MB/s
FL-POINT & READING      256 Kb block: 54567.50 MB/s
FL-POINT & READING      512 Kb block: 48247.89 MB/s
FL-POINT & READING     1024 Kb block: 45184.85 MB/s
FL-POINT & READING     2048 Kb block: 48836.55 MB/s
FL-POINT & READING     4096 Kb block: 48698.67 MB/s
FL-POINT & READING     8192 Kb block: 29096.53 MB/s
FL-POINT & READING    16384 Kb block: 17456.60 MB/s
FL-POINT & READING    32768 Kb block: 13622.21 MB/s
[root@la ramsmp-3.5.0]# ./ramsmp -b 6
RAMspeed/SMP (Linux) v3.5.0 by Rhett M. Hollander and Paul V. Bolotoff, 2002-09

8Gb per pass mode, 2 processes

FL-POINT  Copy:      12304.79 MB/s
FL-POINT  Scale:     11437.40 MB/s
FL-POINT  Add:       14000.12 MB/s
FL-POINT  Triad:     13156.85 MB/s
---
FL-POINT  AVERAGE:   12724.79 MB/s

0x07 基于UnixBench的系统基准测试

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

   System: la.hostus: GNU/Linux
   OS: GNU/Linux -- 3.10.0-327.18.2.el7.x86_64 -- #1 SMP Thu May 12 11:03:55 UTC 2016
   Machine: x86_64 (x86_64)
   Language: en_US.utf8 (charmap="UTF-8", collate="UTF-8")
   CPU 0: Intel(R) Xeon(R) CPU E5-2620 v3 @ 2.40GHz (4800.0 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
   CPU 1: Intel(R) Xeon(R) CPU E5-2620 v3 @ 2.40GHz (4800.0 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
   13:47:43 up  4:12,  2 users,  load average: 0.40, 0.69, 0.41; runlevel 2016-05-29

------------------------------------------------------------------------
Benchmark Run: 日 5月 29 2016 13:47:43 - 14:15:50
2 CPUs in system; running 1 parallel copy of tests

Dhrystone 2 using register variables       30024758.4 lps   (10.0 s, 7 samples)
Double-Precision Whetstone                     3821.0 MWIPS (9.8 s, 7 samples)
Execl Throughput                               3137.4 lps   (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks        837787.4 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks          219267.9 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks       1935587.1 KBps  (30.0 s, 2 samples)
Pipe Throughput                             1473286.5 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                 297858.6 lps   (10.0 s, 7 samples)
Process Creation                               8744.0 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                   6390.0 lpm   (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                   1306.4 lpm   (60.0 s, 2 samples)
System Call Overhead                        2211143.6 lps   (10.0 s, 7 samples)

System Benchmarks Index Values               BASELINE       RESULT    INDEX
Dhrystone 2 using register variables         116700.0   30024758.4   2572.8
Double-Precision Whetstone                       55.0       3821.0    694.7
Execl Throughput                                 43.0       3137.4    729.6
File Copy 1024 bufsize 2000 maxblocks          3960.0     837787.4   2115.6
File Copy 256 bufsize 500 maxblocks            1655.0     219267.9   1324.9
File Copy 4096 bufsize 8000 maxblocks          5800.0    1935587.1   3337.2
Pipe Throughput                               12440.0    1473286.5   1184.3
Pipe-based Context Switching                   4000.0     297858.6    744.6
Process Creation                                126.0       8744.0    694.0
Shell Scripts (1 concurrent)                     42.4       6390.0   1507.1
Shell Scripts (8 concurrent)                      6.0       1306.4   2177.3
System Call Overhead                          15000.0    2211143.6   1474.1
                                                                   ========
System Benchmarks Index Score                                        1348.4

------------------------------------------------------------------------
Benchmark Run: 日 5月 29 2016 14:15:50 - 14:43:56
2 CPUs in system; running 2 parallel copies of tests

Dhrystone 2 using register variables       59875649.1 lps   (10.0 s, 7 samples)
Double-Precision Whetstone                     7647.5 MWIPS (9.8 s, 7 samples)
Execl Throughput                               6405.7 lps   (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks        889383.5 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks          232971.4 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks       2123980.5 KBps  (30.0 s, 2 samples)
Pipe Throughput                             2935571.3 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                 593434.0 lps   (10.0 s, 7 samples)
Process Creation                              17945.5 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                   9513.4 lpm   (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                   1329.2 lpm   (60.0 s, 2 samples)
System Call Overhead                        3214573.0 lps   (10.0 s, 7 samples)

System Benchmarks Index Values               BASELINE       RESULT    INDEX
Dhrystone 2 using register variables         116700.0   59875649.1   5130.7
Double-Precision Whetstone                       55.0       7647.5   1390.5
Execl Throughput                                 43.0       6405.7   1489.7
File Copy 1024 bufsize 2000 maxblocks          3960.0     889383.5   2245.9
File Copy 256 bufsize 500 maxblocks            1655.0     232971.4   1407.7
File Copy 4096 bufsize 8000 maxblocks          5800.0    2123980.5   3662.0
Pipe Throughput                               12440.0    2935571.3   2359.8
Pipe-based Context Switching                   4000.0     593434.0   1483.6
Process Creation                                126.0      17945.5   1424.2
Shell Scripts (1 concurrent)                     42.4       9513.4   2243.7
Shell Scripts (8 concurrent)                      6.0       1329.2   2215.4
System Call Overhead                          15000.0    3214573.0   2143.0
                                                                   ========
System Benchmarks Index Score                                        2079.4

0x08 LAX02 OpenVZ 服务器信息/性能测试

服务器配置/套餐如下:

  • vCPU:2核心
  • 内存:1GB
  • 硬盘:SSD 50GB
  • IP地址:1个IPv4
  • 网络:1000M

洛杉矶数据中心的测试请点击下面的链接:

美国Hostus云服务器(VPS) – OpenVZ 达拉斯数据中心

pachosting购买链接    conoha / z.com购买链接    hostus购买链接

这里是pachosting香港机房和conoha新加坡机房的评测:

新加坡服务器(VPS) – 日本GMO

香港云服务器(VPS) – pachosting

测试的软件和手段如下:

  • ping
  • 路由追踪
  • wget测速
  • speedtest测速
  • 基于dd的硬盘IO测试
  • 基于fio的硬盘IO测试
  • 基于RAMSpeed/SMP的内存测试
  • 基于UnixBench的系统基准测试

0x09 ping / wget / 路由追踪

–0x09.1 ping测试

--- 104.128.233.235 ping statistics ---
3431 packets transmitted, 3425 packets received, 0.2% packet loss
round-trip min/avg/max/stddev = 171.387/180.288/331.478/20.678 ms

–0x09.2 wget测试

chunqideAir:~ terence$ wget https://104.128.233.235/128m.test --no-check-certificate
--2016-05-30 02:21:25--  https://104.128.233.235/128m.test
Connecting to 104.128.233.235:443... connected.
HTTP request sent, awaiting response... 200 OK
Length: 134217728 (128M)
Saving to: '128m.test.1'

2016-05-30 02:21:57 (4.12 MB/s) - '128m.test.1' saved [134217728/134217728]

–0x09.3 路由追踪

0x0A speedtest 测试

8648) China Broadband Communications (Hong Kong, China) [0.00 km]
 
[root@us bench]# speedtest-cli --server 8648
Retrieving speedtest.net configuration...
Retrieving speedtest.net server list...
Testing from HostUS (104.128.233.235)...
Hosted by China Broadband Communications (Hong Kong) [13051.65 km]: 186.277 ms
Testing download speed........................................
Download: 32.05 Mbit/s
Testing upload speed..................................................
Upload: 12.21 Mbit/s
 
 
 
1536) STC (Hong Kong, China) [3.25 km]
 
[root@us bench]# speedtest-cli --server 1536
Retrieving speedtest.net configuration...
Retrieving speedtest.net server list...
Testing from HostUS (104.128.233.235)...
Hosted by STC (Hong Kong) [13048.65 km]: 289.687 ms
Testing download speed........................................
Download: 16.21 Mbit/s
Testing upload speed..................................................
Upload: 12.29 Mbit/s
 
 
 
8170) Atombase Global Datamation (Hong Kong, China) [6.53 km]
 
[root@us bench]# speedtest-cli --server 8170
Retrieving speedtest.net configuration...
Retrieving speedtest.net server list...
Testing from HostUS (104.128.233.235)...
Hosted by Atombase Global Datamation (Hong Kong) [13045.65 km]: 190.7 ms
Testing download speed........................................
Download: 28.91 Mbit/s
Testing upload speed..................................................
Upload: 11.33 Mbit/s
 
 
 
6852) FPT Telecom (Chai Wan, China) [7.86 km]
 
[root@us bench]# speedtest-cli --server 6852
Retrieving speedtest.net configuration...
Retrieving speedtest.net server list...
Testing from HostUS (104.128.233.235)...
Hosted by FPT Telecom (Chai Wan) [13048.35 km]: 237.582 ms
Testing download speed........................................
Download: 38.88 Mbit/s
Testing upload speed..................................................
Upload: 5.56 Mbit/s
 
 
 
5081) ShenZhen Telecom (Shenzhen, China) [34.06 km]
 
[root@us bench]# speedtest-cli --server 5081
Retrieving speedtest.net configuration...
Retrieving speedtest.net server list...
Testing from HostUS (104.128.233.235)...
Hosted by ShenZhen Telecom (Shenzhen) [13019.64 km]: 223.967 ms
Testing download speed........................................
Download: 37.50 Mbit/s
Testing upload speed..................................................
Upload: 12.71 Mbit/s
 
 
 
1849) CTM Internet Services (Macau, Macau) [63.72 km]
 
[root@us bench]# speedtest-cli --server 1849
Retrieving speedtest.net configuration...
Retrieving speedtest.net server list...
Testing from HostUS (104.128.233.235)...
Hosted by CTM Internet Services (Macau) [13066.13 km]: 5102.57 ms
Testing download speed........................................
Download: 1.41 Mbit/s
Testing upload speed..................................................
Upload: 1.34 Mbit/s
 
 
 
3891) Unicom-GZ (Guangzhou, China) [134.80 km]
 
[root@us bench]# speedtest-cli --server 3891
Retrieving speedtest.net configuration...
Retrieving speedtest.net server list...
Testing from HostUS (104.128.233.235)...
Hosted by Unicom-GZ (Guangzhou) [12967.19 km]: 1214.505 ms
Testing download speed........................................
Download: 2.20 Mbit/s
Testing upload speed..................................................
Upload: 2.92 Mbit/s
 
 
 
5985) Hainan Unicom (Haikou, China) [466.43 km]
 
[root@us bench]# speedtest-cli --server 5985
Retrieving speedtest.net configuration...
Retrieving speedtest.net server list...
Testing from HostUS (104.128.233.235)...
Hosted by Hainan Unicom (Haikou) [13342.34 km]: 228.317 ms
Testing download speed........................................
Download: 28.59 Mbit/s
Testing upload speed..................................................
Upload: 9.89 Mbit/s
 
 
 
5506) china unicom (Xiamen, China) [468.88 km]
 
[root@us bench]# speedtest-cli --server 5506
Retrieving speedtest.net configuration...
Retrieving speedtest.net server list...
Testing from HostUS (104.128.233.235)...
Hosted by china unicom (Xiamen) [12740.69 km]: 312.928 ms
Testing download speed........................................
Download: 23.32 Mbit/s
Testing upload speed..................................................
Upload: 7.71 Mbit/s
 
 
 
6132) ChinaTelecom.Hunan (Changsha, China) [671.99 km]
 
[root@us bench]# speedtest-cli --server 6132
Retrieving speedtest.net configuration...
Retrieving speedtest.net server list...
Testing from HostUS (104.128.233.235)...
Hosted by ChinaTelecom.Hunan (Changsha) [12412.52 km]: 229.232 ms
Testing download speed........................................
Download: 21.29 Mbit/s
Testing upload speed..................................................
Upload: 1.47 Mbit/s
 
 
 
4870) Changsha, Hunan Unicom (Changsha, China) [671.99 km]
 
[root@us bench]# speedtest-cli --server 4870
Retrieving speedtest.net configuration...
Retrieving speedtest.net server list...
Testing from HostUS (104.128.233.235)...
Hosted by Changsha, Hunan Unicom (Changsha) [12412.52 km]: 471.209 ms
Testing download speed........................................
Download: 8.57 Mbit/s
Testing upload speed..................................................
Upload: 6.55 Mbit/s
 
 
 
4884) China Unicom FuJian (Fuzhou, China) [672.83 km]
 
[root@us bench]# speedtest-cli --server 4884
Retrieving speedtest.net configuration...
Retrieving speedtest.net server list...
Testing from HostUS (104.128.233.235)...
Hosted by China Unicom FuJian (Fuzhou) [12539.39 km]: 698.767 ms
Testing download speed........................................
Download: 19.20 Mbit/s
Testing upload speed..................................................
Upload: 9.57 Mbit/s
 
 
 
5204) Taiwan Fixed Network (Changhua, Taiwan) [677.49 km]
 
[root@us bench]# speedtest-cli --server 5204
Retrieving speedtest.net configuration...
Retrieving speedtest.net server list...
Testing from HostUS (104.128.233.235)...
Hosted by Taiwan Fixed Network (Changhua) [12743.95 km]: 200.708 ms
Testing download speed........................................
Download: 31.79 Mbit/s
Testing upload speed..................................................
Upload: 13.17 Mbit/s

0x0B IO测试

–0x0B.1 基于dd的硬盘IO测试

[root@us bench]# dd bs=1M count=1024 if=/dev/zero of=1gb.test conv=fdatasync
记录了1024+0 的读入
记录了1024+0 的写出
1073741824字节(1.1 GB)已复制,1.52726 秒,703 MB/秒
[root@us bench]# dd bs=1M count=1024 if=/dev/zero of=1gb.test conv=fdatasync
记录了1024+0 的读入
记录了1024+0 的写出
1073741824字节(1.1 GB)已复制,1.52074 秒,706 MB/秒
[root@us bench]# dd bs=1M count=1024 if=/dev/zero of=1gb.test conv=fdatasync
记录了1024+0 的读入
记录了1024+0 的写出
1073741824字节(1.1 GB)已复制,1.41446 秒,759 MB/秒
[root@us bench]# dd bs=1M count=1024 if=/dev/zero of=1gb.test conv=fdatasync
记录了1024+0 的读入
记录了1024+0 的写出
1073741824字节(1.1 GB)已复制,1.61006 秒,667 MB/秒
[root@us bench]# dd bs=1M count=1024 if=/dev/zero of=1gb.test conv=fdatasync
记录了1024+0 的读入
记录了1024+0 的写出
1073741824字节(1.1 GB)已复制,1.44513 秒,743 MB/秒

–0x0B.2 基于fio的硬盘IO测试

[root@us fio]# fio -filename=/root/bench/test.fio  -direct=1 -rw=randread -bs=4k -size 1G -numjobs=8 -runtime=30 -group_reporting -name=file
file: (g=0): rw=randread, bs=4K-4K/4K-4K/4K-4K, ioengine=psync, iodepth=1
...
fio-2.11-6-gaa7d2
Starting 8 processes
file: Laying out IO file(s) (1 file(s) / 1024MB)
Jobs: 8 (f=8): [r(8)] [100.0% done] [2566KB/0KB/0KB /s] [641/0/0 iops] [eta 00m:00s]
file: (groupid=0, jobs=8): err= 0: pid=22385: Sun May 29 14:53:57 2016
  read : io=68188KB, bw=2271.8KB/s, iops=567, runt= 30016msec
    clat (usec): min=2, max=271201, avg=14075.34, stdev=15176.73
     lat (usec): min=2, max=271202, avg=14075.82, stdev=15176.74
    clat percentiles (usec):
     |  1.00th=[    4],  5.00th=[   94], 10.00th=[ 2224], 20.00th=[ 3952],
     | 30.00th=[ 5664], 40.00th=[ 7392], 50.00th=[ 9024], 60.00th=[11840],
     | 70.00th=[16192], 80.00th=[21888], 90.00th=[32384], 95.00th=[42240],
     | 99.00th=[70144], 99.50th=[87552], 99.90th=[134144], 99.95th=[154624],
     | 99.99th=[224256]
    bw (KB  /s): min=   56, max=  464, per=12.50%, avg=283.96, stdev=64.94
    lat (usec) : 4=0.34%, 10=2.47%, 20=0.02%, 50=0.03%, 100=3.02%
    lat (usec) : 250=2.29%, 500=0.11%, 750=0.02%, 1000=0.01%
    lat (msec) : 2=0.92%, 4=11.00%, 10=34.79%, 20=22.69%, 50=19.14%
    lat (msec) : 100=2.88%, 250=0.27%, 500=0.01%
  cpu          : usr=0.08%, sys=0.26%, ctx=17547, majf=0, minf=326
  IO depths    : 1=100.0%, 2=0.0%, 4=0.0%, 8=0.0%, 16=0.0%, 32=0.0%, >=64=0.0%
     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=0.0%, >=64=0.0%
     issued    : total=r=17047/w=0/d=0, short=r=0/w=0/d=0, drop=r=0/w=0/d=0
     latency   : target=0, window=0, percentile=100.00%, depth=1

Run status group 0 (all jobs):
   READ: io=68188KB, aggrb=2271KB/s, minb=2271KB/s, maxb=2271KB/s, mint=30016msec, maxt=30016msec


[root@us fio]# fio -filename=/root/bench/test.fio  -direct=1 -rw=randread -bs=8k -size 1G -numjobs=8 -runtime=30 -group_reporting -name=file
file: (g=0): rw=randread, bs=8K-8K/8K-8K/8K-8K, ioengine=psync, iodepth=1
...
fio-2.11-6-gaa7d2
Starting 8 processes
Jobs: 8 (f=8): [r(8)] [100.0% done] [4504KB/0KB/0KB /s] [563/0/0 iops] [eta 00m:00s]
file: (groupid=0, jobs=8): err= 0: pid=22397: Sun May 29 14:54:48 2016
  read : io=139808KB, bw=4656.6KB/s, iops=582, runt= 30024msec
    clat (usec): min=3, max=255733, avg=13726.22, stdev=15475.43
     lat (usec): min=3, max=255733, avg=13726.69, stdev=15475.45
    clat percentiles (usec):
     |  1.00th=[    5],  5.00th=[    8], 10.00th=[  155], 20.00th=[ 3696],
     | 30.00th=[ 5408], 40.00th=[ 7136], 50.00th=[ 8768], 60.00th=[11200],
     | 70.00th=[15680], 80.00th=[21120], 90.00th=[31616], 95.00th=[41728],
     | 99.00th=[73216], 99.50th=[89600], 99.90th=[140288], 99.95th=[162816],
     | 99.99th=[195584]
    bw (KB  /s): min=  224, max= 1028, per=12.52%, avg=582.73, stdev=119.97
    lat (usec) : 4=0.11%, 10=5.33%, 20=0.06%, 50=0.02%, 100=1.78%
    lat (usec) : 250=2.95%, 500=0.07%, 1000=0.01%
    lat (msec) : 2=0.68%, 4=10.88%, 10=34.45%, 20=22.53%, 50=17.90%
    lat (msec) : 100=2.83%, 250=0.37%, 500=0.01%
  cpu          : usr=0.08%, sys=0.27%, ctx=17760, majf=0, minf=293
  IO depths    : 1=100.0%, 2=0.0%, 4=0.0%, 8=0.0%, 16=0.0%, 32=0.0%, >=64=0.0%
     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=0.0%, >=64=0.0%
     issued    : total=r=17476/w=0/d=0, short=r=0/w=0/d=0, drop=r=0/w=0/d=0
     latency   : target=0, window=0, percentile=100.00%, depth=1

Run status group 0 (all jobs):
   READ: io=139808KB, aggrb=4656KB/s, minb=4656KB/s, maxb=4656KB/s, mint=30024msec, maxt=30024msec


[root@us fio]# fio -filename=/root/bench/test.fio  -direct=1 -rw=randread -bs=1m -size 1G -numjobs=8 -runtime=30 -group_reporting -name=file
file: (g=0): rw=randread, bs=1M-1M/1M-1M/1M-1M, ioengine=psync, iodepth=1
...
fio-2.11-6-gaa7d2
Starting 8 processes
Jobs: 7 (f=7): [r(7),_(1)] [100.0% done] [3135MB/0KB/0KB /s] [3135/0/0 iops] [eta 00m:00s]
file: (groupid=0, jobs=8): err= 0: pid=22409: Sun May 29 14:55:10 2016
  read : io=8192.0MB, bw=1366.8MB/s, iops=1366, runt=  5994msec
    clat (usec): min=245, max=122408, avg=5764.90, stdev=12443.92
     lat (usec): min=245, max=122408, avg=5765.82, stdev=12443.84
    clat percentiles (usec):
     |  1.00th=[  342],  5.00th=[  386], 10.00th=[  434], 20.00th=[  506],
     | 30.00th=[  580], 40.00th=[  708], 50.00th=[ 1544], 60.00th=[ 2672],
     | 70.00th=[ 3536], 80.00th=[ 4384], 90.00th=[16320], 95.00th=[32640],
     | 99.00th=[65280], 99.50th=[75264], 99.90th=[95744], 99.95th=[111104],
     | 99.99th=[122368]
    bw (KB  /s): min=25026, max=463385, per=10.83%, avg=151520.22, stdev=136062.06
    lat (usec) : 250=0.01%, 500=19.18%, 750=22.14%, 1000=3.76%
    lat (msec) : 2=9.13%, 4=23.47%, 10=9.59%, 20=4.08%, 50=6.40%
    lat (msec) : 100=2.16%, 250=0.07%
  cpu          : usr=0.14%, sys=11.41%, ctx=30733, majf=0, minf=7472
  IO depths    : 1=100.0%, 2=0.0%, 4=0.0%, 8=0.0%, 16=0.0%, 32=0.0%, >=64=0.0%
     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=0.0%, >=64=0.0%
     issued    : total=r=8192/w=0/d=0, short=r=0/w=0/d=0, drop=r=0/w=0/d=0
     latency   : target=0, window=0, percentile=100.00%, depth=1

Run status group 0 (all jobs):
   READ: io=8192.0MB, aggrb=1366.8MB/s, minb=1366.8MB/s, maxb=1366.8MB/s, mint=5994msec, maxt=5994msec

0x0C 基于RAMSpeed/SMP的内存测试

[root@us ramsmp-3.5.0]# ./ramsmp -b 1
RAMspeed/SMP (Linux) v3.5.0 by Rhett M. Hollander and Paul V. Bolotoff, 2002-09

8Gb per pass mode, 2 processes

INTEGER & WRITING         1 Kb block: 33008.85 MB/s
INTEGER & WRITING         2 Kb block: 28424.86 MB/s
INTEGER & WRITING         4 Kb block: 33009.93 MB/s
INTEGER & WRITING         8 Kb block: 34221.96 MB/s
INTEGER & WRITING        16 Kb block: 33818.74 MB/s
INTEGER & WRITING        32 Kb block: 34261.68 MB/s
INTEGER & WRITING        64 Kb block: 30631.71 MB/s
INTEGER & WRITING       128 Kb block: 30348.27 MB/s
INTEGER & WRITING       256 Kb block: 27364.72 MB/s
INTEGER & WRITING       512 Kb block: 18072.08 MB/s
INTEGER & WRITING      1024 Kb block: 18195.87 MB/s
INTEGER & WRITING      2048 Kb block: 17384.70 MB/s
INTEGER & WRITING      4096 Kb block: 17967.32 MB/s
INTEGER & WRITING      8192 Kb block: 9446.23 MB/s
INTEGER & WRITING     16384 Kb block: 7244.83 MB/s
INTEGER & WRITING     32768 Kb block: 6785.31 MB/s
[root@us ramsmp-3.5.0]# ./ramsmp -b 2
RAMspeed/SMP (Linux) v3.5.0 by Rhett M. Hollander and Paul V. Bolotoff, 2002-09

8Gb per pass mode, 2 processes

INTEGER & READING         1 Kb block: 33080.77 MB/s
INTEGER & READING         2 Kb block: 34542.26 MB/s
INTEGER & READING         4 Kb block: 29567.29 MB/s
INTEGER & READING         8 Kb block: 33458.30 MB/s
INTEGER & READING        16 Kb block: 34246.89 MB/s
INTEGER & READING        32 Kb block: 33123.95 MB/s
INTEGER & READING        64 Kb block: 25519.24 MB/s
INTEGER & READING       128 Kb block: 24976.24 MB/s
INTEGER & READING       256 Kb block: 24097.45 MB/s
INTEGER & READING       512 Kb block: 22747.82 MB/s
INTEGER & READING      1024 Kb block: 22614.49 MB/s
INTEGER & READING      2048 Kb block: 23030.47 MB/s
INTEGER & READING      4096 Kb block: 21246.06 MB/s
INTEGER & READING      8192 Kb block: 13425.78 MB/s
INTEGER & READING     16384 Kb block: 9489.73 MB/s
INTEGER & READING     32768 Kb block: 7837.41 MB/s
[root@us ramsmp-3.5.0]# ./ramsmp -b 3
RAMspeed/SMP (Linux) v3.5.0 by Rhett M. Hollander and Paul V. Bolotoff, 2002-09

8Gb per pass mode, 2 processes

INTEGER   Copy:      6905.22 MB/s
INTEGER   Scale:     6826.10 MB/s
INTEGER   Add:       6233.98 MB/s
INTEGER   Triad:     7910.40 MB/s
---
INTEGER   AVERAGE:   6968.92 MB/s


[root@us ramsmp-3.5.0]# ./ramsmp -b 4
RAMspeed/SMP (Linux) v3.5.0 by Rhett M. Hollander and Paul V. Bolotoff, 2002-09

8Gb per pass mode, 2 processes

FL-POINT & WRITING        1 Kb block: 32211.46 MB/s
FL-POINT & WRITING        2 Kb block: 33426.08 MB/s
FL-POINT & WRITING        4 Kb block: 33873.35 MB/s
FL-POINT & WRITING        8 Kb block: 34354.83 MB/s
FL-POINT & WRITING       16 Kb block: 28602.27 MB/s
FL-POINT & WRITING       32 Kb block: 30540.63 MB/s
FL-POINT & WRITING       64 Kb block: 28798.68 MB/s
FL-POINT & WRITING      128 Kb block: 29719.51 MB/s
FL-POINT & WRITING      256 Kb block: 23813.50 MB/s
FL-POINT & WRITING      512 Kb block: 15934.66 MB/s
FL-POINT & WRITING     1024 Kb block: 15406.10 MB/s
FL-POINT & WRITING     2048 Kb block: 14314.09 MB/s
FL-POINT & WRITING     4096 Kb block: 14252.35 MB/s
FL-POINT & WRITING     8192 Kb block: 9099.59 MB/s
FL-POINT & WRITING    16384 Kb block: 5702.48 MB/s
FL-POINT & WRITING    32768 Kb block: 5728.87 MB/s
[root@us ramsmp-3.5.0]# ./ramsmp -b 5
RAMspeed/SMP (Linux) v3.5.0 by Rhett M. Hollander and Paul V. Bolotoff, 2002-09

8Gb per pass mode, 2 processes

FL-POINT & READING        1 Kb block: 34191.52 MB/s
FL-POINT & READING        2 Kb block: 34520.85 MB/s
FL-POINT & READING        4 Kb block: 34832.48 MB/s
FL-POINT & READING        8 Kb block: 33005.71 MB/s
FL-POINT & READING       16 Kb block: 34267.83 MB/s
FL-POINT & READING       32 Kb block: 33959.16 MB/s
FL-POINT & READING       64 Kb block: 29691.57 MB/s
FL-POINT & READING      128 Kb block: 29342.17 MB/s
FL-POINT & READING      256 Kb block: 20210.96 MB/s
FL-POINT & READING      512 Kb block: 25933.68 MB/s
FL-POINT & READING     1024 Kb block: 19932.47 MB/s
FL-POINT & READING     2048 Kb block: 21598.03 MB/s
FL-POINT & READING     4096 Kb block: 24701.16 MB/s
FL-POINT & READING     8192 Kb block: 8510.87 MB/s
FL-POINT & READING    16384 Kb block: 7915.60 MB/s
FL-POINT & READING    32768 Kb block: 7508.05 MB/s
[root@us ramsmp-3.5.0]# ./ramsmp -b 6
RAMspeed/SMP (Linux) v3.5.0 by Rhett M. Hollander and Paul V. Bolotoff, 2002-09

8Gb per pass mode, 2 processes

FL-POINT  Copy:      5914.16 MB/s
FL-POINT  Scale:     6057.14 MB/s
FL-POINT  Add:       6981.11 MB/s
FL-POINT  Triad:     7615.35 MB/s
---
FL-POINT  AVERAGE:   6641.94 MB/s

0x0D 基于UnixBench的系统基准测试

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

   System: us.vpn.c2.myguest.top: GNU/Linux
   OS: GNU/Linux -- 2.6.32-042stab112.15 -- #1 SMP Tue Oct 20 17:22:56 MSK 2015
   Machine: x86_64 (x86_64)
   Language: en_US.utf8 (charmap="UTF-8", collate="UTF-8")
   CPU 0: Intel(R) Xeon(R) CPU L5640 @ 2.27GHz (4533.2 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
   CPU 1: Intel(R) Xeon(R) CPU L5640 @ 2.27GHz (4533.2 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
   15:07:24 up 185 days, 18:27,  1 user,  load average: 0.08, 0.38, 0.42; runlevel 2015-11-25

------------------------------------------------------------------------
Benchmark Run: 日  5月 29 2016 15:07:24 - 15:35:47
2 CPUs in system; running 1 parallel copy of tests

Dhrystone 2 using register variables       22318457.3 lps   (10.0 s, 7 samples)
Double-Precision Whetstone                     2896.0 MWIPS (9.9 s, 7 samples)
Execl Throughput                               2662.1 lps   (29.8 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks        416389.4 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks          127681.2 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks        979723.2 KBps  (30.0 s, 2 samples)
Pipe Throughput                             1029935.3 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                 175609.4 lps   (10.0 s, 7 samples)
Process Creation                               7147.5 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                   3442.4 lpm   (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                    725.3 lpm   (60.1 s, 2 samples)
System Call Overhead                        1399166.1 lps   (10.0 s, 7 samples)

System Benchmarks Index Values               BASELINE       RESULT    INDEX
Dhrystone 2 using register variables         116700.0   22318457.3   1912.5
Double-Precision Whetstone                       55.0       2896.0    526.5
Execl Throughput                                 43.0       2662.1    619.1
File Copy 1024 bufsize 2000 maxblocks          3960.0     416389.4   1051.5
File Copy 256 bufsize 500 maxblocks            1655.0     127681.2    771.5
File Copy 4096 bufsize 8000 maxblocks          5800.0     979723.2   1689.2
Pipe Throughput                               12440.0    1029935.3    827.9
Pipe-based Context Switching                   4000.0     175609.4    439.0
Process Creation                                126.0       7147.5    567.3
Shell Scripts (1 concurrent)                     42.4       3442.4    811.9
Shell Scripts (8 concurrent)                      6.0        725.3   1208.8
System Call Overhead                          15000.0    1399166.1    932.8
                                                                   ========
System Benchmarks Index Score                                         858.9

------------------------------------------------------------------------
Benchmark Run: 日  5月 29 2016 15:35:47 - 16:04:13
2 CPUs in system; running 2 parallel copies of tests

Dhrystone 2 using register variables       44004154.7 lps   (10.0 s, 7 samples)
Double-Precision Whetstone                     5740.3 MWIPS (9.9 s, 7 samples)
Execl Throughput                               5832.7 lps   (29.9 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks        444196.5 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks          132061.8 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks       1121571.4 KBps  (30.0 s, 2 samples)
Pipe Throughput                             1997841.8 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                 339119.1 lps   (10.0 s, 7 samples)
Process Creation                              13177.6 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                   6158.9 lpm   (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                    811.5 lpm   (60.0 s, 2 samples)
System Call Overhead                        2310873.1 lps   (10.0 s, 7 samples)

System Benchmarks Index Values               BASELINE       RESULT    INDEX
Dhrystone 2 using register variables         116700.0   44004154.7   3770.7
Double-Precision Whetstone                       55.0       5740.3   1043.7
Execl Throughput                                 43.0       5832.7   1356.4
File Copy 1024 bufsize 2000 maxblocks          3960.0     444196.5   1121.7
File Copy 256 bufsize 500 maxblocks            1655.0     132061.8    798.0
File Copy 4096 bufsize 8000 maxblocks          5800.0    1121571.4   1933.7
Pipe Throughput                               12440.0    1997841.8   1606.0
Pipe-based Context Switching                   4000.0     339119.1    847.8
Process Creation                                126.0      13177.6   1045.8
Shell Scripts (1 concurrent)                     42.4       6158.9   1452.6
Shell Scripts (8 concurrent)                      6.0        811.5   1352.6
System Call Overhead                          15000.0    2310873.1   1540.6
                                                                   ========
System Benchmarks Index Score                                        1359.4

洛杉矶数据中心的测试请点击下面的链接:

美国Hostus云服务器(VPS) – OpenVZ 达拉斯数据中心

pachosting购买链接    conoha / z.com购买链接    hostus购买链接

这里是pachosting香港机房和conoha新加坡机房的评测:

新加坡服务器(VPS) – 日本GMO

香港云服务器(VPS) – pachosting