打算重新给大家介绍一下iozoom，为什么呢？因为机房、网络、带宽。iozoom刚成立的时候用的是psychz的机房，估计是不满意鸡迷路？反正后来转换了用的sharktech的，接入电信北美骨干+联通北美骨干网络，1000M端口，由sharktech提供20G不缩水的DDOS保护，你知道那个鸡迷路的20G DDOS保护多数时候就是一个玩具…
主机测评以前写过iozoom的vps的测评，现在暂时手头没有他们家的VPS，也就不能来个二次测评了，大家凑合着看第一次写的吧：iozoom-洛杉矶KVM最低款VPS简单测评，性能强悍！
洛杉矶
测试IP：107.167.5.195 ，接入了中国电信和中国联通，网络了得！
芝加哥
测试IP: 204.188.245.67
文章目录
官方网站： www.iozoom.com
KVM 2GB【最低款VPS】
内存：2G
硬盘：20G SSD
CPU：1核
流量：2000G/月
价格：7美元
优惠码：LET
广州电信的不明真相的吃瓜群众表示很惊讶：
C:\Users\gy>ping 107.167.5.195 -t
正在 Ping 107.167.5.195 具有 32 字节的数据:
来自 107.167.5.195 的回复: 字节=32 时间=157ms TTL=52
来自 107.167.5.195 的回复: 字节=32 时间=155ms TTL=52
来自 107.167.5.195 的回复: 字节=32 时间=154ms TTL=52
来自 107.167.5.195 的回复: 字节=32 时间=157ms TTL=52
来自 107.167.5.195 的回复: 字节=32 时间=155ms TTL=52
来自 107.167.5.195 的回复: 字节=32 时间=154ms TTL=52
来自 107.167.5.195 的回复: 字节=32 时间=155ms TTL=52
来自 107.167.5.195 的回复: 字节=32 时间=155ms TTL=52
来自 107.167.5.195 的回复: 字节=32 时间=155ms TTL=52
来自 107.167.5.195 的回复: 字节=32 时间=157ms TTL=52
来自 107.167.5.195 的回复: 字节=32 时间=155ms TTL=52
来自 107.167.5.195 的回复: 字节=32 时间=155ms TTL=52
来自 107.167.5.195 的回复: 字节=32 时间=156ms TTL=52
来自 107.167.5.195 的回复: 字节=32 时间=157ms TTL=52
来自 107.167.5.195 的回复: 字节=32 时间=157ms TTL=52
来自 107.167.5.195 的回复: 字节=32 时间=157ms TTL=52
来自 107.167.5.195 的回复: 字节=32 时间=155ms TTL=52
来自 107.167.5.195 的回复: 字节=32 时间=155ms TTL=52
来自 107.167.5.195 的回复: 字节=32 时间=157ms TTL=52
来自 107.167.5.195 的回复: 字节=32 时间=155ms TTL=52
来自 107.167.5.195 的回复: 字节=32 时间=156ms TTL=52
来自 107.167.5.195 的回复: 字节=32 时间=157ms TTL=52
来自 107.167.5.195 的回复: 字节=32 时间=157ms TTL=52
来自 107.167.5.195 的回复: 字节=32 时间=155ms TTL=52
来自 107.167.5.195 的回复: 字节=32 时间=157ms TTL=52
来自 107.167.5.195 的回复: 字节=32 时间=157ms TTL=52
107.167.5.195 的 Ping 统计信息:
数据包: 已发送 = 26，已接收 = 26，丢失 = 0 (0% 丢失)，
往返行程的估计时间(以毫秒为单位):
最短 = 154ms，最长 = 157ms，平均 = 155ms
Control-C
^C
广州电信tracert 吃瓜群众表示是鲨鱼机房？
| Host | % | Sent | Recv | Best | Avrg | Wrst | Last |
| 192.168.63.1 | 0 | 25 | 25 | 2 | 2 | 8 | 2 |
| No response from host | 100 | 4 | 0 | 0 | 0 | 0 | 0 |
| 14.23.61.73 | 0 | 25 | 25 | 3 | 142 | 1183 | 3 |
| 121.33.196.125 | 0 | 25 | 25 | 2 | 11 | 140 | 3 |
| 183.56.31.37 | 0 | 25 | 25 | 2 | 4 | 6 | 5 |
| 58.61.216.121 | 0 | 25 | 25 | 3 | 4 | 7 | 4 |
| 202.97.33.150 | 45 | 9 | 5 | 0 | 4 | 7 | 7 |
| 202.97.34.66 | 24 | 13 | 10 | 0 | 6 | 10 | 4 |
| 202.97.52.218 | 0 | 25 | 25 | 165 | 168 | 171 | 171 |
| 202.97.52.238 | 0 | 25 | 25 | 161 | 168 | 193 | 164 |
| te0-2-2.chinatelecom.edge01.onewilshire.la.ca.sharktech.net | 0 | 25 | 25 | 160 | 164 | 185 | 161 |
| 10.0.0.6 | 0 | 25 | 25 | 154 | 159 | 201 | 162 |
| lax.iozoom.com | 0 | 25 | 25 | 153 | 154 | 156 | 154 |
本人测试了一下天津联通的tracert走法：
从天津联通–北京联通–美国加利福尼亚州圣何塞 联通–美国加利福尼亚州圣何塞–美国加利福尼亚州洛杉矶–美国加利福尼亚州洛杉矶 sharktech.net
也就是说天津经过北京然后直达了美国加州，在加州境内的圣何塞转入洛杉矶，联通这样的走法也是相当的漂亮了！
经过多个节点的联通线路测试，除了深圳联通是直接去了香港联通，然后直接到美国加州的，其余的全部都是经过北京联通节点直接到美国加州的，整体来说效果都是很理想的！
下面数据不是本人测试的结果，从国外转载而来：
------------------------------------------------------------------------
Benchmark Run: Sat Jul 02 2016 22:45:06 - 23:13:15
1 CPU in system; running 1 parallel copy of tests
Dhrystone 2 using register variables 28439217.5 lps (10.0 s, 7 samples)
Double-Precision Whetstone 3506.7 MWIPS (9.8 s, 7 samples)
Execl Throughput 5800.7 lps (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 1088163.2 KBps (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 313189.7 KBps (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 2142705.0 KBps (30.0 s, 2 samples)
Pipe Throughput 1954010.4 lps (10.0 s, 7 samples)
Pipe-based Context Switching 391524.6 lps (10.0 s, 7 samples)
Process Creation 15155.3 lps (30.0 s, 2 samples)
Shell Scripts (1 concurrent) 9024.5 lpm (60.0 s, 2 samples)
Shell Scripts (8 concurrent) 1183.0 lpm (60.0 s, 2 samples)
System Call Overhead 3934875.8 lps (10.0 s, 7 samples)
System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 28439217.5 2437.0
Double-Precision Whetstone 55.0 3506.7 637.6
Execl Throughput 43.0 5800.7 1349.0
File Copy 1024 bufsize 2000 maxblocks 3960.0 1088163.2 2747.9
File Copy 256 bufsize 500 maxblocks 1655.0 313189.7 1892.4
File Copy 4096 bufsize 8000 maxblocks 5800.0 2142705.0 3694.3
Pipe Throughput 12440.0 1954010.4 1570.7
Pipe-based Context Switching 4000.0 391524.6 978.8
Process Creation 126.0 15155.3 1202.8
Shell Scripts (1 concurrent) 42.4 9024.5 2128.4
Shell Scripts (8 concurrent) 6.0 1183.0 1971.7
System Call Overhead 15000.0 3934875.8 2623.3
========
System Benchmarks Index Score 1749.1
------------------------------------------------------------------------
Benchmark Run: Sat Jul 02 2016 23:13:15 - 23:41:22
1 CPU in system; running 1 parallel copy of tests
Dhrystone 2 using register variables 28343653.9 lps (10.0 s, 7 samples)
Double-Precision Whetstone 3506.0 MWIPS (9.8 s, 7 samples)
Execl Throughput 5789.1 lps (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 1085087.1 KBps (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 312795.5 KBps (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 2162312.9 KBps (30.0 s, 2 samples)
Pipe Throughput 1947864.2 lps (10.0 s, 7 samples)
Pipe-based Context Switching 392665.5 lps (10.0 s, 7 samples)
Process Creation 15724.9 lps (30.0 s, 2 samples)
Shell Scripts (1 concurrent) 9047.9 lpm (60.0 s, 2 samples)
Shell Scripts (8 concurrent) 1185.0 lpm (60.0 s, 2 samples)
System Call Overhead 3932525.8 lps (10.0 s, 7 samples)
System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 28343653.9 2428.8
Double-Precision Whetstone 55.0 3506.0 637.5
Execl Throughput 43.0 5789.1 1346.3
File Copy 1024 bufsize 2000 maxblocks 3960.0 1085087.1 2740.1
File Copy 256 bufsize 500 maxblocks 1655.0 312795.5 1890.0
File Copy 4096 bufsize 8000 maxblocks 5800.0 2162312.9 3728.1
Pipe Throughput 12440.0 1947864.2 1565.8
Pipe-based Context Switching 4000.0 392665.5 981.7
Process Creation 126.0 15724.9 1248.0
Shell Scripts (1 concurrent) 42.4 9047.9 2133.9
Shell Scripts (8 concurrent) 6.0 1185.0 1975.0
System Call Overhead 15000.0 3932525.8 2621.7
========
System Benchmarks Index Score 1754.9
I/O Pings
ioping -c 10 request=1 time=0.2 ms request=2 time=0.3 ms request=3 time=0.2 ms request=4 time=0.3 ms request=5 time=0.3 ms request=6 time=0.2 ms request=7 time=0.2 ms request=8 time=0.3 ms request=9 time=0.2 ms request=10 time=0.2 ms 10 requests completed in 9004.1 ms, 3981 iops, 15.6 mb/s
I/O Seek Test (No Cache)
ioping -RD 8077 iops, 31.6 mb/s min/avg/max/mdev = 0.1/0.1/0.6/0.0 ms
I/O Reads – Sequential
ioping -RL 3255 iops, 813.8 mb/s min/avg/max/mdev = 0.3/0.3/13.0/0.2 ms
I/O Reads – Cached
ioping -RC 501619 iops, 1959.4 mb/s min/avg/max/mdev = 0.0/0.0/0.0/0.0 ms
DD
dd if=/dev/zero of=sb-io-test bs=1M count=1k conv=fdatasync 1.049 s, 1.0 GB/s
dd if=/dev/zero of=sb-io-test bs=64k count=16k conv=fdatasync 0.884909 s, 1.2 GB/s
dd if=/dev/zero of=sb-io-test bs=1M count=1k oflag=dsync 2.35989 s, 455 MB/s
dd if=/dev/zero of=sb-io-test bs=64k count=16k oflag=dsync 13.3407 s, 80.5 MB/s
FIO
| Read IOPS | 77097.0 |
| Read Bandwidth | 308.3 MB/second |
| Write IOPS | 46391.0 |
| Write Bandwidth | 185.5 MB/second |
Raw FIO Output
FIO random reads:
randomreads: (g=0): rw=randread, bs=4K-4K/4K-4K, ioengine=libaio, iodepth=64
fio-2.0.9
Starting 1 process
randomreads: Laying out IO file(s) (1 file(s) / 1024MB)
randomreads: (groupid=0, jobs=1): err= 0: pid=16539: Sat Jul 2 22:42:20 2016
read : io=1024.3MB, bw=308388KB/s, iops=77097 , runt= 3401msec
cpu : usr=11.53%, sys=52.71%, ctx=4831, majf=0, minf=69
IO depths : 1=0.1%, 2=0.1%, 4=0.1%, 8=0.1%, 16=0.1%, 32=0.1%, >=64=100.0%
submit : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=0.0%, >=64=0.0%
complete : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=0.1%, >=64=0.0%
issued : total=r=262207/w=0/d=0, short=r=0/w=0/d=0
Run status group 0 (all jobs):
READ: io=1024.3MB, aggrb=308388KB/s, minb=308388KB/s, maxb=308388KB/s, mint=3401msec,
maxt=3401msec
Disk stats (read/write):
vda: ios=250246/0, merge=0/0, ticks=135136/0, in_queue=135096, util=94.47%
Done
FIO random writes:
randomwrites: (g=0): rw=randwrite, bs=4K-4K/4K-4K, ioengine=libaio, iodepth=64
fio-2.0.9
Starting 1 process
randomwrites: (groupid=0, jobs=1): err= 0: pid=16543: Sat Jul 2 22:42:26 2016
write: io=1024.3MB, bw=185568KB/s, iops=46391 , runt= 5652msec
cpu : usr=5.66%, sys=21.24%, ctx=14379, majf=0, minf=5
IO depths : 1=0.1%, 2=0.1%, 4=0.1%, 8=0.1%, 16=0.1%, 32=0.1%, >=64=100.0%
submit : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=0.0%, >=64=0.0%
complete : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=0.1%, >=64=0.0%
issued : total=r=0/w=262207/d=0, short=r=0/w=0/d=0
Run status group 0 (all jobs):
WRITE: io=1024.3MB, aggrb=185567KB/s, minb=185567KB/s, maxb=185567KB/s, mint=5652msec,
maxt=5652msec
Disk stats (read/write):
vda: ios=0/250606, merge=0/0, ticks=0/312824, in_queue=312772, util=96.80%
Done
网络下载测试：
| Location | Rate |
|---|---|
| Cachefly | 86.1 MB/s |
| Linode, Atlanta, GA, USA | 14.4 MB/s |
| Linode, Dallas, TX, USA | 26.9 MB/s |
| Linode, Tokyo, JP | 16.7 MB/s |
| Linode, London, UK | 6.81 MB/s |
| OVH, Paris, France | 7.86 MB/s |
| SmartDC, Rotterdam, Netherlands | 6.21 MB/s |
| Hetzner, Nuernberg, Germany | 4.71 MB/s |
| iiNet, Perth, WA, Australia | 6.97 MB/s |
| Leaseweb, Haarlem, NL | 9.10 MB/s |
| Leaseweb, Manassas, VA, USA | 15.5 MB/s |
| Softlayer, Singapore | 5.86 MB/s |
| Softlayer, Seattle, WA, USA | 36.8 MB/s |
| Softlayer, San Jose, CA, USA | 65.4 MB/s |
| Softlayer, Washington, DC, USA | 22.9 MB/s |
