0x01 前言

因为用了3年的香港VPS IP被ban,经过协调无法更换IP,所以决定放弃原服务商。进而测试其他CN2线路的VPS服务商。在与网友沟通的过程中了解到魔方云旗下的子品牌:cubecloud,它香港的机房也使用CN2线路,而价格与配置也与我之前使用的相差无几,所以最近进行了测试与观察。

因为是国人开设的平台,我想是出于保护IP资源的缘故,禁止假设任何违反国内法律的服务,这也能理解,相关内容如下:

另外,因为香港机房带宽资源和费用的缘故,上下行带宽分别被限制在50Mbps左右,而且禁止提供大流量服务。如果长时间占用带宽,极有可能会被短时禁用或者永久禁用。

以下测试的时间均为中午时分。

0x02 配置

我写这篇文章的时候,香港节点有以下套餐:

而我选用“香港BGP – 1G”套餐用作测试。

详细配置如下:

  • CPU:2 vCPU
  • 内存:1G
  • 硬盘:15G SSD
  • 带宽:50Mbps
  • 流量:400G
  • IPv4:1
  • IPv6:25

经过检测发现宿主机所用的CPU与描述中的一致,为:

  • Intel(R) Xeon(R) CPU E5-2670 0 @ 2.60GHz

因为我有2颗vCPU核心,所以拥有5.2GHz。

[[email protected] UnixBench]# cat /proc/cpuinfo 
processor   : 0
vendor_id   : GenuineIntel
cpu family  : 6
model       : 45
model name  : Intel(R) Xeon(R) CPU E5-2670 0 @ 2.60GHz
stepping    : 7
microcode   : 0x1
cpu MHz     : 2599.998
cache size  : 16384 KB
physical id : 0
siblings    : 1
core id     : 0
cpu cores   : 1
apicid      : 0
initial apicid  : 0
fpu     : yes
fpu_exception   : yes
cpuid level : 13
wp      : yes
flags       : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon rep_good nopl xtopology eagerfpu pni pclmulqdq ssse3 cx16 pcid sse4_1 sse4_2 x2apic popcnt tsc_deadline_timer aes xsave avx hypervisor lahf_lm spec_ctrl ibpb_support tsc_adjust xsaveopt arat
bogomips    : 5199.99
clflush size    : 64
cache_alignment : 64
address sizes   : 46 bits physical, 48 bits virtual
power management:

 

经过测试,IPv4与所有IPv6均可以用。

0x03 网络测试

0x03.1 ping

--- 103.118.41.4 ping statistics ---
15852 packets transmitted, 15791 received, 0% packet loss, time 15868143ms
rtt min/avg/max/mdev = 16.113/19.462/166.854/8.453 ms

长ping测试共计发出15852次ping,收到15791次回应,丢失61次,接近0%丢包率。我在深圳,ping延迟均值为19ms所有,属于正常值。

0x03.2 wget

wget下载测试分为2部分,分别从我家里下载文件与从服务器下载文件,而服务端下载的文件为vultr.com的1gb测试文件:

[[email protected] temp]# wget https://hnd-jp-ping.vultr.com/vultr.com.1000MB.bin
--2019-06-24 23:23:48--  https://hnd-jp-ping.vultr.com/vultr.com.1000MB.bin
正在解析主机 hnd-jp-ping.vultr.com (hnd-jp-ping.vultr.com)... 108.61.201.151
正在连接 hnd-jp-ping.vultr.com (hnd-jp-ping.vultr.com)|108.61.201.151|:443... 已连接。
已发出 HTTP 请求,正在等待回应... 200 OK
长度:1048576000 (1000M) [application/octet-stream]
正在保存至: “vultr.com.1000MB.bin”

100%[===========================================>] 1,048,576,000 5.72MB/s 用时 2m 59s 

2019-06-24 23:26:48 (5.57 MB/s) - 已保存 “vultr.com.1000MB.bin” [1048576000/1048576000])

下载速度为5.72MB/s,符合标称带宽。以下为上行带宽:

[[email protected] tmp]# wget http://103.118.41.4/1gb-1.test
--2019-06-25 15:47:34--  http://103.118.41.4/1gb-1.test
正在连接 103.118.41.4:80... 已连接。
已发出 HTTP 请求,正在等待回应... 200 OK
长度:1073741824 (1.0G) [application/octet-stream]
正在保存至: “1gb-1.test”

100%[============================================>] 1,073,741,824 5.70MB/s 用时 3m 6s  

2019-06-25 15:50:40 (5.52 MB/s) - 已保存 “1gb-1.test” [1073741824/1073741824])

上行速度为5.7MB/s,也符合标称带宽。

50Mbps的网络速度在香港机房是非常可怕的,不知道长时间占用多长时间会被服务商封禁。

0x03.3 路由追踪

路由追踪也和wget下载测试一样分为两部分,以下是从服务器到我家宽带的追踪结果:

[[email protected] ~]# traceroute 113.92.159.7
traceroute to 113.92.159.7 (113.92.159.7), 30 hops max, 60 byte packets
 1  * * *
 2  * * *
 3  59.43.248.149 (59.43.248.149)  10.250 ms  10.199 ms 59.43.181.185 (59.43.181.185)  5.876 ms
 4  59.43.248.201 (59.43.248.201)  173.510 ms 59.43.250.81 (59.43.250.81)  10.778 ms 59.43.187.177 (59.43.187.177)  10.920 ms
 5  59.43.187.121 (59.43.187.121)  17.224 ms 59.43.187.149 (59.43.187.149)  50.718 ms 59.43.187.141 (59.43.187.141)  50.714 ms
 6  59.43.130.153 (59.43.130.153)  50.635 ms 59.43.130.105 (59.43.130.105)  45.005 ms 59.43.130.125 (59.43.130.125)  41.109 ms
 7  59.43.20.66 (59.43.20.66)  40.860 ms 59.43.114.46 (59.43.114.46)  40.248 ms  40.087 ms
 8  59.43.30.249 (59.43.30.249)  33.698 ms  122.484 ms *
 9  202.105.153.170 (202.105.153.170)  26.359 ms * 202.105.159.190 (202.105.159.190)  18.910 ms
10  202.105.153.174 (202.105.153.174)  25.249 ms * * 

因为我家宽带禁ping,所以第11跳到我家是超时,我并没有放上来。从第3跳开始到第8跳均为CN2线路,先到达广州在到深圳。以下为我家到服务器的追踪结果:

quanchunqideMacBook-Pro:~ terencechuen$ traceroute 103.118.41.4
traceroute to 103.118.41.4 (103.118.41.4), 64 hops max, 52 byte packets
 1  front.t.com (10.1.1.12)  87.670 ms  25.695 ms  44.242 ms
 2  pfsense.t.com (10.1.1.1)  50.998 ms  23.469 ms  47.264 ms
 3  113.92.156.1 (113.92.156.1)  27.769 ms  21.296 ms  55.462 ms
 4  61.146.244.201 (61.146.244.201)  19.579 ms
    61.146.244.213 (61.146.244.213)  26.801 ms
    202.105.159.201 (202.105.159.201)  19.527 ms
 5  183.56.65.18 (183.56.65.18)  10.670 ms
    183.56.65.22 (183.56.65.22)  13.503 ms
    183.56.65.66 (183.56.65.66)  18.533 ms
 6  59.43.80.117 (59.43.80.117)  12.609 ms  10.587 ms  14.007 ms
 7  59.43.130.126 (59.43.130.126)  21.250 ms  25.364 ms  25.436 ms
 8  59.43.187.122 (59.43.187.122)  26.542 ms  20.834 ms
    59.43.187.90 (59.43.187.90)  72.674 ms
 9  59.43.183.106 (59.43.183.106)  26.694 ms
    59.43.248.202 (59.43.248.202)  23.324 ms
    59.43.248.246 (59.43.248.246)  37.700 ms
10  59.43.247.94 (59.43.247.94)  36.330 ms  19.540 ms  16.110 ms
11  63.140.7.14 (63.140.7.14)  16.913 ms  54.340 ms  45.992 ms

同样的,数据先从深圳到广州,然后经过CN2线路直达香港。

0x03.4 speedtest

# 香港STC
[[email protected] ~]# speedtest-cli --server 1536
Retrieving speedtest.net configuration...
Testing from Rainbow network limited (103.118.41.4)...
Retrieving speedtest.net server list...
Retrieving information for the selected server...
Hosted by STC (Hong Kong) [0.00 km]: 17.978 ms
Testing download speed..............................
Download: 24.82 Mbit/s
Testing upload speed..............................
Upload: 48.44 Mbit/s

# 广州电信
[[email protected] ~]# speedtest-cli --server 17251
Retrieving speedtest.net configuration...
Testing from Rainbow network limited (103.118.41.4)...
Retrieving speedtest.net server list...
Retrieving information for the selected server...
Hosted by ChinaTelecom-GZ (Guangzhou) [134.80 km]: 133.394 ms
Testing download speed..............................
Download: 44.61 Mbit/s
Testing upload speed..............................
Upload: 40.44 Mbit/s

# 福建联通
[[email protected] ~]# speedtest-cli --server 4884
Retrieving speedtest.net configuration...
Testing from Rainbow network limited (103.118.41.4)...
Retrieving speedtest.net server list...
Retrieving information for the selected server...
Hosted by China Unicom FuJian (Fuzhou) [672.83 km]: 232.842 ms
Testing download speed..............................
Download: 37.34 Mbit/s
Testing upload speed..............................
Upload: 16.50 Mbit/s

# 上海移动
[[email protected] ~]# speedtest-cli --server 25637
Retrieving speedtest.net configuration...
Testing from Rainbow network limited (103.118.41.4)...
Retrieving speedtest.net server list...
Retrieving information for the selected server...
Hosted by Chinamobile-5G (Shanghai) [1232.40 km]: 81.469 ms
Testing download speed..............................
Download: 37.14 Mbit/s
Testing upload speed..............................
Upload: 28.87 Mbit/s

以上为3个节点的测试结果,结果如下:

  • 香港STC:
    • 下行:24.82 Mbit/s
    • 上行:48.44 Mbit/s
  • 广州电信:
    • 下行:44.61 Mbit/s
    • 上行:40.44 Mbit/s
  • 福建联通:
    • 下行:37.34 Mbit/s
    • 上行:16.50 Mbit/s
  • 上海移动:
    • 下行:37.14 Mbit/s
    • 上行:28.87 Mbit/s

0x04 性能测试

0x04.1 dd磁盘测试

[[email protected] temp]# dd bs=1M count=1024 if=/dev/zero of=1gb-1.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,4.20283 秒,255 MB/秒

[[email protected] temp]# dd bs=1M count=1024 if=/dev/zero of=1gb-2.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,4.73821 秒,227 MB/秒

[[email protected] temp]# dd bs=1M count=1024 if=/dev/zero of=1gb-3.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,4.73617 秒,227 MB/秒

[[email protected] temp]# dd bs=1M count=1024 if=/dev/zero of=1gb-4.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,6.4464 秒,167 MB/秒

[[email protected] temp]# dd bs=1M count=1024 if=/dev/zero of=1gb-5.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,4.59268 秒,234 MB/秒

经过5次dd命令的测试发现,速度在220MB/s左右,这个数值肯定是经过限制的,但这也能理解,速度完全能接受。

0x04.2 fio

CRC 加密测试:

[[email protected] fio]# ./fio fio -crctest
md5:          449.92 MiB/sec
crc64:        306.96 MiB/sec
crc32:        260.27 MiB/sec
crc32c:      7424.81 MiB/sec
crc16:        289.88 MiB/sec
crc7:         341.96 MiB/sec
sha1:         313.01 MiB/sec
sha256:       124.05 MiB/sec
sha512:       209.31 MiB/sec
xxhash:      4138.85 MiB/sec
murmur3:     2126.09 MiB/sec
jhash:       1464.10 MiB/sec
fnv:         5565.82 MiB/sec
sha3-224:      91.60 MiB/sec
sha3-256:      86.02 MiB/sec
sha3-384:      66.30 MiB/sec
sha3-512:      45.72 MiB/sec

4k随机读写测试:

[[email protected] fio]# fio -filename=/root/bench/test.fio  -direct=1 -rw=rw -bs=4k -size 2G -numjobs=8 -runtime=30 -group_reporting -name=file
file: (g=0): rw=rw, bs=(R) 4096B-4096B, (W) 4096B-4096B, (T) 4096B-4096B, ioengine=psync, iodepth=1
...
fio-3.14-6-g97134
Starting 8 processes
file: Laying out IO file (1 file / 2048MiB)
Jobs: 8 (f=8): [M(8)][100.0%][r=32.5MiB/s,w=32.7MiB/s][r=8307,w=8366 IOPS][eta 00m:00s]
file: (groupid=0, jobs=8): err= 0: pid=4061: Mon Jun 24 23:55:33 2019
  read: IOPS=7947, BW=31.0MiB/s (32.6MB/s)(932MiB/30009msec)
    clat (usec): min=42, max=15002, avg=499.05, stdev=506.13
     lat (usec): min=43, max=15004, avg=500.66, stdev=506.19
    clat percentiles (usec):
     |  1.00th=[   61],  5.00th=[   71], 10.00th=[   80], 20.00th=[   93],
     | 30.00th=[  106], 40.00th=[  126], 50.00th=[  208], 60.00th=[  603],
     | 70.00th=[  750], 80.00th=[  914], 90.00th=[ 1139], 95.00th=[ 1336],
     | 99.00th=[ 1811], 99.50th=[ 2057], 99.90th=[ 3785], 99.95th=[ 5473],
     | 99.99th=[10421]
   bw (  KiB/s): min=27952, max=35696, per=100.00%, avg=31790.93, stdev=216.18, samples=478
   iops        : min= 6988, max= 8924, avg=7947.66, stdev=54.03, samples=478
  write: IOPS=7958, BW=31.1MiB/s (32.6MB/s)(933MiB/30009msec)
    clat (usec): min=49, max=15038, avg=490.39, stdev=518.74
     lat (usec): min=50, max=15040, avg=492.10, stdev=518.82
    clat percentiles (usec):
     |  1.00th=[   66],  5.00th=[   73], 10.00th=[   79], 20.00th=[   89],
     | 30.00th=[   98], 40.00th=[  110], 50.00th=[  167], 60.00th=[  586],
     | 70.00th=[  742], 80.00th=[  906], 90.00th=[ 1123], 95.00th=[ 1336],
     | 99.00th=[ 1811], 99.50th=[ 2057], 99.90th=[ 4047], 99.95th=[ 6652],
     | 99.99th=[11338]
   bw (  KiB/s): min=27128, max=36702, per=100.00%, avg=31835.98, stdev=263.13, samples=478
   iops        : min= 6782, max= 9175, avg=7958.78, stdev=65.76, samples=478
  lat (usec)   : 50=0.03%, 100=29.07%, 250=21.57%, 500=4.66%, 750=14.76%
  lat (usec)   : 1000=14.75%
  lat (msec)   : 2=14.59%, 4=0.48%, 10=0.08%, 20=0.01%
  cpu          : usr=1.58%, sys=7.71%, ctx=850463, 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 rwts: total=238497,238835,0,0 short=0,0,0,0 dropped=0,0,0,0
     latency   : target=0, window=0, percentile=100.00%, depth=1

Run status group 0 (all jobs):
   READ: bw=31.0MiB/s (32.6MB/s), 31.0MiB/s-31.0MiB/s (32.6MB/s-32.6MB/s), io=932MiB (977MB), run=30009-30009msec
  WRITE: bw=31.1MiB/s (32.6MB/s), 31.1MiB/s-31.1MiB/s (32.6MB/s-32.6MB/s), io=933MiB (978MB), run=30009-30009msec

Disk stats (read/write):
  vda: ios=236777/237161, merge=0/5, ticks=16958/17147, in_queue=33905, util=73.75%

32k随机读写测试:

[[email protected] fio]# fio -filename=/root/bench/test.fio  -direct=1 -rw=rw -bs=32k -size 2G -numjobs=8 -runtime=30 -group_reporting -name=file
file: (g=0): rw=rw, bs=(R) 32.0KiB-32.0KiB, (W) 32.0KiB-32.0KiB, (T) 32.0KiB-32.0KiB, ioengine=psync, iodepth=1
...
fio-3.14-6-g97134
Starting 8 processes
Jobs: 8 (f=8): [M(8)][100.0%][r=206MiB/s,w=203MiB/s][r=6595,w=6492 IOPS][eta 00m:00s]
file: (groupid=0, jobs=8): err= 0: pid=4071: Mon Jun 24 23:56:27 2019
  read: IOPS=6744, BW=211MiB/s (221MB/s)(6324MiB/30004msec)
    clat (usec): min=46, max=96217, avg=587.56, stdev=698.28
     lat (usec): min=47, max=96219, avg=589.19, stdev=698.37
    clat percentiles (usec):
     |  1.00th=[   71],  5.00th=[   82], 10.00th=[   90], 20.00th=[  105],
     | 30.00th=[  120], 40.00th=[  143], 50.00th=[  237], 60.00th=[  685],
     | 70.00th=[  865], 80.00th=[ 1057], 90.00th=[ 1336], 95.00th=[ 1582],
     | 99.00th=[ 2278], 99.50th=[ 2835], 99.90th=[ 6521], 99.95th=[ 8029],
     | 99.99th=[13042]
   bw (  KiB/s): min=177555, max=243264, per=100.00%, avg=215834.30, stdev=1732.42, samples=479
   iops        : min= 5548, max= 7602, avg=6744.55, stdev=54.16, samples=479
  write: IOPS=6742, BW=211MiB/s (221MB/s)(6322MiB/30004msec)
    clat (usec): min=58, max=97640, avg=581.46, stdev=849.20
     lat (usec): min=59, max=97642, avg=583.86, stdev=849.32
    clat percentiles (usec):
     |  1.00th=[   79],  5.00th=[   87], 10.00th=[   93], 20.00th=[  104],
     | 30.00th=[  114], 40.00th=[  128], 50.00th=[  221], 60.00th=[  676],
     | 70.00th=[  865], 80.00th=[ 1057], 90.00th=[ 1319], 95.00th=[ 1582],
     | 99.00th=[ 2245], 99.50th=[ 2704], 99.90th=[ 6521], 99.95th=[ 8356],
     | 99.99th=[13435]
   bw (  KiB/s): min=181268, max=249408, per=100.00%, avg=215752.45, stdev=1923.28, samples=479
   iops        : min= 5664, max= 7794, avg=6742.00, stdev=60.12, samples=479
  lat (usec)   : 50=0.01%, 100=16.74%, 250=33.49%, 500=2.95%, 750=10.34%
  lat (usec)   : 1000=13.83%
  lat (msec)   : 2=20.99%, 4=1.44%, 10=0.19%, 20=0.03%, 50=0.01%
  lat (msec)   : 100=0.01%
  cpu          : usr=1.39%, sys=7.31%, ctx=722544, majf=0, minf=294
  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 rwts: total=202364,202299,0,0 short=0,0,0,0 dropped=0,0,0,0
     latency   : target=0, window=0, percentile=100.00%, depth=1

Run status group 0 (all jobs):
   READ: bw=211MiB/s (221MB/s), 211MiB/s-211MiB/s (221MB/s-221MB/s), io=6324MiB (6631MB), run=30004-30004msec
  WRITE: bw=211MiB/s (221MB/s), 211MiB/s-211MiB/s (221MB/s-221MB/s), io=6322MiB (6629MB), run=30004-30004msec

Disk stats (read/write):
  vda: ios=202341/201621, merge=0/26, ticks=17668/17843, in_queue=35359, util=75.95%

1m随机读写测试:

[[email protected] fio]# fio -filename=/root/bench/test.fio  -direct=1 -rw=rw -bs=1m -size 2G -numjobs=8 -runtime=30 -group_reporting -name=file
file: (g=0): rw=rw, bs=(R) 1024KiB-1024KiB, (W) 1024KiB-1024KiB, (T) 1024KiB-1024KiB, ioengine=psync, iodepth=1
...
fio-3.14-6-g97134
Starting 8 processes
Jobs: 8 (f=8): [M(8)][100.0%][r=1367MiB/s,w=1437MiB/s][r=1367,w=1437 IOPS][eta 00m:00s]
file: (groupid=0, jobs=8): err= 0: pid=4088: Mon Jun 24 23:57:19 2019
  read: IOPS=1409, BW=1410MiB/s (1478MB/s)(8029MiB/5695msec)
    clat (usec): min=269, max=19557, avg=2612.39, stdev=2608.17
     lat (usec): min=271, max=19559, avg=2614.14, stdev=2608.28
    clat percentiles (usec):
     |  1.00th=[  310],  5.00th=[  334], 10.00th=[  355], 20.00th=[  388],
     | 30.00th=[  424], 40.00th=[  482], 50.00th=[ 1778], 60.00th=[ 3261],
     | 70.00th=[ 3982], 80.00th=[ 4817], 90.00th=[ 6063], 95.00th=[ 7177],
     | 99.00th=[10290], 99.50th=[11863], 99.90th=[16188], 99.95th=[17171],
     | 99.99th=[19530]
   bw (  MiB/s): min= 1209, max= 1603, per=99.67%, avg=1405.12, stdev=14.89, samples=88
   iops        : min= 1209, max= 1602, avg=1404.36, stdev=14.90, samples=88
  write: IOPS=1467, BW=1467MiB/s (1538MB/s)(8355MiB/5695msec)
    clat (usec): min=264, max=19095, avg=2849.86, stdev=2649.66
     lat (usec): min=285, max=19177, avg=2878.50, stdev=2652.41
    clat percentiles (usec):
     |  1.00th=[  330],  5.00th=[  367], 10.00th=[  388], 20.00th=[  424],
     | 30.00th=[  478], 40.00th=[  611], 50.00th=[ 2606], 60.00th=[ 3523],
     | 70.00th=[ 4228], 80.00th=[ 5014], 90.00th=[ 6259], 95.00th=[ 7504],
     | 99.00th=[10552], 99.50th=[12256], 99.90th=[18220], 99.95th=[18482],
     | 99.99th=[19006]
   bw (  MiB/s): min= 1199, max= 1752, per=99.80%, avg=1464.18, stdev=21.72, samples=88
   iops        : min= 1199, max= 1752, avg=1463.45, stdev=21.70, samples=88
  lat (usec)   : 500=37.73%, 750=7.10%, 1000=1.50%
  lat (msec)   : 2=2.41%, 4=19.71%, 10=30.30%, 20=1.25%
  cpu          : usr=0.94%, sys=6.19%, ctx=29696, majf=0, minf=283
  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 rwts: total=8029,8355,0,0 short=0,0,0,0 dropped=0,0,0,0
     latency   : target=0, window=0, percentile=100.00%, depth=1

Run status group 0 (all jobs):
   READ: bw=1410MiB/s (1478MB/s), 1410MiB/s-1410MiB/s (1478MB/s-1478MB/s), io=8029MiB (8419MB), run=5695-5695msec
  WRITE: bw=1467MiB/s (1538MB/s), 1467MiB/s-1467MiB/s (1538MB/s-1538MB/s), io=8355MiB (8761MB), run=5695-5695msec

Disk stats (read/write):
  vda: ios=23742/24723, merge=0/1, ticks=6014/8505, in_queue=14400, util=85.50%

磁盘性能优异,可以满足建站数据库的IO需求。

0x04.3 ramsmp

[[email protected] 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: 45142.41 MB/s
INTEGER & WRITING         2 Kb block: 44066.94 MB/s
INTEGER & WRITING         4 Kb block: 43806.58 MB/s
INTEGER & WRITING         8 Kb block: 40139.74 MB/s
INTEGER & WRITING        16 Kb block: 42045.90 MB/s
INTEGER & WRITING        32 Kb block: 44595.87 MB/s
INTEGER & WRITING        64 Kb block: 40527.02 MB/s
INTEGER & WRITING       128 Kb block: 40645.91 MB/s
INTEGER & WRITING       256 Kb block: 37791.09 MB/s
INTEGER & WRITING       512 Kb block: 33703.93 MB/s
INTEGER & WRITING      1024 Kb block: 32810.49 MB/s
INTEGER & WRITING      2048 Kb block: 31270.32 MB/s
INTEGER & WRITING      4096 Kb block: 31673.51 MB/s
INTEGER & WRITING      8192 Kb block: 24289.44 MB/s
INTEGER & WRITING     16384 Kb block: 15607.49 MB/s
INTEGER & WRITING     32768 Kb block: 13302.32 MB/s
[[email protected] 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: 87817.28 MB/s
INTEGER & READING         2 Kb block: 86177.05 MB/s
INTEGER & READING         4 Kb block: 87203.25 MB/s
INTEGER & READING         8 Kb block: 87532.48 MB/s
INTEGER & READING        16 Kb block: 87042.43 MB/s
INTEGER & READING        32 Kb block: 87997.20 MB/s
INTEGER & READING        64 Kb block: 60152.45 MB/s
INTEGER & READING       128 Kb block: 59282.73 MB/s
INTEGER & READING       256 Kb block: 51561.78 MB/s
INTEGER & READING       512 Kb block: 44697.05 MB/s
INTEGER & READING      1024 Kb block: 43020.82 MB/s
INTEGER & READING      2048 Kb block: 43211.86 MB/s
INTEGER & READING      4096 Kb block: 38726.76 MB/s
INTEGER & READING      8192 Kb block: 23284.37 MB/s
INTEGER & READING     16384 Kb block: 16825.80 MB/s
INTEGER & READING     32768 Kb block: 15147.93 MB/s
[[email protected] 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:      17611.72 MB/s
INTEGER   Scale:     16829.60 MB/s
INTEGER   Add:       17858.31 MB/s
INTEGER   Triad:     18683.61 MB/s
---
INTEGER   AVERAGE:   17745.81 MB/s

[[email protected] 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: 45712.23 MB/s
FL-POINT & WRITING        2 Kb block: 45940.58 MB/s
FL-POINT & WRITING        4 Kb block: 46172.02 MB/s
FL-POINT & WRITING        8 Kb block: 45723.61 MB/s
FL-POINT & WRITING       16 Kb block: 45868.64 MB/s
FL-POINT & WRITING       32 Kb block: 43355.04 MB/s
FL-POINT & WRITING       64 Kb block: 36825.58 MB/s
FL-POINT & WRITING      128 Kb block: 40326.25 MB/s
FL-POINT & WRITING      256 Kb block: 37154.22 MB/s
FL-POINT & WRITING      512 Kb block: 34026.89 MB/s
FL-POINT & WRITING     1024 Kb block: 33211.68 MB/s
FL-POINT & WRITING     2048 Kb block: 32393.15 MB/s
FL-POINT & WRITING     4096 Kb block: 31359.91 MB/s
FL-POINT & WRITING     8192 Kb block: 22182.43 MB/s
FL-POINT & WRITING    16384 Kb block: 14873.41 MB/s
FL-POINT & WRITING    32768 Kb block: 13909.00 MB/s
[[email protected] 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: 45163.77 MB/s
FL-POINT & READING        2 Kb block: 45641.98 MB/s
FL-POINT & READING        4 Kb block: 43520.99 MB/s
FL-POINT & READING        8 Kb block: 41236.50 MB/s
FL-POINT & READING       16 Kb block: 43639.01 MB/s
FL-POINT & READING       32 Kb block: 46468.81 MB/s
FL-POINT & READING       64 Kb block: 45347.90 MB/s
FL-POINT & READING      128 Kb block: 44775.45 MB/s
FL-POINT & READING      256 Kb block: 42469.50 MB/s
FL-POINT & READING      512 Kb block: 41735.53 MB/s
FL-POINT & READING     1024 Kb block: 41238.04 MB/s
FL-POINT & READING     2048 Kb block: 40835.03 MB/s
FL-POINT & READING     4096 Kb block: 40187.82 MB/s
FL-POINT & READING     8192 Kb block: 26469.01 MB/s
FL-POINT & READING    16384 Kb block: 17975.76 MB/s
FL-POINT & READING    32768 Kb block: 17679.39 MB/s
[[email protected] 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:      13034.13 MB/s
FL-POINT  Scale:     13454.45 MB/s
FL-POINT  Add:       17346.80 MB/s
FL-POINT  Triad:     17541.83 MB/s
---
FL-POINT  AVERAGE:   15344.30 MB/s

内存性能也中规中矩,毕竟是DDR3服务器的内存,性能也不会有太大差异。

0x04.4 Unix Benchmark

# Unix Benchmark
========================================================================
   BYTE UNIX Benchmarks (Version 5.1.3)

   System: hk2: GNU/Linux
   OS: GNU/Linux -- 3.10.0-693.17.1.el7.x86_64 -- #1 SMP Thu Jan 25 20:13:58 UTC 2018
   Machine: x86_64 (x86_64)
   Language: en_US.utf8 (charmap="UTF-8", collate="UTF-8")
   CPU 0: Intel(R) Xeon(R) CPU E5-2670 0 @ 2.60GHz (5200.0 bogomips)
          x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
   CPU 1: Intel(R) Xeon(R) CPU E5-2670 0 @ 2.60GHz (5200.0 bogomips)
          x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
   02:21:39 up  3:09,  1 user,  load average: 0.00, 0.01, 0.05; runlevel 2019-06-24

------------------------------------------------------------------------
Benchmark Run: 二 6月 25 2019 02:21:39 - 02:49:47
2 CPUs in system; running 1 parallel copy of tests

Dhrystone 2 using register variables       33017714.6 lps   (10.0 s, 7 samples)
Double-Precision Whetstone                     3964.0 MWIPS (9.9 s, 7 samples)
Execl Throughput                               1502.7 lps   (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks        216647.8 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks           57698.7 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks        715857.9 KBps  (30.0 s, 2 samples)
Pipe Throughput                              328033.9 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                  65604.0 lps   (10.0 s, 7 samples)
Process Creation                               4478.0 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                   3490.1 lpm   (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                    754.1 lpm   (60.1 s, 2 samples)
System Call Overhead                         263404.2 lps   (10.0 s, 7 samples)

System Benchmarks Index Values               BASELINE       RESULT    INDEX
Dhrystone 2 using register variables         116700.0   33017714.6   2829.3
Double-Precision Whetstone                       55.0       3964.0    720.7
Execl Throughput                                 43.0       1502.7    349.5
File Copy 1024 bufsize 2000 maxblocks          3960.0     216647.8    547.1
File Copy 256 bufsize 500 maxblocks            1655.0      57698.7    348.6
File Copy 4096 bufsize 8000 maxblocks          5800.0     715857.9   1234.2
Pipe Throughput                               12440.0     328033.9    263.7
Pipe-based Context Switching                   4000.0      65604.0    164.0
Process Creation                                126.0       4478.0    355.4
Shell Scripts (1 concurrent)                     42.4       3490.1    823.1
Shell Scripts (8 concurrent)                      6.0        754.1   1256.9
System Call Overhead                          15000.0     263404.2    175.6
                                                                   ========
System Benchmarks Index Score                                         527.9

------------------------------------------------------------------------
Benchmark Run: 二 6月 25 2019 02:49:47 - 03:17:54
2 CPUs in system; running 2 parallel copies of tests

Dhrystone 2 using register variables       66211241.4 lps   (10.0 s, 7 samples)
Double-Precision Whetstone                     8032.5 MWIPS (9.9 s, 7 samples)
Execl Throughput                               3100.0 lps   (29.9 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks        426913.1 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks          107510.0 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks       1375466.7 KBps  (30.0 s, 2 samples)
Pipe Throughput                              653768.1 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                 133489.5 lps   (10.0 s, 7 samples)
Process Creation                               9267.0 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                   5802.3 lpm   (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                    797.4 lpm   (60.1 s, 2 samples)
System Call Overhead                         524011.0 lps   (10.0 s, 7 samples)

System Benchmarks Index Values               BASELINE       RESULT    INDEX
Dhrystone 2 using register variables         116700.0   66211241.4   5673.6
Double-Precision Whetstone                       55.0       8032.5   1460.4
Execl Throughput                                 43.0       3100.0    720.9
File Copy 1024 bufsize 2000 maxblocks          3960.0     426913.1   1078.1
File Copy 256 bufsize 500 maxblocks            1655.0     107510.0    649.6
File Copy 4096 bufsize 8000 maxblocks          5800.0    1375466.7   2371.5
Pipe Throughput                               12440.0     653768.1    525.5
Pipe-based Context Switching                   4000.0     133489.5    333.7
Process Creation                                126.0       9267.0    735.5
Shell Scripts (1 concurrent)                     42.4       5802.3   1368.5
Shell Scripts (8 concurrent)                      6.0        797.4   1329.0
System Call Overhead                          15000.0     524011.0    349.3
                                                                   ========
System Benchmarks Index Score                                         982.9

可惜宿主机使用的是初代E5-26系列的CPU,性能不太理想,即使在单核分数仅有527.9,而双核分数为982.9,较其他服务商低,但也能满足基本建站需求。

0x05 结语

对于一款月付只需要69元,带宽高达50Mbps的香港CN2线路的VPS,还需要考虑吗?因为是初次接触,还不知道该厂商的客服质量如何。

在我实际的使用中发现centos 7的系统模板有问题,yum居然存在数据库异常,首次使用需要自行修复,这个问题对于技术水平较低的朋友可能难以解决。

经过近一周的测试,尚未发现其他问题。以下为我的推广链接,如果大家感兴趣,欢迎点击以下链接后购买,让我能有服务器放置我的博客:

https://www.cubecloud.net/aff.php?aff=1533

感谢!