腾讯云主机的 IO 惨不忍睹

V2EX = way to explore

V2EX 是一个关于分享和探索的地方

现在注册

已注册用户请登录

这是一个创建于 1893 天前的主题，其中的信息可能已经有所发展或是发生改变。

1U1G1M 的主机，活动的时候购买的，随机 IO 不到 10M/s, 大家测试一下自己的服务器，看看是不是活动主机的 IO 都是这么差。

测试流程

安装 sysbench

yum install sysbench

准备测试数据

sysbench fileio --file-total-size=2G --file-num=100  --file-test-mode=rndrw prepare

开始测试

sysbench fileio --file-total-size=2G --file-num=100  --file-test-mode=rndrw run

收集测试结果

[root@VM_45_207_centos ~]# sysbench fileio --file-total-size=2G --file-num=100  --file-test-mode=rndrw run
sysbench 1.0.17 (using system LuaJIT 2.0.4)

Running the test with following options:
Number of threads: 1
Initializing random number generator from current time


Extra file open flags: (none)
100 files, 20.48MiB each
2GiB total file size
Block size 16KiB
Number of IO requests: 0
Read/Write ratio for combined random IO test: 1.50
Periodic FSYNC enabled, calling fsync() each 100 requests.
Calling fsync() at the end of test, Enabled.
Using synchronous I/O mode
Doing random r/w test
Initializing worker threads...

Threads started!


File operations:
    reads/s:                      137.04
    writes/s:                     91.33
    fsyncs/s:                     237.99

Throughput:
    read, MiB/s:                  2.14
    written, MiB/s:               1.43

General statistics:
    total time:                          10.0825s
    total number of events:              4603

Latency (ms):
         min:                                    0.00
         avg:                                    2.17
         max:                                   23.14
         95th percentile:                        5.67
         sum:                                 9988.99

Threads fairness:
    events (avg/stddev):           4603.0000/0.00
    execution time (avg/stddev):   9.9890/0.00

下面是我在本地机械硬盘上的虚拟机测试的测试结果，虚拟机软件 VMware WorkStation

 ⚡ root@dev2  ~   master  sysbench fileio --file-test-mode=rndrw  run
sysbench 1.0.17 (using bundled LuaJIT 2.1.0-beta2)

Running the test with following options:
Number of threads: 1
Initializing random number generator from current time


Extra file open flags: (none)
128 files, 16MiB each
2GiB total file size
Block size 16KiB
Number of IO requests: 0
Read/Write ratio for combined random IO test: 1.50
Periodic FSYNC enabled, calling fsync() each 100 requests.
Calling fsync() at the end of test, Enabled.
Using synchronous I/O mode
Doing random r/w test
Initializing worker threads...

Threads started!


File operations:
    reads/s:                      5081.59
    writes/s:                     3387.73
    fsyncs/s:                     10846.47

Throughput:
    read, MiB/s:                  79.40
    written, MiB/s:               52.93

General statistics:
    total time:                          10.0160s
    total number of events:              193399

Latency (ms):
         min:                                    0.00
         avg:                                    0.05
         max:                                    5.00
         95th percentile:                        0.16
         sum:                                 9856.46

Threads fairness:
    events (avg/stddev):           193399.0000/0.00
    execution time (avg/stddev):   9.8565/0.00

62 条回复 • 2019-10-28 21:43:02 +08:00

zhybb2010

2019-09-29 13:52:49 +08:00

[root@VM_0_16_centos test]# sysbench fileio --file-total-size=2G --file-num=100 --file-test-mode=rndrw run
sysbench 1.0.17 (using system LuaJIT 2.0.4)

Running the test with following options:
Number of threads: 1
Initializing random number generator from current time

Extra file open flags: (none)
100 files, 20.48MiB each
2GiB total file size
Block size 16KiB
Number of IO requests: 0
Read/Write ratio for combined random IO test: 1.50
Periodic FSYNC enabled, calling fsync() each 100 requests.
Calling fsync() at the end of test, Enabled.
Using synchronous I/O mode
Doing random r/w test
Initializing worker threads...

Threads started!

File operations:
reads/s: 327.70
writes/s: 218.47
fsyncs/s: 550.14

Throughput:
read, MiB/s: 5.12
written, MiB/s: 3.41

General statistics:
total time: 10.0682s
total number of events: 10940

Latency (ms):
min: 0.01
avg: 0.91
max: 24.51
95th percentile: 2.30
sum: 9966.85

Threads fairness:
events (avg/stddev): 10940.0000/0.00
execution time (avg/stddev): 9.9668/0.00

前天买的 99/year.

U2Fsd

2019-09-29 13:53:58 +08:00

是真的差。。所以还得另外买个 RDS 数据库

lihongjie0209

2019-09-29 13:54:07 +08:00

@zhybb2010 #1 感谢反馈，这个 IO 不是一般的差啊

lihongjie0209

2019-09-29 13:54:49 +08:00

@U2Fsd #2 嗯，也就只能跑应用服务器了

ahmcsxcc

2019-09-29 13:55:19 +08:00

我的腾讯云连 ssh 得等一两分钟才能连上

lihongjie0209

2019-09-29 13:57:36 +08:00

@ahmcsxcc #5 开 ssh 日志看看

tinybaby365

2019-09-29 13:59:31 +08:00 via iPhone

只是给你打日志用的，希望你是无状态的服务，其他都买买买

zhybb2010

2019-09-29 14:06:11 +08:00

跑跑爬虫脚本，上传到 oss 还行的

ahmcsxcc

2019-09-29 14:19:37 +08:00

File operations:
reads/s: 118.65
writes/s: 79.10
fsyncs/s: 206.56

Throughput:
read, MiB/s: 1.85
written, MiB/s: 1.24

General statistics:
total time: 10.1114s
total number of events: 3989

Latency (ms):
min: 0.00
avg: 2.50
max: 101.73
95th percentile: 6.43
sum: 9984.63

Threads fairness:
events (avg/stddev): 3989.0000/0.00
execution time (avg/stddev): 9.9846/0.00

lihongjie0209

2019-09-29 14:20:31 +08:00

@ahmcsxcc #9 你这个更惨

eason1874

2019-09-29 14:20:37 +08:00

你们对低配特价主机这么高预期的吗？

在我眼里，这些一百几十块的特价主机能稳定跑一些轻量应用就够了，从不指望在性能方面能有好的表现。

lihongjie0209

2019-09-29 14:22:11 +08:00

@eason1874 #11 我基本的预期是比普通机械硬盘慢 30%左右，毕竟是虚拟机。现在感觉我想多了

dalibaxiaoliba

2019-09-29 14:25:35 +08:00 via Android

@ahmcsxcc 这个也太黑了吧

mikeguan

2019-09-29 14:30:30 +08:00 via Android

@lihongjie0209 #12 按照磁盘大小限速，10g 磁盘和 100g 磁盘 IO 是不一样的，磁盘大小到达一定值就不限速了这就达到磁盘本身的限制。

lihongjie0209

2019-09-29 14:31:15 +08:00

@mikeguan #14 长知识的，谢谢

infra

2019-09-29 14:36:51 +08:00

提工单把限速打开就可以了吧

liuhuansir

2019-09-29 14:41:34 +08:00

Running the test with following options:
Number of threads: 1
Initializing random number generator from current time

Extra file open flags: (none)
100 files, 20.48MiB each
2GiB total file size
Block size 16KiB
Number of IO requests: 0
Read/Write ratio for combined random IO test: 1.50
Periodic FSYNC enabled, calling fsync() each 100 requests.
Calling fsync() at the end of test, Enabled.
Using synchronous I/O mode
Doing random r/w test
Initializing worker threads...

Threads started!

File operations:
reads/s: 768.69
writes/s: 512.40
fsyncs/s: 1285.47

Throughput:
read, MiB/s: 12.00
written, MiB/s: 8.00

General statistics:
total time: 10.0208s
total number of events: 25656

Latency (ms):
min: 0.00
avg: 0.39
max: 15.98
95th percentile: 0.83
sum: 9919.53

Threads fairness:
events (avg/stddev): 25656.0000/0.00
execution time (avg/stddev): 9.9195/0.00
我这个什么水平

lihongjie0209

2019-09-29 14:43:25 +08:00

@liuhuansir #17 超过了目前统计的 99.99%

heiheidewo

2019-09-29 14:54:07 +08:00

不懂为啥会被限速？ https://www.v2ex.com/t/300804 这里也有一个帖子，阿里云的

opengps

2019-09-29 14:55:07 +08:00

所有云都这样，虚拟机硬盘 io 都严重损失，ssd 的才勉强跟物理机机械硬盘划等号

liuhuansir

2019-09-29 14:59:18 +08:00

@lihongjie0209 难道跟活动的价格有关么？我的是 700 多买了三年，不像现在这么便宜

liuxu

2019-09-29 15:03:22 +08:00

真惨。。
[root@VM_0_9_centos ~]# sysbench fileio --file-total-size=2G --file-num=100 --file-test-mode=rndrw run
sysbench 1.0.17 (using system LuaJIT 2.0.4)

Running the test with following options:
Number of threads: 1
Initializing random number generator from current time

Extra file open flags: (none)
100 files, 20.48MiB each
2GiB total file size
Block size 16KiB
Number of IO requests: 0
Read/Write ratio for combined random IO test: 1.50
Periodic FSYNC enabled, calling fsync() each 100 requests.
Calling fsync() at the end of test, Enabled.
Using synchronous I/O mode
Doing random r/w test
Initializing worker threads...

Threads started!

File operations:
reads/s: 776.46
writes/s: 517.64
fsyncs/s: 1300.47

Throughput:
read, MiB/s: 12.13
written, MiB/s: 8.09

General statistics:
total time: 10.0436s
total number of events: 25964

Latency (ms):
min: 0.00
avg: 0.38
max: 28.53
95th percentile: 1.67
sum: 9949.76

Threads fairness:
events (avg/stddev): 25964.0000/0.00
execution time (avg/stddev): 9.9498/0.00

liuxu

2019-09-29 15:04:38 +08:00

@liuhuansir 看来你我是邻居了

CallMeReznov

2019-09-29 15:07:21 +08:00

File operations:
reads/s: 730.94
writes/s: 487.29
fsyncs/s: 1223.22

Throughput:
read, MiB/s: 11.42
written, MiB/s: 7.61

General statistics:
total time: 10.0127s
total number of events: 24350

Latency (ms):
min: 0.01
avg: 0.41
max: 99.49
95th percentile: 1.14
sum: 9959.39

Threads fairness:
events (avg/stddev): 24350.0000/0.00
execution time (avg/stddev): 9.9594/0.00

祖传 BUG 价阿里新加坡的测试数据

其实阿里云也一样,14 还是 15 年我刚接触云这块,公司的数据库服务器就直接扔云上的,8G 4C.
结果突然某一天夜里业务爆卡,查询仅有的一些日志也看不出个所以然.
进数据库看是某些线程锁死了,就直接给 KILL 了,可半个小时又炸了.
折腾了两天,最后在别人提点下查了一下 DISK TIME, 一路狂飙.........
直接买了台新主机把数据库迁移过去就解决了.... 找阿里云问,人家也回答不出个所以然.
但好巧不巧,没几天人阿里云就出了 SSD 云盘了....

fredcc

2019-09-29 15:08:00 +08:00

非活动 2 核 4G 机器

sysbench 1.0.17 (using system LuaJIT 2.0.4)

Running the test with following options:
Number of threads: 1
Initializing random number generator from current time

Extra file open flags: (none)
100 files, 20.48MiB each
2GiB total file size
Block size 16KiB
Number of IO requests: 0
Read/Write ratio for combined random IO test: 1.50
Periodic FSYNC enabled, calling fsync() each 100 requests.
Calling fsync() at the end of test, Enabled.
Using synchronous I/O mode
Doing random r/w test
Initializing worker threads...

Threads started!

File operations:
reads/s: 748.40
writes/s: 498.93
fsyncs/s: 1256.11

Throughput:
read, MiB/s: 11.69
written, MiB/s: 7.79

General statistics:
total time: 10.0198s
total number of events: 24988

Latency (ms):
min: 0.00
avg: 0.40
max: 31.54
95th percentile: 1.42
sum: 9982.82

Threads fairness:
events (avg/stddev): 24988.0000/0.00
execution time (avg/stddev): 9.9828/0.00

ColoThor

2019-09-29 15:09:22 +08:00

sysbench 1.0.17 (using system LuaJIT 2.0.4)

Running the test with following options:
Number of threads: 1
Initializing random number generator from current time

Extra file open flags: (none)
100 files, 20.48MiB each
2GiB total file size
Block size 16KiB
Number of IO requests: 0
Read/Write ratio for combined random IO test: 1.50
Periodic FSYNC enabled, calling fsync() each 100 requests.
Calling fsync() at the end of test, Enabled.
Using synchronous I/O mode
Doing random r/w test
Initializing worker threads...

Threads started!

File operations:
reads/s: 1777.52
writes/s: 1184.95
fsyncs/s: 2966.86

Throughput:
read, MiB/s: 27.77
written, MiB/s: 18.51

General statistics:
total time: 10.0087s
total number of events: 59256

Latency (ms):
min: 0.00
avg: 0.17
max: 37.48
95th percentile: 0.69
sum: 9968.93

Threads fairness:
events (avg/stddev): 59256.0000/0.00
execution time (avg/stddev): 9.9689/0.00
阿里云 4 核 8G5M，腾讯云学生机就惨不忍睹了

lihongjie0209

2019-09-29 15:13:12 +08:00

@ColoThor
@fredcc
付费用户就是快

pota

2019-09-29 15:19:39 +08:00

sysbench 1.0.17 (using system LuaJIT 2.0.4)

Running the test with following options:
Number of threads: 1
Initializing random number generator from current time

Extra file open flags: (none)
100 files, 20.48MiB each
2GiB total file size
Block size 16KiB
Number of IO requests: 0
Read/Write ratio for combined random IO test: 1.50
Periodic FSYNC enabled, calling fsync() each 100 requests.
Calling fsync() at the end of test, Enabled.
Using synchronous I/O mode
Doing random r/w test
Initializing worker threads...

Threads started!

File operations:
reads/s: 287.95
writes/s: 191.97
fsyncs/s: 486.88

Throughput:
read, MiB/s: 4.50
written, MiB/s: 3.00

General statistics:
total time: 10.0618s
total number of events: 9630

Latency (ms):
min: 0.00
avg: 1.03
max: 22.61
95th percentile: 2.81
sum: 9962.83

Threads fairness:
events (avg/stddev): 9630.0000/0.00
execution time (avg/stddev): 9.9628/0.00

很久之前买的学生主机。。。

airyland

2019-09-29 15:24:51 +08:00

我有这么一台机子，经常因为搜狗(不带 ua 的非标准爬虫)的爬虫突然蜂拥过来导致 io 飙升然后无响应宕机。

silencefent

2019-09-29 15:25:23 +08:00

你机械硬盘比我 sata3 口上的 intel S3500 快 40%?
File operations:
reads/s: 3497.78
writes/s: 2331.85
fsyncs/s: 5833.52

Throughput:
read, MiB/s: 54.63
written, MiB/s: 36.42

General statistics:
total time: 10.0135s
total number of events: 116739

Latency (ms):
min: 0.00
avg: 0.08
max: 0.89
95th percentile: 0.24
sum: 9882.63

Threads fairness:
events (avg/stddev): 116739.0000/0.00
execution time (avg/stddev): 9.8826/0.00

oldw4ng

2019-09-29 15:27:42 +08:00

sysbench 1.0.17 (using system LuaJIT 2.0.4)

Running the test with following options:
Number of threads: 1
Initializing random number generator from current time

Extra file open flags: (none)
100 files, 20.48MiB each
2GiB total file size
Block size 16KiB
Number of IO requests: 0
Read/Write ratio for combined random IO test: 1.50
Periodic FSYNC enabled, calling fsync() each 100 requests.
Calling fsync() at the end of test, Enabled.
Using synchronous I/O mode
Doing random r/w test
Initializing worker threads...

Threads started!

File operations:
reads/s: 760.76
writes/s: 507.17
fsyncs/s: 1268.33

Throughput:
read, MiB/s: 11.88
written, MiB/s: 7.92

General statistics:
total time: 10.0931s
total number of events: 25504

Latency (ms):
min: 0.00
avg: 0.39
max: 34.87
95th percentile: 1.61
sum: 9961.66

Threads fairness:
events (avg/stddev): 25504.0000/0.00
execution time (avg/stddev): 9.9617/0.00

niubee1

2019-09-29 15:27:46 +08:00

云主机 IO 都差，这是常识

lihongjie0209

2019-09-29 15:28:39 +08:00

@silencefent #30 我的系统是 windows10 lts，VMware WorkStation 最新版本，我记得 vmtools 也安装了

westoy

2019-09-29 15:30:38 +08:00

云主机共享型实例 IO 和 CPU 都是超卖重灾区，哪有好的，有也是邻居善(闲)良(置), 以前 AWS 上 IO 优化方案就是做 raid0........

gamexg

2019-09-29 15:32:20 +08:00 via Android

碰到过，发工单可解

userdhf

2019-09-29 15:38:16 +08:00

这是架设在 u 盘上的云主机么。。

silencefent

2019-09-29 15:39:17 +08:00

@lihongjie0209 跟系统关系不大,我是 linux centos7 的实体服务器

lihongjie0209

2019-09-29 16:06:32 +08:00

@silencefent #37 这就奇怪了

phpitboy

2019-09-29 16:19:36 +08:00

1C1G 的机器只适合跑一些轻量的服务或应用，如博客、日志等，这么便宜的机器不要太多预期~~ahh

xh520630

2019-09-29 16:23:24 +08:00

sysbench 1.0.17 (using system LuaJIT 2.0.4)

Running the test with following options:
Number of threads: 1
Initializing random number generator from current time

Extra file open flags: (none)
100 files, 20.48MiB each
2GiB total file size
Block size 16KiB
Number of IO requests: 0
Read/Write ratio for combined random IO test: 1.50
Periodic FSYNC enabled, calling fsync() each 100 requests.
Calling fsync() at the end of test, Enabled.
Using synchronous I/O mode
Doing random r/w test
Initializing worker threads...

Threads started!

File operations:
reads/s: 786.51
writes/s: 524.34
fsyncs/s: 1316.34

Throughput:
read, MiB/s: 12.28
written, MiB/s: 8.19

General statistics:
total time: 10.0251s
total number of events: 26245

Latency (ms):
min: 0.00
avg: 0.38
max: 43.87
95th percentile: 1.30
sum: 9957.99

Threads fairness:
events (avg/stddev): 26245.0000/0.00
execution time (avg/stddev): 9.9580/0.00

看⑧懂

JimmyTinsley

2019-09-29 16:24:04 +08:00

sysbench 1.0.17 (using system LuaJIT 2.0.4)

Running the test with following options:
Number of threads: 1
Initializing random number generator from current time

Extra file open flags: (none)
100 files, 20.48MiB each
2GiB total file size
Block size 16KiB
Number of IO requests: 0
Read/Write ratio for combined random IO test: 1.50
Periodic FSYNC enabled, calling fsync() each 100 requests.
Calling fsync() at the end of test, Enabled.
Using synchronous I/O mode
Doing random r/w test
Initializing worker threads...

Threads started!

File operations:
reads/s: 1288.83
writes/s: 859.15
fsyncs/s: 2157.38

Throughput:
read, MiB/s: 20.13
written, MiB/s: 13.42

General statistics:
total time: 10.0059s
total number of events: 43006

Latency (ms):
min: 0.00
avg: 0.23
max: 14.06
95th percentile: 0.44
sum: 9956.45

Threads fairness:
events (avg/stddev): 43006.0000/0.00
execution time (avg/stddev): 9.9565/0.00

我是 vultr 的 1C1G, 不过似乎是 SSD, 跑分还行啊

lands

2019-09-29 18:11:32 +08:00

百度 2C2G
$ sysbench fileio --file-total-size=2G --file-num=100 --file-test-mode=rndrw run
sysbench 1.0.17 (using system LuaJIT 2.0.4)

Running the test with following options:
Number of threads: 1
Initializing random number generator from current time

Extra file open flags: (none)
100 files, 20.48MiB each
2GiB total file size
Block size 16KiB
Number of IO requests: 0
Read/Write ratio for combined random IO test: 1.50
Periodic FSYNC enabled, calling fsync() each 100 requests.
Calling fsync() at the end of test, Enabled.
Using synchronous I/O mode
Doing random r/w test
Initializing worker threads...

Threads started!

File operations:
reads/s: 946.48
writes/s: 630.99
fsyncs/s: 1582.06

Throughput:
read, MiB/s: 14.78
written, MiB/s: 9.86

General statistics:
total time: 10.0143s
total number of events: 31546

Latency (ms):
min: 0.00
avg: 0.32
max: 38.72
95th percentile: 0.99
sum: 9955.21

Threads fairness:
events (avg/stddev): 31546.0000/0.00
execution time (avg/stddev): 9.9552/0.00

Chingim

2019-09-29 18:25:40 +08:00

太惨了, 连 usb2.0 的速度都没有?

ilihai

2019-09-29 19:15:50 +08:00

用楼主的命令：

FATAL: Too large position discovered in request!

怎么破？

xiofee

2019-09-30 03:20:41 +08:00

两年前买的 1U2G1Mbps 腾讯云活动机器
-----------------------------
[root@VM_0_11_centos ~]# sysbench fileio --file-total-size=2G --file-num=100 --file-test-mode=rndrw run
sysbench 1.0.17 (using system LuaJIT 2.0.4)

Running the test with following options:
Number of threads: 1
Initializing random number generator from current time

Extra file open flags: (none)
100 files, 20.48MiB each
2GiB total file size
Block size 16KiB
Number of IO requests: 0
Read/Write ratio for combined random IO test: 1.50
Periodic FSYNC enabled, calling fsync() each 100 requests.
Calling fsync() at the end of test, Enabled.
Using synchronous I/O mode
Doing random r/w test
Initializing worker threads...

Threads started!

File operations:
reads/s: 268.22
writes/s: 178.88
fsyncs/s: 456.63

Throughput:
read, MiB/s: 4.19
written, MiB/s: 2.79

General statistics:
total time: 10.0717s
total number of events: 9004

Latency (ms):
min: 0.01
avg: 1.11
max: 17.60
95th percentile: 2.61
sum: 9964.08

Threads fairness:
events (avg/stddev): 9004.0000/0.00
execution time (avg/stddev): 9.9641/0.00

ryd994

2019-09-30 06:05:21 +08:00

因为你给的钱不够
云主机都是储存和计算节点分离，磁盘通过网络挂载。带宽够用，但是延迟问题无解。如果你对一致性没有太高要求的话可以加钱带本地 nvme 缓存，也就是所谓的 IO 优化实例。否则无解。

lihongjie0209

2019-09-30 08:51:15 +08:00

@ryd994 #46 IO 优化实例适不适合做数据库服务器，如果不合适，有什么推荐的

ryd994

2019-09-30 09:29:08 +08:00

@lihongjie0209 带本地 write back 缓存的肯定可以，因为性能基本等于物理机
具体腾讯用的是什么我也不确定，你可以自己试试效果怎么样

afirefish

2019-09-30 09:30:00 +08:00

腾讯的：
Category Test Result
HDParm Disk Read 12.67 MB/s
HDParm Cached Disk Read 100.43 MB/s
DD Disk Write 40.8 MB/s
FIO 4k random read IOPS ( KB/s)
FIO 4k random write IOPS ( KB/s)
IOZone 4k read 5471 KB/s
IOZone 4k write 1561 KB/s
IOZone 4k random read 5860 KB/s
IOZone 4k random write 1582 KB/s
-----------------------------------------------------------------------
华为的：
Category Test Result
HDParm Disk Read 156.06 MB/s
HDParm Cached Disk Read 190.75 MB/s
DD Disk Write 164 MB/s
FIO 4k random read 5776 IOPS (23107 KB/s)
FIO 4k random write 7243 IOPS (28975 KB/s)
IOZone 4k read 12447 KB/s
IOZone 4k write 6167 KB/s
IOZone 4k random read 10055 KB/s
IOZone 4k random write 5075 KB/s
-----------------------------------------------------------------------

腾讯的 1H2G 的学生机，华为的是 200 一年的学生机。相比之下腾讯机器真的是惨不忍睹。

GoRoad

2019-09-30 10:12:17 +08:00

腾讯云的学生机

sysbench 1.0.17 (using system LuaJIT 2.0.4)

Running the test with following options:
Number of threads: 1
Initializing random number generator from current time

Extra file open flags: (none)
100 files, 20.48MiB each
2GiB total file size
Block size 16KiB
Number of IO requests: 0
Read/Write ratio for combined random IO test: 1.50
Periodic FSYNC enabled, calling fsync() each 100 requests.
Calling fsync() at the end of test, Enabled.
Using synchronous I/O mode
Doing random r/w test
Initializing worker threads...

Threads started!

File operations:
reads/s: 273.34
writes/s: 182.26
fsyncs/s: 463.30

Throughput:
read, MiB/s: 4.27
written, MiB/s: 2.85

General statistics:
total time: 10.1213s
total number of events: 9222

Latency (ms):
min: 0.00
avg: 1.08
max: 29.76
95th percentile: 2.43
sum: 9980.24

Threads fairness:
events (avg/stddev): 9222.0000/0.00
execution time (avg/stddev): 9.9802/0.00

GoRoad

2019-09-30 10:17:36 +08:00

接上条这是阿里云的学生机差别有点大
sysbench 1.0.17 (using system LuaJIT 2.0.4)

Running the test with following options:
Number of threads: 1
Initializing random number generator from current time

Extra file open flags: (none)
100 files, 20.48MiB each
2GiB total file size
Block size 16KiB
Number of IO requests: 0
Read/Write ratio for combined random IO test: 1.50
Periodic FSYNC enabled, calling fsync() each 100 requests.
Calling fsync() at the end of test, Enabled.
Using synchronous I/O mode
Doing random r/w test
Initializing worker threads...

Threads started!

File operations:
reads/s: 556.84
writes/s: 371.23
fsyncs/s: 932.26

Throughput:
read, MiB/s: 8.70
written, MiB/s: 5.80

General statistics:
total time: 10.0187s
total number of events: 18542

Latency (ms):
min: 0.01
avg: 0.54
max: 72.08
95th percentile: 1.61
sum: 9981.45

Threads fairness:
events (avg/stddev): 18542.0000/0.00
execution time (avg/stddev): 9.9815/0.00

he583899772

2019-09-30 10:32:03 +08:00

昨天也买了，真的是差的不行，骗钱的

joejhy

2019-09-30 11:26:09 +08:00 via iPhone

IO 测试有很多种维度衡量，块大小 /队列深度 /并发等等都会影响测试结果。
而且不同测试的参数反应出来的结论是不一样的。

像楼主这种测试方式 ysbench fileio --file-total-size=2G --file-num=100 --file-test-mode=rndrw run，明显就是默认的小块+队列深度 1，吞吐带宽低是正常，这种参数反应出来的是 IO 延时；
如果想要测吞吐带宽，那就要大块 128K+队列深度 32 这种的来测吞吐。

lihongjie0209

2019-09-30 12:13:42 +08:00

@joejhy #53 这个只是一个比较宽泛的测试，并不是想测试硬盘的某一个指标的具体性能。我给出了在本地虚拟机的相同测试进行对比，可以得出一个相对的测试结果。

azh7138m

2019-09-30 13:18:36 +08:00

@CallMeReznov 年付 12 刀的阿里云不是不能续费吗？

CFM880

2019-09-30 13:53:31 +08:00

阿里云的
```
root@iZj6ca349oujk89sabu89tZ:~# sysbench fileio --file-total-size=2G --file-num=100 --file-test-mode=rndrw run
sysbench 1.0.17 (using bundled LuaJIT 2.1.0-beta2)

Running the test with following options:
Number of threads: 1
Initializing random number generator from current time

Extra file open flags: (none)
100 files, 20.48MiB each
2GiB total file size
Block size 16KiB
Number of IO requests: 0
Read/Write ratio for combined random IO test: 1.50
Periodic FSYNC enabled, calling fsync() each 100 requests.
Calling fsync() at the end of test, Enabled.
Using synchronous I/O mode
Doing random r/w test
Initializing worker threads...

Threads started!

File operations:
reads/s: 871.18
writes/s: 580.72
fsyncs/s: 1457.29

Throughput:
read, MiB/s: 13.61
written, MiB/s: 9.07

General statistics:
total time: 10.0166s
total number of events: 29046

Latency (ms):
min: 0.00
avg: 0.34
max: 85.67
95th percentile: 0.92
sum: 9957.00

Threads fairness:
events (avg/stddev): 29046.0000/0.00
execution time (avg/stddev): 9.9570/0.00

root@iZj6ca349oujk89sabu89tZ:~#
```

CallMeReznov

2019-09-30 14:00:43 +08:00

@azh7138m #55 后来一个一个月 30-40 包 1T 流量包的版本没限速之前是 200M 带宽现在应该是限速了,但是也比一般的强百倍.

EdwardLeeJan

2019-09-30 14:30:11 +08:00

我的也差得吓人，还好就挂个普通网站而已

sysbench 1.0.17 (using system LuaJIT 2.0.4)

Running the test with following options:
Number of threads: 1
Initializing random number generator from current time

Extra file open flags: (none)
100 files, 20.48MiB each
2GiB total file size
Block size 16KiB
Number of IO requests: 0
Read/Write ratio for combined random IO test: 1.50
Periodic FSYNC enabled, calling fsync() each 100 requests.
Calling fsync() at the end of test, Enabled.
Using synchronous I/O mode
Doing random r/w test
Initializing worker threads...

Threads started!

File operations:
reads/s: 223.03
writes/s: 148.75
fsyncs/s: 377.84

Throughput:
read, MiB/s: 3.48
written, MiB/s: 2.32

General statistics:
total time: 10.0553s
total number of events: 7439

Latency (ms):
min: 0.00
avg: 1.34
max: 53.62
95th percentile: 3.36
sum: 9975.82

Threads fairness:
events (avg/stddev): 7439.0000/0.00
execution time (avg/stddev): 9.9758/0.00

mink

2019-09-30 15:28:47 +08:00

做的是真的差，我就跑了一个 mysql 实例，内存就满了这还是 1G 的机器啊，500 的怎么活。

ragnaroks

2019-09-30 16:20:52 +08:00

[学生机]# sysbench fileio --file-total-size=1G --file-num=100 --file-test-mode=rndrw run
sysbench 1.0.17 (using system LuaJIT 2.0.4)

Running the test with following options:
Number of threads: 1
Initializing random number generator from current time

Extra file open flags: (none)
100 files, 10.24MiB each
1024MiB total file size
Block size 16KiB
Number of IO requests: 0
Read/Write ratio for combined random IO test: 1.50
Periodic FSYNC enabled, calling fsync() each 100 requests.
Calling fsync() at the end of test, Enabled.
Using synchronous I/O mode
Doing random r/w test
Initializing worker threads...

Threads started!

File operations:
reads/s: 253.30
writes/s: 168.87
fsyncs/s: 423.05

Throughput:
read, MiB/s: 3.96
written, MiB/s: 2.63

General statistics:
total time: 10.1834s
total number of events: 8509

Latency (ms):
min: 0.00
avg: 1.17
max: 15.14
95th percentile: 3.55
sum: 9951.22

Threads fairness:
events (avg/stddev): 8509.0000/0.00
execution time (avg/stddev): 9.9512/0.00

---------------------------------------------------------------------------

[特价机]# sysbench fileio --file-total-size=2G --file-num=100 --file-test-mode=rndrw run
sysbench 1.0.17 (using system LuaJIT 2.0.4)

Running the test with following options:
Number of threads: 1
Initializing random number generator from current time

Extra file open flags: (none)
100 files, 20.48MiB each
2GiB total file size
Block size 16KiB
Number of IO requests: 0
Read/Write ratio for combined random IO test: 1.50
Periodic FSYNC enabled, calling fsync() each 100 requests.
Calling fsync() at the end of test, Enabled.
Using synchronous I/O mode
Doing random r/w test
Initializing worker threads...

Threads started!

File operations:
reads/s: 2071.55
writes/s: 1381.04
fsyncs/s: 3457.68

Throughput:
read, MiB/s: 32.36
written, MiB/s: 21.57

General statistics:
total time: 10.0193s
total number of events: 69151

Latency (ms):
min: 0.00
avg: 0.14
max: 30.04
95th percentile: 0.77
sum: 9948.41

Threads fairness:
events (avg/stddev): 69151.0000/0.00
execution time (avg/stddev): 9.9484/0.00

wangxiyu191

2019-10-01 02:17:30 +08:00

还是钱的问题吧，去阿里云买块 PL3 的 ESSD 会惊喜的发现吞吐比单 PCIE 的 SSD 都大，延迟接近。当然价格也比普通的 SSD 云盘要贵。2333333

phithon

2019-10-28 21:43:02 +08:00

同腾讯云……

237481+0 records in
237481+0 records out
121590272 bytes (122 MB, 116 MiB) copied, 7.84412 s, 15.5 MB/s

dd if=/dev/zero of=test 0.10s user 0.44s system 6% cpu 7.846 total