docker-compose部署FastDFS分布式文件系统

文章目录

一、技术选型
二、fastDFS组成部分
三、docker-compose文件
四、客户端nginx配置
五、存储器
spring Boot集成
参考文献

一、技术选型

还有一个更好的google FS（但是他不开源，我也没找到社区版一类的可以不要钱使用的）。
最后考虑到我们存储的都是10M以下的图片，而且访问量不是很高，所以使用了国产的fastDFS(当然也包含爱国情怀)。

在这里插入图片描述

二、fastDFS组成部分

Tracker Server： 主要负责调度工作，起到均衡的作用，管理所有的 Storage Server 和 Group。每个 Storage Server 在启动后会连接 Tracker，告知自己所属 Group 等信息，并保持周期性心跳。多个 Tracker 之间是对等关系，不存在单点故障。Tracker Server 在内存中记录分组和 Storage Server 的状态等信息，不记录文件索引信息，占用的内存量很少。Tracker Server 作为中心结点，管理集群拓扑结构，其主要作用是负载均衡和调度。

Storage Server： 主要提供容量和备份服务，以 Group 为单位，每个 Group 内可以有多台 Storage Server。组内的所有 Storage Server 之间是平等关系，会相互连接进行文件同步，从而保证组内的所有 Storage Server 的文件内容一致。Storage Server 直接利用 OS 的文件系统存储文件，不会对文件进行分块存储，客户端上传的文件和 Storage Server 上的文件一一对应（V3 引入的小文件合并存储除外）。每个 Storage Server 的存储依赖于本地文件系统，可配置多个数据存储目录。

Client： 与 Tracker Server 和 Storage Server 交互，负责文件的上传、下载、删除等操作。客户端可以指定上传到的 Group，当某个 Group 的访问压力较大时，可以在该组增加 Storage Server 来扩充服务能力。

三、docker-compose文件

version: '3.3'
services:
  tracker: # 调度器
    image: season/fastdfs:1.2
    container_name: fastdfs-tracker
    network_mode: host
    restart: always
    command: "tracker"

  storage: # 存储器
    image: season/fastdfs:1.2
    container_name: fastdfs-storage
    network_mode: host
    restart: always
    volumes:
      - "/fastDFS/storage/storage.conf:/fdfs_conf/storage.conf" # 存储器配置文件
      - "/fastDFS/storage/storage_base_path:/fastdfs/storage/data" # 文件存储位置
      - "/fastDFS/storage/store_path0:/fastdfs/store_path" # 存储配置
    environment:
      TRACKER_SERVER: "调度器ip和端口"
    command: "storage"

  nginx: # 客户端
    image: season/fastdfs:1.2
    container_name: fastdfs-nginx
    restart: always
    network_mode: host
    volumes:
      - "/fastDFS/nginx.conf:/etc/nginx/conf/nginx.conf"
      - "/fastDFS/storage/store_path0:/fastdfs/store_path"
      - "/fastDFS/pic:/hydf/fastDFS/pic"
    environment:
      TRACKER_SERVER: "调度器ip和端口"
    command: "nginx"

四、客户端nginx配置

#user  nobody;
worker_processes  1;

#error_log  logs/error.log;
#error_log  logs/error.log  notice;
#error_log  logs/error.log  info;

#pid        logs/nginx.pid;


events {
    worker_connections  1024;
}


http {
    include       mime.types;
    default_type  application/octet-stream;

    #access_log  logs/access.log  main;

    sendfile        on;
    #tcp_nopush     on;

    #keepalive_timeout  0;
    keepalive_timeout  65;

    #gzip  on;

    server {
        listen       8088;
        server_name  localhost;

        #charset koi8-r;

        #缩略图需要使用插件，需要单独构建nginx镜像，此处忽略
        #location /group([0-9])/M00/.*\.(gif|jpg|jpeg|png)$ {
         #   root /fastdfs/storage/data;
         #   image on;
         #   image_output off;
         #   image_jpeg_quality 75;
         #   image_backend off;
        #    image_backend_server http://baidu.com/docs/aabbc.png;
       # }

        # group1
        location /group1/M00 {
        # 文件存储目录
            root /fastdfs/storage/data; # 注意这里要和dockercompose中的storage data存储配置保持一致
            ngx_fastdfs_module;
        }

        #error_page  404              /404.html;

        # redirect server error pages to the static page /50x.html
        #
        error_page   500 502 503 504  /50x.html;
        location = /50x.html {
            root   html;
        }
 }
}

五、存储器


# the name of the group this storage server belongs to
group_name=group1 # 节点名称，后续访问节点要和这个保持一致

# bind an address of this host
# empty for bind all addresses of this host
bind_addr=10.36.6.251 # 绑定本机ip地址（因为是docker所以这里需要指定ip地址）

# if bind an address of this host when connect to other servers
# (this storage server as a client)
# true for binding the address configed by above parameter: "bind_addr"
# false for binding any address of this host
client_bind=true

# the storage server port
port=23000

# connect timeout in seconds
# default value is 30s
connect_timeout=30

# network timeout in seconds
# default value is 30s
network_timeout=60

# heart beat interval in seconds
heart_beat_interval=30

# disk usage report interval in seconds
stat_report_interval=60

# the base path to store data and log files
base_path=/fastdfs/storage

# max concurrent connections the server supported
# default value is 256
# more max_connections means more memory will be used
max_connections=256

# the buff size to recv / send data
# this parameter must more than 8KB
# default value is 64KB
# since V2.00
buff_size = 256KB

# accept thread count
# default value is 1
# since V4.07
accept_threads=1

# work thread count, should <= max_connections
# work thread deal network io
# default value is 4
# since V2.00
work_threads=4

# if disk read / write separated
##  false for mixed read and write
##  true for separated read and write
# default value is true
# since V2.00
disk_rw_separated = true

# disk reader thread count per store base path
# for mixed read / write, this parameter can be 0
# default value is 1
# since V2.00
disk_reader_threads = 1

# disk writer thread count per store base path
# for mixed read / write, this parameter can be 0
# default value is 1
# since V2.00
disk_writer_threads = 1

# when no entry to sync, try read binlog again after X milliseconds
# must > 0, default value is 200ms
sync_wait_msec=50

# after sync a file, usleep milliseconds
# 0 for sync successively (never call usleep)
sync_interval=0

# storage sync start time of a day, time format: Hour:Minute
# Hour from 0 to 23, Minute from 0 to 59
sync_start_time=00:00

# storage sync end time of a day, time format: Hour:Minute
# Hour from 0 to 23, Minute from 0 to 59
sync_end_time=23:59

# write to the mark file after sync N files
# default value is 500
write_mark_file_freq=500

# path(disk or mount point) count, default value is 1
store_path_count=1

# store_path#, based 0, if store_path0 not exists, it's value is base_path
# the paths must be exist
store_path0=/fastdfs/store_path
#store_path1=/home/yuqing/fastdfs2

# subdir_count  * subdir_count directories will be auto created under each
# store_path (disk), value can be 1 to 256, default value is 256
subdir_count_per_path=256

# tracker_server can ocur more than once, and tracker_server format is
#  "host:port", host can be hostname or ip address
tracker_server=调度器ip地址和端口

#standard log level as syslog, case insensitive, value list:
### emerg for emergency
### alert
### crit for critical
### error
### warn for warning
### notice
### info
### debug
log_level=info

#unix group name to run this program,
#not set (empty) means run by the group of current user
run_by_group=

#unix username to run this program,
#not set (empty) means run by current user
run_by_user=

# allow_hosts can ocur more than once, host can be hostname or ip address,
# "*" means match all ip addresses, can use range like this: 10.0.1.[1-15,20] or
# host[01-08,20-25].domain.com, for example:
# allow_hosts=10.0.1.[1-15,20]
# allow_hosts=host[01-08,20-25].domain.com
allow_hosts=*

# the mode of the files distributed to the data path
# 0: round robin(default)
# 1: random, distributted by hash code
file_distribute_path_mode=0

# valid when file_distribute_to_path is set to 0 (round robin),
# when the written file count reaches this number, then rotate to next path
# default value is 100
file_distribute_rotate_count=100

# call fsync to disk when write big file
# 0: never call fsync
# other: call fsync when written bytes >= this bytes
# default value is 0 (never call fsync)
fsync_after_written_bytes=0

# sync log buff to disk every interval seconds
# must > 0, default value is 10 seconds
sync_log_buff_interval=10

# sync binlog buff / cache to disk every interval seconds
# default value is 60 seconds
sync_binlog_buff_interval=10

# sync storage stat info to disk every interval seconds
# default value is 300 seconds
sync_stat_file_interval=300

# thread stack size, should >= 512KB
# default value is 512KB
thread_stack_size=512KB

# the priority as a source server for uploading file.
# the lower this value, the higher its uploading priority.
# default value is 10
upload_priority=10

# the NIC alias prefix, such as eth in Linux, you can see it by ifconfig -a
# multi aliases split by comma. empty value means auto set by OS type
# default values is empty
if_alias_prefix=

# if check file duplicate, when set to true, use FastDHT to store file indexes
# 1 or yes: need check
# 0 or no: do not check
# default value is 0
check_file_duplicate=0

# file signature method for check file duplicate
## hash: four 32 bits hash code
## md5: MD5 signature
# default value is hash
# since V4.01
file_signature_method=hash

# namespace for storing file indexes (key-value pairs)
# this item must be set when check_file_duplicate is true / on
key_namespace=FastDFS

# set keep_alive to 1 to enable persistent connection with FastDHT servers
# default value is 0 (short connection)
keep_alive=0

# you can use "#include filename" (not include double quotes) directive to
# load FastDHT server list, when the filename is a relative path such as
# pure filename, the base path is the base path of current/this config file.
# must set FastDHT server list when check_file_duplicate is true / on
# please see INSTALL of FastDHT for detail
##include /home/yuqing/fastdht/conf/fdht_servers.conf

# if log to access log
# default value is false
# since V4.00
use_access_log = false

# if rotate the access log every day
# default value is false
# since V4.00
rotate_access_log = false

# rotate access log time base, time format: Hour:Minute
# Hour from 0 to 23, Minute from 0 to 59
# default value is 00:00
# since V4.00
access_log_rotate_time=00:00

# if rotate the error log every day
# default value is false
# since V4.02
rotate_error_log = false

# rotate error log time base, time format: Hour:Minute
# Hour from 0 to 23, Minute from 0 to 59
# default value is 00:00
# since V4.02
error_log_rotate_time=00:00

# rotate access log when the log file exceeds this size
# 0 means never rotates log file by log file size
# default value is 0
# since V4.02
rotate_access_log_size = 0

# rotate error log when the log file exceeds this size
# 0 means never rotates log file by log file size
# default value is 0
# since V4.02
rotate_error_log_size = 0

# if skip the invalid record when sync file
# default value is false
# since V4.02
file_sync_skip_invalid_record=false

# if use connection pool
# default value is false
# since V4.05
use_connection_pool = false

# connections whose the idle time exceeds this time will be closed
# unit: second
# default value is 3600
# since V4.05
connection_pool_max_idle_time = 3600

# use the ip address of this storage server if domain_name is empty,
# else this domain name will ocur in the url redirected by the tracker server
http.domain_name=

# the port of the web server on this storage server
http.server_port=8888

spring Boot集成

pom文件引入工具包

   <!--fastDFS-->
        <dependency>
            <groupId>com.github.tobato</groupId>
            <artifactId>fastdfs-client</artifactId>
            <version>1.26.5</version>
        </dependency>

java文件上传，这里因为名称长度有要求，所以我直接不要文件名字了，随机了一个然后加上原文件后缀

 File file = new File(s);
            String fileName = file.getName();
            StorePath path = storageClient.uploadFile("group1", new FileInputStream(file), file.length(), fileName.substring(fileName.lastIndexOf(".") + 1));
            System.out.println(path.getFullPath());

上传完成后的访问路径，由client所在的nginx客户端地址和返回回来的存储路径拼合就可以直接访问
http://{{nginx client客户端ip地址}}/group1/M00/00/00/CiQG-2ZeyV-AWmHcAA3vSx2O3n4972.png

参考文献

https://github.com/happyfish100/fastdfs
https://cloud.tencent.com/developer/article/2072195
https://blog.51cto.com/u_12740336/6943977
https://blog.csdn.net/weixin_44002151/article/details/131617686
https://blog.csdn.net/ZHUZIH6/article/details/129973644
https://download.csdn.net/blog/column/12340564/136098096