不依赖与物理介质，可以随时收缩扩展
1 fastDFS 角色
tracker 文件系统管理者
整个文件系统核心，文件系统管理者
storage 节点
服务器启动时主动向tracker汇报信息，容量大小。。。
tracker要先于storage启动
client 客户端
首先访问tracker ，tracker返回使用那个storage节点
然后客户端在建立连接到storage节点上传文件
2 fastDFS 集群
集群喝分布式的区别
集群：多台机器同时对外提供服务
如果少了一台还可以对外提供服务
分布式：一套分布在多态机器上
少了一台可能导致整个系统瘫痪
client 集群
多个客户同时上传和下载文件
tracker 集群
防止单点故障
整个文件系统核心挂了，整个DFS系统不能使用
storage 集群
两种方式:
1、稳定性、健壮性
数据备份
2、扩展性
整个文件系统扩容
通过组的方式来管理节点
同组备份
异组扩容
结论：容量最小就是改组可用容量
3 fastDFS 安装
1、GitHub下载 fastdfs 和 libfastcommon https://github.com/happyfish100
2、解压 commmon
3、./make.sh
4、sudo ./make.sh install
1、解压 fastdfs
2、make.sh
3、sudo ./make.sh install
验证fdfs_test
4 fastDFS 配置
cd /etc/fdfs/
ls
sudo vim tracker.conf
启动：fdfs_tracker /etc/fdfs/tracker.conf
# is this config file disabled
# false for enabled
# true for disabled
disabled=false #启用当前配置文件
# bind an address of this host
# empty for bind all addresses of this host
bind_addr= #绑定的IP地址 默认不填为0.0.0.0
#如果绑定127的地址只能通过127来访问，
#绑定192的地址只能通过192来访问
# the tracker server port
port=22122
# connect timeout in seconds
# default value is 30s
connect_timeout=30
# network timeout in seconds
# default value is 30s
network_timeout=60
# the base path to store data and log files
base_path=/home/xxx/fastdfs/tracker #存储数据和日志文件的地址 必填
#并且对应tracker要有访问权限
# max concurrent connections this server supported
max_connections=256
# accept thread count
# default value is 1
# since V4.07
accept_threads=1
# work thread count, should <= max_connections
# default value is 4
# since V2.00
work_threads=4
# min buff size
# default value 8KB
min_buff_size = 8KB
# max buff size
# default value 128KB
max_buff_size = 128KB
# the method of selecting group to upload files
# 0: round robin 轮询
# 1: specify group 指定某个组 那么store_group就指定那个组
# 2: load balance, select the max free space group to upload file 负载均衡
store_lookup=2 #客户端使用哪一个组的storage来上传文件
# which group to upload file
# when store_lookup set to 1, must set store_group to the group name
store_group=group2
# which storage server to upload file
# 那个服务器来上传 指定那个服务器 上面是指定那个组
# 0: round robin (default) 轮询
# 1: the first server order by ip address ip地址第一台
# 2: the first server order by priority (the minimal) 根据权重来使用
# Note: if use_trunk_file set to true, must set store_server to 1 or 2
store_server=0
# which path(means disk or mount point) of the storage server to upload file
# 0: round robin
# 2: load balance, select the max free space path to upload file
store_path=0 #使用目录 可用不用配
# which storage server to download file 指定用来下载的文件的服务器
# 0: round robin (default)
# 1: the source storage server which the current file uploaded to 那台上传那台下载
download_server=0
# reserved storage space for system or other applications.
# if the free(available) space of any stoarge server in
# a group <= reserved_storage_space,
# no file can be uploaded to this group.
# bytes unit can be one of follows:
### G or g for gigabyte(GB)
### M or m for megabyte(MB)
### K or k for kilobyte(KB)
### no unit for byte(B)
### XX.XX% as ratio such as reserved_storage_space = 10%
reserved_storage_space = 10%
#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,
# "*" (only one asterisk) means match all ip addresses
# we can use CIDR ips like 192.168.5.64/26
# and also use range like these: 10.0.1.[0-254] and 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=192.168.5.64/26
allow_hosts=*
# sync log buff to disk every interval seconds
# default value is 10 seconds
sync_log_buff_interval = 10
# check storage server alive interval seconds
check_active_interval = 120
# thread stack size, should >= 64KB
# default value is 64KB
thread_stack_size = 64KB
# auto adjust when the ip address of the storage server changed
# default value is true
storage_ip_changed_auto_adjust = true
# storage sync file max delay seconds
# default value is 86400 seconds (one day)
# since V2.00
storage_sync_file_max_delay = 86400
# the max time of storage sync a file
# default value is 300 seconds
# since V2.00
storage_sync_file_max_time = 300
# if use a trunk file to store several small files
# default value is false
# since V3.00
use_trunk_file = false
# the min slot size, should <= 4KB
# default value is 256 bytes
# since V3.00
slot_min_size = 256
# the max slot size, should > slot_min_size
# store the upload file to trunk file when it's size <= this value
# default value is 16MB
# since V3.00
slot_max_size = 16MB
# the trunk file size, should >= 4MB
# default value is 64MB
# since V3.00
trunk_file_size = 64MB
# if create trunk file advancely
# default value is false
# since V3.06
trunk_create_file_advance = false
# the time base to create trunk file
# the time format: HH:MM
# default value is 02:00
# since V3.06
trunk_create_file_time_base = 02:00
# the interval of create trunk file, unit: second
# default value is 38400 (one day)
# since V3.06
trunk_create_file_interval = 86400
# the threshold to create trunk file
# when the free trunk file size less than the threshold, will create
# the trunk files
# default value is 0
# since V3.06
trunk_create_file_space_threshold = 20G
# if check trunk space occupying when loading trunk free spaces
# the occupied spaces will be ignored
# default value is false
# since V3.09
# NOTICE: set this parameter to true will slow the loading of trunk spaces
# when startup. you should set this parameter to true when neccessary.
trunk_init_check_occupying = false
# if ignore storage_trunk.dat, reload from trunk binlog
# default value is false
# since V3.10
# set to true once for version upgrade when your version less than V3.10
trunk_init_reload_from_binlog = false
# the min interval for compressing the trunk binlog file
# unit: second
# default value is 0, 0 means never compress
# FastDFS compress the trunk binlog when trunk init and trunk destroy
# recommand to set this parameter to 86400 (one day)
# since V5.01
trunk_compress_binlog_min_interval = 0
# if use storage ID instead of IP address
# default value is false
# since V4.00
use_storage_id = false
# specify storage ids filename, can use relative or absolute path
# since V4.00
storage_ids_filename = storage_ids.conf
# id type of the storage server in the filename, values are:
## ip: the ip address of the storage server
## id: the server id of the storage server
# this paramter is valid only when use_storage_id set to true
# default value is ip
# since V4.03
id_type_in_filename = ip
# if store slave file use symbol link
# default value is false
# since V4.01
store_slave_file_use_link = false
# 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 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
# keep days of the log files
# 0 means do not delete old log files
# default value is 0
log_file_keep_days = 0
# 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
# HTTP port on this tracker server
http.server_port=8080
# check storage HTTP server alive interval seconds
# <= 0 for never check
# default value is 30
http.check_alive_interval=30
# check storage HTTP server alive type, values are:
# tcp : connect to the storge server with HTTP port only,
# do not request and get response
# http: storage check alive url must return http status 200
# default value is tcp
http.check_alive_type=tcp
# check storage HTTP server alive uri/url
# NOTE: storage embed HTTP server support uri: /status.html
http.check_alive_uri=/status.html
---------------------sudo vim client.conf-----------------------
# connect timeout in seconds
# default value is 30s
connect_timeout=30
# network timeout in seconds
# default value is 30s
network_timeout=60
# the base path to store log files
base_path=/home/xxx/fastdfs/storage
# tracker_server can ocur more than once, and tracker_server format is
# "host:port", host can be hostname or ip address
tracker_server=127.0.0.1:22122 这个无所谓
#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
# 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
# if load FastDFS parameters from tracker server
# since V4.05
# default value is false
load_fdfs_parameters_from_tracker=false
# if use storage ID instead of IP address
# same as tracker.conf
# valid only when load_fdfs_parameters_from_tracker is false
# default value is false
# since V4.05
use_storage_id = false
# specify storage ids filename, can use relative or absolute path
# same as tracker.conf
# valid only when load_fdfs_parameters_from_tracker is false
# since V4.05
storage_ids_filename = storage_ids.conf
#HTTP settings
http.tracker_server_port=80
#use "#include" directive to include HTTP other settiongs
##include http.conf
---------------------sudo vim storage.con-----------------------
# is this config file disabled
# false for enabled
# true for disabled
disabled=false
# the name of the group this storage server belongs to
#
# comment or remove this item for fetching from tracker server,
# in this case, use_storage_id must set to true in tracker.conf,
# and storage_ids.conf must be configed correctly.
group_name=group1 #分组
# bind an address of this host
# empty for bind all addresses of this host
bind_addr=
# 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=/home/xxxxx/fastdfs/storage
#存储数据和日志文件的地址 必填
#并且对应storage要有访问权限
# 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
#上传文件存储到那个路径 主要看硬盘数量，确定路径数量 下标从0开始
# store_path#, based 0, if store_path0 not exists, it's value is base_path
# the paths must be exist
store_path0=/home/xxx/fastdfs/storage/storage0
#store_path0=/home/xxxx/fastdfs/storage/storage1
#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=127.0.0.2:22122
#如果是本机 storage和tracker tracker不要填127.0.0.1启动失败，作者不想把两个服务器放本机
#这个server很重要
#配置tracker 服务器的IP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,
# "*" (only one asterisk) means match all ip addresses
# we can use CIDR ips like 192.168.5.64/26
# and also use range like these: 10.0.1.[0-254] and 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=192.168.5.64/26
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
# keep days of the log files
# 0 means do not delete old log files
# default value is 0
log_file_keep_days = 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
测试 fdfs_upload_file /etc/fdfs/client.conf ./client.conf