请教fish:v4.06版本，fastdfs的trunk设置不生效问题，请各位帮忙看看

alex_sh

请教下大家，单机部署了fastdfs v4.06进行小文件的性能测试，在一台机器（centos 6.4)同时部署了tracker server，storage server，nginx（这个应该没有问题吧？）。
具体配置如下：
tracker server的配置文件：use_trunk_file的选项设置为true
# is this config file disabled
# false for enabled
# true for disabled
disabled=false

# bind an address of this host
# empty for bind all addresses of this host
bind_addr=10.121.*.*

# 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=/opt/fastdfs

# max concurrent connections this server supported
max_connections=256

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

# the method of selecting group to upload files
# 0: round robin
# 1: specify group
# 2: load balance, select the max free space group to upload file
store_lookup=2

# 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
# 0: round robin (default)
# 1: the first server order by ip address
# 2: the first server order by priority (the minimal)
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

# which storage server to download file
# 0: round robin (default)
# 1: the source storage server which the current file uploaded to
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=debug

#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=*

# 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 = true

# 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

# 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

# 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

stroage server的配置文件

# is this config file disabled
# false for enabled
# true for disabled
disabled=false

# the name of the group this storage server belongs to
group_name=group1

# 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=false

# 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=/root/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

# 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=81

# store_path#, based 0, if store_path0 not exists, it's value is base_path
# the paths must be exist
store_path0=/srv/node/sdb

# subdir_count  * subdir_count directories will be auto created under each
subdir_count_per_path=6

# tracker_server can ocur more than once, and tracker_server format is
#  "host:port", host can be hostname or ip address
tracker_server=10.121.56.70:22122

#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=debug

#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 = true

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

# 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=8080

mod fdfs 的配置文件
# connect timeout in seconds
# default value is 30s
connect_timeout=2

# network recv and send timeout in seconds
# default value is 30s
network_timeout=30

# the base path to store log files
base_path=/tmp

# if load FastDFS parameters from tracker server
# since V1.12
# default value is false
load_fdfs_parameters_from_tracker=true

# storage sync file max delay seconds
# same as tracker.conf
# valid only when load_fdfs_parameters_from_tracker is false
# since V1.12
# default value is 86400 seconds (one day)
storage_sync_file_max_delay = 86400

# 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 V1.13
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 V1.13
storage_ids_filename = storage_ids.conf

# FastDFS tracker_server can ocur more than once, and tracker_server format is
#  "host:port", host can be hostname or ip address
# valid only when load_fdfs_parameters_from_tracker is true
tracker_server=10.121.56.70:22122

# the port of the local storage server
# the default value is 23000
storage_server_port=23000

# the group name of the local storage server
group_name=group1

# if the url / uri including the group name
# set to false when uri like /M00/00/00/xxx
# set to true when uri like ${group_name}/M00/00/00/xxx, such as group1/M00/xxx
# default value is false
url_have_group_name = false

# path(disk or mount point) count, default value is 1
# must same as storage.conf
store_path_count=1

# store_path#, based 0, if store_path0 not exists, it's value is base_path
# the paths must be exist
# must same as storage.conf
store_path0=/srv/node/sdb

# 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=debug

# set the log filename, such as /usr/local/apache2/logs/mod_fastdfs.log
# empty for output to stderr (apache and nginx error_log file)
log_filename=

# response mode when the file not exist in the local file system
## proxy: get the content from other storage server, then send to client
## redirect: redirect to the original storage server (HTTP Header is Location)
response_mode=proxy

# 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
# this paramter used to get all ip address of the local host
# default values is empty
if_alias_prefix=

# if need find content type from file extension name
# should set to false in apache server because it done by apache
# should set to true in nginx server
http.need_find_content_type=false

# use "#include" directive to include HTTP config file
# NOTE: #include is an include directive, do NOT remove the # before include
#include http.conf


# if support flv
# default value is false
# since v1.15
flv_support = true

# flv file extension name
# default value is flv
# since v1.15
flv_extension = flv


# set the group count
# set to none zero to support multi-group
# set to 0  for single group only
# groups settings section as [group1], [group2], ..., [groupN]
# default value is 0
# since v1.14
group_count = 0

# group settings for group #1
# since v1.14
# when support multi-group, uncomment following section
#[group1]
#group_name=group1
#storage_server_port=23000
#store_path_count=2
#store_path0=/home/yuqing/fastdfs
#store_path1=/home/yuqing/fastdfs1

# group settings for group #2
# since v1.14
# when support multi-group, uncomment following section as neccessary
#[group2]
#group_name=group2
#storage_server_port=23000
#store_path_count=1
#store_path0=/home/yuqing/fastdfs


client的配置文件如下：
# 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=/tmp/fastdfs

# tracker_server can ocur more than once, and tracker_server format is
#  "host:port", host can be hostname or ip address
tracker_server=10.121.56.70:22122

#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=debug

# 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=8080

#use "#include" directive to include HTTP other settiongs
##include http.conf



上面配置以后，上传是成功的，通过url下载也是可以的，可是就是还是继续生成单独的文件，没有把小文件合并成一个大文件来存储。
[root@10.121.56.70 fdfs]# /usr/local/bin/fdfs_test /etc/fdfs/client.conf upload ~/fastdfs-nginx-module_v1.15.tar.gz
This is FastDFS client test program v4.06

Copyright (C) 2008, Happy Fish / YuQing

FastDFS may be copied only under the terms of the GNU General
Public License V3, which may be found in the FastDFS source kit.
Please visit the FastDFS Home Page http://www.csource.org/
for more detail.

[2014-11-03 12:13:42] DEBUG - base_path=/tmp/fastdfs, connect_timeout=30, network_timeout=60, tracker_server_count=1, anti_steal_token=0, anti_steal_secret_key length=0, use_connection_pool=0, g_connection_pool_max_idle_time=3600s, use_storage_id=0, storage server id count: 0

tracker_query_storage_store_list_without_group:
        server 1. group_name=, ip_addr=10.121.56.70, port=23000

group_name=group1, ip_addr=10.121.56.70, port=23000
storage_upload_by_filename
group_name=group1, remote_filename=M01/00/00/Cnk4RlRXAPWIKgVZAABDcB0FSToAAAABAAAN5sAAEOI.tar.gz
source ip address: 10.121.56.70
file timestamp=2014-11-03 12:13:41
file size=17264
file crc32=486885690
file url: http://10.121.56.70:8080/group1/ ... BAAAN5sAAEOI.tar.gz
storage_upload_slave_by_filename
group_name=group1, remote_filename=M01/00/00/Cnk4RlRXAPWIKgVZAABDcB0FSToAAAABAAAN5sAAEOI_big.tar.gz
source ip address: 10.121.56.70
file timestamp=2014-11-03 12:13:42
file size=17264
file crc32=486885690
file url: http://10.121.56.70:8080/group1/ ... N5sAAEOI_big.tar.gz

在对应的目录结构下的文件如下:

[root@10.121.56.70 00]# ls
000001                                                    Cnk4RlRXAPWIKgVZAABDcB0FSToAAAABAAAN5sAAEOI_big.tar.gz
Cnk4RlRTYF-ILJftAAA3g-hFYrgAAAABAAAAAAAADeb_big.tar.gz    Cnk4RlRXAPWIKgVZAABDcB0FSToAAAABAAAN5sAAEOI_big.tar.gz-m
Cnk4RlRTYF-ILJftAAA3g-hFYrgAAAABAAAAAAAADeb_big.tar.gz-m  Cnk4RlRXAPWIKgVZAABDcB0FSToAAAABAAAN5sAAEOI.tar.gz-m
Cnk4RlRTYF-ILJftAAA3g-hFYrgAAAABAAAAAAAADeb.tar.gz-m

请教下大家，到底是哪里设置出了问题了？
请各位帮忙看看。

happy_fish100

从文件和meta data文件，会以独立的文件存储的。

alex_sh

回复 2# happy_fish100

请教一下，我如果要做到合并存储，服务器要怎么设置，有没有什么问题？还是请求需要有个特殊flag header？

   

happy_fish100

回复 3# alex_sh

开启了合并存储特性后，上传小于一定大小的普通文件，就会使用合并存储特性。

alex_sh

回复 4# happy_fish100

请教一下fish大牛，什么叫从文件和meta data文件?  我这个上传文件这个文件应该就是普通的文件吧？ 如果一个普通文件上传要产生一个从文件或者meta文件，那就失去了减少inode消耗的设计初衷？或者有什么办法关闭掉这个功能？

我测试上传（fastdfs-nginx-module_v1.15.tar.gz）的文件大小是17K，配置文件中的配置# slot_max_size = 16MB，是小于16m, 按照逻辑应该要被存在trunk文件中的。不应该消耗额外的任何的inode。
   

happy_fish100

>>请教一下fish大牛，什么叫从文件和meta data文件?  我这个上传文件这个文件应该就是普通的文件吧？ 如果一个普通文件上传要产生一个从文件或者meta文件，那就失去了减少inode消耗的设计初衷？或者有什么办法关闭掉这个功能？
A: 不要纠结测试程序，你实际不用从文件和文件附加属性（meta data）这个两个特性即可。

>>我测试上传（fastdfs-nginx-module_v1.15.tar.gz）的文件大小是17K，配置文件中的配置# slot_max_size = 16MB，是小于16m, 按照逻辑应该要被存在trunk文件中的。不应该消耗额外的任何的inode。
A:  这样的文件会使用合并存储。你看生成的文件ID长度就知道了。

alex_sh

回复 6# happy_fish100

谢谢fish！
>>请教一下fish大牛，什么叫从文件和meta data文件?  我这个上传文件这个文件应该就是普通的文件吧？ 如果一个普通文件上传要产生一个从文件或者meta文件，那就失去了减少inode消耗的设计初衷？或者有什么办法关闭掉这个功能？
A: 不要纠结测试程序，你实际不用从文件和文件附加属性（meta data）这个两个特性即可。

请教一下，怎么才能关闭这两个特性？

>>我测试上传（fastdfs-nginx-module_v1.15.tar.gz）的文件大小是17K，配置文件中的配置# slot_max_size = 16MB，是小于16m, 按照逻辑应该要被存在trunk文件中的。不应该消耗额外的任何的inode。
A:  这样的文件会使用合并存储。你看生成的文件ID长度就知道了。
从这个结果来看，应该是没有合并，是我设置的问题？还是关闭上面两个特性以后就产生trunkID+offset这样的标示的文件ID？