[20190313]備份問題.txt

--//生產系統遇到備份問題,同事請求檢檢視看,提示應該是ulimit引數限制.

--//首先我不熟悉這套備份系統,我心裡很反感這套備份模式,我開始以為修改/etc/security/limits.conf就ok了.

# grep -v "^#" /etc/security/limits.conf

oracle soft nproc 2047

oracle hard nproc 16384

oracle soft nofile 65536

oracle hard nofile 65536

oracle soft memlock 2457600

oracle hard memlock 2457600

--//發現還是不行,問了一些細節,發現透過root程式下的一個服務完成備份:

# ps -ef | grep avata[r]

root 23601 1 0 2018 ? 00:00:06 /usr/local/avatar/client_server/sbin/avatardevice -v -c /usr/local/avatar/client_server/etc/avatardevice.conf

root 23613 1 0 2018 ? 05:16:39 /usr/local/avatar/client_server/sbin/avatarclient -v -c /usr/local/avatar/client_server/etc/avatarclient.conf

--//而這兩個程式是root使用者的,這樣應該修改root使用者對於引數加入如下:

* soft nofile 65536

* hard nofile 65536

--//我在猜想為什麼該程式要開啟如此之多的檔案控制程式碼.

# ls -l /proc/23613/fd |wc

591 4902 47629

--//昏,已經使用591個檔案控制程式碼.

# ls -l /proc/23613/fd | cut -f2 -d ">" | sort | uniq -c

3 /dev/null

1 socket:[76605529]

1 total 0

292 /usr/local/avatar/client_server/data

292 /usr/local/avatar/client_server/data/ora_scripts

1 /usr/local/avatar/client_server/log

1 /usr/local/avatar/client_server/log/avatarclient20181022.log

--//很明顯這家公司的產品寫的程式有問題,大量的重複開啟相同的檔案控制程式碼,!!估計每次備份開啟1次,292天就292次,並且完成後竟然不

--//寫關閉控制程式碼的語句,國內的水平就是這樣!!打著所謂的高科技騙人,

--//這樣再大的引數設定最終也會撐爆的,也許最佳的方式定時重啟這個服務.

# service avatarclient restart

Stopping the Avatar Client daemon

Stopping the Avatar Device daemon

Starting the Avatar Device daemon

Starting the Avatar Client daemon

# ps -ef | grep avata[r]

root 5414 1 0 15:53 ? 00:00:00 /usr/local/avatar/client_server/sbin/avatardevice -v -c /usr/local/avatar/client_server/etc/avatardevice.conf

root 5425 1 0 15:53 ? 00:00:00 /usr/local/avatar/client_server/sbin/avatarclient -v -c /usr/local/avatar/client_server/etc/avatarclient.conf

# ls -l /proc/5425/fd

total 0

lr-x------ 1 root root 64 2019-03-13 15:53:52 0 -> /dev/null

lr-x------ 1 root root 64 2019-03-13 15:53:52 1 -> /dev/null

lr-x------ 1 root root 64 2019-03-13 15:53:52 2 -> /dev/null

lrwx------ 1 root root 64 2019-03-13 15:53:52 3 -> socket:[86753325]

lr-x------ 1 root root 64 2019-03-13 15:53:52 4 -> /usr/local/avatar/client_server/log

lrwx------ 1 root root 64 2019-03-13 15:53:52 5 -> /usr/local/avatar/client_server/log/avatarclient20190313.log

--//現在沒有前面看到的2個檔案控制程式碼.

# cat /proc/5425/limits

Limit Soft Limit Hard Limit Units

Max cpu time unlimited unlimited seconds

Max file size unlimited unlimited bytes

Max data size unlimited unlimited bytes

Max stack size 10485760 unlimited bytes

Max core file size 0 unlimited bytes

Max resident set unlimited unlimited bytes

Max processes 1024 30148 processes

Max open files 1024 1024 files

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Max locked memory 65536 65536 bytes

Max address space unlimited unlimited bytes

Max file locks unlimited unlimited locks

Max pending signals 30148 30148 signals

Max msgqueue size 819200 819200 bytes

Max nice priority 0 0

Max realtime priority 0 0

Max realtime timeout unlimited unlimited us

--//注:可以發現我這樣操作不行,必須登出root使用者然後再重新啟動服務才生效.以下是退出重啟後的情況:

ps -ef | grep avata[r]

root 5905 1 0 16:00 ? 00:00:00 /usr/local/avatar/client_server/sbin/avatardevice -v -c /usr/local/avatar/client_server/etc/avatardevice.conf

root 5916 1 0 16:00 ? 00:00:00 /usr/local/avatar/client_server/sbin/avatarclient -v -c /usr/local/avatar/client_server/etc/avatarclient.conf

# cat /proc/5916/limits