Linux Memory Recovery kernel parameters

ss-atu| awk '/^tcp/{++s[$2]} END {for (a in S) print A,s[a]} '

PS up PID (RSS: Actual memory size, long-standing memory)

PS o pid,comm,minflt,majflt PID (second page interrupt, page break) page break: The process of allocating memory is called page Break home interrupt from swap, (home interrupt too much will affect performance) page break from memory page error: Re-establish physical memory with virtual inside Correspondence between the existing

Vm.swappiness rhel-7 (30%) 100 tendencies with swap 0 tend to buff/cache (memory)

Memory Reclamation Parameters:

Vm.dirty_expire_centisecs = 3000 (Dirty page aging time, default 30 seconds, how long to brush the disk once)

Vm.dirty_writeback_centisecs = How often does Pdflush work (monitoring)

Vm.dirty_background_ratio = 10 If the dirty page reaches the remaining 10%,kernel in tune, not Pdflush

Vm.dirty_ratio = 30 Low memory 30 seconds once (to 20%) small data file, then a number of more, you can appropriately set this value a little bit better performance. (Brush disk slow)

vm.dirty_bytes = 0; vm.dirty_background_bytes = 0 Arrival byte

Oom Killer

Vm.panic_on_oom = 0 0: Open 1: Off

/proc/pid/oom_adj Range: 17 to 15 (-17 smaller less likely to be killed)

Please refer to Kernel-doc for details.

Catalog:/USR/SHARE/DOC/KERNEL-DOC-*/DOCUMENTATION/VM Memory

Internet

sysctl-a | grep Rmem

Net.core.rmem_default = 212992

Net.core.rmem_max = 212992

Net.ipv4.tcp_rmem = 4096873806291456

Net.ipv4.udp_rmem_min = 4096

sysctl-a | grep Tcp_mem

Net.ipv4.tcp_mem = 422165629184432

Overcommit_memory = 0 Default (3 modes)

0: The kernel checks to see if there is enough memory available for the process to use, and if enough memory is available, the memory request is allowed; otherwise, the memory request fails and the error is returned to the application process

1: Always allow excessive use, suitable for some scientific applications, classic example is code using sparse array

The composition relies almost on virtual memory.

2: Do not allow excessive use,

Commit is rejected when the system allocates more memory than swap+50% (the default) physical RAM (n% is determined by Vm.overcommit_ratio).

The Overcommit policy is set through Vm.overcommit_memory.

The percentage of Overcommit is set by Vm.overcommit_ratio.

Vm.overcommit_ratio = 50

Vm.min_free_kbytes

This article is from the "Silence" blog, make sure to keep this source http://silencezone.blog.51cto.com/3613477/1870881

Linux Memory Recovery kernel parameters