linux大内存页 HugePages on Linux

HugePages on Linux

  HugePages是linux内核的一个特性，使用hugepage可以用更大的内存页来取代传统的4K页面。使用HugePage主要带来如下好处

   1，没有swap。Notswappable: HugePages are not swappable. Therefore there is no page-in/page-outmechanism overhead.HugePages are universally regarded as pinned.

   2，减轻快表压力。Reliefof TLB pressure:TLB表格的更小了，效率提高

   3，减轻换页表的负载。每个表单需64字节，如果管理50GB的物理内存，如果使用传统4K页面pagetable需要800M大小,而是用HugePages仅需要40M

   4，提高内存的性能，降低CPU负载，原理同上

HugePages和oracle AMM（自动内存管理）是互斥的，所有使用HugePages必须设置内存参数MEMORY_TARGET / MEMORY_MAX_TARGET 为0

配置HugePages的具体步骤

1、修改内核参数memlock，单位是KB，如果内存是128G，memlock的大小要稍微小于物理内存。计划lock 100GB的内存大小。参数设置为大约SGA是没有坏处的。

vi /etc/security/limits.conf

*  soft   memlock    104857600

*  hard   memlock    104857600

2，使用数据库帐号验证大小

[oracle@dtydb5 ~]$ ulimit -a|grep lock

core file size          (blocks, -c) 0

file size               (blocks, -f) unlimited

max locked memory       (kbytes, -l) 104857600

file locks                      (-x) unlimited

3，如果使用AMM内存管理，要取消改设置。MEMORY_TARGET和 MEMORY_MAX_TARGET参数设置为0

SQL> alter system reset memory_targetscope=spfile ;

SQL> alter system resetmemory_max_target scope=spfile;

SQL> alter system set sga_target = 10Gscope=spfile;

SQL> alter system setpga_aggregate_target = 4G scope = spfile;

 4，计算需要使用的hugepage页面的大小。hugepage目前只能用于共享内存段等少量内存类型，例如oracle SGA。PGA则不适用，这些内存一般不能用于其它用途，因此设置太小则不足够放下所有内存段，太大则空间浪费。

目前hugepage的大小

[root@dtydb5 ~]# grep Hugepagesize /proc/meminfo
Hugepagesize:     2048 kB

 简单的计算原理是total SGA_MAX_SIZE(多个instance的总和）/hugepagesize + N

N为少量内存盈余，一般多出100就足够了。如果主机内存128GB，计划70GB用于SGA共享内存，则大内存页需70×1024/2=35840

也可使用oracle提供的计算公式，基本原理是使用ipcs -m来计算共享内存段的大小。统计前注意关闭AMM；

vi hugepages_settings.sh

#!/bin/bash

#

# hugepages_settings.sh

#

# Linux bash script to compute values for the

# recommended HugePages/HugeTLB configuration

#

# Note: This script does calculation for all shared memory

# segments available when the script is run, no matter it

# is an Oracle RDBMS shared memory segment or not.

#

# This script is provided by Doc ID 401749.1 from My Oracle Support

#

 

# Welcome text

echo "

This script is provided by Doc ID 401749.1 from My Oracle Support

() where it is intended to compute values for

the recommended HugePages/HugeTLB configuration for the current shared

memory segments. Before proceeding with the execution please make sure

that:

 * Oracle Database instance(s) are up and running

 * Oracle Database 11g Automatic Memory Management (AMM) is not setup

   (See Doc ID 749851.1)

 * The shared memory segments can be listed by command:

     # ipcs -m

 Press Enter to proceed..."

 read

 # Check for the kernel version

KERN=`uname -r | awk -F. '{ printf("%d.%d\n",$1,$2); }'`

 # Find out the HugePage size

HPG_SZ=`grep Hugepagesize /proc/meminfo | awk '{print $2}'`

 # Initialize the counter

NUM_PG=0

 # Cumulative number of pages required to handle the running shared memory segments

for SEG_BYTES in `ipcs -m | awk '{print $5}' | grep "[0-9][0-9]*"`

do

   MIN_PG=`echo "$SEG_BYTES/($HPG_SZ*1024)" | bc -q`

   if [ $MIN_PG -gt 0 ]; then

      NUM_PG=`echo "$NUM_PG+$MIN_PG+1" | bc -q`

   fi

done

 RES_BYTES=`echo "$NUM_PG * $HPG_SZ * 1024" | bc -q`

 # An SGA less than 100MB does not make sense

# Bail out if that is the case

if [ $RES_BYTES -lt 100000000 ]; then

   echo "***********"

   echo "** ERROR **"

   echo "***********"

   echo "Sorry! There are not enough total of shared memory segments allocated for

HugePages configuration. HugePages can only be used for shared memory segments

that you can list by command:

    # ipcs -m

 of a size that can match an Oracle Database SGA. Please make sure that:

 * Oracle Database instance is up and running

 * Oracle Database 11g Automatic Memory Management (AMM) is not configured"

   exit 1

fi

 # Finish with results

case $KERN in

   '2.4') HUGETLB_POOL=`echo "$NUM_PG*$HPG_SZ/1024" | bc -q`;

          echo "Recommended setting: vm.hugetlb_pool = $HUGETLB_POOL" ;;

   '2.6') echo "Recommended setting: vm.nr_hugepages = $NUM_PG" ;;

    *) echo "Unrecognized kernel version $KERN. Exiting." ;;

esac

 # End

 5，修改vm.nr_hugepages参数,值为上步计算的数值

参数vm.nr_hugepages指明了内存页数，如果设置大内存页为100G，则vm.nr_hugepages的大小为70G×1024×1024/2048K=35840

vi /etc/sysctl.conf

 vm.nr_hugepages = 35840

 sysctl -p 命令使配置生效。

6,关闭数据库，重启主机和数据库（理论上不需要重启主机，建议重启）

 7，验证是否设置正确

grep HugePages /proc/meminfo

 HugePages_Free小于HugePages_Total的值则表示设置成功。如果HugePages_Rsvd应该保持少量保留内存。

 注意，HugePages如果配置不恰当会引起系统性能下降等风险，需要慎重。

参考资料

HugePages on Linux: What It Is... and WhatIt Is Not... [ID 361323.1] 

HugePages on Oracle Linux 64-bit [ID361468.1]