如何查找物理cpu，cpu核心和逻辑cpu的数量

环境

  • Red Hat Enterprise Linux 4
  • Red Hat Enterprise Linux 5
  • Red Hat Enterprise Linux 6
  • Red Hat Enterprise Linux 7

问题

  • x86 / x86_64系统上的物理CPU，CPU内核和逻辑CPU之间有什么区别？
  • 如何从RHEL操作系统获取可用处理器列表?

决议

  • 物理CPU数量

    • 下面的命令将显示一个系统有多少活动的物理处理器。例如:如果这个数字是2，则可以打开系统机箱，用手删除2个物理处理器。

       
      $ grep physical.id /proc/cpuinfo | sort -u | wc -l
2

       

  • 每个CPU的核心数

    • 在具有多核处理器的系统上，下面的命令应该报告每个物理处理器的CPU内核数量(尽管在极少数情况下可能不会)。例如:如果这个数字是4，而物理CPU是2，那么这2个物理处理器中的每个都有4个CPU内核，总共有8个内核。

       
      $ grep cpu.cores /proc/cpuinfo | sort -u
cpu cores : 4

       

  • 逻辑处理器数量

    • 最后这个命令将显示Linux内核所看到的“逻辑”处理器的总数。这个数字通常是三个统计数据中最重要的。它是处理器的有效数量——就操作系统而言，这是能够在任何给定微秒内工作的不同cpu的数量。示例:继续上面的示例场景，下面看到的数字可以是16而不是8。简单地说，如果这个命令显示的数字与CPU内核的总数不同，这是因为在CPU上启用了超线程，从而进一步划分了每个内核(在本例中，分为两个可用的“线程”)。

       
      $ grep processor /proc/cpuinfo | wc -l
16

       

       

许可?

  • 为了确定RHEL许可原因的cpu数量，上面的第一个命令就足够了;但是，要进行更多的讨论，请咨询 如何确定系统上的CPU插槽数

  • 如果购买的许可根据插槽（已填充或未填充），处理器或内核的数量而变化的第三方软件，请与软件供应商联系，以确切了解它们如何计算CPU数量。

工具

  • 注意，Red Hat Enterprise Linux 6和7附带了lscpu命令，该命令可以打印出系统处理器的简单可读摘要。此外，在RHEL6中，hwloc包是可用的(RHEL7附带它)——hwloc包括lstopo命令，以及各种hwloc-*命令。

  • 在RHEL6之前，直接检查/proc/cpuinfo(如上所述)或使用x86info或dmidecode命令(同名rpm)都能查到相同的信息。

  • 其他第三方选项没有提供担保:xsos(由本文的原始作者开发)和lshw(可在EPEL中获得)。

  • 对于任何版本的Red Hat Enterprise Linux:本文附带的BASH脚本都会解析/proc/cpuinfo，以打印如下所示的易于阅读的摘要。(注意，它没有提供任何保证或官方支持。)
    Raw
    $ cpu
128 logical processors (64 CPU cores)
8 Intel Xeon CPU X7560 @ 2.27GHz (flags: constant_tsc,ht,lm,pae,vmx) 
└─16 threads / 8 cores each
     1 #!/bin/bash
 2 #
 3 # This simple script uses /proc/cpuinfo (or filename of your choosing) to print
 4 # a succinct summary about a system's processors.
 5 # Other useful utilities (some only available in RHEL6 or EPEL):
 6 #   x86info, dmidecode, lscpu, cpuid, lshw, lstopo, xsos
 7 #
 8 # Originally uploaded to redhat.com by Ryan Sawhill <rsaw@redhat.com>, Sep 2012; Updated Jan 2013
 9 # This code is from xsos, which can do so much more <http://github.com/ryran/xsos>
10 #
11 
12 # Get input
13 if [[ -r $1 && -f $1 ]]; then
14   # If passed a readable file, use that
15   cpuinfo=$1
16 else
17   # Otherwise, use /proc/cpuinfo
18   cpuinfo=/proc/cpuinfo
19 fi
20 
21 # Get model of cpu
22 model_cpu=$(awk -F: '/^model name/{print $2; exit}' <"$cpuinfo")
23 
24 # If no model detected (e.g. on Itanium), try to use vendor+family
25 [[ -z $model_cpu ]] && {
26   vendor=$(awk -F: '/^vendor /{print $2; exit}' <"$cpuinfo")
27   family=$(awk -F: '/^family /{print $2; exit}' <"$cpuinfo")
28   model_cpu="$vendor$family"
29 }
30 
31 # Clean up cpu model string
32 model_cpu=$(sed -e 's,(R),,g' -e 's,(TM),,g' -e 's,  *, ,g' -e 's,^ ,,' <<<"$model_cpu")
33 
34 # Get number of logical processors
35 num_cpu=$(awk '/^processor/{n++} END{print n}' <"$cpuinfo")
36 
37 # Get number of physical processors
38 num_cpu_phys=$(grep '^physical id' <"$cpuinfo" | sort -u | wc -l)
39 
40 # If "physical id" not found, we cannot make any assumptions (Virtualization--)
41 # But still, multiplying by 0 in some crazy corner case is bad, so set it to 1
42 # If num of physical *was* detected, add it to the beginning of the model string
43 [[ $num_cpu_phys == 0 ]] && num_cpu_phys=1 || model_cpu="$num_cpu_phys $model_cpu"
44 
45 # If number of logical != number of physical, try to get info on cores & threads
46 if [[ $num_cpu != $num_cpu_phys ]]; then
47   
48   # Detect number of threads (logical) per cpu
49   num_threads_per_cpu=$(awk '/^siblings/{print $3; exit}' <"$cpuinfo")
50   
51   # Two possibile ways to detect number of cores
52   cpu_cores=$(awk '/^cpu cores/{print $4; exit}' <"$cpuinfo")
53   core_id=$(grep '^core id' <"$cpuinfo" | sort -u | wc -l)
54   
55   # The first is the most accurate, if it works
56   if [[ -n $cpu_cores ]]; then
57     num_cores_per_cpu=$cpu_cores
58   
59   # If "cpu cores" doesn't work, "core id" method might (e.g. Itanium)
60   elif [[ $core_id -gt 0 ]]; then
61     num_cores_per_cpu=$core_id
62   fi
63   
64   # If found info on cores, setup core variables for printing
65   if [[ -n $num_cores_per_cpu ]]; then
66     cores1="($((num_cpu_phys*num_cores_per_cpu)) CPU cores)"
67     cores2=" / $num_cores_per_cpu cores"
68   # If didn't find info on cores, assume single-core cpu(s)
69   else
70     cores2=" / 1 core"
71   fi
72   
73   # If found siblings (threads), setup the variable for the final line
74   [[ -n $num_threads_per_cpu ]] &&
75     coresNthreads="\n└─$num_threads_per_cpu threads${cores2} each"
76 fi
77 
78 # Check important cpu flags
79 # pae=physical address extensions  *  lm=64-bit  *  vmx=Intel hw-virt  *  svm=AMD hw-virt
80 # ht=hyper-threading  *  aes=AES-NI  *  constant_tsc=Constant Time Stamp Counter
81 cpu_flags=$(egrep -o "pae|lm|vmx|svm|ht|aes|constant_tsc" <"$cpuinfo" | sort -u | sed ':a;N;$!ba;s/\n/,/g')
82 [[ -n $cpu_flags ]] && cpu_flags="(flags: $cpu_flags)"
83 
84 # Check kernel version; print warning if Xen
85 [[ $(uname -r) =~ xen ]] && {
86   echo "Warning: kernel for localhost detected as $(uname -r)"
87   echo "With Xen, CPU layout in /proc/cpuinfo will be inaccurate; consult dmidecode"
88 }
89 
90 # Print out the deets
91 echo -e "${num_cpu} logical processors ${cores1}"
92 echo -e "${model_cpu} ${cpu_flags} ${coresNthreads}"
    cpu.sh

     

posted @ 2019-03-27 15:22  augusite  阅读(845)  评论(0)  编辑  收藏  举报