zoukankan      html  css  js  c++  java
  • docker内存和cpu调试

     本地启动了一个sshd的容器服务,但该容器经常会被重启导致ssh连接失败,使用kubectl describe pod命令查看改命令发现有容器返回值为137,一般是系统环境原因,且一般为内存不足导致的,参见:Container exits with non-zero exit code 137

    Started:      Tue, 20 Nov 2018 12:14:42 +0800
    Last State:   Terminated
    Reason:       Error
    Exit Code:    137
    Started:      Mon, 19 Nov 2018 14:18:22 +0800
    Finished:     Tue, 20 Nov 2018 12:14:16 +0800
    • 登陆该容器的node节点,查看系统日志发现sshd申请内存严重超时,且看到normal ZONE中的free<min,这种情况下会触发内核杀死进程回收内存,可能会导致sshd容器或containerd进程重启。min的值由vm.min_free_kbytes设置,原理参见min_free_kbytes
    Nov 20 04:02:36 ip-172-20-54-91 kernel: [91374.975004] sshd: page allocation stalls for 20388ms, order:0, mode:0x24200ca(GFP_HIGHUSER_MOVABLE)
    Nov 20 04:02:36 ip-172-20-54-91 kernel: [91374.984454] CPU: 3 PID: 1257 Comm: sshd Not tainted 4.9.0-7-amd64 #1 Debian 4.9.110-3+deb9u2
    Nov 20 04:02:36 ip-172-20-54-91 kernel: [91374.988477] Hardware name: Xen HVM domU, BIOS 4.2.amazon 08/24/2006
    Nov 20 04:02:36 ip-172-20-54-91 kernel: [91374.995081]  0000000000000000 ffffffff90d30694 ffffffff91401218 ffffb76e46b5fb60
    Nov 20 04:02:36 ip-172-20-54-91 kernel: [91375.004170]  ffffffff90b89d0a 024200ca00000006 ffffffff91401218 ffffb76e46b5fb00
    Nov 20 04:02:36 ip-172-20-54-91 kernel: [91375.004170]  ffff8b5300000010 ffffb76e46b5fb70 ffffb76e46b5fb20 286e078452d92816
    Nov 20 04:02:36 ip-172-20-54-91 kernel: [91375.004170] Call Trace:
    Nov 20 04:02:36 ip-172-20-54-91 kernel: [91375.004170]  [<ffffffff90d30694>] ? dump_stack+0x5c/0x78
    Nov 20 04:02:36 ip-172-20-54-91 kernel: [91375.026383]  [<ffffffff90b89d0a>] ? warn_alloc+0x13a/0x160
    Nov 20 04:02:36 ip-172-20-54-91 kernel: [91375.026383]  [<ffffffff90b8a735>] ? __alloc_pages_slowpath+0x995/0xbf0
    Nov 20 04:02:36 ip-172-20-54-91 kernel: [91375.026383]  [<ffffffff9100fee1>] ? __schedule+0x241/0x6f0
    Nov 20 04:02:36 ip-172-20-54-91 kernel: [91375.026383]  [<ffffffff90a1bc81>] ? xen_clocksource_get_cycles+0x11/0x20
    Nov 20 04:02:36 ip-172-20-54-91 kernel: [91375.026383]  [<ffffffff90aef21e>] ? ktime_get+0x3e/0xb0
    Nov 20 04:02:36 ip-172-20-54-91 kernel: [91375.026383]  [<ffffffff90b8ab91>] ? __alloc_pages_nodemask+0x201/0x260
    Nov 20 04:02:36 ip-172-20-54-91 kernel: [91375.026383]  [<ffffffff90bdd39e>] ? alloc_pages_vma+0xae/0x260
    Nov 20 04:02:36 ip-172-20-54-91 kernel: [91375.026383]  [<ffffffff90bb43c9>] ? wp_page_copy+0x89/0x700
    Nov 20 04:02:36 ip-172-20-54-91 kernel: [91375.026383]  [<ffffffff90bb56c1>] ? do_wp_page+0x161/0x7e0
    Nov 20 04:02:36 ip-172-20-54-91 kernel: [91375.026383]  [<ffffffff90bc5261>] ? page_add_file_rmap+0x11/0x110
    Nov 20 04:02:36 ip-172-20-54-91 kernel: [91375.026383]  [<ffffffff90bb7812>] ? alloc_set_pte+0x3c2/0x550
    Nov 20 04:02:36 ip-172-20-54-91 kernel: [91375.026383]  [<ffffffff90bb8422>] ? handle_mm_fault+0x832/0x1280
    Nov 20 04:02:36 ip-172-20-54-91 kernel: [91375.026383]  [<ffffffff90a61015>] ? __do_page_fault+0x255/0x4f0
    Nov 20 04:02:36 ip-172-20-54-91 kernel: [91375.026383]  [<ffffffff91016018>] ? page_fault+0x28/0x30
    Nov 20 04:02:36 ip-172-20-54-91 kernel: [91375.110910] Mem-Info:
    Nov 20 04:02:36 ip-172-20-54-91 kernel: [91375.113701] active_anon:3868989 inactive_anon:1176 isolated_anon:0
    Nov 20 04:02:36 ip-172-20-54-91 kernel: [91375.113701]  active_file:23607 inactive_file:21078 isolated_file:720
    Nov 20 04:02:36 ip-172-20-54-91 kernel: [91375.113701]  unevictable:0 dirty:8 writeback:0 unstable:0
    Nov 20 04:02:36 ip-172-20-54-91 kernel: [91375.113701]  slab_reclaimable:16746 slab_unreclaimable:57137
    Nov 20 04:02:36 ip-172-20-54-91 kernel: [91375.113701]  mapped:38107 shmem:3568 pagetables:20708 bounce:0
    Nov 20 04:02:36 ip-172-20-54-91 kernel: [91375.113701]  free:33020 free_pcp:370 free_cma:0
    Nov 20 04:02:36 ip-172-20-54-91 kernel: [91375.143413] Node 0 active_anon:15475956kB inactive_anon:4704kB active_file:94428kB inactive_file:84312kB unevictable:0kB isolated(anon):0kB isolated(file):2880kB mapped:152428kB dirty:32kB writeback:0kB shmem:14272kB shmem_thp: 0kB shmem_pmdmapped: 0kB anon_thp: 135168kB writeback_tmp:0kB unstable:0kB pages_scanned:50 all_unreclaimable? no
    Nov 20 04:02:36 ip-172-20-54-91 kernel: [91375.169765] Node 0 DMA free:15904kB min:64kB low:80kB high:96kB active_anon:0kB inactive_anon:0kB active_file:0kB inactive_file:0kB unevictable:0kB writepending:0kB present:15988kB managed:15904kB mlocked:0kB slab_reclaimable:0kB slab_unreclaimable:0kB kernel_stack:0kB pagetables:0kB bounce:0kB free_pcp:0kB local_pcp:0kB free_cma:0kB
    Nov 20 04:02:36 ip-172-20-54-91 kernel: [91375.195526] lowmem_reserve[]: 0 3741 16011 16011 16011
    Nov 20 04:02:36 ip-172-20-54-91 kernel: [91375.201354] Node 0 DMA32 free:64640kB min:15776kB low:19720kB high:23664kB active_anon:3624584kB inactive_anon:144kB active_file:17908kB inactive_file:15952kB unevictable:0kB writepending:0kB present:3915776kB managed:3850208kB mlocked:0kB slab_reclaimable:11200kB slab_unreclaimable:45456kB kernel_stack:12508kB pagetables:16536kB bounce:0kB free_pcp:508kB local_pcp:0kB free_cma:0kB
    Nov 20 04:02:36 ip-172-20-54-91 kernel: [91375.230119] lowmem_reserve[]: 0 0 12270 12270 12270
    Nov 20 04:02:36 ip-172-20-54-91 kernel: [91375.235036] Node 0 Normal free:51536kB min:51740kB low:64672kB high:77604kB active_anon:11851568kB inactive_anon:4560kB active_file:76636kB inactive_file:68596kB unevictable:0kB writepending:32kB present:12845056kB managed:12569296kB mlocked:0kB slab_reclaimable:55784kB slab_unreclaimable:183092kB kernel_stack:47380kB pagetables:66296kB bounce:0kB free_pcp:1056kB local_pcp:0kB free_cma:0kB
    • 同时可以参见/proc/meminfo中的MemTotal和SwapTotal,可以发现内存已经不足,也可以查看/proc/buddyinfo文件,查看剩余连续内存的分布,小内存比较多时说明内存碎片化比较严重

    附:使用perf进行cpu占用率进行分析

    • 如下代码中,函数AA死循环,预期会占用大量CPU资源
    #include<stdio.h>
    #include<stdlib.h>
    
    void AA(){
        int i=0;
        while(1){
            i++;
        }
    }
    
    void BB(){
    
        printf("BB
    ");
    }
    
    int main(){
        BB();
        AA();
    
    }
    • 首先使用top命令查看cpu占用率,可以看出用户空间cpu占用率达到了50%,而内核空间很低,可以看出cpu占用率主要在用户态,涉及系统调用比较少
    %Cpu(s): 50.0 us,  8.3 sy,  0.0 ni, 41.7 id,  0.0 wa,  0.0 hi,  0.0 si,  0.0 st
    • 使用perf top,部分结果如下,可以看到一个名为test的进程,同时可以看到一个名为AA的符号,该符号就是名为AA的函数
    Samples: 699K of event 'cpu-clock', Event count (approx.): 8217702565                                                                                                                     
    Overhead  Shared Object                  Symbol                                                                                                                                           
      99.68%  test                           [.] AA                                                                                                                                           
       0.12%  [kernel]                       [k] _raw_spin_unlock_irqrestore                                                                                                                  
       0.06%  [kernel]                       [k] __do_softirq                                                                                                                                 
       0.02%  [kernel]                       [k] e1000_xmit_frame                                                                                                                             
       0.01%  libc-2.17.so                   [.] _int_malloc                                                                                                                                  
       0.00%  [kernel]                       [k] clear_page                                                                                                                                   
       0.00%  libvmtools.so.0.0.0            [.] Backdoor_InOut                                                                                                                               
       0.00%  [kernel]                       [k] kstat_irqs                                                                                                                                   
    • 使用perf record记录下10s以内的cpu 处理器时钟使用情况,通过perf report可以看到占用率高的进程的调用栈
    perf record -a -e cycles -o cycle.perf -g sleep 10
    # perf report -i cycle.perf|more
    # To display the perf.data header info, please use --header/--header-only options.
    #
    #
    # Total Lost Samples: 0
    #
    # Samples: 22K of event 'cpu-clock'
    # Event count (approx.): 5736750000
    #
    # Children      Self  Command          Shared Object        Symbol                                                                    
    # ........  ........  ...............  ...................  ..........................................................................
    #
        88.97%     0.00%  test             libc-2.17.so         [.] __libc_start_main
                |
                ---__libc_start_main
                   main
                   AA
    
        88.97%     0.00%  test             test                 [.] main
                |
                ---main
                   AA
    
        88.97%    88.88%  test             test                 [.] AA
                |          
                 --88.88%--__libc_start_main
                           main
                           AA

    TIPS:

    • perf工具依赖ELF文件的debug段信息,如果调试到一个stripped binary时因为无法解析会打印16进制信息。
    • perf工具无法兼容编译时解析被 -fomit-frame-pointer优化的程序,参见perf CPU Sampling

    参见:

    https://utcc.utoronto.ca/~cks/space/blog/linux/DecodingPageAllocFailures

    https://www.cnblogs.com/004x/p/6651600.htm

    http://tldp.org/LDP/Linux-Filesystem-Hierarchy/html/proc.html

    https://utcc.utoronto.ca/~cks/space/blog/linux/KernelMemoryZones

    https://blog.csdn.net/lickylin/article/details/50726847

    http://www.10tiao.com/html/497/201606/2456160252/1.html

    https://www.kernel.org/doc/Documentation/filesystems/proc.txt

  • 相关阅读:
    时间管理的心理建设与优先矩阵
    在oracle中计算时间差
    android环境搭建
    有效沟通的六个步骤
    5招教你把握Java性能监控(转自51testing)
    选项卡TabHost
    Excel导入导出数据库02
    画廊视图Gallery
    拖动条SeekBar及星级评分条
    在应用程序级别之外使用注册为allowDefinition='MachineToApplication' 的节是错误的
  • 原文地址:https://www.cnblogs.com/charlieroro/p/10064022.html
Copyright © 2011-2022 走看看