# smit dump_estimate

        # sysdumpdev -e
        0453-041 Estimated dump size in bytes: 850395136

        #mklv -y dumplv -t sysdump rootvg 15        →在 rootvg 上創(chuàng)建 15 個 PP 大小的 DUMP 設(shè)備dumplv
        #sysdumpdev -s /dev/dumplv -P                →設(shè)置主DUMP設(shè)備為/dev/dumplv
        primary /dev/dumplv
        secondary /dev/sysdumpnull
        copy directory /var/adm/ras
        forced copy flag FALSE
        always allow dump FALSE
        dump compression OFF

        #mklv -y hd7 -t sysdump rootvg 15   → 創(chuàng)建15個pp大小的DUMP設(shè)備，名為hd7
        #sysdumpdev -s /dev/hd7 -p           → 制定此設(shè)備為第二個DUMP設(shè)備
        primary /dev/dumplv
        secondary /dev/hd7
        copy directory /var/adm/ras
        forced copy flag FALSE
        always allow dump FALSE
        dump compression OFF

        #df -k /var
        Filesystem       1024-blocks Free %Used  Iused    %Iused  Mounted on
        /dev/hd9var      32768         31268    5%       143 64% /var

        # chfs -asize=+240000 /var

        # sysdumpdev -PD /var/adm/ras

        # Mount /var for copycore
        echo "rc.boot: executing \"fsck -fp var\"" \    →檢查var文件系統(tǒng)
        >>/../tmp/boot_log
        fsck -fp /var
        echo "rc.boot: executing \"mount /var\"" \
        >>/../tmp/boot_log
        mount /var                                           →mount /var文件系統(tǒng)
        [ $? -ne 0 ] && loopled 0x518
        # retrieve dump
        echo "rc.boot: executing \"copycore\"" \
        >>/../tmp/boot_log
        copycore                                             →復(fù)制DUMP
        umount /var

        # sysdumpdev -KP

        # sysdumpdev -CP

        # lsattr -El sys0            →顯示是否自動重啟動
        SW_dist_intr    false               Enable SW distribution of interrupts
        autorestart     true                Automatically REBOOT system after a crash
        boottype        disk                N/A
        conslogin       enable              System Console Login
        cpuguard        disable             CPU Guard
        frequency       1097312280         System Bus Frequency
        fullcore        false               Enable full CORE dump
        fwversion       IBM,2b304_430      Firmware version and revision levels
        id_to_partition 0X04514535A2CE4701 Partition ID
        id_to_system    0X04514535A2CE4700 System ID
        iostat          false               Continuously maintain DISK I/O history
        keylock         normal              State of system keylock at boot time
        maxbuf          20                  Maximum number of pages in block I/O BUFFER
        maxmbuf         0                   Maximum Kbytes of real memory allowed for MB
        maxpout         0                   HIGH water mark for pending write I/Os per file
        maxuproc        128                 Maximum number of PROCESSES allowed per user
        minpout         0                   LOW water mark for pending write I/Os per file
        modelname       IBM,8842-41X       Machine name
        ncargs          6                   ARG/ENV list size in 4K byte blocks
        pre430core      false               Use pre-430 style CORE dump
        pre520tune      disable             Pre-520 tuning compatibility mode
        realmem         2031616             Amount of usable physical memory in Kbytes
        rtasversion    1                   Open Firmware RTAS version
        systemid        IBM,0399GCA4N      Hardware system identifier
        # smit chgsys                                    使用smit進行修改
        # chdev -l sys0 -a autorestart='true'        使用命令進行修改

注意

如果沒有按順序顯示c0x，而是ccx（x是2~9的數(shù)字），那么這表示是重復(fù)上次信息，跟著的位置代碼不會是完整的8段，只會包含變化的內(nèi)容，即只有不同的才會顯示。例如：

        # sysdumpdev -L
        0453-039 Device name: /dev/dumplv                  →DUMP設(shè)備名
        Major device number: 10
        Minor device number: 2
        Size: 8837632 bytes                                →壓縮后大小
        Uncompressed Size: 32900935 bytes                  →未壓縮大小
        Date/Time: Fri Sep 22 13:01:41 PDT 2000            →生成時間
        Dump status: 0
        dump completed successfully                        →DUMP正常生成
        Dump copy filename: /var/adm/ras/vmcore.0.Z        →存在DUMP，文件是vmcore.0.Z

        # cd /var/adm/ras
        # uncompress vmcore.0.Z

    # kdb /var/adm/ras/vmcore.0
    The specified kernel file is a UP kernel
    vmcore.1 mapped from @ 70000000 to @ 71fdba81
    Preserving 880793 bytes of symbol table
    First symbol __mulh
    KERNEXT FUNCTION NAME CACHE (90112 bytes) allocated
    KERNEXT COMMANDS SPACE (4096 bytes) allocated
    Component Names:
    1) dmp_minimal [5 entries]
    . . . .
    Dump analysis on CHRP_UP_PCI POWER_PC POWER_604
    machine with 1 cpu(s) (32-bit registers)
    Processing symbol table...
    .......................done
    (0)>

        # kdb -m dump_file -u /usr/lib/boot/unix
        The specified kernel file is a 64-bit kernel
        core mapped from @ 700000000000000 to @ 7000000000120a7
        Preserving 884137 bytes of symbol table
        First symbol __mulh
        KERNEXT FUNCTION NAME CACHE (90112 bytes) allocated
        KERNEXT COMMANDS SPACE (8192 bytes) allocated
        Component Dump Table not found.
        Kernel not included in this dump.
        dump core corrupted
        make sure /usr/lib/boot/unix refers to the running kernel

注意

以上錯誤的含義是DUMP所在機器的內(nèi)核與指定的內(nèi)核程序（/usr/lib/boot/unix）不一致，無法分析。因此為了在其他機器上進行DUMP分析，不但需要DUMP文件，還需要保留此機器內(nèi)核文件：/unix（因為/unix一般是一個鏈接文件，要復(fù)制其鏈接的源文件而不是鏈接）。

        (0)> stat                                       → 顯示DUMP當(dāng)時系統(tǒng)狀態(tài)
        SYSTEM_CONFIGURATION:
        CHRP_UP_PCI POWER_PC POWER_604 machine with 1 cpu(s) (32-bit registers)
        SYSTEM STATUS:
        sysname... AIX
        nodename.. garbagepig
        release... 1
        version... 5                                    → 操作系統(tǒng)版本
        machine... 000931134C00
        nid....... 0931134C
        time of crash: Mon Oct 4 14∶14∶14 2004      →DUMP時間
        age of system: 3 min., 11 sec.
        xmalloc debug: disabled
        abend code: 300                                → DUMP ABEND代碼
            csa: 0x2ff3b400
            exception struct:
              dar:   0x00000000
              dsisr: 0x00000000:
              srv:   0x00000000
              dar2:  0x0000000         dsirr: 0x00000000: (errno) "Error 0"
        > t -mk                                          →堆棧跟蹤命令
        Skipping first MST
        MST STACK TRACE:
        0x2ff3b400 (excpt=00000018:0a000000:00000000:00000018:00000106) (intpri=3)
              IAR:      .so_pin_more_stack+3c (000a6808):     stw   r3,0x18(r4)
              LR:       .so_pin_more_stack+38 (000a6804)
              2ff3b220: .soaccept+84 (000d75f8)
              2ff3b290: .sodequeue+228 (000d7490)
              2ff3b300: .accept1+3a8 (000d6fcc)
              2ff3b380: .naccept+14 (000db2c0)
              2ff3b3c0: .sys_call_ret+0 (00003a90)
              00009032: .nbc_min_cache_init+4c (000c7d10)
              00008001: .low+0 (00000000)
        (0) > cpu                     →顯示可切換的CPU信息
        0 1
        (0) > cpu 1                   →轉(zhuǎn)到第一顆CPU（原來是由第0顆CPU）
          (1) > status                 →顯示正在執(zhí)行的線程（2顆CPU，兩個線程）
        CPU TID TSLOT PID PSLOT PROC_NAME
        0 205 2 204 2 wait
        1 5819 88 2CA0 44 kdb_mp
        (1) > th ＊                    →顯示第一顆CPU處理的全部線程
        ……
        (1) > p ＊                     →顯示第一顆CPU處理的全部進程
        ……
        (1) >p ＊ -s ACTIVE           → 顯示所有活動進程
        SLOT NAME STATE PID PPID ADSPACE CL #THS
        pvproc+000000 0 swapper ACTIVE 0000000 0000000 0000000000000B00 0 0001
        pvproc+000280 1 init ACTIVE 0000001 0000000 000000000000E2FD 0 0001
        pvproc+000500 2 wait ACTIVE 0000204 0000000 0000000000001B02 0 0001
        pvproc+000780 3 wait ACTIVE 0000306 0000000 0000000000002B04 0 0001
        pvproc+000A00 4 lrud ACTIVE 0000408 0000000 0000000000003B06 65 0001
        pvproc+000C80 5 xmgc ACTIVE 000050A 0000000 000000000000BB16 65 0001
        pvproc+000F00 6 netm ACTIVE 000060C 0000000 000000000000CB18 65 0001
        pvproc+001180 7 gil ACTIVE 000070E 0000000 000000000000DB1A 65 0005
        (1)> f                                  →顯示堆棧跟蹤
        pvthread+004900 STACK:
        [00034648].panic_trap+000000 ()     → 推斷原因，系統(tǒng)panic
        [021DCCC4]Duck+000018 ()
        [021DCCC4]Duck+000018 ()
        [021DCC7C]Daffy+000020 (00000001, 2FF3AB10)
        [0055E9E8]config_kmod+00016C (??, ??, ??)
        [0055EDCC]sysconfig+0000F8 (??, ??, ??)
        [00003A50].sys_call+000000 ()       →導(dǎo)致系統(tǒng)panic的指令在這個位置
            地址       例程     偏移量
        [kdb_get_memory] no real storage @ 2FF22B68
        (0) > q                                 →退出

        #include <stdio.h>
        #include <sys/core.h>
        void main(int argc, char ＊argv[])
        {
              FILE ＊corefile;
              struct core_dumpx c_file;
              char command[256];
              if (argc != 2)  {
                fprintf(stderr, "Usage: %s <corefile>\n", ＊argv);
                exit(1);
              }
              if ((corefile = fopen(argv[1], "r")) == NULL)  {
                perror(argv[1]);
                exit(1);
              }
              fread(&c_file, sizeof(c_file), 1, corefile);
              fclose(corefile);
              sprintf(command, "lquerypv -h %s 6E0 64 | head -1 | awk '{print $6}'", argv[1]);
              printf("Core created by: \n");
              system(command);
              printf("Signal number and cause of error number: %i\n", c_file. c_signo);
              printf("Core file type: %i\n", c_file.c_flag);
              printf("Number of core dump modules: %i\n", c_file.c_entries);
              printf("Core file format number: %i\n", c_file.c_version);
              printf("Thread identifier: %i\n", c_file.c_flt.th.ti_tid);
              printf("Process identifier: %i\n", c_file.c_flt.th.ti_pid);
              printf("Current effective priority: %i\n", c_file.c_flt.th.ti_pri);
              printf("Processor Usage: %i\n", c_file.c_flt.th.ti_cpu);
              printf("Processor bound to: cpu%i\n", c_file.c_flt.th.ti_cpuid);
              if (c_file.c_flt.th.ti_cpu>1)
                printf("Last Processor: cpu%i\n", c_file.c_flt.th.ti_affinity);
              exit(0);
        }