sqlplus 启动数据库(startup)的时候报如下错误：
Errors in file /oracle/admin/lyon/udump/lyon_ora_4236.trc:
ORA-00600: internal error code, arguments: [keltnfy-ldmInit], [46], [1], [], [], [], [], []
USER: terminating instance due to error 600
Instance terminated by USER, pid = 4236
 
检查4236 trace文件：
/oracle/admin/lyon/udump/lyon_ora_4236.trc
Oracle Database 10g Enterprise Edition Release 10.2.0.1.0 - Production
With the Partitioning, OLAP and Data Mining options
ORACLE_HOME = /oracle/product/10.2/db_1
System name:    Linux
Node name:      wangchang.hs.handsome.com.cn
Release:        2.6.9-42.ELsmp
Version:        #1 SMP Wed Jul 12 23:27:17 EDT 2006
Machine:        i686
Instance name: lyon
Redo thread mounted by this instance: 0
Oracle process number: 0
Unix process pid: 4236, image: oracle@wangchang.hs.handsome.com.cn

KCCDEBUG_LEVEL = 0
Dynamic strand is set to TRUE
Running with 2 shared and 18 private strand(s). Zero-copy redo is FALSE
*** 2010-03-05 06:46:57.552
ksedmp: internal or fatal error
ORA-00600: internal error code, arguments: [keltnfy-ldmInit], [46], [1], [], [], [], [], []
Current SQL information unavailable - no session.
----- Call Stack Trace -----
calling              call     entry                argument values in hex
location             type     point                (? means dubious value)
-------------------- -------- -------------------- ----------------------------
ksedst()+27          call     ksedst1()            0 ? 1 ?
ksedmp()+557         call     ksedst()             0 ? CC30220 ? B7000000 ? 0 ?
                                                   81BDB74 ? 7CBFD4 ?
ksfdmp()+19          call     ksedmp()             3 ? BFFFC378 ? AC05C0D ?
                                                   CBC2A40 ? 3 ? CB740C0 ?
kgerinv()+177        call     00000000             CBC2A40 ? 3 ?
kgeasnmierr()+40     call     kgerinv()            CBC2A40 ? CC47398 ? C323640 ?
                                                   2 ? BFFFC3B0 ?
keltnfy()+441        call     kgeasnmierr()        CBC2A40 ? CC47398 ? C323640 ?
                                                   2 ? 0 ? 2E ? 0 ? 0 ? 1 ? 0 ?
kscnfy()+457         call     00000000             F ? 32A4AE9C ?
ksucrp()+1392        call     kscnfy()             F ? 32A4AE9C ?
opistr_real()+2150   call     ksucrp()             0 ? BFFFCC8C ? 7CC650 ?
                                                   CBC2A40 ? CBC2A40 ? 4 ?
opistr()+684         call     opistr_real()        30 ? 2 ? BFFFECD4 ?
opiodr()+2347        call     00000000             30 ? 2 ? BFFFECD4 ?
...........
根据具体错误编号：keltnfy-ldmInit。我google了一把，发现有很多这样的解答。
可以确定是由于Oracle对主机名无法解析或者无法确定地址时会出现此错误。
由于公司的地址都是DHCP的。
现在他根据主机名wangchang无法进行解析到具体的地址，因此出现了报错。
原来在/etc/hosts配置了对应的地址和主机名(wanghf)。因此通过hostname wanghf
将主机名改为wanghf，oracle就能从该文件中找到对应的主机地址了。