In the process of sorting out my ganglia setup, I faulted two xen''s,
one of which just happened to be on a serial line.
The fault occured when I shutdown the xenU domains on 16 hosts. The two
hosts that crashed are the two to which gmetad linked from a host
outside the cluster. So I am guessing some funny business with multicast
pkts on a xenU that did _not_ have IP_MULTICAST configured. In fact, I
was rebooting to start a xenU that did have MULICAST configured.
xen0 does not have MULTICAST configured either but it does have
CONFIG_XEN_WRITABLE_PAGETABLES on.
Have people run gmond on xenU as a data_source for gmetad?
Here is the console output, and gdb disassembler..
device vif4.0 left promiscuous mode
xen-br0: port 2(vif4.0) entering disabled state
xen-br0: port 2(vif4.0) entering disabled state
(XEN) CPU: 0
(XEN) EIP: 0808:[<fc507335>]
(XEN) EFLAGS: 00013296
(XEN) eax: 00000000 ebx: 31ee2063 ecx: fc5fa680 edx: 00000001
(XEN) esi: fd8ae530 edi: 00031ee2 ebp: 00000003 esp: fc503bd8
(XEN) ds: 0810 es: 0810 fs: 0810 gs: 0810 ss: 0810
(XEN) Stack trace from ESP=fc503bd8:
(XEN) 33320810 ff97d000 00000000 31ee2063 fd8ae530 370e0000 370e0001 [fc51b4ca]
(XEN) 00000001 fc5fa680 00031ee2 00000003 00000000 00000000 fc5fa680
[fc509a60]
(XEN) 00000001 fd460eb8 00000001 00000166 ff817000 fc5fa680 20000000
fd460ea0
(XEN) 00000387 57fe0000 57fe0001 [fc51b2a8] fd460ea0 00000000 00003286
fd997f30
(XEN) 00000000 00000000 fc5fa680 ffadd000 0003799a fd997f30 00000000
00000400
(XEN) ffadc000 fc5fa680 40000000 ffffffff fc5fa680 fd936670 c0000003
[fc517e58]
(XEN) fd936670 00000000 fd936670 fc5fa6c8 fc5fa680 00000000 fffffffd
[fc517ad5]
(XEN) fc5fa680 fc5fa6c8 fffffffd [fc50e5a9] fc5fa70c fc5fa680 00000000
[fc505f21]
(XEN) fc5fa680 00000000 fc5fa680 [fc504cab] fc5fa680 bfffe5f0 00000050
00004376
(XEN) 00004376 [fc50911d] 0000000c 00000000 00000010 fc5fa6c8 00000000
00000000
(XEN) 00000000 [fc5113d4] 0000000c 00000000 00000092 000013b3 ffffffea
000013b3
(XEN) 00000000 eca3e242 00000ef3 30000000 fc5ff124 fc5fe1ac 00000000
fc5f99c0
(XEN) 00000096 0001c05d 00000000 0001c05d 00000000 4092b4c0 00001b43
0073f597
(XEN) fc5ff124 fc5fe1ac 00000000 fc5f99c0 00000092 00000086 00371db6
00000000
(XEN) 00000096 0064cc7e 00000000 0064cc7e 00000000 4fadb55d 00004381
00000000
(XEN) fc5ff124 fc5fe1ac 00000000 fc5f99c0 00000096 00000001 fc5fe1ac
00000000
(XEN) fc5f99c0 00000082 00000000 4fadb55d 00004381 fc5fe1ac 00000096
00000000
(XEN) fc5f99c0 00000096 0000001b 00000000 00000096 fc5f99c0 fc5f99c0
fc5ff560
(XEN) [fc51a9ef] fc5f99c0 00000000 00000000 000006c0 fc56b400 0000001b
ffa6b000
(XEN) [fc51a7e7] 0000001b [fc518de8] fc503e48 fc5fa680 00072239 00203092
0406015
(XEN) Call Trace from ESP=fc503bd8: [<fc51b4ca>] [<fc509a60>]
[<fc51b2a8>] [<fc517e58>] [<fc517ad5>] [<fc50e5a9>]
(XEN) [<fc505f21>] [<fc504cab>] [<fc50911d>]
[<fc5113d4>] [<fc51a9ef>] [<fc51a7e7>]
(XEN) [<fc518de8>] [<fc522b63>] [<fc51c4c3>]
[<fc51a894>] [<fc51be3c>] [<fc525893>]
****************************************
CPU0 FATAL PAGE FAULT
[error_code=00000000]
Faulting linear address might be 00000b65
Aieee! CPU0 is toast...
****************************************
Reboot in five seconds...
(gdb) disas 0xfc507335
Dump of assembler code for function gnttab_try_map:
0xfc507320 <gnttab_try_map+0>: push %ebp
0xfc507321 <gnttab_try_map+1>: xor %eax,%eax
0xfc507323 <gnttab_try_map+3>: push %edi
0xfc507324 <gnttab_try_map+4>: push %esi
0xfc507325 <gnttab_try_map+5>: push %ebx
0xfc507326 <gnttab_try_map+6>: sub $0xc,%esp
0xfc507329 <gnttab_try_map+9>: mov 0x20(%esp),%edx
0xfc50732d <gnttab_try_map+13>: mov 0x28(%esp),%edi
0xfc507331 <gnttab_try_map+17>: mov 0x2c(%esp),%ebp
0xfc507335 <gnttab_try_map+21>: mov 0xb64(%edx),%esi
0xfc50733b <gnttab_try_map+27>: test %esi,%esi
0xfc50733d <gnttab_try_map+29>: je 0xfc50738e
<gnttab_try_map+110>
0xfc50733f <gnttab_try_map+31>: lock decb 0x8(%esi)
0xfc507343 <gnttab_try_map+35>: js 0xfc5279c7
<crash_domain_fixup3+788>
0xfc507349 <gnttab_try_map+41>: mov %edi,%ecx
0xfc50734b <gnttab_try_map+43>: and $0xff,%ecx
0xfc507351 <gnttab_try_map+49>: lea (%esi,%ecx,2),%edx
0xfc507354 <gnttab_try_map+52>: cmpw $0xffffffff,0xc(%edx)
0xfc507359 <gnttab_try_map+57>: lea 0xc(%edx),%ecx
0xfc50735c <gnttab_try_map+60>: je 0xfc507388
<gnttab_try_map+104>
0xfc50735e <gnttab_try_map+62>: mov 0x4(%esi),%ebx
0xfc507361 <gnttab_try_map+65>: jmp 0xfc507370
<gnttab_try_map+80>
0xfc507363 <gnttab_try_map+67>: nop
(gdb) disas 0xfc51b4ca
...
0xfc51b4af <put_page_type+991>: mov 0x34(%esp),%ecx
0xfc51b4b3 <put_page_type+995>: add $0x2,%edx
0xfc51b4b6 <put_page_type+998>: mov %edx,0xc(%esp)
0xfc51b4ba <put_page_type+1002>: mov 0x28(%esp),%edx
0xfc51b4be <put_page_type+1006>: mov %ecx,0x4(%esp)
0xfc51b4c2 <put_page_type+1010>: mov %edx,(%esp)
0xfc51b4c5 <put_page_type+1013>: call 0xfc507320
<gnttab_try_map>
(gdb) disas 0xfc509a60
0xfc509a40 <free_domheap_pages+224>: movb $0xff,0x46(%ebp)
0xfc509a44 <free_domheap_pages+228>: movb $0x1,0x44(%ebp)
0xfc509a48 <free_domheap_pages+232>: mov %ebx,0x4(%esp)
0xfc509a4c <free_domheap_pages+236>: mov 0x18(%esp),%edi
0xfc509a50 <free_domheap_pages+240>: movl $0x1,(%esp)
0xfc509a57 <free_domheap_pages+247>: mov %edi,0x8(%esp)
0xfc509a5b <free_domheap_pages+251>: call 0xfc5095c0
<free_heap_pages>
-------------------------------------------------------
This SF.net email is sponsored by: IT Product Guide on ITManagersJournal
Use IT products in your business? Tell us what you think of them. Give us
Your Opinions, Get Free ThinkGeek Gift Certificates! Click to find out more
http://productguide.itmanagersjournal.com/guidepromo.tmpl
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/xen-devel