[Top] [All Lists]
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

RE: [Xen-users] Domain 0 reboot when network flow is heavy

 

> -----Original Message-----
> From: xen-users-bounces@xxxxxxxxxxxxxxxxxxx 
> [mailto:xen-users-bounces@xxxxxxxxxxxxxxxxxxx] On Behalf Of Tim Post
> Sent: 26 June 2007 10:20
> To: Xin Chen
> Cc: xen-users
> Subject: Re: [Xen-users] Domain 0 reboot when network flow is heavy
> 
> On Tue, 2007-06-26 at 19:09 +1000, Xin Chen wrote:
> 
> 
> > well, ftp works , domain 0 didn't reboot.
> > ftp takes:
> > in 1.9e+03 seconds (5.1e-07 Kbytes/s)
> > <I don't really know 1.9e_03 = how long, and 5.1e-07 Kb = 
> how fast..>
> 
> I completely lost dom-0 seeing similar things, however guests that
> didn't get I/O at all were still sputtering to a syslog server and my
> setup was different. It (dom-0) just went 'poof'.
> 
> When I power cycled the server, most of dom-0's root file 
> system (ext3)
> was in an existentially challenged state of being, including logs.
> 
> I don't have logs, or anything else which is why I didn't ship a bug
> report to xen-devel.
> 
> Not quite the same experience, but I have been getting _weird_ results
> with 3.1 on AMD-V machines using 32P kernel and HV with all PV guests.
> Some frequent crashes with 64 bit HV and dom-0 also. I have yet to try
> mixing them. 
> 
> I'm not even sure how I could go about filing such a bug report. Hi,
> yes, Xen Devel? The Bermuda triangle moved into my desktop 
> and disrupted
> your software, I just thought you ought to know ... 
> 
> Should such things be reported? I'm really not saying anything other
> than 'I think it might be broken, somehow."

Yes, I think this type of bug should be reported, for two reasons:
1. If there's some statistics of how often and when this happens,
there's a better chance of someone looking at it because it's
"important". 
2. If there's some pattern (e.g. certain network cards, certain variants
of the kernel or some such) that can help the debug process, that will
become more noticable when there's multiple reporters of the problem. 

The fact that it's "difficult to debug/describe" shouldn't really
prevent a bug-report. 

--
Mats
> 
> Best,
> --Tim
> 
> > Xin Chen wrote:
> > 
> > > I tried the same thing again, using scp copying.....
> > > this time even worse, 16%... domain 0 reboots.....
> > >
> > > ok, I will try using ftp to copy the 20Gb file now...
> > >
> > > Xin Chen wrote:
> > >
> > >> Hi All,
> > >>
> > >> I am not sure about this, just wondering anyone has the similar 
> > >> situation with me::
> > >>
> > >> I was using  scp command on a remote server, copying a 
> 20G file into 
> > >> Domain 0 server.
> > >> the speed displayed is around 8Mb/s
> > >>
> > >> waiting...
> > >> waiting...
> > >>
> > >> at 67%, it stopped, why? because Domain 0 reboot.....
> > >>
> > >> I check the log, nothing useful. I guess it is because 
> the network 
> > >> flowing,
> > >> because the domain 0 has been running for 3 weeks until 
> today I do 
> > >> the copying.
> > >>
> > >> I attached some info, please give me some advice, thanks a lot!!
> > >>
> > >> xin
> > >>
> > >> [root@XenServer xen]# uname -a
> > >> Linux XenServer 2.6.18-1.2798.fc6xen #1 SMP Mon Oct 16 
> 15:11:19 EDT 
> > >> 2006 i686 i686 i386 GNU/Linux
> > >>
> > >> [root@XenServer xen]# xm info
> > >> host                   : XenServer
> > >> release                : 2.6.18-1.2798.fc6xen
> > >> version                : #1 SMP Mon Oct 16 15:11:19 EDT 2006
> > >> machine                : i686
> > >> nr_cpus                : 4
> > >> nr_nodes               : 1
> > >> sockets_per_node       : 1
> > >> cores_per_socket       : 4
> > >> threads_per_core       : 1
> > >> cpu_mhz                : 1600
> > >> hw_caps                : 
> > >> bfebfbff:20100000:00000000:00000140:0004e33d:00000000:00000001
> > >> total_memory           : 4094
> > >> free_memory            : 0
> > >> xen_major              : 3
> > >> xen_minor              : 0
> > >> xen_extra              : .3-rc3-1.2798.f
> > >> xen_caps               : xen-3.0-x86_32p hvm-3.0-x86_32 
> hvm-3.0-x86_32p
> > >> xen_pagesize           : 4096
> > >> platform_params        : virt_start=0xf5800000
> > >> xen_changeset          : unavailable
> > >> cc_compiler            : gcc version 4.1.1 20061011 (Red 
> Hat 4.1.1-30)
> > >> cc_compile_by          : brewbuilder
> > >> cc_compile_domain      : build.redhat.com
> > >> cc_compile_date        : Mon Oct 16 14:34:31 EDT 2006
> > >> xend_config_format     : 2
> > >>
> > >> /var/log/xend.log
> > >> [2007-06-24 01:08:55 xend 3125] DEBUG 
> (DevController:149) Waiting for 
> > >> 51712.
> > >> [2007-06-24 01:08:55 xend 3125] DEBUG (DevController:472) 
> > >> hotplugStatusCallback
> > >> /local/domain/0/backend/tap/6/51712/hotplug-status.
> > >> [2007-06-24 01:08:55 xend 3125] DEBUG (DevController:486) 
> > >> hotplugStatusCallback
> > >> 1.
> > >> [2007-06-24 01:08:55 xend 3125] DEBUG 
> (DevController:143) Waiting for 
> > >> devices vt
> > >> pm.
> > >> [2007-06-24 01:08:55 xend 3125] INFO (XendDomain:370) 
> Domain stimpy 
> > >> (6) unpaused
> > >> .
> > >> *[2007-06-26 17:18:55 xend 3154] INFO (SrvDaemon:283) 
> Xend Daemon 
> > >> started  -> here is the place reboot.*
> > >> [2007-06-26 17:18:55 xend 3154] INFO (SrvDaemon:287) 
> Xend changeset: 
> > >> unavailable
> > >>  .
> > >> [2007-06-26 17:18:55 xend.XendDomainInfo 3154] DEBUG 
> > >> (XendDomainInfo:212) XendDo
> > >> mainInfo.recreate({'paused': 0, 'cpu_time': 
> 29578464995L, 'ssidref': 
> > >> 0, 'handle'
> > >> : [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], 
> > >> 'shutdown_reason': 0, 'dying
> > >> ': 0, 'dom': 0, 'mem_kb': 4012156, 'maxmem_kb': -4, 
> 'max_vcpu_id': 3, 
> > >> 'crashed':
> > >>  0, 'running': 1, 'shutdown': 0, 'online_vcpus': 4, 
> 'blocked': 0})
> > >> [2007-06-26 17:18:55 xend.XendDomainInfo 3154] INFO 
> > >> (XendDomainInfo:224) Recreat
> > >> ing domain 0, UUID 00000000-0000-0000-0000-000000000000.
> > >> [2007-06-26 17:18:55 xend.XendDomainInfo 3154] WARNING 
> > >> (XendDomainInfo:246) No v
> > >> m path in store for existing domain 0
> > >> [2007-06-26 17:18:55 xend.XendDomainInfo 3154] DEBUG 
> > >> (XendDomainInfo:715) Storin
> > >> g VM details: {'shadow_memory': '0', 'uuid': 
> > >> '00000000-0000-0000-0000-0000000000
> > >> 00', 'on_reboot': 'restart', 'on_poweroff': 'destroy', 'name': 
> > >> 'Domain-0', 'xend
> > >> /restart_count': '0', 'vcpus': '4', 'vcpu_avail': '15', 
> 'memory': 
> > >> '3919', 'on_cr
> > >> ash': 'restart', 'maxmem': '3919'}
> > >> [2007-06-26 17:18:56 xend.XendDomainInfo 3154] DEBUG 
> > >> (XendDomainInfo:750) Storin
> > >> g domain details: {'cpu/1/availability': 'online', 
> > >> 'cpu/3/availability': 'online
> > >> ', 'name': 'Domain-0', 'console/limit': '1048576', 
> > >> 'cpu/2/availability': 'online
> > >> ', 'vm': '/vm/00000000-0000-0000-0000-000000000000', 
> 'domid': '0', 
> > >> 'cpu/0/availa
> > >> bility': 'online', 'memory/target': '4013056'}
> > >> [2007-06-26 17:18:56 xend 3154] DEBUG (XendDomain:153) number of 
> > >> vcpus to use is
> > >>  0
> > >> [2007-06-26 17:18:56 xend 3154] INFO (SrvServer:116) unix 
> > >> path=/var/lib/xend/xen
> > >> d-socket
> > >>
> > >>
> > >> /var/log/message:
> > >> Jun 26 17:14:58 XenServer kernel: peth1: received packet 
> with  own 
> > >> address as so
> > >> urce address
> > >> Jun 26 17:15:57 XenServer last message repeated 2 times
> > >> Jun 26 17:15:57 XenServer kernel: peth0: received packet 
> with  own 
> > >> address as so
> > >> urce address
> > >> Jun 26 17:16:01 XenServer kernel: peth1: received packet 
> with  own 
> > >> address as so
> > >> urce address
> > >> Jun 26 17:17:00 XenServer kernel: peth1: received packet 
> with  own 
> > >> address as so
> > >> urce address
> > >> *Jun 26 17:18:38 XenServer syslogd 1.4.1: restart. --> 
> here is the 
> > >> place reboot*
> > >> Jun 26 17:18:38 XenServer kernel: klogd 1.4.1, log source = 
> > >> /proc/kmsg started.
> > >> Jun 26 17:18:38 XenServer kernel: Linux version 
> 2.6.18-1.2798.fc6xen 
> > >> (brewbuilde
> > >> r@xxxxxxxxxxxxxxxxxxxxxxxxxxx) (gcc version 4.1.1 
> 20061011 (Red Hat 
> > >> 4.1.1-30)) #
> > >> 1 SMP Mon Oct 16 15:11:19 EDT 2006
> > >> Jun 26 17:18:38 XenServer kernel: BIOS-provided physical RAM map:
> > >> Jun 26 17:18:38 XenServer kernel:  Xen: 0000000000000000 - 
> > >> 00000000f575f000 (usa
> > >> ble)
> > >> Jun 26 17:18:38 XenServer kernel: 3199MB HIGHMEM available.
> > >> Jun 26 17:18:38 XenServer kernel: 727MB LOWMEM available.
> > >> Jun 26 17:18:38 XenServer kernel: NX (Execute Disable) 
> protection: 
> > >> active
> > >> Jun 26 17:18:38 XenServer kernel: found SMP MP-table at 000f5f20
> > >> Jun 26 17:18:38 XenServer kernel: DMI present.
> > >> Jun 26 17:18:38 XenServer kernel: ACPI: LAPIC (acpi_id[0x00] 
> > >> lapic_id[0x00] enab
> > >> led)
> > >> Jun 26 17:18:38 XenServer kernel: ACPI: LAPIC (acpi_id[0x01] 
> > >> lapic_id[0x01] enab
> > >> led)
> > >> Jun 26 17:18:38 XenServer kernel: ACPI: LAPIC (acpi_id[0x02] 
> > >> lapic_id[0x02] enab
> > >> led)
> > >> Jun 26 17:18:38 XenServer kernel: ACPI: LAPIC (acpi_id[0x03] 
> > >> lapic_id[0x03] enab
> > >> led)
> > >> Jun 26 17:18:38 XenServer kernel: ACPI: LAPIC_NMI 
> (acpi_id[0x00] high 
> > >> edge lint[
> > >> 0x1])
> > >> Jun 26 17:18:38 XenServer kernel: ACPI: LAPIC_NMI 
> (acpi_id[0x01] high 
> > >> edge lint[
> > >> 0x1])
> > >> Jun 26 17:18:38 XenServer kernel: ACPI: LAPIC_NMI 
> (acpi_id[0x02] high 
> > >> edge lint[
> > >> 0x1])
> > >> Jun 26 17:18:38 XenServer kernel: ACPI: LAPIC_NMI 
> (acpi_id[0x03] high 
> > >> edge lint[
> > >> 0x1])
> > >> Jun 26 17:18:38 XenServer kernel: ACPI: IOAPIC (id[0x04] 
> > >> address[0xfec00000] gsi
> > >> _base[0])
> > >> Jun 26 17:18:38 XenServer kernel: IOAPIC[0]: apic_id 4, 
> version 32, 
> > >> address 0xfe
> > >> c00000, GSI 0-23
> > >> Jun 26 17:18:38 XenServer kernel: ACPI: IOAPIC (id[0x05] 
> > >> address[0xfec80000] gsi
> > >> _base[24])
> > >>
> > >> 
> --------------------------------------------------------------
> ----------
> > >>
> > >> _______________________________________________
> > >> Xen-users mailing list
> > >> Xen-users@xxxxxxxxxxxxxxxxxxx
> > >> http://lists.xensource.com/xen-users
> > >>
> > >
> > >
> > > _______________________________________________
> > > Xen-users mailing list
> > > Xen-users@xxxxxxxxxxxxxxxxxxx
> > > http://lists.xensource.com/xen-users
> > 
> > 
> > 
> > _______________________________________________
> > Xen-users mailing list
> > Xen-users@xxxxxxxxxxxxxxxxxxx
> > http://lists.xensource.com/xen-users
> 
> 
> _______________________________________________
> Xen-users mailing list
> Xen-users@xxxxxxxxxxxxxxxxxxx
> http://lists.xensource.com/xen-users
> 
> 
> 



_______________________________________________
Xen-users mailing list
Xen-users@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-users

 

©2013 Xen Project, A Linux Foundation Collaborative Project. All Rights Reserved.
Linux Foundation is a registered trademark of The Linux Foundation.
Xen Project is a trademark of The Linux Foundation.

Rackspace

Lists.xenproject.org is hosted with RackSpace, monitoring our
servers 24x7x365 and backed by RackSpace's Fanatical Support®.