Hi,
If this occurred solely when upgrading the amount of RAM in the system (did
you even get to increase the memory size of individual domUs yet?) I'd
suggest this is probably some kind of bug and should be referred to the
xen-devel list.
Cheers,
Mark
On Saturday 10 March 2007 18:12, sergiu@xxxxxx wrote:
> Hi,
>
> I've build an entire army of xen PV and HVM guests. I succeded to resolve
> any problem encountered in my xen-projects. Everything was jus great in my
> "perfect-xen-world" until I've changed something simple.
>
> THE PROBLEM: I've made an upgrade from 2GB RAM to 4GB RAM and everything
> was screwed up: zombie domUs, corrupted tap:aio files, tons of erros etc.
> If I'm going back to old configuration with 2 GB of RAM the everything
> comes back to normal.
>
> First time I thought that new DDR2 modules are the cause of this cataclysm
> but memtest did not return any error. That was on my Intel Server with 4 x
> 1 GB DDR2 modules at 533 Mhz and 1 x Intel(R) Pentium(R) D CPU 3.40GHz
> with 2 cores and 2 MB L2 Cache on each core.
>
> I've made additional tests on a separated machine: Dell PowerEdge 1950
> with 8 x 512 DDR2 modules at 677 Mhz and 2 x Intel(R) Xeon(R) CPU 5130 @
> 2.00GHz with 2 cores / CPU and 4 MB L2 Cache on each core. The problem is
> exactly the same... but if I'm using only 2 GB of RAM everything is ok.
>
> Issues:
>
> * I don't think Intel SE7230NH1 and Dell PE 1950 servers had hardware
> problems that could cause this problem
>
> * A non-PAE kernel can only address up to 4GB of memory... I do not have
> more than 4 GB of RAM
>
> * I found some articles related to Xen having problems with more than 4
> Gbytes of network traffic
>
> * I found some articles related to LSI Logic RAID Controllers combined
> with linux driver having problems on machines with 4 GB of memory
>
> * It's something related to memory holes?
>
> * It's something related only to Fedora Core Xen Kernels?
>
> Here are some about my setup
>
> ---------------------------------------------------
>
> ** Details on dom0:
>
> title Fedora Core (2.6.19-1.2911.6.5.fc6xen)
> root (hd0,0)
> kernel /xen.gz-2.6.19-1.2911.6.5.fc6
> module /vmlinuz-2.6.19-1.2911.6.5.fc6xen ro root=/dev/sda1
> module /initrd-2.6.19-1.2911.6.5.fc6xen.img
>
> host : localhost.localdomain
> release : 2.6.19-1.2911.6.5.fc6xen
> version : #1 SMP Sun Mar 4 16:59:41 EST 2007
> machine : i686
> nr_cpus : 4
> nr_nodes : 1
> sockets_per_node : 2
> cores_per_socket : 2
> threads_per_core : 1
> cpu_mhz : 1995
> hw_caps :
> bfebfbff:20100000:00000000:00000140:0004e33d:00000000:00000001
> total_memory : 4095
> free_memory : 512
> xen_major : 3
> xen_minor : 0
> xen_extra : .3-0-1.2911.6.5
> 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 20070105 (Red Hat 4.1.1-51)
> cc_compile_by : brewbuilder
> cc_compile_domain : build.redhat.com
> cc_compile_date : Sun Mar 4 15:44:49 EST 2007
> xend_config_format : 2
>
>
> ** Parts from xm dmesg
>
>
> Xen version 3.0.3-0-1.2911.6.5.fc6 (brewbuilder@xxxxxxxxxxxxxxxx) (gcc
> version 4.1.1 20070105 (Red Hat 4.1.1-51)) Sun Mar 4 15:44:49 EST 2007
> Latest ChangeSet: unavailable
>
> (XEN) Command line: /boot/xen.gz-2.6.19-1.2911.6.5.fc6
> (XEN) Physical RAM map:
> (XEN) 0000000000000000 - 00000000000a0000 (usable)
> (XEN) 0000000000100000 - 00000000cffa8000 (usable)
> (XEN) 00000000cffa8000 - 00000000cffb7c00 (ACPI data)
> (XEN) 00000000cffb7c00 - 00000000d0000000 (reserved)
> (XEN) 00000000e0000000 - 00000000f0000000 (reserved)
> (XEN) 00000000fe000000 - 0000000100000000 (reserved)
> (XEN) 0000000100000000 - 0000000130000000 (usable)
> (XEN) System RAM: 4095MB (4193568kB)
> (XEN) Xen heap: 9MB (10224kB)
> (XEN) PAE enabled, limit: 16 GB
> (XEN) found SMP MP-table at 000fe710
> (XEN) DMI 2.4 present.
> (XEN) Using APIC driver default
>
>
> (XEN) VMXON is done
>
>
> (XEN) ENABLING IO-APIC IRQs
> (XEN) -> Using new ACK method
> (XEN) ..TIMER: vector=0xF0 apic1=0 pin1=2 apic2=-1 pin2=-1
> (XEN) checking TSC synchronization across 4 CPUs: passed.
> (XEN) Platform timer is 14.318MHz HPET
> (XEN) Brought up 4 CPUs
> (XEN) Machine check exception polling timer started.
> (XEN) *** LOADING DOMAIN 0 ***
> (XEN) Domain 0 kernel supports features = { 0000001f }.
> (XEN) Domain 0 kernel requires features = { 00000000 }.
> (XEN) PHYSICAL MEMORY ARRANGEMENT:
> (XEN) Dom0 alloc.: 0000000007000000->0000000008000000 (999720 pages to
> be allocated)
> (XEN) VIRTUAL MEMORY ARRANGEMENT:
> (XEN) Loaded kernel: c0400000->c085aa08
> (XEN) Init. ramdisk: c085b000->c0b8e000
> (XEN) Phys-Mach map: c0b8e000->c0f624a0
> (XEN) Start info: c0f63000->c0f6346c
> (XEN) Page tables: c0f64000->c0f71000
> (XEN) Boot stack: c0f71000->c0f72000
> (XEN) TOTAL: c0000000->c1000000
> (XEN) ENTRY ADDRESS: c0400000
> (XEN) Dom0 has maximum 4 VCPUs
> (XEN) Initrd len 0x333000, start at 0xc085b000
> (XEN) Scrubbing Free RAM:
> .................................................done.
> (XEN) Xen trace buffers: disabled
> (XEN) Xen is relinquishing VGA console.
> (XEN) *** Serial input -> DOM0 (type 'CTRL-a' three times to switch input
> to Xen).
>
>
> ** xm list
>
> Name ID Mem(MiB) VCPUs State Time(s)
> Domain-0 0 3024 4 r----- 115.8
> Zombie-test5 16 256 1 ----cd 0.5
>
>
> ** Details on domU:
>
> Configuration
>
> name = "test1"
> memory = "256"
> disk = [ 'tap:aio:/huge/test1.img,xvda,w', ]
> bootloader="/usr/bin/pygrub"
> on_reboot = 'restart'
> on_crash = 'restart'
>
>
> Errors extracted from xm console test1
>
>
> Loading xenblk.ko module
> Registering block device major 202
> xvda:<1>WARNING: g.e. still in use!
> WARNING: leaking g.e. and page still in use!
> end_request: I/O error, dev xvda, sector 0
> Buffer I/O error on device xvda, logical block 0
> WARNING: g.e. still in use!
> WARNING: leaking g.e. and page still in use!
> end_request: I/O error, dev xvda, sector 0
> Buffer I/O error on device xvda, logical block 0
> WARNING: g.e. still in use!
> WARNING: leaking g.e. and page still in use!
> end_request: I/O error, dev xvda, sector 0
> Buffer I/O error on device xvda, logical block 0
> unable to read partition table
> Creating root device.
> WARNING: g.e. still in use!
> WARNING: leaking g.e. and page still in use!
> end_request: I/O error, dev xvda, sector 20971392
> Buffer I/O error on device xvda, logical block 2621424
> WARNING: g.e. still in use!
> WARNING: leaking g.e. and page still in use!
> end_request: I/O error, dev xvda, sector 20971392
> Buffer I/O error on device xvda, logical block 2621424
> WARNING: g.e. still in use!
> WARNING: leaking g.e. and page still in use!
> WARNING: g.e. still in use!
> WARNING: leaking g.e. and page still in use!
> WARNING: g.e. still in use!
> WARNING: leaking g.e. and page still in use!
> WARNING: g.e. still in use!
> WARNING: leaking g.e. and page still in use!
> WARNING: g.e. still in use!
> WARNING: leaking g.e. and page still in use!
> WARNING: g.e. still in use!
> WARNING: leaking g.e. and page still in use!
> WARNING: g.e. still in use!
> WARNING: leaking g.e. and page still in use!
> WARNING: g.e. still in use!
> WARNING: leaking g.e. and page still in use!
> end_request: I/O error, dev xvda, sector 0
> Buffer I/O error on device xvda, logical block 0
> Buffer I/O error on device xvda, logical block 1
> Buffer I/O error on device xvda, logical block 2
> Buffer I/O error on device xvda, logical block 3
> Buffer I/O error on device xvda, logical block 4
> WARNING: g.e. still in use!
> WARNING: leaking g.e. and page still in use!
> end_request: I/O error, dev xvda, sector 0
> Mounting root filesystem.
> WARNING: g.e. still in use!
> WARNING: leaking g.e. and page still in use!
> end_request: I/O error, dev xvda, sector 20971392
> WARNING: g.e. still in use!
> WARNING: leaking g.e. and page still in use!
> end_request: I/O error, dev xvda, sector 20971392
> WARNING: g.e. still in use!
> WARNING: leaking g.e. and page still in use!
> WARNING: g.e. still in use!
> WARNING: leaking g.e. and page still in use!
> WARNING: g.e. still in use!
> WARNING: leaking g.e. and page still in use!
> WARNING: g.e. still in use!
> WARNING: leaking g.e. and page still in use!
> WARNING: g.e. still in use!
> WARNING: leaking g.e. and page still in use!
> WARNING: g.e. still in use!
> WARNING: leaking g.e. and page still in use!
> WARNING: g.e. still in use!
> WARNING: leaking g.e. and page still in use!
> WARNING: g.e. still in use!
> WARNING: leaking g.e. and page still in use!
> end_request: I/O error, dev xvda, sector 0
> WARNING: g.e. still in use!
> WARNING: leaking g.e. and page still in use!
> end_request: I/O error, dev xvda, sector 0
> mount: could not find filesystem '/dev/root'
> Setting up other filesystems.
> Setting up new root fs
> setuproot: moving /dev failed: No such file or directory
> no fstab.sys, mounting internal defaults
> setuproot: error mounting /proc: No such file or directory
> setuproot: error mounting /sys: No such file or directory
> Switching to new root and running init.
> unmounting old /dev
> unmounting old /proc
> unmounting old /sys
> switchroot: mount failed: No such file or directory
> Kernel panic - not syncing: Attempted to kill init!
>
> ---------------------------------------------------
>
> I can understand that (for the moment) I cannot rely on Xen in production
> enviroments BUT I never imagine that Xen could be so unpredictable!
--
Dave: Just a question. What use is a unicyle with no seat? And no pedals!
Mark: To answer a question with a question: What use is a skateboard?
Dave: Skateboards have wheels.
Mark: My wheel has a wheel!
_______________________________________________
Xen-users mailing list
Xen-users@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-users
|
Home