We have tested the latest xen on VT platform with Intel 915/E8500
chipset.
Here is the test summary:
Issues:
- Cannot boot Four VMX at same time on IA32 host
- Cannot boot Windows XP SP1/SP2 on IA32e host
- Create IA32-PAE VMX on IA32e host will make VMX kernel panic
- Create IA32 VMX on IA32e host will make VMX hang
- Destroying VMX with 4G memory may make xend hang on IA-32e
IA-32:
- Cannot bootup Four VMX at same time
+ Build&Boot SMP xen0 without problem
+ Can bootup unmodified IA-32 2.4/2.6 linux in SMP VMX domain
+ Can bootup unmodified IA-32 WindowsXP SP1/SP2 in VMX domain
+ Can bootup SMP VMX & XenU with different memory size
(VMX:64MB,128MB,196MB,256MB,512MB.XenU:256MB)
+ A selected subset of LTP runs well in SMP VMX domain(2.6)
+ Can startX in Dom0
+ Can bootup IA-32 2.6 linux in SMP VMX domain with acpi enable
IA-32_PAE:
- Cannot bootup Four VMX at same time
+ Build&Boot SMP xen0 without problem
+ Can bootup unmodified IA-32 2.6 linux in VMX domain
+ Can bootup unmodified IA-32 WindowXP SP1 in VMX domain
+ Can bootup VMX & XenU with different memory size
(VMX:64MB,128MB,196MB,256MB,512MB,1500MB.XenU:256MB)
+ Can startX in Dom0
+ Can bootup IA-32 2.6 linux in VMX domain with acpi enable
IA-32e:
- Can NOT bootup unmodified IA32(2.4, 2.6) linux in VMX domain
- Can NOT bootup unmodified IA32PAE 2.6 linux in VMX domain
- Can NOT bootup unmodified IA-32 WindowXP SP1/SP2 in VMX domain
+ Build&Boot SMP xen0 without problem
+ Can bootup unmodified IA-32e(2.6) linux in VMX domain
+ Can bootup VMX & xenU with different memory size.
(VMX:128MB,256MB,384MB,512MB,1024M,4096MB.XenU:256MB)
+ A selected subset of LTP runs well in VMX domain(2.6)
+ Can startX in Dom0
+ Can bootup IA-32e 2.6 linux in VMX domain with acpi enable
For details
------------------------------------------------------------
Platform: IA-32
Service OS: FC5, IA-32, SMP
Hardware: Grandstale
Default guest OS: IA-32-SMP, 2.6 kernel
1, one vmx with memory 512M PASS
2, one xenU with memory 256M PASS
3, 2 vmx and 2 xenU coexist PASS
4, four vmx coexist(64M,128M,196M,256M) FAIL
5, network in VMX domain PASS
6, network in XenU domain PASS
7, one window domain PASS
8, 1 xpsp1 and 1 xpsp2 windows domains coexist PASS
9, XenU migration PASS
10,subset LTP test in VMX domain PASS
11,one vmx boot with base kernel(2.6.16) PASS
12,xm-test FAIL
13,kernel build in smp guest PASS
14,StartX in Dom0 PASS
15,one vmx with acpi enable PASS
LTP test result on IA-32
Summary Test Report of Last Session
=================================================== Total
Pass Fail NoResult Crash
===================================================ltp 194 194
0 0 0
===================================================ltp 194 194
0 0 0
mm 21 21 0 0 0
dio 28 28 0 0 0
nptl 1 1 0 0 0
math 10 10 0 0 0
ipc 8 8 0 0 0
pty 3 3 0 0 0
quickhit 120 120 0 0 0
sched 3 3 0 0 0
===================================================Total 194 194
0 0 0
Platform: IA-32_PAE
Service OS: RHEL4U1, IA-32_PAE, SMP
Hardware: Grandstal
Default guest OS: IA-32-SMP, 2.6 kernel, PAE support
1, one vmx with memory 512M PASS
2, one vmx with memory 1.5GB PASS
3, one xenU with memory 256M PASS
4, 2 vmx and 2 xenU coexist PASS
5, four vmx coexist(64M,128M,196M,256M) FAIL
6, network in VMX domain PASS
7, network in XenU domain PASS
8, one xpsp1 window domain PASS
9, xm-test FAIL
10,XenU migration FAIL
11,one vmx boot with base kernel(2.6.16) PASS
12,StartX in Dom0 PASS
13,one vmx with acpi enable PASS
Platform: IA-32e
Service OS: RHEL4U2, IA-32e, SMP
Hardware: Paxville
Default guest OS: IA-32e, 2.6 kernel
1, one vmx with memory 1024M PASS
2, one xenU with memory 256M PASS
3, 2 vmx and 2 xenU coexist PASS
4, four vmx coexist(two IA32 kernel, two IA32e kernel) FAIL
5, network in VMX domain PASS
6, network in XenU domain PASS
7, one IA32 2.6 VMX domain with memory 256M FAIL
8, one IA-32PAE 2.6 VMX domain with 1500M FAIL
9, IA-32 and IA-32PAE VMX coexist FAIL
10, IA-32,IA-32PAE and IA-32e VMX coexist FAIL
11, LTP in VMX PASS
12, one xpsp1 window domain FAIL
13, 1 xpsp1 and 1 xpsp2 windows domains coexist FAIL
14, xm-test FAIL
15,one vmx boot with base kernel(2.6.16) PASS
16,Build base kernel in 64bit VMX domain PASS
17,StartX in Dom0 PASS
18,one vmx with acpi enable PASS
LTP test result on IA-32e
Summary Test Report of Last Session
=================================================== Total
Pass Fail NoResult Crash
===================================================ltp 195 195
0 0 0
===================================================ltp 195 195
0 0 0
mm 21 21 0 0 0
dio 28 28 0 0 0
nptl 1 1 0 0 0
math 10 10 0 0 0
ipc 8 8 0 0 0
pty 3 3 0 0 0
quickhit 121 121 0 0 0
sched 3 3 0 0 0
===================================================Total 195 195
0 0 0
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xensource.com
http://lists.xensource.com/xen-devel
Stefan Kaltenbrunner
2006-Jul-14 16:01 UTC
Re: [Xen-devel] VMX status report 10680:f692a0a476c5
Zheng, Jeff wrote:> > We have tested the latest xen on VT platform with Intel 915/E8500 > chipset. > > > Here is the test summary: > > > Issues: > > - Cannot boot Four VMX at same time on IA32 host > - Cannot boot Windows XP SP1/SP2 on IA32e host > - Create IA32-PAE VMX on IA32e host will make VMX kernel panic > - Create IA32 VMX on IA32e host will make VMX hang > - Destroying VMX with 4G memory may make xend hang on IA-32eFYI: on my Pentium D920 box with a 64bit hypervisor WinXP SP2 is broken on -unstable for a while now: (XEN) ff, This opcode isn''t handled yet! (XEN) handle_mmio: failed to decode instruction (XEN) mmio opcode: va 0xb8216, gpa 0xb8216, len 3: ff 77 16 (XEN) domain_crash_sync called from platform.c:857 (XEN) Domain 6 (vcpu#0) crashed on cpu#0: (XEN) ----[ Xen-3.0-unstable Not tainted ]---- (XEN) CPU: 0 (XEN) RIP: c000:[<0000000000003c09>] (XEN) RFLAGS: 0000000000033006 CONTEXT: hvm (XEN) rax: 00000000000f0060 rbx: 0000000000000200 rcx: 00000000000f0005 (XEN) rdx: 0000000000000000 rsi: 0000000000000000 rdi: 00000000000d0500 (XEN) rbp: 00000000000dffcc rsp: 000000000000ffb8 r8: 0000000000000000 (XEN) r9: 0000000000000000 r10: 0000000000000000 r11: 0000000000000000 (XEN) r12: 0000000000000000 r13: 0000000000000000 r14: 0000000000000000 (XEN) r15: 0000000000000000 cr0: 0000000000050032 cr3: 00000000183b8000 (XEN) ds: b800 es: 0000 fs: 0010 gs: 0010 ss: 0000 cs: c000 the very same issue affects my Fedora Core 5 VMX domain. Stefan _______________________________________________ Xen-devel mailing list Xen-devel@lists.xensource.com http://lists.xensource.com/xen-devel
This should be an issue of credit scheduler. It should be ok if use sedf. Thanks Yunfeng>-----Original Message----- >From: xen-devel-bounces@lists.xensource.com >[mailto:xen-devel-bounces@lists.xensource.com] On Behalf Of Stefan >Kaltenbrunner >Sent: 2006年7月15日 0:02 >To: Zheng, Jeff >Cc: xen-devel@lists.xensource.com >Subject: Re: [Xen-devel] VMX status report 10680:f692a0a476c5 > >Zheng, Jeff wrote: >> >> We have tested the latest xen on VT platform with Intel 915/E8500 >> chipset. >> >> >> Here is the test summary: >> >> >> Issues: >> >> - Cannot boot Four VMX at same time on IA32 host >> - Cannot boot Windows XP SP1/SP2 on IA32e host >> - Create IA32-PAE VMX on IA32e host will make VMX kernel panic >> - Create IA32 VMX on IA32e host will make VMX hang >> - Destroying VMX with 4G memory may make xend hang on IA-32e > >FYI: on my Pentium D920 box with a 64bit hypervisor WinXP SP2 is broken >on -unstable for a while now: > >(XEN) ff, This opcode isn''t handled yet! >(XEN) handle_mmio: failed to decode instruction >(XEN) mmio opcode: va 0xb8216, gpa 0xb8216, len 3: ff 77 16 >(XEN) domain_crash_sync called from platform.c:857 >(XEN) Domain 6 (vcpu#0) crashed on cpu#0: >(XEN) ----[ Xen-3.0-unstable Not tainted ]---- >(XEN) CPU: 0 >(XEN) RIP: c000:[<0000000000003c09>] >(XEN) RFLAGS: 0000000000033006 CONTEXT: hvm >(XEN) rax: 00000000000f0060 rbx: 0000000000000200 rcx: 00000000000f0005 >(XEN) rdx: 0000000000000000 rsi: 0000000000000000 rdi: 00000000000d0500 >(XEN) rbp: 00000000000dffcc rsp: 000000000000ffb8 r8: 0000000000000000 >(XEN) r9: 0000000000000000 r10: 0000000000000000 r11: 0000000000000000 >(XEN) r12: 0000000000000000 r13: 0000000000000000 r14: 0000000000000000 >(XEN) r15: 0000000000000000 cr0: 0000000000050032 cr3: 00000000183b8000 >(XEN) ds: b800 es: 0000 fs: 0010 gs: 0010 ss: 0000 cs: c000 > >the very same issue affects my Fedora Core 5 VMX domain. > > >Stefan > >_______________________________________________ >Xen-devel mailing list >Xen-devel@lists.xensource.com >http://lists.xensource.com/xen-devel_______________________________________________ Xen-devel mailing list Xen-devel@lists.xensource.com http://lists.xensource.com/xen-devel
Stefan Kaltenbrunner
2006-Jul-14 16:36 UTC
Re: [Xen-devel] VMX status report 10680:f692a0a476c5
Zhao, Yunfeng wrote:> This should be an issue of credit scheduler. > It should be ok if use sedf.ah - with SEDF it now seems to work just fine though rather slow (>15min to boot seems a bit excessive). thanks Stefan _______________________________________________ Xen-devel mailing list Xen-devel@lists.xensource.com http://lists.xensource.com/xen-devel
>FYI: on my Pentium D920 box with a 64bit hypervisor WinXP SP2 is broken >on -unstable for a while now: > >(XEN) ff, This opcode isn''t handled yet! >(XEN) handle_mmio: failed to decode instruction >(XEN) mmio opcode: va 0xb8216, gpa 0xb8216, len 3: ff 77 16 >(XEN) domain_crash_sync called from platform.c:857 >(XEN) Domain 6 (vcpu#0) crashed on cpu#0: >(XEN) ----[ Xen-3.0-unstable Not tainted ]---- >(XEN) CPU: 0 >(XEN) RIP: c000:[<0000000000003c09>] >(XEN) RFLAGS: 0000000000033006 CONTEXT: hvm >(XEN) rax: 00000000000f0060 rbx: 0000000000000200 rcx: >00000000000f0005 >(XEN) rdx: 0000000000000000 rsi: 0000000000000000 rdi: >00000000000d0500 >(XEN) rbp: 00000000000dffcc rsp: 000000000000ffb8 r8: >0000000000000000 >(XEN) r9: 0000000000000000 r10: 0000000000000000 r11: >0000000000000000 >(XEN) r12: 0000000000000000 r13: 0000000000000000 r14: >0000000000000000 >(XEN) r15: 0000000000000000 cr0: 0000000000050032 cr3: >00000000183b8000 >(XEN) ds: b800 es: 0000 fs: 0010 gs: 0010 ss: 0000 cs: c000 > >the very same issue affects my Fedora Core 5 VMX domain. >Fixed by changeset 10704. -Xin _______________________________________________ Xen-devel mailing list Xen-devel@lists.xensource.com http://lists.xensource.com/xen-devel