public inbox for kvm@vger.kernel.org
 help / color / mirror / Atom feed
* ABAT Testing report, kernel 76f0301b5.., user 04cff0e47..
@ 2007-07-23  9:09 Zhao, Yunfeng
       [not found] ` <10EA09EFD8728347A513008B6B0DA77A01CBF1D2-wq7ZOvIWXbNpB2pF5aRoyrfspsVTdybXVpNB7YpNyf8@public.gmane.org>
  0 siblings, 1 reply; 3+ messages in thread
From: Zhao, Yunfeng @ 2007-07-23  9:09 UTC (permalink / raw)
  To: kvm-devel-5NWGOfrQmneRv+LV9MX5uipxlwaOVQ5f; +Cc: Zhao, Yunfeng

Hi, all

This is today's ABAT testing result against kvm.git 76f0301b5e4d2603d8e1ee5295db29faea660b49 and kvm-userspace.git 04cff0e47c4cc1e3d51f917a657b97ac2ed29719
We are still using UP guests in the testing, we will try to enable some SMP Windows and Linux tests in this week.

One new issue is about performance regression since KVM-29
1. Performance regression since KVM-29
https://sourceforge.net/tracker/index.php?func=detail&aid=1758756&group_id=180599&atid=893831

##What's working:
 Can boot most ia32/ia32e UP Linux guests with either acpi enabled or acpi disabled.
 Can boot ia32 UP UP Windows 2k, Windows XP, and Windows 2k3 guests with either acpi enabled or acpi disabled.
 Can boot Vista RTM with acpi, but network doesn't work. A workaround is installing a win2k ne2000 driver.
 Save/Restore works on both ia32 and IA32e
 Live migration works on ia32 and ia32e
 ia32 guest can be migrated from ia32 host to ia32e host
 Keybord, mouse, ide disk, vga, and nic work well.

##What's not working:
 Can NOT boot guest with > 2GB mem
 Can NOT boot ia32e UP/SMP Windows guests
 Can NOT boot ia32e rhel4u3 with -no-acpi
 Timer is not accurate
 Booting multiple guests likely fails

Issue list in ABAT Testing:
================================================
1. Could not create kvm guest with memory >=2040
https://sourceforge.net/tracker/index.php?func=detail&aid=1736307&group_id=180599&atid=893831
2. Create multiple guests simultaneously or create one guest many times may fail
https://sourceforge.net/tracker/index.php?func=detail&aid=1741312&group_id=180599&atid=893831
3. Can not boot IA32e RHEL 4u3 guest with -no-acpi
https://sourceforge.net/tracker/index.php?func=detail&aid=1741314&group_id=180599&atid=893831
4. Can not boot 64 bits windows
https://sourceforge.net/tracker/index.php?func=detail&aid=1741318&group_id=180599&atid=893831
5. Some ltp test cases fail
https://sourceforge.net/tracker/index.php?func=detail&aid=1741316&group_id=180599&atid=893831
6. Performance regression since KVM-29
https://sourceforge.net/tracker/index.php?func=detail&aid=1758756&group_id=180599&atid=893831

Issue list in ABAT Testing:
================================================
1. Could not create kvm guest with memory >=2040 
https://sourceforge.net/tracker/index.php?func=detail&aid=1736307&group_id=180599&atid=893831
2. Create multiple guests simultaneously or create one guest many times may fail 
https://sourceforge.net/tracker/index.php?func=detail&aid=1741312&group_id=180599&atid=893831
3. Can not boot IA32e RHEL 4u3 guest with -no-acpi
https://sourceforge.net/tracker/index.php?func=detail&aid=1741314&group_id=180599&atid=893831
4. Can not boot 64 bits windows
https://sourceforge.net/tracker/index.php?func=detail&aid=1741318&group_id=180599&atid=893831
5. Some ltp test cases fail
https://sourceforge.net/tracker/index.php?func=detail&aid=1741316&group_id=180599&atid=893831

 Test environment
================================================
Platform                Paxville-Harwich
CPU                     16
Memory size             8G'

 

Details
================================================
PAE:
1. boot guest with 256M memory                                  PASS
2. boot two windows xp guest                                    PASS
3. boot 4 same guest in parallel                                PASS
4. boot linux and windows guest in parallel                     PASS
5. boot 4G linux guest                                          FAIL
6. boot guest with 1500M memory                                 PASS
7. boot windows 2003 with ACPI enabled                          PASS
8. boot 32 bit vista with win2000 ne2000 driver                Pass  
9. boot Windows xp with ACPI enabled                            PASS
10. boot Windows 2000 without ACPI                              PASS
11. kernel build in guest OS                                    PASS
12. LTP on linux guest                                          PASS
13. boot base kernel linux                                      PASS


IA32e:
1. boot four 32-bit guest in parallel                             PASS
2. boot four 64-bit guest in parallel                             FAIL
3. boot 4G 64-bit guest                                       FAIL
4. boot 4G pae guest                                          FAIL
5. boot 32-bit linux and 32 bit windows guest in parallel     PASS
6. boot 32-bit guest with 1500M memory                         PASS
7. boot 32-bit guest with 256M memory                           PASS
8. boot 64-bit guest with 1500M memory                         PASS
9. boot 64-bit guest with 256M memory                           PASS
10. boot two 32-bit windows xp in parallel                      PASS
11. boot four 32-bit different guest in parallel                   PASS
12. save/restore 64-bit linux guests                             PASS
13. save/restore 32-bit linux guests                             PASS
14. boot 32-bit windows 2003 with ACPI enabled                 PASS
15. boot 32-bit Windows xp with ACPI enabled                   PASS
16. boot 32-bit Windows 2000 without ACPI                      PASS
17. boot 64-bit windows 2003 with ACPI enabled                 FAIL
18. boot 64-bit Windows xp with ACPI enabled                   FAIL
19. boot 64-bit vista                                          FAIL
20. kernel build in 32-bit linux guest OS                      PASS
21. kernel build in 64-bit linux guest OS                       PASS
22. LTP on 32-bit linux guest OS                                 PASS
23. LTP on 64-bit linux guest OS                                 PASS

PAE:
               Summary Test Report of Last Session
=====================================================================
                            Total   Pass    Fail    NoResult   Crash
=====================================================================
control_panel               7       6       1         0        0
Restart                     2       2       0         0        0
gtest                       8       7       1         0        0
=====================================================================
control_panel               7       6       1         0        0
 :KVM_four_sguest_PAE_gPA   1       1       0         0        0
 :KVM_256M_guest_PAE_gPAE   1       1       0         0        0
 :KVM_linux_win_PAE_gPAE    1       1       0         0        0
 :KVM_1500M_guest_PAE_gPA   1       1       0         0        0
 :KVM_SR_PAE_gPAE           1       1       0         0        0
 :KVM_two_winxp_PAE_gPAE    1       1       0         0        0
 :KVM_4G_guest_PAE_gPAE     1       0       1         0        0
Restart                     2       2       0         0        0
 :GuestPAE_PAE_gPAE         1       1       0         0        0
 :BootTo32pae_PAE_gPAE      1       1       0         0        0
gtest                       8       7       1         0        0
 :ltp_nightly_PAE_gPAE      1       1       0         0        0
 :boot_up_acpi_PAE_gPAE     1       1       0         0        0
 :boot_up_vista_PAE_gPAE    1       0       1         0        0
 :boot_up_acpi_xp_PAE_gPA   1       1       0         0        0
 :boot_up_acpi_win2k3_PAE   1       1       0         0        0
 :boot_base_kernel_PAE_gP   1       1       0         0        0
 :kb_nightly_PAE_gPAE       1       1       0         0        0
 :boot_up_noacpi_win2k_PA   1       1       0         0        0
=====================================================================
Total                       17      15      2         0        0

Report Summary on IA32e
=====================================================================
                            Total   Pass    Fail    NoResult   Crash
=====================================================================
control_panel               13      11      2         0        0
Restart                     3       3       0         0        0
gtest                       17      12      5         0        0
=====================================================================
control_panel               13      11      2         0        0
 :KVM_four_sguest_64_gPAE   1       1       0         0        0
 :KVM_4G_guest_64_g64       1       0       1         0        0
 :KVM_four_sguest_64_g64    1       1       0         0        0
 :KVM_linux_win_64_gPAE     1       1       0         0        0
 :KVM_1500M_guest_64_gPAE   1       1       0         0        0
 :KVM_SR_64_g64             1       1       0         0        0
 :KVM_256M_guest_64_g64     1       1       0         0        0
 :KVM_1500M_guest_64_g64    1       1       0         0        0
 :KVM_4G_guest_64_gPAE      1       0       1         0        0
 :KVM_SR_64_gPAE            1       1       0         0        0
 :KVM_256M_guest_64_gPAE    1       1       0         0        0
 :KVM_two_winxp_64_gPAE     1       1       0         0        0
 :KVM_four_dguest_64_gPAE   1       1       0         0        0
Restart                     3       3       0         0        0
 :BootTo64_64_g64           1       1       0         0        0
 :Guest64_64_gPAE           1       1       0         0        0
 :GuestPAE_64_g64           1       1       0         0        0
gtest                       17      12      5         0        0
 :boot_up_acpi_64_gPAE      1       1       0         0        0
 :boot_up_noacpi_win2k3_6   1       0       1         0        0
 :boot_up_noacpi_xp_64_gP   1       1       0         0        0
 :boot_up_noacpi_xp_64_g6   1       0       1         0        0
 :bootx_64_g64              1       1       0         0        0
 :boot_base_kernel_64_gPA   1       1       0         0        0
 :boot_up_vista_64_g64      1       0       1         0        0
 :boot_base_kernel_64_g64   1       1       0         0        0
 :bootx_64_gPAE             1       1       0         0        0
 :kb_nightly_64_gPAE        1       1       0         0        0
 :ltp_nightly_64_gPAE       1       1       0         0        0
 :boot_up_vista_64_gPAE     1       0       1         0        0
 :ltp_nightly_64_g64        1       1       0         0        0
 :boot_up_acpi_64_g64       1       0       1         0        0
 :boot_up_noacpi_win2k_64   1       1       0         0        0
 :boot_up_noacpi_win2k3_6   1       1       0         0        0
 :kb_nightly_64_g64         1       1       0         0        0
=====================================================================
Total                       33      26      7         0        0

Yunfeng

-------------------------------------------------------------------------
This SF.net email is sponsored by: Splunk Inc.
Still grepping through log files to find problems?  Stop.
Now Search log events and configuration files using AJAX and a browser.
Download your FREE copy of Splunk now >>  http://get.splunk.com/

^ permalink raw reply	[flat|nested] 3+ messages in thread

* Re: ABAT Testing report, kernel 76f0301b5.., user 04cff0e47..
       [not found] ` <10EA09EFD8728347A513008B6B0DA77A01CBF1D2-wq7ZOvIWXbNpB2pF5aRoyrfspsVTdybXVpNB7YpNyf8@public.gmane.org>
@ 2007-07-23 16:12   ` Avi Kivity
       [not found]     ` <46A4D35E.5010708-atKUWr5tajBWk0Htik3J/w@public.gmane.org>
  0 siblings, 1 reply; 3+ messages in thread
From: Avi Kivity @ 2007-07-23 16:12 UTC (permalink / raw)
  To: Zhao, Yunfeng; +Cc: kvm-devel-5NWGOfrQmneRv+LV9MX5uipxlwaOVQ5f

Zhao, Yunfeng wrote:
> Hi, all
>
> This is today's ABAT testing result against kvm.git 76f0301b5e4d2603d8e1ee5295db29faea660b49 and kvm-userspace.git 04cff0e47c4cc1e3d51f917a657b97ac2ed29719
> We are still using UP guests in the testing, we will try to enable some SMP Windows and Linux tests in this week.
>
> One new issue is about performance regression since KVM-29
> 1. Performance regression since KVM-29
> https://sourceforge.net/tracker/index.php?func=detail&aid=1758756&group_id=180599&atid=893831
>
>   

I bisected this to

commit 8a1449563b3e5ede56b28cc977c8da22a17cdf51
Author: Luca Tettamanti <kronos.it-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
Date:   Tue Jun 19 22:41:38 2007 +0200

    KVM: Avoid useless memory write when possible

    When writing to normal memory and the memory area is unchanged the write
    can be safely skipped, avoiding the costly kvm_mmu_pte_write.

    Signed-Off-By: Luca Tettamanti <kronos.it-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
    Signed-off-by: Avi Kivity <avi-atKUWr5tajBWk0Htik3J/w@public.gmane.org>

diff --git a/drivers/kvm/kvm_main.c b/drivers/kvm/kvm_main.c
index 7826f16..5603000 100644
--- a/drivers/kvm/kvm_main.c
+++ b/drivers/kvm/kvm_main.c
@@ -1170,8 +1170,10 @@ static int emulator_write_phys(struct kvm_vcpu 
*vcpu, gpa_t gpa,
                return 0;
        mark_page_dirty(vcpu->kvm, gpa >> PAGE_SHIFT);
        virt = kmap_atomic(page, KM_USER0);
-       kvm_mmu_pte_write(vcpu, gpa, virt + offset, val, bytes);
-       memcpy(virt + offset_in_page(gpa), val, bytes);
+       if (memcmp(virt + offset_in_page(gpa), val, bytes)) {
+               kvm_mmu_pte_write(vcpu, gpa, virt + offset, val, bytes);
+               memcpy(virt + offset_in_page(gpa), val, bytes);
+       }
        kunmap_atomic(virt, KM_USER0);
        return 1;
 }

The effect with this patch applied is that pf_fixed grows very high.  
I'm guessing that this is because not calling kvm_mmu_pte_write() 
defeats the fork detector and causes a high amount of emulated writes to 
page table when fork() resets the writable bit on read-only ptes.

-- 
error compiling committee.c: too many arguments to function


-------------------------------------------------------------------------
This SF.net email is sponsored by: Splunk Inc.
Still grepping through log files to find problems?  Stop.
Now Search log events and configuration files using AJAX and a browser.
Download your FREE copy of Splunk now >>  http://get.splunk.com/

^ permalink raw reply related	[flat|nested] 3+ messages in thread

* Re: ABAT Testing report, kernel 76f0301b5.., user 04cff0e47..
       [not found]     ` <46A4D35E.5010708-atKUWr5tajBWk0Htik3J/w@public.gmane.org>
@ 2007-07-24  5:10       ` Zhao, Yunfeng
  0 siblings, 0 replies; 3+ messages in thread
From: Zhao, Yunfeng @ 2007-07-24  5:10 UTC (permalink / raw)
  To: Avi Kivity; +Cc: kvm-devel-5NWGOfrQmneRv+LV9MX5uipxlwaOVQ5f

[-- Attachment #1: Type: text/plain, Size: 2665 bytes --]

Just verified that the performance issue has already been fixed on KVM-32.
Thanks 
Yunfeng


>-----Original Message-----
>From: Avi Kivity [mailto:avi-atKUWr5tajBWk0Htik3J/w@public.gmane.org]
>Sent: 2007年7月24日 0:12
>To: Zhao, Yunfeng
>Cc: kvm-devel-5NWGOfrQmneRv+LV9MX5uipxlwaOVQ5f@public.gmane.org
>Subject: Re: [kvm-devel] ABAT Testing report, kernel 76f0301b5.., user
>04cff0e47..
>
>Zhao, Yunfeng wrote:
>> Hi, all
>>
>> This is today's ABAT testing result against kvm.git
>76f0301b5e4d2603d8e1ee5295db29faea660b49 and kvm-userspace.git
>04cff0e47c4cc1e3d51f917a657b97ac2ed29719
>> We are still using UP guests in the testing, we will try to enable some SMP
>Windows and Linux tests in this week.
>>
>> One new issue is about performance regression since KVM-29
>> 1. Performance regression since KVM-29
>>
>https://sourceforge.net/tracker/index.php?func=detail&aid=1758756&group_id=
>180599&atid=893831
>>
>>
>
>I bisected this to
>
>commit 8a1449563b3e5ede56b28cc977c8da22a17cdf51
>Author: Luca Tettamanti <kronos.it-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
>Date:   Tue Jun 19 22:41:38 2007 +0200
>
>    KVM: Avoid useless memory write when possible
>
>    When writing to normal memory and the memory area is unchanged the write
>    can be safely skipped, avoiding the costly kvm_mmu_pte_write.
>
>    Signed-Off-By: Luca Tettamanti <kronos.it-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
>    Signed-off-by: Avi Kivity <avi-atKUWr5tajBWk0Htik3J/w@public.gmane.org>
>
>diff --git a/drivers/kvm/kvm_main.c b/drivers/kvm/kvm_main.c
>index 7826f16..5603000 100644
>--- a/drivers/kvm/kvm_main.c
>+++ b/drivers/kvm/kvm_main.c
>@@ -1170,8 +1170,10 @@ static int emulator_write_phys(struct kvm_vcpu
>*vcpu, gpa_t gpa,
>                return 0;
>        mark_page_dirty(vcpu->kvm, gpa >> PAGE_SHIFT);
>        virt = kmap_atomic(page, KM_USER0);
>-       kvm_mmu_pte_write(vcpu, gpa, virt + offset, val, bytes);
>-       memcpy(virt + offset_in_page(gpa), val, bytes);
>+       if (memcmp(virt + offset_in_page(gpa), val, bytes)) {
>+               kvm_mmu_pte_write(vcpu, gpa, virt + offset, val, bytes);
>+               memcpy(virt + offset_in_page(gpa), val, bytes);
>+       }
>        kunmap_atomic(virt, KM_USER0);
>        return 1;
> }
>
>The effect with this patch applied is that pf_fixed grows very high.
>I'm guessing that this is because not calling kvm_mmu_pte_write()
>defeats the fork detector and causes a high amount of emulated writes to
>page table when fork() resets the writable bit on read-only ptes.
>
>--
>error compiling committee.c: too many arguments to function


[-- Attachment #2: Type: text/plain, Size: 315 bytes --]

-------------------------------------------------------------------------
This SF.net email is sponsored by: Splunk Inc.
Still grepping through log files to find problems?  Stop.
Now Search log events and configuration files using AJAX and a browser.
Download your FREE copy of Splunk now >>  http://get.splunk.com/

[-- Attachment #3: Type: text/plain, Size: 186 bytes --]

_______________________________________________
kvm-devel mailing list
kvm-devel-5NWGOfrQmneRv+LV9MX5uipxlwaOVQ5f@public.gmane.org
https://lists.sourceforge.net/lists/listinfo/kvm-devel

^ permalink raw reply	[flat|nested] 3+ messages in thread

end of thread, other threads:[~2007-07-24  5:10 UTC | newest]

Thread overview: 3+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2007-07-23  9:09 ABAT Testing report, kernel 76f0301b5.., user 04cff0e47 Zhao, Yunfeng
     [not found] ` <10EA09EFD8728347A513008B6B0DA77A01CBF1D2-wq7ZOvIWXbNpB2pF5aRoyrfspsVTdybXVpNB7YpNyf8@public.gmane.org>
2007-07-23 16:12   ` Avi Kivity
     [not found]     ` <46A4D35E.5010708-atKUWr5tajBWk0Htik3J/w@public.gmane.org>
2007-07-24  5:10       ` Zhao, Yunfeng

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox