Hi all, This is the test report of xen-unstable tree, no issue found and two issues fixed. Version Info: ================================================================xen-changeset: 25929:fee83ac77d8c Dom0: linux.git 3.5.4 ================================================================ New issue(0) ============= Fixed issues(2) =============1. RHEL6.2/6.1 guest runs quite slow http://bugzilla.xen.org/bugzilla/show_bug.cgi?id=1811 2. XenU PV guest with VIF network cannot boot up with Linux3.6 dom0 http://bugzilla.xen.org/bugzilla/show_bug.cgi?id=1832 Old issues(9) =============1. [ACPI] System cann''t resume after do suspend http://bugzilla.xen.org/bugzilla/show_bug.cgi?id=1707 2. [XL]"xl vcpu-set" causes dom0 crash or panic http://bugzilla.xen.org/bugzilla/show_bug.cgi?id=1730 3. [VT-D]fail to detach NIC from guest http://bugzilla.xen.org/bugzilla/show_bug.cgi?id=1736 4. Sometimes Xen panic on ia32pae Sandybridge when restore guest http://bugzilla.xen.org/bugzilla/show_bug.cgi?id=1747 5. after detaching a VF from a guest, shutdown the guest is very slow http://bugzilla.xen.org/bugzilla/show_bug.cgi?id=1812 6. Poor performance when do guest save/restore and migration with linux 3.1 dom0 http://bugzilla.xen.org/bugzilla/show_bug.cgi?id=1784 7. vcpu-set doesn''t take effect on guest http://bugzilla.xen.org/bugzilla/show_bug.cgi?id=1822 8.Fail to probe NIC driver in domu http://bugzilla.xen.org/bugzilla/show_bug.cgi?id=1824 9. Dom0 cannot be shutdown before PCI device detachment from guest http://bugzilla.xen.org/bugzilla/show_bug.cgi?id=1826 Best Regards, Ronghui Wu(Gabriel)
On Mon, Sep 24, 2012 at 06:17:33AM +0000, Wu, GabrielX wrote:> Hi all, > > This is the test report of xen-unstable tree, no issue found and two issues fixed.Wohoo! Great!> > Version Info: > ================================================================> xen-changeset: 25929:fee83ac77d8c > Dom0: linux.git 3.5.4 > ================================================================> > New issue(0) > =============> > Fixed issues(2) > =============> 1. RHEL6.2/6.1 guest runs quite slow > http://bugzilla.xen.org/bugzilla/show_bug.cgi?id=1811 > 2. XenU PV guest with VIF network cannot boot up with Linux3.6 dom0 > http://bugzilla.xen.org/bugzilla/show_bug.cgi?id=1832 > > Old issues(9) > =============> 1. [ACPI] System cann''t resume after do suspend > http://bugzilla.xen.org/bugzilla/show_bug.cgi?id=1707 > 2. [XL]"xl vcpu-set" causes dom0 crash or panic > http://bugzilla.xen.org/bugzilla/show_bug.cgi?id=1730 > 3. [VT-D]fail to detach NIC from guest > http://bugzilla.xen.org/bugzilla/show_bug.cgi?id=1736 > 4. Sometimes Xen panic on ia32pae Sandybridge when restore guest > http://bugzilla.xen.org/bugzilla/show_bug.cgi?id=1747 > 5. after detaching a VF from a guest, shutdown the guest is very slow > http://bugzilla.xen.org/bugzilla/show_bug.cgi?id=1812 > 6. Poor performance when do guest save/restore and migration with linux 3.1 dom0 > http://bugzilla.xen.org/bugzilla/show_bug.cgi?id=1784Added some questions in the bug.> 7. vcpu-set doesn''t take effect on guest > http://bugzilla.xen.org/bugzilla/show_bug.cgi?id=1822 > 8.Fail to probe NIC driver in domu > http://bugzilla.xen.org/bugzilla/show_bug.cgi?id=1824 > 9. Dom0 cannot be shutdown before PCI device detachment from guest > http://bugzilla.xen.org/bugzilla/show_bug.cgi?id=1826The same - added some questions that I believe I asked on the mailing list last time.> > > Best Regards, > Ronghui Wu(Gabriel) > > _______________________________________________ > Xen-devel mailing list > Xen-devel@lists.xen.org > http://lists.xen.org/xen-devel >
> -----Original Message----- > From: Konrad Rzeszutek [mailto:ketuzsezr@gmail.com] On Behalf Of > Konrad Rzeszutek Wilk > Sent: Monday, September 24, 2012 9:16 PM > To: Wu, GabrielX > Cc: xen-devel@lists.xen.org; Ren, Yongjie; Liu, RongrongX; Liu, SongtaoX; > Zhou, Chao > Subject: Re: [Xen-devel] VMX status report. Xen:25929 & Dom0:3.5.4 > > > 6. Poor performance when do guest save/restore and migration with > linux 3.1 dom0 > > http://bugzilla.xen.org/bugzilla/show_bug.cgi?id=1784 > > Added some questions in the bug.Output of "perf stat xl migrate 1 localhost" for localhost migration. 87086.962947 task-clock # 0.964 CPUs utilized 132,882 context-switches # 0.002 M/sec 10,252 CPU-migrations # 0.000 M/sec 18,159 page-faults # 0.000 M/sec <not counted> cycles <not counted> stalled-cycles-frontend <not counted> stalled-cycles-backend <not counted> instructions <not counted> branches <not counted> branch-misses 90.299519242 seconds time elapsed BTW, do you know why the last 6 counter didn''t have data? Only met this issue when running ''perf stat'' command in Dom0. The following is the output of "perf record -e cpu-clock xl migrate 1 localhost" command. [ perf record: Woken up 10 times to write data ] [ perf record: Captured and wrote 3.321 MB perf.data (~145093 samples) ] # Events: 86K cpu-clock # # Overhead Command Shared Object Symbol # ........ ............... ..................... ................................ # 32.08% libxl-save-help [kernel.kallsyms] [k] hypercall_page 27.42% ssh libcrypto.so.1.0.0 [.] 0x7a6ba 14.73% libxl-save-help [kernel.kallsyms] [k] smp_call_function_many 4.51% ssh libcrypto.so.1.0.0 [.] md5_block_asm_data_order 4.19% ssh ssh [.] 0x28af6 1.83% ssh [kernel.kallsyms] [k] hypercall_page 1.44% ssh libcrypto.so.1.0.0 [.] AES_encrypt 1.32% libxl-save-help [kernel.kallsyms] [k] find_next_bit 0.81% libxl-save-help [kernel.kallsyms] [k] xen_send_IPI_one 0.78% libxl-save-help [kernel.kallsyms] [k] pvclock_clocksource_read 0.71% libxl-save-help [kernel.kallsyms] [k] unmap_single_vma 0.66% ssh [kernel.kallsyms] [k] copy_user_generic_string 0.51% libxl-save-help [kernel.kallsyms] [k] xen_vcpu_stolen (didn''t include other more lines.) Also, added update in the bugzilla.> > 7. vcpu-set doesn''t take effect on guest > > http://bugzilla.xen.org/bugzilla/show_bug.cgi?id=1822 > > 8.Fail to probe NIC driver in domu > > http://bugzilla.xen.org/bugzilla/show_bug.cgi?id=1824 > > 9. Dom0 cannot be shutdown before PCI device detachment from guest > > http://bugzilla.xen.org/bugzilla/show_bug.cgi?id=1826 > > The same - added some questions that I believe I asked on the mailing > list last time.my fault. I''ll reply to the email thread you asked me the question.