| Message ID | 1371632965-20077-4-git-send-email-xiaoguangrong@linux.vnet.ibm.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
Il 19/06/2013 11:09, Xiao Guangrong ha scritto: > Document write_flooding_count to Documentation/virtual/kvm/mmu.txt > > Signed-off-by: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com> > --- > Documentation/virtual/kvm/mmu.txt | 8 ++++++++ > arch/x86/include/asm/kvm_host.h | 5 +++++ > 2 files changed, 13 insertions(+) > > diff --git a/Documentation/virtual/kvm/mmu.txt b/Documentation/virtual/kvm/mmu.txt > index ce6df51..5a6b2e2 100644 > --- a/Documentation/virtual/kvm/mmu.txt > +++ b/Documentation/virtual/kvm/mmu.txt > @@ -214,6 +214,14 @@ Shadow pages contain the following information: > It is only used on 32bit host which helps us to detect whether updating the > 64bit spte is complete so that we can avoid reading the truncated value out > of mmu-lock. > + write_flooding_count: > + In order to sync the page table between guest and host, the page sometimes > + needs to be write-protected (see "Synchronized and unsynchronized pages" > + below), any write to the page can cause write emulation. If the emulation > + on the page is too frequent we'd better unmap the page to avoid the > + future emulation. write_flooding_count aims at this optimization which is > + increased when the page needs to be write emulated and cleared when the > + page is actually used. A guest may write to a page table many times, causing a lot of emulations if the page needs to be write-protected (see "Synchronized and unsynchronized pages" below). Leaf pages can be unsynchronized so that they do not trigger frequent emulation, but this is not possible for non-leafs. This field counts the number of emulations since the last time the page table was actually used; if emulation is triggered too frequently on this page, KVM will unmap the page to avoid emulation in the future. > Reverse map > =========== > diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h > index 1dac2c1..5eb5382 100644 > --- a/arch/x86/include/asm/kvm_host.h > +++ b/arch/x86/include/asm/kvm_host.h > @@ -234,6 +234,11 @@ struct kvm_mmu_page { > int clear_spte_count; > #endif > > + /* > + * Increased when the page needs to be write emulated, cleared > + * when the page is actually used as page table to avoid frequent > + * emulation on the page. > + */ /* Number of writes since the last time traversal visited this page. */ wdyt, better or worse? Paolo > int write_flooding_count; > }; > > -- To unsubscribe from this list: send the line "unsubscribe kvm" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
On 06/19/2013 07:58 PM, Paolo Bonzini wrote: > Il 19/06/2013 11:09, Xiao Guangrong ha scritto: >> Document write_flooding_count to Documentation/virtual/kvm/mmu.txt >> >> Signed-off-by: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com> >> --- >> Documentation/virtual/kvm/mmu.txt | 8 ++++++++ >> arch/x86/include/asm/kvm_host.h | 5 +++++ >> 2 files changed, 13 insertions(+) >> >> diff --git a/Documentation/virtual/kvm/mmu.txt b/Documentation/virtual/kvm/mmu.txt >> index ce6df51..5a6b2e2 100644 >> --- a/Documentation/virtual/kvm/mmu.txt >> +++ b/Documentation/virtual/kvm/mmu.txt >> @@ -214,6 +214,14 @@ Shadow pages contain the following information: >> It is only used on 32bit host which helps us to detect whether updating the >> 64bit spte is complete so that we can avoid reading the truncated value out >> of mmu-lock. >> + write_flooding_count: >> + In order to sync the page table between guest and host, the page sometimes >> + needs to be write-protected (see "Synchronized and unsynchronized pages" >> + below), any write to the page can cause write emulation. If the emulation >> + on the page is too frequent we'd better unmap the page to avoid the >> + future emulation. write_flooding_count aims at this optimization which is >> + increased when the page needs to be write emulated and cleared when the >> + page is actually used. > > A guest may write to a page table many times, causing a lot of > emulations if the page needs to be write-protected (see "Synchronized > and unsynchronized pages" below). Leaf pages can be unsynchronized > so that they do not trigger frequent emulation, but this is not > possible for non-leafs. This field counts the number of emulations > since the last time the page table was actually used; if emulation > is triggered too frequently on this page, KVM will unmap the page > to avoid emulation in the future. very nice. > >> Reverse map >> =========== >> diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h >> index 1dac2c1..5eb5382 100644 >> --- a/arch/x86/include/asm/kvm_host.h >> +++ b/arch/x86/include/asm/kvm_host.h >> @@ -234,6 +234,11 @@ struct kvm_mmu_page { >> int clear_spte_count; >> #endif >> >> + /* >> + * Increased when the page needs to be write emulated, cleared >> + * when the page is actually used as page table to avoid frequent >> + * emulation on the page. >> + */ > > /* Number of writes since the last time traversal visited this page. */ > > wdyt, better or worse? I think it is better. :) Thanks for your refining. -- To unsubscribe from this list: send the line "unsubscribe kvm" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
diff --git a/Documentation/virtual/kvm/mmu.txt b/Documentation/virtual/kvm/mmu.txt index ce6df51..5a6b2e2 100644 --- a/Documentation/virtual/kvm/mmu.txt +++ b/Documentation/virtual/kvm/mmu.txt @@ -214,6 +214,14 @@ Shadow pages contain the following information: It is only used on 32bit host which helps us to detect whether updating the 64bit spte is complete so that we can avoid reading the truncated value out of mmu-lock. + write_flooding_count: + In order to sync the page table between guest and host, the page sometimes + needs to be write-protected (see "Synchronized and unsynchronized pages" + below), any write to the page can cause write emulation. If the emulation + on the page is too frequent we'd better unmap the page to avoid the + future emulation. write_flooding_count aims at this optimization which is + increased when the page needs to be write emulated and cleared when the + page is actually used. Reverse map =========== diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 1dac2c1..5eb5382 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -234,6 +234,11 @@ struct kvm_mmu_page { int clear_spte_count; #endif + /* + * Increased when the page needs to be write emulated, cleared + * when the page is actually used as page table to avoid frequent + * emulation on the page. + */ int write_flooding_count; };
Document write_flooding_count to Documentation/virtual/kvm/mmu.txt Signed-off-by: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com> --- Documentation/virtual/kvm/mmu.txt | 8 ++++++++ arch/x86/include/asm/kvm_host.h | 5 +++++ 2 files changed, 13 insertions(+)