Avi Kivity wrote:
On 01/04/2011 04:18 PM, Rik van Riel wrote:
So should I resend the patch with the ple_gap default
changed to 128, or are you willing to ack the current
patch?
I think 128 is safer given than 41 was too low. We have to take into
account newer cpus and slower
Riel,
Thanks for your patch. I have changed the ple_gap to 128 on xen side,
but forget the patch for KVM:(
A little bit big is no harm, but more perf data is better.
Rik van Riel wrote:
On some CPUs, a ple_gap of 41 is simply insufficient to ever trigger
PLE exits, even with the
;
break;
case KVM_CAP_COALESCED_MMIO:
Chris Wright wrote:
* Zhai, Edwin (edwin.z...@intel.com) wrote:
These 2 patches enable optional parameter(default 0) - PCI segment(or
domain) besides BDF, when assigning PCI device to guest.
Signed-off-by: Zhai Edwin edwin.z...@intel.com
Looks good
Jan Kiszka wrote:
Marcelo Tosatti wrote:
Applied, thanks.
Please send one patch per email, with patch inlined, in the future.
This commit doesn't build without KVM_CAP_PCI_SEGMENT, please fix.
Jan,
What does it mean? Can we update all files except the kvm.h?
Thanks,
These 2 patches enable optional parameter(default 0) - PCI segment(or
domain) besides BDF, when assigning PCI device to guest.
Signed-off-by: Zhai Edwin edwin.z...@intel.com
--
best rgds,
edwin
Index: linux-2.6/virt/kvm/assigned-dev.c
Avi,
Any comments for this new patch?
Thanks,
Zhai, Edwin wrote:
Avi Kivity wrote:
+#define KVM_VMX_DEFAULT_PLE_GAP41
+#define KVM_VMX_DEFAULT_PLE_WINDOW 4096
+static int __read_mostly ple_gap = KVM_VMX_DEFAULT_PLE_GAP;
+module_param(ple_gap, int, S_IRUGO);
+
+static int __read_mostly
Avi,
I modify it according your comments. The only thing I want to keep is
the module param ple_gap/window. Although they are not per-guest, they
can be used to find the right value, and disable PLE for debug purpose.
Thanks,
Avi Kivity wrote:
On 09/28/2009 11:33 AM, Zhai, Edwin wrote
Avi Kivity wrote:
+#define KVM_VMX_DEFAULT_PLE_GAP41
+#define KVM_VMX_DEFAULT_PLE_WINDOW 4096
+static int __read_mostly ple_gap = KVM_VMX_DEFAULT_PLE_GAP;
+module_param(ple_gap, int, S_IRUGO);
+
+static int __read_mostly ple_window = KVM_VMX_DEFAULT_PLE_WINDOW;
+module_param(ple_window,
Avi,
hrtimer is used for sleep in attached patch, which have similar perf
gain with previous one. Maybe we can check in this patch first, and turn
to direct yield in future, as you suggested.
Thanks,
edwin
Avi Kivity wrote:
On 09/23/2009 05:04 PM, Zhai, Edwin wrote:
Avi
Avi,
This is the patch to enable PLE, which depends on the a small change of
Linux scheduler
(see http://lkml.org/lkml/2009/5/20/447).
According to our discussion last time, one missing part is that if PLE
exit, pick up an unscheduled vcpu at random and schedule it. But
further investigation
Mark,
Do you have time to push the Linux scheduler changes for Pause Filtering
now? It's almost done after your work. If needing any help, pls. let me
know.
Thanks,
edwin
Langsdorf, Mark wrote:
Um, I am afraid we have the different result... With your
scheduler patch, we got 1% more
indicate that most spinlocks are held for less than 2^12 cycles.
Performance tests show that with 2X LP over-commitment we can get +2% perf
improvement for kernel build(Even more perf gain with more LPs).
Signed-off-by: Zhai Edwin edwin.z...@intel.com
include/asm/vmx.h |4
kvm/vmx.c
12 matches
Mail list logo