All of lore.kernel.org
 help / color / mirror / Atom feed
diff for duplicates of <20200413102549.GA22532@in.ibm.com>

diff --git a/a/1.txt b/N1/1.txt
index cd004be..2a11a8e 100644
--- a/a/1.txt
+++ b/N1/1.txt
@@ -40,10 +40,10 @@ On Wed, Apr 08, 2020 at 12:29:57PM +1000, David Gibson wrote:
 > > > >        we set bool enable_guest_stop = true;
 > > > > 
 > > > >     2. During KVM guest entry, clear PSSCR[ESL|EC] iff
-> > > >        enable_guest_stop = true.
+> > > >        enable_guest_stop == true.
 > > > > 
 > > > >     3. In kvm_vm_ioctl_check_extension(), for a new capability
-> > > >        KVM_CAP_STOP, return true iff enable_guest_top = true.
+> > > >        KVM_CAP_STOP, return true iff enable_guest_top == true.
 > > > > 
 > > > > QEMU:
 > > > >    Check with the hypervisor if KVM_CAP_STOP is present. If so,
@@ -124,9 +124,9 @@ The wakeup latency of trap-and-emulated stop0lite (referred to as
 compared to H_CEDE. It is in the order of 5-6us while the wakeup
 latency of H_CEDE is ~25-30us.
 
-===================================
+======================================================================
 Wakeup Latency measured using a timer (in ns) [Lower is better]
-===================================
+======================================================================
 Idle state |  Nr samples |  Min    | Max    | Median | Avg   | Stddev|
 ----------------------------------------------------------------------
 snooze     |   60        |  787    | 1059   |  938   | 937.4 | 42.27 |
@@ -137,12 +137,12 @@ stop0lite  |   60        | 2378    | 7659   | 5006   |5093.6 |1578.7 |
 Emulated   |             |         |        |        |       |       |
 ----------------------------------------------------------------------
 Shared CEDE|   60        | 9550    | 36694  | 29219  |28564.1|3545.9 |
-===================================
+======================================================================
 
 
-===================================
+======================================================================
 Wakeup latency measured using an IPI (in ns) [Lower is better]
-===================================
+======================================================================
 Idle state |  Nr    |  Min    | Max    | Median | Avg     | Stddev   |
            |samples |         |        |        |         |          |
 ----------------------------------------------------------------------
@@ -154,7 +154,7 @@ stop0lite  |   60   |     3580|    8154|    5596|  5644.95|   1368.44|
 Emulated   |        |         |        |        |         |          |
 ----------------------------------------------------------------------
 Shared CEDE|   60   |    20147|   36305|   21827| 26762.65|   6875.01|
-===================================
+======================================================================
 
 > 
 >  * We'll only be able to enable this in a new qemu machine type
diff --git a/a/content_digest b/N1/content_digest
index c02b816..f5b5b77 100644
--- a/a/content_digest
+++ b/N1/content_digest
@@ -7,7 +7,7 @@
  "ref\020200408022957.GC44664@umbus.fritz.box\0"
  "From\0Gautham R Shenoy <ego@linux.vnet.ibm.com>\0"
  "Subject\0Re: [RFC/PATCH  2/3] pseries/kvm: Clear PSSCR[ESL|EC] bits before guest entry\0"
- "Date\0Mon, 13 Apr 2020 10:37:49 +0000\0"
+ "Date\0Mon, 13 Apr 2020 15:55:49 +0530\0"
  "To\0David Gibson <david@gibson.dropbear.id.au>\0"
  "Cc\0Gautham R Shenoy <ego@linux.vnet.ibm.com>"
   Michael Neuling <mikey@neuling.org>
@@ -61,10 +61,10 @@
  "> > > >        we set bool enable_guest_stop = true;\n"
  "> > > > \n"
  "> > > >     2. During KVM guest entry, clear PSSCR[ESL|EC] iff\n"
- "> > > >        enable_guest_stop = true.\n"
+ "> > > >        enable_guest_stop == true.\n"
  "> > > > \n"
  "> > > >     3. In kvm_vm_ioctl_check_extension(), for a new capability\n"
- "> > > >        KVM_CAP_STOP, return true iff enable_guest_top = true.\n"
+ "> > > >        KVM_CAP_STOP, return true iff enable_guest_top == true.\n"
  "> > > > \n"
  "> > > > QEMU:\n"
  "> > > >    Check with the hypervisor if KVM_CAP_STOP is present. If so,\n"
@@ -145,9 +145,9 @@
  "compared to H_CEDE. It is in the order of 5-6us while the wakeup\n"
  "latency of H_CEDE is ~25-30us.\n"
  "\n"
- "===================================\n"
+ "======================================================================\n"
  "Wakeup Latency measured using a timer (in ns) [Lower is better]\n"
- "===================================\n"
+ "======================================================================\n"
  "Idle state |  Nr samples |  Min    | Max    | Median | Avg   | Stddev|\n"
  "----------------------------------------------------------------------\n"
  "snooze     |   60        |  787    | 1059   |  938   | 937.4 | 42.27 |\n"
@@ -158,12 +158,12 @@
  "Emulated   |             |         |        |        |       |       |\n"
  "----------------------------------------------------------------------\n"
  "Shared CEDE|   60        | 9550    | 36694  | 29219  |28564.1|3545.9 |\n"
- "===================================\n"
+ "======================================================================\n"
  "\n"
  "\n"
- "===================================\n"
+ "======================================================================\n"
  "Wakeup latency measured using an IPI (in ns) [Lower is better]\n"
- "===================================\n"
+ "======================================================================\n"
  "Idle state |  Nr    |  Min    | Max    | Median | Avg     | Stddev   |\n"
  "           |samples |         |        |        |         |          |\n"
  "----------------------------------------------------------------------\n"
@@ -175,7 +175,7 @@
  "Emulated   |        |         |        |        |         |          |\n"
  "----------------------------------------------------------------------\n"
  "Shared CEDE|   60   |    20147|   36305|   21827| 26762.65|   6875.01|\n"
- "===================================\n"
+ "======================================================================\n"
  "\n"
  "> \n"
  ">  * We'll only be able to enable this in a new qemu machine type\n"
@@ -203,4 +203,4 @@
  "Thanks and Regards\n"
  gautham.
 
-a8a705ccb7aff8dfbdd172350ac42393409a917c5e6b312682b5cef322f806bc
+9244481ba88f767e1b51a8c2148b1f97f2a39efe4bb35f69a280ddc462551c94

This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.