Re: [Qemu-devel] latest rc: virtio-blk hangs forever after migration

["Marcin Gibuła" <m.gibula@beyond.pl>]

[-- Attachment #1: Type: text/plain, Size: 1044 bytes --]

>> 2.1-rc2 behaves exactly the same.
>>
>> Interestingly enough, reseting guest system causes I/O to work again. So
>> it's not qemu that hangs on IO, rather it fails to notify guest about
>> completed operations that were issued during migration.
>>
>> And its somehow caused by calling cpu_synchronize_all_states() inside
>> kvmclock_vm_state_change().
>>
>>
>>
>> As for testing with cache=writeback, I'll try to setup some iscsi to test
>> it.
>
> Awesome, thanks! AFAIK you`ll not be able to use write cache with
> iscsi for migration. VM which had a reset before hangs always when
> freshly launched have a chance to be migrated successfully. And yes,
> it looks like lower layer forgetting to notify driver about some
> operations at a glance.

Andrey,

could you try attached patch? It's an incredibly ugly workaround that 
calls cpu_synchronize_all_states() in a way that bypasses lazy execution 
logic.

But it works for me. If that works for you as well, its somehow related 
to lazy execution of cpu_synchronize_all_states.

-- 
mg

[-- Attachment #2: io-hang.patch --]
[-- Type: text/x-patch, Size: 3151 bytes --]

diff -ru qemu-2.1.0-rc2/cpus.c qemu-2.1.0-rc2-fixed/cpus.c
--- qemu-2.1.0-rc2/cpus.c	2014-07-15 23:49:14.000000000 +0200
+++ qemu-2.1.0-rc2-fixed/cpus.c	2014-07-17 15:09:09.306696284 +0200
@@ -505,6 +505,15 @@
     }
 }
 
+void cpu_synchronize_all_states_always(void)
+{
+    CPUState *cpu;
+
+    CPU_FOREACH(cpu) {
+        cpu_synchronize_state_always(cpu);
+    }
+}
+
 void cpu_synchronize_all_post_reset(void)
 {
     CPUState *cpu;
diff -ru qemu-2.1.0-rc2/hw/i386/kvm/clock.c qemu-2.1.0-rc2-fixed/hw/i386/kvm/clock.c
--- qemu-2.1.0-rc2/hw/i386/kvm/clock.c	2014-07-15 23:49:14.000000000 +0200
+++ qemu-2.1.0-rc2-fixed/hw/i386/kvm/clock.c	2014-07-17 15:08:25.627063756 +0200
@@ -126,7 +126,7 @@
             return;
         }
 
-        cpu_synchronize_all_states();
+        cpu_synchronize_all_states_always();
         ret = kvm_vm_ioctl(kvm_state, KVM_GET_CLOCK, &data);
         if (ret < 0) {
             fprintf(stderr, "KVM_GET_CLOCK failed: %s\n", strerror(ret));
diff -ru qemu-2.1.0-rc2/include/sysemu/cpus.h qemu-2.1.0-rc2-fixed/include/sysemu/cpus.h
--- qemu-2.1.0-rc2/include/sysemu/cpus.h	2014-07-15 23:49:14.000000000 +0200
+++ qemu-2.1.0-rc2-fixed/include/sysemu/cpus.h	2014-07-17 15:09:23.256578916 +0200
@@ -7,6 +7,7 @@
 void pause_all_vcpus(void);
 void cpu_stop_current(void);
 
+void cpu_synchronize_all_states_always(void);
 void cpu_synchronize_all_states(void);
 void cpu_synchronize_all_post_reset(void);
 void cpu_synchronize_all_post_init(void);
diff -ru qemu-2.1.0-rc2/include/sysemu/kvm.h qemu-2.1.0-rc2-fixed/include/sysemu/kvm.h
--- qemu-2.1.0-rc2/include/sysemu/kvm.h	2014-07-15 23:49:14.000000000 +0200
+++ qemu-2.1.0-rc2-fixed/include/sysemu/kvm.h	2014-07-17 15:11:54.855303171 +0200
@@ -346,9 +346,11 @@
 #endif /* NEED_CPU_H */
 
 void kvm_cpu_synchronize_state(CPUState *cpu);
+void kvm_cpu_synchronize_state_always(CPUState *cpu);
 void kvm_cpu_synchronize_post_reset(CPUState *cpu);
 void kvm_cpu_synchronize_post_init(CPUState *cpu);
 
+
 /* generic hooks - to be moved/refactored once there are more users */
 
 static inline void cpu_synchronize_state(CPUState *cpu)
@@ -358,6 +360,13 @@
     }
 }
 
+static inline void cpu_synchronize_state_always(CPUState *cpu)
+{
+    if (kvm_enabled()) {
+        kvm_cpu_synchronize_state_always(cpu);
+    }
+}
+
 static inline void cpu_synchronize_post_reset(CPUState *cpu)
 {
     if (kvm_enabled()) {
diff -ru qemu-2.1.0-rc2/kvm-all.c qemu-2.1.0-rc2-fixed/kvm-all.c
--- qemu-2.1.0-rc2/kvm-all.c	2014-07-15 23:49:14.000000000 +0200
+++ qemu-2.1.0-rc2-fixed/kvm-all.c	2014-07-17 15:14:04.884208826 +0200
@@ -1652,6 +1652,13 @@
     s->coalesced_flush_in_progress = false;
 }
 
+static void do_kvm_cpu_synchronize_state_always(void *arg)
+{
+    CPUState *cpu = arg;
+
+    kvm_arch_get_registers(cpu);
+}
+
 static void do_kvm_cpu_synchronize_state(void *arg)
 {
     CPUState *cpu = arg;
@@ -1669,6 +1676,11 @@
     }
 }
 
+void kvm_cpu_synchronize_state_always(CPUState *cpu)
+{
+    run_on_cpu(cpu, do_kvm_cpu_synchronize_state_always, cpu);
+}
+
 void kvm_cpu_synchronize_post_reset(CPUState *cpu)
 {
     kvm_arch_put_registers(cpu, KVM_PUT_RESET_STATE);