diff mbox series

[1/2] Fixed a QEMU hang when guest poweroff in COLO mode

Message ID 1636533456-5374-1-git-send-email-lei.rao@intel.com (mailing list archive)
State New, archived
Headers show
Series [1/2] Fixed a QEMU hang when guest poweroff in COLO mode | expand

Commit Message

Rao, Lei Nov. 10, 2021, 8:37 a.m. UTC
From: "Rao, Lei" <lei.rao@intel.com>

When the PVM guest poweroff, the COLO thread may wait a semaphore
in colo_process_checkpoint().So, we should wake up the COLO thread
before migration shutdown.

Signed-off-by: Lei Rao <lei.rao@intel.com>
---
 include/migration/colo.h |  1 +
 migration/colo.c         | 14 ++++++++++++++
 migration/migration.c    | 10 ++++++++++
 3 files changed, 25 insertions(+)

Comments

Juan Quintela Nov. 10, 2021, 9:55 a.m. UTC | #1
"Rao, Lei" <lei.rao@intel.com> wrote:
> From: "Rao, Lei" <lei.rao@intel.com>
>
> When the PVM guest poweroff, the COLO thread may wait a semaphore
> in colo_process_checkpoint().So, we should wake up the COLO thread
> before migration shutdown.
>
> Signed-off-by: Lei Rao <lei.rao@intel.com>

A couple of notes.

> ---
>  include/migration/colo.h |  1 +
>  migration/colo.c         | 14 ++++++++++++++
>  migration/migration.c    | 10 ++++++++++
>  3 files changed, 25 insertions(+)
>
> diff --git a/include/migration/colo.h b/include/migration/colo.h
> index 768e1f0..525b45a 100644
> --- a/include/migration/colo.h
> +++ b/include/migration/colo.h
> @@ -37,4 +37,5 @@ COLOMode get_colo_mode(void);
>  void colo_do_failover(void);
>  
>  void colo_checkpoint_notify(void *opaque);
> +void colo_shutdown(COLOMode mode);
>  #endif
> diff --git a/migration/colo.c b/migration/colo.c
> index 2415325..385c1d7 100644
> --- a/migration/colo.c
> +++ b/migration/colo.c
> @@ -820,6 +820,20 @@ static void colo_wait_handle_message(MigrationIncomingState *mis,
>      }
>  }
>  
> +void colo_shutdown(COLOMode mode)
> +{
> +    if (mode == COLO_MODE_PRIMARY) {
> +        MigrationState *s = migrate_get_current();
> +
> +        qemu_event_set(&s->colo_checkpoint_event);
> +        qemu_sem_post(&s->colo_exit_sem);
> +    } else {
> +        MigrationIncomingState *mis = migration_incoming_get_current();
> +
> +        qemu_sem_post(&mis->colo_incoming_sem);
> +    }
> +}
> +
>  void *colo_process_incoming_thread(void *opaque)
>  {
>      MigrationIncomingState *mis = opaque;
> diff --git a/migration/migration.c b/migration/migration.c
> index abaf6f9..9df6328 100644
> --- a/migration/migration.c
> +++ b/migration/migration.c
> @@ -225,6 +225,16 @@ void migration_cancel(const Error *error)
>  
>  void migration_shutdown(void)
>  {
> +    COLOMode mode = get_colo_mode();
> +
> +    /*
> +     * When the QEMU main thread exit, the COLO thread
> +     * may wait a semaphore. So, we should wakeup the
> +     * COLO thread before migration shutdown.
> +     */
> +    if (mode != COLO_MODE_NONE) {
> +        colo_shutdown(mode);
> +     }

don't put the code on the main path.

Could you just put all of this inside a colo_shutdown() call?

Thanks, Juan.

>      /*
>       * Cancel the current migration - that will (eventually)
>       * stop the migration using this structure
Rao, Lei Nov. 10, 2021, 12:53 p.m. UTC | #2
OK, will be changed in V2.

Thanks,
Lei

-----Original Message-----
From: Juan Quintela <quintela@redhat.com> 
Sent: Wednesday, November 10, 2021 5:55 PM
To: Rao, Lei <lei.rao@intel.com>
Cc: Zhang, Chen <chen.zhang@intel.com>; zhang.zhanghailiang@huawei.com; dgilbert@redhat.com; qemu-devel@nongnu.org
Subject: Re: [PATCH 1/2] Fixed a QEMU hang when guest poweroff in COLO mode

"Rao, Lei" <lei.rao@intel.com> wrote:
> From: "Rao, Lei" <lei.rao@intel.com>
>
> When the PVM guest poweroff, the COLO thread may wait a semaphore in 
> colo_process_checkpoint().So, we should wake up the COLO thread before 
> migration shutdown.
>
> Signed-off-by: Lei Rao <lei.rao@intel.com>

A couple of notes.

> ---
>  include/migration/colo.h |  1 +
>  migration/colo.c         | 14 ++++++++++++++
>  migration/migration.c    | 10 ++++++++++
>  3 files changed, 25 insertions(+)
>
> diff --git a/include/migration/colo.h b/include/migration/colo.h index 
> 768e1f0..525b45a 100644
> --- a/include/migration/colo.h
> +++ b/include/migration/colo.h
> @@ -37,4 +37,5 @@ COLOMode get_colo_mode(void);  void 
> colo_do_failover(void);
>  
>  void colo_checkpoint_notify(void *opaque);
> +void colo_shutdown(COLOMode mode);
>  #endif
> diff --git a/migration/colo.c b/migration/colo.c index 
> 2415325..385c1d7 100644
> --- a/migration/colo.c
> +++ b/migration/colo.c
> @@ -820,6 +820,20 @@ static void colo_wait_handle_message(MigrationIncomingState *mis,
>      }
>  }
>  
> +void colo_shutdown(COLOMode mode)
> +{
> +    if (mode == COLO_MODE_PRIMARY) {
> +        MigrationState *s = migrate_get_current();
> +
> +        qemu_event_set(&s->colo_checkpoint_event);
> +        qemu_sem_post(&s->colo_exit_sem);
> +    } else {
> +        MigrationIncomingState *mis = 
> + migration_incoming_get_current();
> +
> +        qemu_sem_post(&mis->colo_incoming_sem);
> +    }
> +}
> +
>  void *colo_process_incoming_thread(void *opaque)  {
>      MigrationIncomingState *mis = opaque; diff --git 
> a/migration/migration.c b/migration/migration.c index abaf6f9..9df6328 
> 100644
> --- a/migration/migration.c
> +++ b/migration/migration.c
> @@ -225,6 +225,16 @@ void migration_cancel(const Error *error)
>  
>  void migration_shutdown(void)
>  {
> +    COLOMode mode = get_colo_mode();
> +
> +    /*
> +     * When the QEMU main thread exit, the COLO thread
> +     * may wait a semaphore. So, we should wakeup the
> +     * COLO thread before migration shutdown.
> +     */
> +    if (mode != COLO_MODE_NONE) {
> +        colo_shutdown(mode);
> +     }

don't put the code on the main path.

Could you just put all of this inside a colo_shutdown() call?

Thanks, Juan.

>      /*
>       * Cancel the current migration - that will (eventually)
>       * stop the migration using this structure
diff mbox series

Patch

diff --git a/include/migration/colo.h b/include/migration/colo.h
index 768e1f0..525b45a 100644
--- a/include/migration/colo.h
+++ b/include/migration/colo.h
@@ -37,4 +37,5 @@  COLOMode get_colo_mode(void);
 void colo_do_failover(void);
 
 void colo_checkpoint_notify(void *opaque);
+void colo_shutdown(COLOMode mode);
 #endif
diff --git a/migration/colo.c b/migration/colo.c
index 2415325..385c1d7 100644
--- a/migration/colo.c
+++ b/migration/colo.c
@@ -820,6 +820,20 @@  static void colo_wait_handle_message(MigrationIncomingState *mis,
     }
 }
 
+void colo_shutdown(COLOMode mode)
+{
+    if (mode == COLO_MODE_PRIMARY) {
+        MigrationState *s = migrate_get_current();
+
+        qemu_event_set(&s->colo_checkpoint_event);
+        qemu_sem_post(&s->colo_exit_sem);
+    } else {
+        MigrationIncomingState *mis = migration_incoming_get_current();
+
+        qemu_sem_post(&mis->colo_incoming_sem);
+    }
+}
+
 void *colo_process_incoming_thread(void *opaque)
 {
     MigrationIncomingState *mis = opaque;
diff --git a/migration/migration.c b/migration/migration.c
index abaf6f9..9df6328 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -225,6 +225,16 @@  void migration_cancel(const Error *error)
 
 void migration_shutdown(void)
 {
+    COLOMode mode = get_colo_mode();
+
+    /*
+     * When the QEMU main thread exit, the COLO thread
+     * may wait a semaphore. So, we should wakeup the
+     * COLO thread before migration shutdown.
+     */
+    if (mode != COLO_MODE_NONE) {
+        colo_shutdown(mode);
+     }
     /*
      * Cancel the current migration - that will (eventually)
      * stop the migration using this structure