[COLO-Frame,v18,17/34] COLO failover: Introduce state to record failover process

Commit Message

Zhanghailiang Aug. 3, 2016, 12:25 p.m. UTC

When handling failover, we do different things according to the different stage
of failover process, here we introduce a global atomic variable to record the
status of failover.

We add four failover status to indicate the different stage of failover process.
You should use the helpers to get and set the value.

Signed-off-by: zhanghailiang <[e-mail]>
Reviewed-by: Dr. David Alan Gilbert <[e-mail]>
---
v11:
- fix several typos found by Dave
- Add Reviewed-by tag
---
 include/migration/failover.h | 10 ++++++++++
 migration/colo-failover.c    | 37 +++++++++++++++++++++++++++++++++++++
 migration/colo.c             |  4 ++++
 migration/trace-events       |  1 +
 4 files changed, 52 insertions(+)

Comments

Dr. David Alan Gilbert Aug. 9, 2016, 9:17 a.m. UTC | #1

* zhanghailiang ([e-mail]) wrote:

> +        error_report("Unkown error for failover, old_state=%d", old_state);

 Tiny typo; 'Unknown'.
Don't bother reposting just for that, we can fix it later; or fix it if
you have to repost anyway.

Dave

> +        return;
> +    }
>      /*TODO: Do failover work */
>  }
>  
>  void failover_request_active(Error **errp)
>  {
> +   if (failover_set_state(FAILOVER_STATUS_NONE, FAILOVER_STATUS_REQUEST)
> +         != FAILOVER_STATUS_NONE) {
> +        error_setg(errp, "COLO failover is already actived");
> +        return;
> +    }
>      failover_bh = qemu_bh_new(colo_failover_bh, NULL);
>      qemu_bh_schedule(failover_bh);
>  }
>  
> +void failover_init_state(void)
> +{
> +    failover_state = FAILOVER_STATUS_NONE;
> +}
> +
> +int failover_set_state(int old_state, int new_state)
> +{
> +    int old;
> +
> +    old = atomic_cmpxchg(&failover_state, old_state, new_state);
> +    if (old == old_state) {
> +        trace_colo_failover_set_state(new_state);
> +    }
> +    return old;
> +}
> +
> +int failover_get_state(void)
> +{
> +    return atomic_read(&failover_state);
> +}
> +
>  void qmp_x_colo_lost_heartbeat(Error **errp)
>  {
>      if (get_colo_mode() == COLO_MODE_UNKNOWN) {
> diff --git a/migration/colo.c b/migration/colo.c
> index b445279..9afc527 100644
> --- a/migration/colo.c
> +++ b/migration/colo.c
> @@ -232,6 +232,8 @@ static void colo_process_checkpoint(MigrationState *s)
>      Error *local_err = NULL;
>      int ret;
>  
> +    failover_init_state();
> +
>      s->rp_state.from_dst_file = qemu_file_get_return_path(s->to_dst_file);
>      if (!s->rp_state.from_dst_file) {
>          error_report("Open QEMUFile from_dst_file failed");
> @@ -331,6 +333,8 @@ void *colo_process_incoming_thread(void *opaque)
>      migrate_set_state(&mis->state, MIGRATION_STATUS_ACTIVE,
>                        MIGRATION_STATUS_COLO);
>  
> +    failover_init_state();
> +
>      mis->to_src_file = qemu_file_get_return_path(mis->from_src_file);
>      if (!mis->to_src_file) {
>          error_report("colo incoming thread: Open QEMUFile to_src_file failed");
> diff --git a/migration/trace-events b/migration/trace-events
> index 82dc7a0..d9f44ba 100644
> --- a/migration/trace-events
> +++ b/migration/trace-events
> @@ -214,3 +214,4 @@ migration_tls_incoming_handshake_complete(void) ""
>  colo_vm_state_change(const char *old, const char *new) "Change '%s' => '%s'"
>  colo_send_message(const char *msg) "Send '%s' message"
>  colo_receive_message(const char *msg) "Receive '%s' message"
> +colo_failover_set_state(int new_state) "new state %d"
> -- 
> 1.8.3.1
> 
> 
--
Dr. David Alan Gilbert / [e-mail] / Manchester, UK

Zhanghailiang Aug. 10, 2016, 4:07 a.m. UTC | #2

On 2016/8/9 17:17, Dr. David Alan Gilbert wrote:
> * zhanghailiang ([e-mail]) wrote:
>
>> +        error_report("Unkown error for failover, old_state=%d", old_state);
>
>   Tiny typo; 'Unknown'.
> Don't bother reposting just for that, we can fix it later; or fix it if
> you have to repost anyway.
>

OK, thanks.

> Dave
>
>> +        return;
>> +    }
>>       /*TODO: Do failover work */
>>   }
>>
>>   void failover_request_active(Error **errp)
>>   {
>> +   if (failover_set_state(FAILOVER_STATUS_NONE, FAILOVER_STATUS_REQUEST)
>> +         != FAILOVER_STATUS_NONE) {
>> +        error_setg(errp, "COLO failover is already actived");
>> +        return;
>> +    }
>>       failover_bh = qemu_bh_new(colo_failover_bh, NULL);
>>       qemu_bh_schedule(failover_bh);
>>   }
>>
>> +void failover_init_state(void)
>> +{
>> +    failover_state = FAILOVER_STATUS_NONE;
>> +}
>> +
>> +int failover_set_state(int old_state, int new_state)
>> +{
>> +    int old;
>> +
>> +    old = atomic_cmpxchg(&failover_state, old_state, new_state);
>> +    if (old == old_state) {
>> +        trace_colo_failover_set_state(new_state);
>> +    }
>> +    return old;
>> +}
>> +
>> +int failover_get_state(void)
>> +{
>> +    return atomic_read(&failover_state);
>> +}
>> +
>>   void qmp_x_colo_lost_heartbeat(Error **errp)
>>   {
>>       if (get_colo_mode() == COLO_MODE_UNKNOWN) {
>> diff --git a/migration/colo.c b/migration/colo.c
>> index b445279..9afc527 100644
>> --- a/migration/colo.c
>> +++ b/migration/colo.c
>> @@ -232,6 +232,8 @@ static void colo_process_checkpoint(MigrationState *s)
>>       Error *local_err = NULL;
>>       int ret;
>>
>> +    failover_init_state();
>> +
>>       s->rp_state.from_dst_file = qemu_file_get_return_path(s->to_dst_file);
>>       if (!s->rp_state.from_dst_file) {
>>           error_report("Open QEMUFile from_dst_file failed");
>> @@ -331,6 +333,8 @@ void *colo_process_incoming_thread(void *opaque)
>>       migrate_set_state(&mis->state, MIGRATION_STATUS_ACTIVE,
>>                         MIGRATION_STATUS_COLO);
>>
>> +    failover_init_state();
>> +
>>       mis->to_src_file = qemu_file_get_return_path(mis->from_src_file);
>>       if (!mis->to_src_file) {
>>           error_report("colo incoming thread: Open QEMUFile to_src_file failed");
>> diff --git a/migration/trace-events b/migration/trace-events
>> index 82dc7a0..d9f44ba 100644
>> --- a/migration/trace-events
>> +++ b/migration/trace-events
>> @@ -214,3 +214,4 @@ migration_tls_incoming_handshake_complete(void) ""
>>   colo_vm_state_change(const char *old, const char *new) "Change '%s' => '%s'"
>>   colo_send_message(const char *msg) "Send '%s' message"
>>   colo_receive_message(const char *msg) "Receive '%s' message"
>> +colo_failover_set_state(int new_state) "new state %d"
>> --
>> 1.8.3.1
>>
>>
> --
> Dr. David Alan Gilbert / [e-mail] / Manchester, UK
>
> .
>

Patch

diff --git a/include/migration/failover.h b/include/migration/failover.h
index 3274735..fe71bb4 100644
--- a/include/migration/failover.h
+++ b/include/migration/failover.h
@@ -15,6 +15,16 @@ 
 
 #include "qemu-common.h"
 
+typedef enum COLOFailoverStatus {
+    FAILOVER_STATUS_NONE = 0,
+    FAILOVER_STATUS_REQUEST = 1, /* Request but not handled */
+    FAILOVER_STATUS_HANDLING = 2, /* In the process of handling failover */
+    FAILOVER_STATUS_COMPLETED = 3, /* Finish the failover process */
+} COLOFailoverStatus;
+
+void failover_init_state(void);
+int failover_set_state(int old_state, int new_state);
+int failover_get_state(void);
 void failover_request_active(Error **errp);
 
 #endif
diff --git a/migration/colo-failover.c b/migration/colo-failover.c
index 413675d..69aac55 100644
--- a/migration/colo-failover.c
+++ b/migration/colo-failover.c
@@ -15,22 +15,59 @@ 
 #include "migration/failover.h"
 #include "qmp-commands.h"
 #include "qapi/qmp/qerror.h"
+#include "qemu/error-report.h"
+#include "trace.h"
 
 static QEMUBH *failover_bh;
+static COLOFailoverStatus failover_state;
 
 static void colo_failover_bh(void *opaque)
 {
+    int old_state;
+
     qemu_bh_delete(failover_bh);
     failover_bh = NULL;
+    old_state = failover_set_state(FAILOVER_STATUS_REQUEST,
+                                   FAILOVER_STATUS_HANDLING);
+    if (old_state != FAILOVER_STATUS_REQUEST) {
+        error_report("Unkown error for failover, old_state=%d", old_state);
+        return;
+    }
     /*TODO: Do failover work */
 }
 
 void failover_request_active(Error **errp)
 {
+   if (failover_set_state(FAILOVER_STATUS_NONE, FAILOVER_STATUS_REQUEST)
+         != FAILOVER_STATUS_NONE) {
+        error_setg(errp, "COLO failover is already actived");
+        return;
+    }
     failover_bh = qemu_bh_new(colo_failover_bh, NULL);
     qemu_bh_schedule(failover_bh);
 }
 
+void failover_init_state(void)
+{
+    failover_state = FAILOVER_STATUS_NONE;
+}
+
+int failover_set_state(int old_state, int new_state)
+{
+    int old;
+
+    old = atomic_cmpxchg(&failover_state, old_state, new_state);
+    if (old == old_state) {
+        trace_colo_failover_set_state(new_state);
+    }
+    return old;
+}
+
+int failover_get_state(void)
+{
+    return atomic_read(&failover_state);
+}
+
 void qmp_x_colo_lost_heartbeat(Error **errp)
 {
     if (get_colo_mode() == COLO_MODE_UNKNOWN) {
diff --git a/migration/colo.c b/migration/colo.c
index b445279..9afc527 100644
--- a/migration/colo.c
+++ b/migration/colo.c
@@ -232,6 +232,8 @@  static void colo_process_checkpoint(MigrationState *s)
     Error *local_err = NULL;
     int ret;
 
+    failover_init_state();
+
     s->rp_state.from_dst_file = qemu_file_get_return_path(s->to_dst_file);
     if (!s->rp_state.from_dst_file) {
         error_report("Open QEMUFile from_dst_file failed");
@@ -331,6 +333,8 @@  void *colo_process_incoming_thread(void *opaque)
     migrate_set_state(&mis->state, MIGRATION_STATUS_ACTIVE,
                       MIGRATION_STATUS_COLO);
 
+    failover_init_state();
+
     mis->to_src_file = qemu_file_get_return_path(mis->from_src_file);
     if (!mis->to_src_file) {
         error_report("colo incoming thread: Open QEMUFile to_src_file failed");
diff --git a/migration/trace-events b/migration/trace-events
index 82dc7a0..d9f44ba 100644
--- a/migration/trace-events
+++ b/migration/trace-events
@@ -214,3 +214,4 @@  migration_tls_incoming_handshake_complete(void) ""
 colo_vm_state_change(const char *old, const char *new) "Change '%s' => '%s'"
 colo_send_message(const char *msg) "Send '%s' message"
 colo_receive_message(const char *msg) "Receive '%s' message"
+colo_failover_set_state(int new_state) "new state %d"