qemu-devel
[Top][All Lists]
Advanced

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [Qemu-devel] [PATCH 3/7] migration: Wait for semaphore before comple


From: Peter Xu
Subject: Re: [Qemu-devel] [PATCH 3/7] migration: Wait for semaphore before completing migration
Date: Wed, 18 Oct 2017 11:35:19 +0800
User-agent: Mutt/1.5.24 (2015-08-30)

On Wed, Oct 11, 2017 at 08:13:13PM +0100, Dr. David Alan Gilbert (git) wrote:
> From: "Dr. David Alan Gilbert" <address@hidden>
> 
> Wait for a semaphore before completing the migration,
> if the previously added capability was enabled.
> 
> Signed-off-by: Dr. David Alan Gilbert <address@hidden>
> ---
>  migration/migration.c | 47 +++++++++++++++++++++++++++++++++++++++++++++++
>  migration/migration.h |  3 +++
>  2 files changed, 50 insertions(+)
> 
> diff --git a/migration/migration.c b/migration/migration.c
> index e1a87c3d23..b411a7bb63 100644
> --- a/migration/migration.c
> +++ b/migration/migration.c
> @@ -1967,6 +1967,46 @@ fail:
>  }
>  
>  /**
> + * migration_maybe_pause: Pause if required to by migrate_pause_before_device
> + * called with the iothread locked
> + * Returns: 0 on success
> + */
> +static int migration_maybe_pause(MigrationState *s, int 
> *current_active_state)
> +{
> +    int ret;
> +    if (!migrate_pause_before_device()) {
> +        return 0;
> +    }
> +    ret = bdrv_inactivate_all();

My understanding is that the crash was caused by mirrored block device
IO triggered after the inactivation, then... should we do this after
waiting for the semaphore (possibly at [1] below) to make sure the
block jobs are completed?  Or did I miss anything?

> +    if (ret) {
> +        error_report("%s: bdrv_inactivate_all() failed (%d)",
> +                     __func__, ret);
> +        return ret;
> +    }
> +
> +    s->block_inactive = true;
> +
> +    /* Since leaving this state is not atomic with posting the semaphore
> +     * it's possible that someone could have issued multiple migrate_continue
> +     * and the semaphore is incorrectly positive at this point;
> +     * the docs say it's undefined to reinit a semaphore that's already
> +     * init'd, so use timedwait to eat up any existing posts.
> +     */
> +    while (qemu_sem_timedwait(&s->pause_sem, 1) == 0);
> +
> +    qemu_mutex_unlock_iothread();
> +    migrate_set_state(&s->state, *current_active_state,
> +                      MIGRATION_STATUS_PAUSE_BEFORE_DEVICE);
> +    qemu_sem_wait(&s->pause_sem);

[1]

> +    migrate_set_state(&s->state, MIGRATION_STATUS_PAUSE_BEFORE_DEVICE,
> +                      MIGRATION_STATUS_DEVICE);
> +    *current_active_state = MIGRATION_STATUS_DEVICE;
> +    qemu_mutex_lock_iothread();
> +
> +    return s->state == MIGRATION_STATUS_DEVICE ? 0 : -EINVAL;
> +}
> +
> +/**
>   * migration_completion: Used by migration_thread when there's not much left.
>   *   The caller 'breaks' the loop when this returns.
>   *
> @@ -1992,6 +2032,11 @@ static void migration_completion(MigrationState *s, 
> int current_active_state,
>              bool inactivate = !migrate_colo_enabled();
>              ret = vm_stop_force_state(RUN_STATE_FINISH_MIGRATE);
>              if (ret >= 0) {
> +                ret = migration_maybe_pause(s, &current_active_state);
> +                /* If this worked it will already have inactivated */
> +                inactivate &= !migrate_pause_before_device();
> +            }
> +            if (ret >= 0) {
>                  qemu_file_set_rate_limit(s->to_dst_file, INT64_MAX);
>                  ret = qemu_savevm_state_complete_precopy(s->to_dst_file, 
> false,
>                                                           inactivate);
> @@ -2372,6 +2417,7 @@ static void migration_instance_finalize(Object *obj)
>  
>      g_free(params->tls_hostname);
>      g_free(params->tls_creds);
> +    qemu_sem_destroy(&ms->pause_sem);
>  }
>  
>  static void migration_instance_init(Object *obj)
> @@ -2382,6 +2428,7 @@ static void migration_instance_init(Object *obj)
>      ms->state = MIGRATION_STATUS_NONE;
>      ms->xbzrle_cache_size = DEFAULT_MIGRATE_CACHE_SIZE;
>      ms->mbps = -1;
> +    qemu_sem_init(&ms->pause_sem, 0);
>  
>      params->tls_hostname = g_strdup("");
>      params->tls_creds = g_strdup("");
> diff --git a/migration/migration.h b/migration/migration.h
> index 37feea5453..447e8b3f79 100644
> --- a/migration/migration.h
> +++ b/migration/migration.h
> @@ -121,6 +121,9 @@ struct MigrationState
>      /* Flag set once the migration thread called bdrv_inactivate_all */
>      bool block_inactive;
>  
> +    /* Migration is paused due to pause-before-device */
> +    QemuSemaphore pause_sem;
> +
>      /* The semaphore is used to notify COLO thread that failover is finished 
> */
>      QemuSemaphore colo_exit_sem;
>  
> -- 
> 2.13.6
> 

-- 
Peter Xu



reply via email to

[Prev in Thread] Current Thread [Next in Thread]