Re: [Qemu-devel] [PATCH V6 09/10] migration: add postcopy total blocktime into query-migrate

["Dr. David Alan Gilbert" <dgilbert@redhat.com>]

* Alexey Perevalov (a.perevalov@samsung.com) wrote:
> Postcopy total blocktime is available on destination side only.
> But query-migrate was possible only for source. This patch
> adds ability to call query-migrate on destination.
> To be able to see postcopy blocktime, need to request postcopy-blocktime
> capability.
> 
> The query-migrate command will show following sample result:
> {"return":
>     "postcopy-vcpu-blocktime": [115, 100],
>     "status": "completed",
>     "postcopy-blocktime": 100
> }}
> 
> postcopy_vcpu_blocktime contains list, where the first item is the first
> vCPU in QEMU.
> 
> This patch has a drawback, it combines states of incoming and
> outgoing migration. Ongoing migration state will overwrite incoming
> state. Looks like better to separate query-migrate for incoming and
> outgoing migration or add parameter to indicate type of migration.
> 
> Signed-off-by: Alexey Perevalov <a.perevalov@samsung.com>
> ---
>  hmp.c                         | 15 +++++++++
>  include/migration/migration.h |  4 +++
>  migration/migration.c         | 40 +++++++++++++++++++++--
>  migration/postcopy-ram.c      | 75 +++++++++++++++++++++++++++++++++++++++++++
>  migration/trace-events        |  1 +
>  qapi-schema.json              |  9 +++++-
>  6 files changed, 140 insertions(+), 4 deletions(-)
> 
> diff --git a/hmp.c b/hmp.c
> index 3dceaf8..25135e7 100644
> --- a/hmp.c
> +++ b/hmp.c
> @@ -260,6 +260,21 @@ void hmp_info_migrate(Monitor *mon, const QDict *qdict)
>                         info->cpu_throttle_percentage);
>      }
>  
> +    if (info->has_postcopy_blocktime) {
> +        monitor_printf(mon, "postcopy blocktime: %" PRId64 "\n",
> +                info->postcopy_blocktime);
> +    }
> +
> +    if (info->has_postcopy_vcpu_blocktime) {
> +        Visitor *v;
> +        char *str;
> +        v = string_output_visitor_new(false, &str);
> +        visit_type_int64List(v, NULL, &info->postcopy_vcpu_blocktime, NULL);
> +        visit_complete(v, &str);
> +        monitor_printf(mon, "postcopy vcpu blocktime: %s\n", str);
> +        g_free(str);
> +        visit_free(v);
> +    }
>      qapi_free_MigrationInfo(info);
>      qapi_free_MigrationCapabilityStatusList(caps);
>  }
> diff --git a/include/migration/migration.h b/include/migration/migration.h
> index 4e05c83..c9d4954 100644
> --- a/include/migration/migration.h
> +++ b/include/migration/migration.h
> @@ -123,6 +123,10 @@ struct MigrationIncomingState {
>  
>  MigrationIncomingState *migration_incoming_get_current(void);
>  void migration_incoming_state_destroy(void);
> +/*
> + * Functions to work with blocktime context
> + */
> +void fill_destination_postcopy_migration_info(MigrationInfo *info);
>  
>  struct MigrationState
>  {
> diff --git a/migration/migration.c b/migration/migration.c
> index e10284e..4da0c20 100644
> --- a/migration/migration.c
> +++ b/migration/migration.c
> @@ -651,14 +651,15 @@ static void populate_ram_info(MigrationInfo *info, MigrationState *s)
>      }
>  }
>  
> -MigrationInfo *qmp_query_migrate(Error **errp)
> +static void fill_source_migration_info(MigrationInfo *info)
>  {
> -    MigrationInfo *info = g_malloc0(sizeof(*info));
>      MigrationState *s = migrate_get_current();
>  
>      switch (s->state) {
>      case MIGRATION_STATUS_NONE:
>          /* no migration has happened ever */
> +        /* do not overwrite destination migration status */
> +        return;
>          break;
>      case MIGRATION_STATUS_SETUP:
>          info->has_status = true;
> @@ -744,10 +745,43 @@ MigrationInfo *qmp_query_migrate(Error **errp)
>          break;
>      }
>      info->status = s->state;
> +}
>  
> -    return info;
> +static void fill_destination_migration_info(MigrationInfo *info)
> +{
> +    MigrationIncomingState *mis = migration_incoming_get_current();
> +
> +    switch (mis->state) {
> +    case MIGRATION_STATUS_NONE:
> +        return;
> +        break;
> +    case MIGRATION_STATUS_SETUP:
> +    case MIGRATION_STATUS_CANCELLING:
> +    case MIGRATION_STATUS_CANCELLED:
> +    case MIGRATION_STATUS_ACTIVE:
> +    case MIGRATION_STATUS_POSTCOPY_ACTIVE:
> +    case MIGRATION_STATUS_FAILED:
> +    case MIGRATION_STATUS_COLO:
> +        info->has_status = true;
> +        break;
> +    case MIGRATION_STATUS_COMPLETED:
> +        info->has_status = true;
> +        fill_destination_postcopy_migration_info(info);
> +        break;
> +    }
> +    info->status = mis->state;
>  }
>  
> +MigrationInfo *qmp_query_migrate(Error **errp)
> +{
> +    MigrationInfo *info = g_malloc0(sizeof(*info));
> +
> +    fill_destination_migration_info(info);
> +    fill_source_migration_info(info);
> +
> +    return info;
> + }
> +
>  void qmp_migrate_set_capabilities(MigrationCapabilityStatusList *params,
>                                    Error **errp)
>  {
> diff --git a/migration/postcopy-ram.c b/migration/postcopy-ram.c
> index e70c44b..3dc3869 100644
> --- a/migration/postcopy-ram.c
> +++ b/migration/postcopy-ram.c
> @@ -139,6 +139,73 @@ static struct PostcopyBlocktimeContext *blocktime_context_new(void)
>      return ctx;
>  }
>  
> +static int64List *get_vcpu_blocktime_list(PostcopyBlocktimeContext *ctx)
> +{
> +    int64List *list = NULL, *entry = NULL;
> +    int i;
> +
> +    for (i = smp_cpus - 1; i >= 0; i--) {
> +            entry = g_new0(int64List, 1);
> +            entry->value = ctx->vcpu_blocktime[i];
> +            entry->next = list;
> +            list = entry;
> +    }
> +
> +    return list;
> +}
> +
> +/*
> + * This function just provide calculated blocktime per cpu and trace it.
> + * Total blocktime is calculated in mark_postcopy_blocktime_end.
> + *
> + *
> + * Assume we have 3 CPU
> + *
> + *      S1        E1           S1               E1
> + * -----***********------------xxx***************------------------------> CPU1
> + *
> + *             S2                E2
> + * ------------****************xxx---------------------------------------> CPU2
> + *
> + *                         S3            E3
> + * ------------------------****xxx********-------------------------------> CPU3
> + *
> + * We have sequence S1,S2,E1,S3,S1,E2,E3,E1
> + * S2,E1 - doesn't match condition due to sequence S1,S2,E1 doesn't include CPU3
> + * S3,S1,E2 - sequence includes all CPUs, in this case overlap will be S1,E2 -
> + *            it's a part of total blocktime.
> + * S1 - here is last_begin
> + * Legend of the picture is following:
> + *              * - means blocktime per vCPU
> + *              x - means overlapped blocktime (total blocktime)
> + */

That's probably too much detail for this function - since this function
now does very little except call the others.

However, other than the comment:


Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>

> +void fill_destination_postcopy_migration_info(MigrationInfo *info)
> +{
> +    MigrationIncomingState *mis = migration_incoming_get_current();
> +    PostcopyBlocktimeContext *bc = mis->blocktime_ctx;
> +
> +    if (!bc) {
> +        return;
> +    }
> +
> +    info->has_postcopy_blocktime = true;
> +    info->postcopy_blocktime = bc->total_blocktime;
> +    info->has_postcopy_vcpu_blocktime = true;
> +    info->postcopy_vcpu_blocktime = get_vcpu_blocktime_list(bc);
> +}
> +
> +static uint64_t get_postcopy_total_blocktime(void)
> +{
> +    MigrationIncomingState *mis = migration_incoming_get_current();
> +    PostcopyBlocktimeContext *bc = mis->blocktime_ctx;
> +
> +    if (!bc) {
> +        return 0;
> +    }
> +
> +    return bc->total_blocktime;
> +}
> +
>  /**
>   * receive_ufd_features: check userfault fd features, to request only supported
>   * features in the future.
> @@ -497,6 +564,9 @@ int postcopy_ram_incoming_cleanup(MigrationIncomingState *mis)
>      }
>  
>      postcopy_state_set(POSTCOPY_INCOMING_END);
> +    /* here should be blocktime receiving back operation */
> +    trace_postcopy_ram_incoming_cleanup_blocktime(
> +            get_postcopy_total_blocktime());
>      migrate_send_rp_shut(mis, qemu_file_get_error(mis->from_src_file) != 0);
>  
>      if (mis->postcopy_tmp_page) {
> @@ -926,6 +996,11 @@ void *postcopy_get_tmp_page(MigrationIncomingState *mis)
>  
>  #else
>  /* No target OS support, stubs just fail */
> +void fill_destination_postcopy_migration_info(MigrationInfo *info)
> +{
> +    error_report("%s: No OS support", __func__);
> +}
> +
>  bool postcopy_ram_supported_by_host(MigrationIncomingState *mis)
>  {
>      error_report("%s: No OS support", __func__);
> diff --git a/migration/trace-events b/migration/trace-events
> index 7bdadbb..55a3b6e 100644
> --- a/migration/trace-events
> +++ b/migration/trace-events
> @@ -195,6 +195,7 @@ postcopy_ram_incoming_cleanup_closeuf(void) ""
>  postcopy_ram_incoming_cleanup_entry(void) ""
>  postcopy_ram_incoming_cleanup_exit(void) ""
>  postcopy_ram_incoming_cleanup_join(void) ""
> +postcopy_ram_incoming_cleanup_blocktime(uint64_t total) "total blocktime %" PRIu64
>  save_xbzrle_page_skipping(void) ""
>  save_xbzrle_page_overflow(void) ""
>  ram_save_iterate_big_wait(uint64_t milliconds, int iterations) "big wait: %" PRIu64 " milliseconds, %d iterations"
> diff --git a/qapi-schema.json b/qapi-schema.json
> index 78617fe..4be0b09 100644
> --- a/qapi-schema.json
> +++ b/qapi-schema.json
> @@ -712,6 +712,11 @@
>  #              @status is 'failed'. Clients should not attempt to parse the
>  #              error strings. (Since 2.7)
>  #
> +# @postcopy-blocktime: total time when all vCPU were blocked during postcopy
> +#           live migration (Since 2.10)
> +#
> +# @postcopy-vcpu-blocktime: list of the postcopy blocktime per vCPU (Since 2.10)
> +#
>  # Since: 0.14.0
>  ##
>  { 'struct': 'MigrationInfo',
> @@ -723,7 +728,9 @@
>             '*downtime': 'int',
>             '*setup-time': 'int',
>             '*cpu-throttle-percentage': 'int',
> -           '*error-desc': 'str'} }
> +           '*error-desc': 'str',
> +           '*postcopy-blocktime' : 'int64',
> +           '*postcopy-vcpu-blocktime': ['int64']} }
>  
>  ##
>  # @query-migrate:
> -- 
> 1.8.3.1
> 
--
Dr. David Alan Gilbert / dgilbert@redhat.com / Manchester, UK