Re: [Qemu-devel] [RFC PATCH v2 07/12] mc: introduce additional QMP statistics for micro-checkpointing

[Juan Quintela]

address@hidden wrote:
> From: "Michael R. Hines" <address@hidden>
>
> MC provides a lot of new information, including the same RAM statistics
> that ordinary migration does, so we centralize a lot of that printing
> code into a common function so that the QMP printing statements don't
> get duplicated too much.
>
> We also introduce a new MCStats structure (like MigrationStats) due
> to the large number of non-migration related statistics - don't want
> to confuse migration and MC too much, so let's keep them separate for now.
>
> Signed-off-by: Michael R. Hines <address@hidden>

We can add the non-mc stats if you split them.  And you get a smaller
series.

Later, Juan.


> ---
>  hmp.c                         | 17 +++++++++
>  include/migration/migration.h |  6 +++
>  migration.c                   | 86 
> ++++++++++++++++++++++++++-----------------
>  qapi-schema.json              | 33 +++++++++++++++++
>  4 files changed, 109 insertions(+), 33 deletions(-)
>
> diff --git a/hmp.c b/hmp.c
> index 1af0809..edf062e 100644
> --- a/hmp.c
> +++ b/hmp.c
> @@ -203,6 +203,23 @@ void hmp_info_migrate(Monitor *mon, const QDict *qdict)
>                         info->disk->total >> 10);
>      }
>  
> +    if (info->has_mc) {
> +        monitor_printf(mon, "checkpoints: %" PRIu64 "\n",
> +                       info->mc->checkpoints);
> +        monitor_printf(mon, "xmit_time: %" PRIu64 " ms\n",
> +                       info->mc->xmit_time);
> +        monitor_printf(mon, "log_dirty_time: %" PRIu64 " ms\n",
> +                       info->mc->log_dirty_time);
> +        monitor_printf(mon, "migration_bitmap_time: %" PRIu64 " ms\n",
> +                       info->mc->migration_bitmap_time);
> +        monitor_printf(mon, "ram_copy_time: %" PRIu64 " ms\n",
> +                       info->mc->ram_copy_time);
> +        monitor_printf(mon, "copy_mbps: %0.2f mbps\n",
> +                       info->mc->copy_mbps);
> +        monitor_printf(mon, "throughput: %0.2f mbps\n",
> +                       info->mc->mbps);
> +    }
> +
>      if (info->has_xbzrle_cache) {
>          monitor_printf(mon, "cache size: %" PRIu64 " bytes\n",
>                         info->xbzrle_cache->cache_size);
> diff --git a/include/migration/migration.h b/include/migration/migration.h
> index e876a2c..f18ff5e 100644
> --- a/include/migration/migration.h
> +++ b/include/migration/migration.h
> @@ -53,14 +53,20 @@ struct MigrationState
>      int state;
>      MigrationParams params;
>      double mbps;
> +    double copy_mbps;
>      int64_t total_time;
>      int64_t downtime;
>      int64_t expected_downtime;
> +    int64_t xmit_time;
> +    int64_t ram_copy_time;
> +    int64_t log_dirty_time;
> +    int64_t bitmap_time;
>      int64_t dirty_pages_rate;
>      int64_t dirty_bytes_rate;
>      bool enabled_capabilities[MIGRATION_CAPABILITY_MAX];
>      int64_t xbzrle_cache_size;
>      int64_t setup_time;
> +    int64_t checkpoints;
>  };
>  
>  void process_incoming_migration(QEMUFile *f);
> diff --git a/migration.c b/migration.c
> index f42dae4..0ccbeaa 100644
> --- a/migration.c
> +++ b/migration.c
> @@ -59,7 +59,6 @@ MigrationState *migrate_get_current(void)
>          .state = MIG_STATE_NONE,
>          .bandwidth_limit = MAX_THROTTLE,
>          .xbzrle_cache_size = DEFAULT_MIGRATE_CACHE_SIZE,
> -        .mbps = -1,
>      };
>  
>      return &current_migration;
> @@ -173,6 +172,31 @@ static void get_xbzrle_cache_stats(MigrationInfo *info)
>      }
>  }
>  
> +static void get_ram_stats(MigrationState *s, MigrationInfo *info)
> +{
> +    info->has_total_time = true;
> +    info->total_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME)
> +        - s->total_time;
> +
> +    info->has_ram = true;
> +    info->ram = g_malloc0(sizeof(*info->ram));
> +    info->ram->transferred = ram_bytes_transferred();
> +    info->ram->total = ram_bytes_total();
> +    info->ram->duplicate = dup_mig_pages_transferred();
> +    info->ram->skipped = skipped_mig_pages_transferred();
> +    info->ram->normal = norm_mig_pages_transferred();
> +    info->ram->normal_bytes = norm_mig_bytes_transferred();
> +    info->ram->mbps = s->mbps;
> +
> +    if (blk_mig_active()) {
> +        info->has_disk = true;
> +        info->disk = g_malloc0(sizeof(*info->disk));
> +        info->disk->transferred = blk_mig_bytes_transferred();
> +        info->disk->remaining = blk_mig_bytes_remaining();
> +        info->disk->total = blk_mig_bytes_total();
> +    }
> +}
> +
>  MigrationInfo *qmp_query_migrate(Error **errp)
>  {
>      MigrationInfo *info = g_malloc0(sizeof(*info));
> @@ -199,26 +223,8 @@ MigrationInfo *qmp_query_migrate(Error **errp)
>          info->has_setup_time = true;
>          info->setup_time = s->setup_time;
>  
> -        info->has_ram = true;
> -        info->ram = g_malloc0(sizeof(*info->ram));
> -        info->ram->transferred = ram_bytes_transferred();
> -        info->ram->remaining = ram_bytes_remaining();
> -        info->ram->total = ram_bytes_total();
> -        info->ram->duplicate = dup_mig_pages_transferred();
> -        info->ram->skipped = skipped_mig_pages_transferred();
> -        info->ram->normal = norm_mig_pages_transferred();
> -        info->ram->normal_bytes = norm_mig_bytes_transferred();
> +        get_ram_stats(s, info);
>          info->ram->dirty_pages_rate = s->dirty_pages_rate;
> -        info->ram->mbps = s->mbps;
> -
> -        if (blk_mig_active()) {
> -            info->has_disk = true;
> -            info->disk = g_malloc0(sizeof(*info->disk));
> -            info->disk->transferred = blk_mig_bytes_transferred();
> -            info->disk->remaining = blk_mig_bytes_remaining();
> -            info->disk->total = blk_mig_bytes_total();
> -        }
> -
>          get_xbzrle_cache_stats(info);
>          break;
>      case MIG_STATE_COMPLETED:
> @@ -227,22 +233,37 @@ MigrationInfo *qmp_query_migrate(Error **errp)
>          info->has_status = true;
>          info->status = g_strdup("completed");
>          info->has_total_time = true;
> -        info->total_time = s->total_time;
> +        info->total_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME)
> +            - s->total_time;
>          info->has_downtime = true;
>          info->downtime = s->downtime;
>          info->has_setup_time = true;
>          info->setup_time = s->setup_time;
>  
> -        info->has_ram = true;
> -        info->ram = g_malloc0(sizeof(*info->ram));
> -        info->ram->transferred = ram_bytes_transferred();
> -        info->ram->remaining = 0;
> -        info->ram->total = ram_bytes_total();
> -        info->ram->duplicate = dup_mig_pages_transferred();
> -        info->ram->skipped = skipped_mig_pages_transferred();
> -        info->ram->normal = norm_mig_pages_transferred();
> -        info->ram->normal_bytes = norm_mig_bytes_transferred();
> -        info->ram->mbps = s->mbps;
> +        get_ram_stats(s, info);
> +        break;
> +    case MIG_STATE_CHECKPOINTING:
> +        info->has_status = true;
> +        info->status = g_strdup("checkpointing");
> +        info->has_setup_time = true;
> +        info->setup_time = s->setup_time;
> +        info->has_downtime = true;
> +        info->downtime = s->downtime;
> +
> +        get_ram_stats(s, info);
> +        info->ram->dirty_pages_rate = s->dirty_pages_rate;
> +        get_xbzrle_cache_stats(info);
> +
> +
> +        info->has_mc = true;
> +        info->mc = g_malloc0(sizeof(*info->mc));
> +        info->mc->xmit_time = s->xmit_time;
> +        info->mc->log_dirty_time = s->log_dirty_time; 
> +        info->mc->migration_bitmap_time = s->bitmap_time;
> +        info->mc->ram_copy_time = s->ram_copy_time;
> +        info->mc->copy_mbps = s->copy_mbps;
> +        info->mc->mbps = s->mbps;
> +        info->mc->checkpoints = s->checkpoints;
>          break;
>      case MIG_STATE_ERROR:
>          info->has_status = true;
> @@ -646,8 +667,7 @@ static void *migration_thread(void *opaque)
>              double bandwidth = transferred_bytes / time_spent;
>              max_size = bandwidth * migrate_max_downtime() / 1000000;
>  
> -            s->mbps = time_spent ? (((double) transferred_bytes * 8.0) /
> -                    ((double) time_spent / 1000.0)) / 1000.0 / 1000.0 : -1;
> +            s->mbps = MBPS(transferred_bytes, time_spent);
>  
>              DPRINTF("transferred %" PRIu64 " time_spent %" PRIu64
>                      " bandwidth %g max_size %" PRId64 "\n",
> diff --git a/qapi-schema.json b/qapi-schema.json
> index 3c2ee4d..7306adc 100644
> --- a/qapi-schema.json
> +++ b/qapi-schema.json
> @@ -603,6 +603,36 @@
>             'cache-miss': 'int', 'overflow': 'int' } }
>  
>  ##
> +# @MCStats
> +#
> +# Detailed Micro Checkpointing (MC) statistics
> +#
> +# @mbps: throughput of transmitting last MC 
> +#
> +# @xmit-time: milliseconds to transmit last MC 
> +#
> +# @log-dirty-time: milliseconds to GET_LOG_DIRTY for last MC 
> +#
> +# @migration-bitmap-time: milliseconds to prepare dirty bitmap for last MC
> +#
> +# @ram-copy-time: milliseconds to ram_save_live() last MC to staging memory
> +#
> +# @copy-mbps: throughput of ram_save_live() to staging memory for last MC 
> +#
> +# @checkpoints: cummulative total number of MCs generated 
> +#
> +# Since: 2.x
> +##
> +{ 'type': 'MCStats',
> +  'data': {'mbps': 'number',
> +           'xmit-time': 'uint64',
> +           'log-dirty-time': 'uint64',
> +           'migration-bitmap-time': 'uint64', 
> +           'ram-copy-time': 'uint64',
> +           'checkpoints' : 'uint64',
> +           'copy-mbps': 'number' }}
> +
> +##
>  # @MigrationInfo
>  #
>  # Information about current migration process.
> @@ -624,6 +654,8 @@
>  #                migration statistics, only returned if XBZRLE feature is on 
> and
>  #                status is 'active' or 'completed' (since 1.2)
>  #
> +# @mc: #options @MCStats containing details Micro-Checkpointing statistics
> +#
>  # @total-time: #optional total amount of milliseconds since migration 
> started.
>  #        If migration has ended, it returns the total migration
>  #        time. (since 1.2)
> @@ -648,6 +680,7 @@
>    'data': {'*status': 'str', '*ram': 'MigrationStats',
>             '*disk': 'MigrationStats',
>             '*xbzrle-cache': 'XBZRLECacheStats',
> +           '*mc': 'MCStats',
>             '*total-time': 'int',
>             '*expected-downtime': 'int',
>             '*downtime': 'int',