expected_downtime value is not accurate with dirty_pages_rate * page_size, using ram_bytes_remaining would yeild it correct. It will initially be a gross over-estimate, but for for non-converging migrations it should approach a reasonable estimate later on.
currently bandwidth and expected_downtime value are calculated in migration_update_counters() during each iteration from migration_thread(), where as remaining ram is calculated in qmp_query_migrate() when we actually call "info migrate". Due to this there is some difference in expected_downtime value being calculated. with this patch bandwidth, expected_downtime and remaining ram are calculated in migration_update_counters(), retrieve the same value during "info migrate". By this approach we get almost close enough value. Reported-by: Michael Roth <mdr...@linux.vnet.ibm.com> Signed-off-by: Balamuruhan S <bal...@linux.vnet.ibm.com> --- migration/migration.c | 11 ++++++++--- migration/migration.h | 1 + 2 files changed, 9 insertions(+), 3 deletions(-) diff --git a/migration/migration.c b/migration/migration.c index 52a5092add..5d721ee481 100644 --- a/migration/migration.c +++ b/migration/migration.c @@ -614,7 +614,7 @@ static void populate_ram_info(MigrationInfo *info, MigrationState *s) } if (s->state != MIGRATION_STATUS_COMPLETED) { - info->ram->remaining = ram_bytes_remaining(); + info->ram->remaining = s->ram_bytes_remaining; info->ram->dirty_pages_rate = ram_counters.dirty_pages_rate; } } @@ -2227,6 +2227,7 @@ static void migration_update_counters(MigrationState *s, transferred = qemu_ftell(s->to_dst_file) - s->iteration_initial_bytes; time_spent = current_time - s->iteration_start_time; bandwidth = (double)transferred / time_spent; + s->ram_bytes_remaining = ram_bytes_remaining(); s->threshold_size = bandwidth * s->parameters.downtime_limit; s->mbps = (((double) transferred * 8.0) / @@ -2237,8 +2238,12 @@ static void migration_update_counters(MigrationState *s, * recalculate. 10000 is a small enough number for our purposes */ if (ram_counters.dirty_pages_rate && transferred > 10000) { - s->expected_downtime = ram_counters.dirty_pages_rate * - qemu_target_page_size() / bandwidth; + /* + * It will initially be a gross over-estimate, but for for + * non-converging migrations it should approach a reasonable estimate + * later on + */ + s->expected_downtime = s->ram_bytes_remaining / bandwidth; } qemu_file_reset_rate_limit(s->to_dst_file); diff --git a/migration/migration.h b/migration/migration.h index 8d2f320c48..8584f8e22e 100644 --- a/migration/migration.h +++ b/migration/migration.h @@ -128,6 +128,7 @@ struct MigrationState int64_t downtime_start; int64_t downtime; int64_t expected_downtime; + int64_t ram_bytes_remaining; bool enabled_capabilities[MIGRATION_CAPABILITY__MAX]; int64_t setup_time; /* -- 2.14.3