migration: always initialise ram_counters for a new migration

This patch fix a multifd migration bug in migration speed calculation, this
problem can be reproduced as follows:
1. start a vm and give a heavy memory write stress to prevent the vm be
   successfully migrated to destination
2. begin a migration with multifd
3. migrate for a long time [actually, this can be measured by transferred bytes]
4. migrate cancel
5. begin a new migration with multifd, the migration will directly run into
   migration_completion phase

Reason as follows:

Migration update bandwidth and s->threshold_size in function
migration_update_counters after BUFFER_DELAY time:

    current_bytes = migration_total_bytes(s);
    transferred = current_bytes - s->iteration_initial_bytes;
    time_spent = current_time - s->iteration_start_time;
    bandwidth = (double)transferred / time_spent;
    s->threshold_size = bandwidth * s->parameters.downtime_limit;

In multifd migration, migration_total_bytes function return
qemu_ftell(s->to_dst_file) + ram_counters.multifd_bytes.
s->iteration_initial_bytes will be initialized to 0 at every new migration,
but ram_counters is a global variable, and history migration data will be
accumulated. So if the ram_counters.multifd_bytes is big enough, it may lead
pending_size >= s->threshold_size become false in migration_iteration_run
after the first migration_update_counters.

Signed-off-by: Ivan Ren <ivanren@tencent.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Reviewed-by: Wei Yang <richardw.yang@linux.intel.com>
Suggested-by: Wei Yang <richardw.yang@linux.intel.com>
Message-Id: <1564741121-1840-1-git-send-email-ivanren@tencent.com>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
This commit is contained in:
Ivan Ren 2019-08-02 18:18:41 +08:00 committed by Dr. David Alan Gilbert
parent 14adf288d3
commit 87f3bd8717
2 changed files with 20 additions and 6 deletions

View File

@ -1911,6 +1911,11 @@ static bool migrate_prepare(MigrationState *s, bool blk, bool blk_inc,
}
migrate_init(s);
/*
* set ram_counters memory to zero for a
* new migration
*/
memset(&ram_counters, 0, sizeof(ram_counters));
return true;
}
@ -3034,6 +3039,17 @@ static void migration_calculate_complete(MigrationState *s)
}
}
static void update_iteration_initial_status(MigrationState *s)
{
/*
* Update these three fields at the same time to avoid mismatch info lead
* wrong speed calculation.
*/
s->iteration_start_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
s->iteration_initial_bytes = migration_total_bytes(s);
s->iteration_initial_pages = ram_get_total_transferred_pages();
}
static void migration_update_counters(MigrationState *s,
int64_t current_time)
{
@ -3069,9 +3085,7 @@ static void migration_update_counters(MigrationState *s,
qemu_file_reset_rate_limit(s->to_dst_file);
s->iteration_start_time = current_time;
s->iteration_initial_bytes = current_bytes;
s->iteration_initial_pages = ram_get_total_transferred_pages();
update_iteration_initial_status(s);
trace_migrate_transferred(transferred, time_spent,
bandwidth, s->threshold_size);
@ -3194,7 +3208,7 @@ static void *migration_thread(void *opaque)
rcu_register_thread();
object_ref(OBJECT(s));
s->iteration_start_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
update_iteration_initial_status(s);
qemu_savevm_state_header(s->to_dst_file);
@ -3259,8 +3273,7 @@ static void *migration_thread(void *opaque)
* the local variables. This is important to avoid
* breaking transferred_bytes and bandwidth calculation
*/
s->iteration_start_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
s->iteration_initial_bytes = 0;
update_iteration_initial_status(s);
}
current_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);

View File

@ -1456,6 +1456,7 @@ static int qemu_savevm_state(QEMUFile *f, Error **errp)
}
migrate_init(ms);
memset(&ram_counters, 0, sizeof(ram_counters));
ms->to_dst_file = f;
qemu_mutex_unlock_iothread();