Re: [PATCH v2 3/3] migration-test: Make sure that multifd and cancel works

[Dr. David Alan Gilbert]

* Juan Quintela (address@hidden) wrote:
> "Dr. David Alan Gilbert" <address@hidden> wrote:
> > * Juan Quintela (address@hidden) wrote:
> >> Test that this sequerce works:
> >> 
> >> - launch source
> >> - launch target
> >> - start migration
> >> - cancel migration
> >> - relaunch target
> >> - do migration again
> >> 
> >> Signed-off-by: Juan Quintela <address@hidden>
> >> Reviewed-by: Dr. David Alan Gilbert <address@hidden>
> >> Signed-off-by: Juan Quintela <address@hidden>
> >> 
> >> ---
> >> 
> >> - Wait for 1st trhead to move to cancelled before launching second
> >>   migration
> >> - Add 'to2' parameter to diferentiate 1st and second target.
> >> ---
> >>  tests/migration-test.c | 110 ++++++++++++++++++++++++++++++++++++++++-
> >>  1 file changed, 109 insertions(+), 1 deletion(-)
> >> 
> >> diff --git a/tests/migration-test.c b/tests/migration-test.c
> >> index 1a8d06718e..7a833d65ce 100644
> >> --- a/tests/migration-test.c
> >> +++ b/tests/migration-test.c
> >> @@ -387,6 +387,14 @@ static void migrate_recover(QTestState *who, const 
> >> char *uri)
> >>      qobject_unref(rsp);
> >>  }
> >>  
> >> +static void migrate_cancel(QTestState *who)
> >> +{
> >> +    QDict *rsp;
> >> +
> >> +    rsp = wait_command(who, "{ 'execute': 'migrate_cancel' }");
> >> +    qobject_unref(rsp);
> >> +}
> >> +
> >>  static void migrate_set_capability(QTestState *who, const char 
> >> *capability,
> >>                                     bool value)
> >>  {
> >> @@ -419,6 +427,8 @@ static void migrate_postcopy_start(QTestState *from, 
> >> QTestState *to)
> >>  typedef struct {
> >>      bool hide_stderr;
> >>      bool use_shmem;
> >> +    /* only launch the target process */
> >> +    bool only_target;
> >>      char *opts_source;
> >>      char *opts_target;
> >>  } MigrateStart;
> >> @@ -534,7 +544,9 @@ static int test_migrate_start(QTestState **from, 
> >> QTestState **to,
> >>                                   arch_source, shmem_opts, 
> >> args->opts_source,
> >>                                   ignore_stderr);
> >>      g_free(arch_source);
> >> -    *from = qtest_init(cmd_source);
> >> +    if (!args->only_target) {
> >> +        *from = qtest_init(cmd_source);
> >> +    }
> >>      g_free(cmd_source);
> >>  
> >>      cmd_target = g_strdup_printf("-accel kvm -accel tcg%s%s "
> >> @@ -1257,6 +1269,101 @@ static void test_multifd_tcp(void)
> >>      free(uri);
> >>  }
> >>  
> >> +/*
> >> + * This test does:
> >> + *  source               target
> >> + *                       migrate_incoming
> >> + *     migrate
> >> + *     migrate_cancel
> >> + *                       launch another target
> >> + *     migrate
> >> + *
> >> + *  And see that it works
> >> + */
> >> +
> >> +static void test_multifd_tcp_cancel(void)
> >> +{
> >> +    MigrateStart *args = migrate_start_new();
> >> +    QTestState *from, *to, *to2;
> >> +    QDict *rsp;
> >> +    char *uri;
> >> +
> >> +    args->hide_stderr = true;
> >> +
> >> +    if (test_migrate_start(&from, &to, "defer", args)) {
> >> +        return;
> >> +    }
> >> +
> >> +    /*
> >> +     * We want to pick a speed slow enough that the test completes
> >> +     * quickly, but that it doesn't complete precopy even on a slow
> >> +     * machine, so also set the downtime.
> >> +     */
> >> +    /* 1 ms should make it not converge*/
> >> +    migrate_set_parameter_int(from, "downtime-limit", 1);
> >> +    /* 1GB/s */
> >> +    migrate_set_parameter_int(from, "max-bandwidth", 1000000000);
> >
> > See previous comment about my update in the postcopy test, but OK.
> 
> Yes and no O:-)
> 
> function                 value
> --------                 -----
> postcopy_prepare            30 000 000
> precopy_unix             1 000 000 000
> xbzrle                   1 000 000 000
> precpy_tcp               1 000 000 000
> fd_proto                 1 000 000 000
> auto-converge            1 000 000 000
> multifd                  1 000 000 000
> multifd_cancel           1 000 000 000
> 
> Can we agree to create three global constants with the following values:
> 
> 
> const long long downtime_initial = 1;
> const long long downtime_final = 300;  /* or ever 600 */
> const long long bandwidth_initial = 30 000 000;
> 
> And substitute everywhere with the rigths constants?

Yeh, so we just have to make sure we only change it in the places
where we want to/dont want it to converge.

> Thanks, Juan.
> 
> >> +    migrate_set_parameter_int(from, "multifd-channels", 16);
> >> +    migrate_set_parameter_int(to, "multifd-channels", 16);
> >> +
> >> +    migrate_set_capability(from, "multifd", "true");
> >> +    migrate_set_capability(to, "multifd", "true");
> >> +
> >> +    /* Start incoming migration from the 1st socket */
> >> +    rsp = wait_command(to, "{ 'execute': 'migrate-incoming',"
> >> +                           "  'arguments': { 'uri': 'tcp:127.0.0.1:0' 
> >> }}");
> >> +    qobject_unref(rsp);
> >> +
> >> +    /* Wait for the first serial output from the source */
> >> +    wait_for_serial("src_serial");
> >> +
> >> +    uri = migrate_get_socket_address(to, "socket-address");
> >> +
> >> +    migrate_qmp(from, uri, "{}");
> >> +
> >> +    wait_for_migration_pass(from);
> >> +
> >> +    migrate_cancel(from);
> >
> > You might want to add something here to validate that the cancel has
> > finished before starting the new one.
> 
> 
> >> +    args = migrate_start_new();
> >> +    args->only_target = true;
> >> +
> >> +    if (test_migrate_start(&from, &to2, "defer", args)) {
> >> +        return;
> >> +    }
> >> +
> >> +    migrate_set_parameter_int(to2, "multifd-channels", 16);
> >> +
> >> +    migrate_set_capability(to2, "multifd", "true");
> >> +
> >> +    /* Start incoming migration from the 1st socket */
> >> +    rsp = wait_command(to2, "{ 'execute': 'migrate-incoming',"
> >> +                            "  'arguments': { 'uri': 'tcp:127.0.0.1:0' 
> >> }}");
> >> +    qobject_unref(rsp);
> >> +
> >> +    /* 300ms it should converge */
> >> +    migrate_set_parameter_int(from, "downtime-limit", 300);
> >> +
> >> +    uri = migrate_get_socket_address(to2, "socket-address");
> >> +
> >> +    wait_for_migration_status(from, "cancelled", NULL);
> 
> That is exactly what this last line does, not?
> The rest of things that we do here are for "to2" instance, that don't
> affect us at all.
> 
> Once told that, I think that it makes sense to just move the set of
> downtime-limit after the migration.

Ah OK, yes, that's fine.

Dave

> Thanks, Juan.
> 
> 
> >> +
> >> +    migrate_qmp(from, uri, "{}");
> >> +
> >> +    wait_for_migration_pass(from);
> >> +
> >> +    if (!got_stop) {
> >> +        qtest_qmp_eventwait(from, "STOP");
> >> +    }
> >> +    qtest_qmp_eventwait(to2, "RESUME");
> >> +
> >> +    wait_for_serial("dest_serial");
> >> +    wait_for_migration_complete(from);
> >> +    test_migrate_end(from, to2, true);
> >> +    free(uri);
> >> +}
> >> +
> >>  int main(int argc, char **argv)
> >>  {
> >>      char template[] = "/tmp/migration-test-XXXXXX";
> >> @@ -1322,6 +1429,7 @@ int main(int argc, char **argv)
> >>  
> >>      qtest_add_func("/migration/auto_converge", 
> >> test_migrate_auto_converge);
> >>      qtest_add_func("/migration/multifd/tcp", test_multifd_tcp);
> >> +    qtest_add_func("/migration/multifd/tcp/cancel", 
> >> test_multifd_tcp_cancel);
> >>  
> >>      ret = g_test_run();
> >>  
> >> -- 
> >> 2.24.1
> >> 
> > --
> > Dr. David Alan Gilbert / address@hidden / Manchester, UK
--
Dr. David Alan Gilbert / address@hidden / Manchester, UK