Re: [PATCH v2 11/11] tests/migration-test: Add a test for postcopy hangs during RECOVER

[Fabiano Rosas <farosas@suse.de>]

Peter Xu <peterx@redhat.com> writes:

>  
> +static void wait_for_postcopy_status(QTestStatus *one, const char *status)
> +{

QTestState *who

> +    wait_for_migration_status(from, status,

s/from/who

> +                              (const char * []) { "failed", "active",
> +                                                  "completed", NULL });
> +}
> +
> +static void postcopy_recover_fail(QTestState *from, QTestState *to)
> +{
> +    int ret, pair1[2], pair2[2];
> +    char c;
> +
> +    /* Create two unrelated socketpairs */
> +    ret = qemu_socketpair(PF_LOCAL, SOCK_STREAM, 0, pair1);
> +    g_assert_cmpint(ret, ==, 0);
> +
> +    ret = qemu_socketpair(PF_LOCAL, SOCK_STREAM, 0, pair2);
> +    g_assert_cmpint(ret, ==, 0);
> +
> +    /*
> +     * Give the guests unpaired ends of the sockets, so they'll all blocked
> +     * at reading.  This mimics a wrong channel established.
> +     */
> +    qtest_qmp_fds_assert_success(from, &pair1[0], 1,
> +                                 "{ 'execute': 'getfd',"
> +                                 "  'arguments': { 'fdname': 'fd-mig' }}");
> +    qtest_qmp_fds_assert_success(to, &pair2[0], 1,
> +                                 "{ 'execute': 'getfd',"
> +                                 "  'arguments': { 'fdname': 'fd-mig' }}");
> +
> +    /*
> +     * Write the 1st byte as QEMU_VM_COMMAND (0x8) for the dest socket, to
> +     * emulate the 1st byte of a real recovery, but stops from there to
> +     * keep dest QEMU in RECOVER.  This is needed so that we can kick off
> +     * the recover process on dest QEMU (by triggering the G_IO_IN event).
> +     *
> +     * NOTE: this trick is not needed on src QEMUs, because src doesn't
> +     * rely on an pre-existing G_IO_IN event, so it will always trigger the
> +     * upcoming recovery anyway even if it can read nothing.
> +     */
> +#define QEMU_VM_COMMAND              0x08
> +    c = QEMU_VM_COMMAND;
> +    ret = send(pair2[1], &c, 1, 0);
> +    g_assert_cmpint(ret, ==, 1);
> +
> +    migrate_recover(to, "fd:fd-mig");
> +    migrate_qmp(from, "fd:fd-mig", "{'resume': true}");
> +
> +    /*
> +     * Make sure both QEMU instances will go into RECOVER stage, then test
> +     * kicking them out using migrate-pause.
> +     */
> +    wait_for_postcopy_status(from, "postcopy-recover")

semicolon

> +    wait_for_postcopy_status(to, "postcopy-recover");
> +
> +    /*
> +     * This would be issued by the admin upon noticing the hang, we should
> +     * make sure we're able to kick this out.
> +     */
> +    migrate_pause(from);
> +    wait_for_postcopy_status(from, "postcopy-paused");
> +
> +    /* Do the same test on dest */
> +    migrate_pause(to);
> +    wait_for_postcopy_status(to, "postcopy-paused");
> +
> +    close(pair1[0]);
> +    close(pair1[1]);
> +    close(pair2[0]);
> +    close(pair2[1]);
> +}