diff mbox series

[6/6] tests/qtest/migration: Add a cancel test

Message ID 20241202220137.32584-7-farosas@suse.de (mailing list archive)
State New
Headers show
Series migration: Fix issues during qmp_migrate_cancel | expand

Commit Message

Fabiano Rosas Dec. 2, 2024, 10:01 p.m. UTC
The qmp_migrate_cancel() command is poorly tested and code inspection
reveals that there might be concurrency issues with its usage. Add a
test that runs a migration and calls qmp_migrate_cancel() at specific
moments.

In order to make the test more deterministic, instead of calling
qmp_migrate_cancel() at random moments during migration, do it after
the migration status change events are seen.

The expected result is that qmp_migrate_cancel() on the source ends
migration on the source with the "cancelled" state and ends migration
on the destination with the "failed" state.

Signed-off-by: Fabiano Rosas <farosas@suse.de>
---
 tests/qtest/migration-test.c | 243 +++++++++++++++++++++++++++++++++++
 1 file changed, 243 insertions(+)
diff mbox series

Patch

diff --git a/tests/qtest/migration-test.c b/tests/qtest/migration-test.c
index 74d3000198..48942289bf 100644
--- a/tests/qtest/migration-test.c
+++ b/tests/qtest/migration-test.c
@@ -23,6 +23,8 @@ 
 #include "qapi/qmp/qlist.h"
 #include "ppc-util.h"
 
+#include "qapi-types-migration.h"
+
 #include "migration-helpers.h"
 #include "tests/migration/migration-test.h"
 #ifdef CONFIG_GNUTLS
@@ -3774,6 +3776,234 @@  static bool kvm_dirty_ring_supported(void)
 #endif
 }
 
+static void test_cancel_src_after_failed(QTestState *from, QTestState *to,
+                                         const char *uri, const char *phase)
+{
+    /*
+     * No migrate_incoming_qmp() at the start to force source into
+     * failed state during migrate_qmp().
+     */
+
+    wait_for_serial("src_serial");
+    migrate_ensure_converge(from);
+
+    migrate_qmp(from, to, uri, NULL, "{}");
+
+    migration_event_wait(from, phase);
+    migrate_cancel(from);
+
+    /* cancelling will not move the migration out of 'failed' */
+
+    wait_for_migration_status(from, "failed",
+                              (const char * []) { "completed", NULL });
+
+    /*
+     * Not waiting for the destination because it never started
+     * migration.
+     */
+}
+
+static void test_cancel_src_after_cancelled(QTestState *from, QTestState *to,
+                                            const char *uri, const char *phase)
+{
+    migrate_incoming_qmp(to, uri, "{ 'exit-on-error': false }");
+
+    wait_for_serial("src_serial");
+    migrate_ensure_converge(from);
+
+    migrate_qmp(from, to, uri, NULL, "{}");
+
+    /* To move to cancelled/cancelling */
+    migrate_cancel(from);
+    migration_event_wait(from, phase);
+
+    /* The migrate_cancel under test */
+    migrate_cancel(from);
+
+    wait_for_migration_status(from, "cancelled",
+                              (const char * []) { "completed", NULL });
+
+    wait_for_migration_status(to, "failed",
+                              (const char * []) { "completed", NULL });
+}
+
+static void test_cancel_src_after_complete(QTestState *from, QTestState *to,
+                                           const char *uri, const char *phase)
+{
+    migrate_incoming_qmp(to, uri, "{ 'exit-on-error': false }");
+
+    wait_for_serial("src_serial");
+    migrate_ensure_converge(from);
+
+    migrate_qmp(from, to, uri, NULL, "{}");
+
+    migration_event_wait(from, phase);
+    migrate_cancel(from);
+
+    /*
+     * qmp_migrate_cancel() exits early if migration is not running
+     * anymore, the status will not change to cancelled.
+     */
+    wait_for_migration_complete(from);
+    wait_for_migration_complete(to);
+}
+
+static void test_cancel_src_after_none(QTestState *from, QTestState *to,
+                                       const char *uri, const char *phase)
+{
+    /*
+     * Test that cancelling without a migration happening does not
+     * affect subsequent migrations
+     */
+    migrate_cancel(to);
+
+    wait_for_serial("src_serial");
+    migrate_cancel(from);
+
+    migrate_incoming_qmp(to, uri, "{ 'exit-on-error': false }");
+
+    migrate_ensure_converge(from);
+    migrate_qmp(from, to, uri, NULL, "{}");
+
+    wait_for_migration_complete(from);
+    wait_for_migration_complete(to);
+}
+
+static void test_cancel_src_after_postcopy(QTestState *from, QTestState *to,
+                                           const char *uri, const char *phase)
+{
+    bool postcopy_active = g_str_equal(phase, "postcopy-active");
+    bool postcopy_paused = g_str_equal(phase, "postcopy-paused");
+    bool postcopy_recover = g_str_equal(phase, "postcopy-recover-setup") ||
+        g_str_equal(phase, "postcopy-recover");
+
+    migrate_set_capability(from, "postcopy-ram", true);
+    migrate_set_capability(to, "postcopy-ram", true);
+
+    migrate_incoming_qmp(to, uri, "{ 'exit-on-error': false }");
+
+    wait_for_serial("src_serial");
+    migrate_ensure_non_converge(from);
+
+    migrate_qmp(from, to, uri, NULL, "{}");
+
+    migration_event_wait(from, "active");
+
+    /* Turn postcopy speed down, 4K/s is slow enough on any machines */
+    migrate_set_parameter_int(from, "max-postcopy-bandwidth", 4096);
+    qtest_qmp_assert_success(from, "{ 'execute': 'migrate-start-postcopy' }");
+
+    if (!postcopy_active) {
+        migration_event_wait(from, "postcopy-active");
+        migration_event_wait(to, "postcopy-active");
+
+        wait_for_stop(from, &src_state);
+        qtest_qmp_eventwait(to, "RESUME");
+
+        migrate_pause(from);
+    }
+
+    if (postcopy_recover) {
+        migration_event_wait(to, "postcopy-paused");
+        migration_event_wait(from, "postcopy-paused");
+
+        migrate_recover(to, uri);
+        migrate_qmp(from, to, uri, NULL, "{'resume': true}");
+    }
+
+    migration_event_wait(from, phase);
+    migrate_cancel(from);
+    migration_event_wait(from, "cancelling");
+
+    wait_for_migration_status(from, "cancelled",
+                              (const char * []) { "completed", NULL });
+
+    if (postcopy_paused || postcopy_recover) {
+        /*
+         * Cancelling on source is not detectable by the destination,
+         * so it remains paused.
+         */
+        migration_event_wait(to, "postcopy-paused");
+    } else {
+        wait_for_migration_status(to, "failed",
+                                  (const char * []) { "completed", NULL });
+    }
+}
+
+static void test_cancel_src_pre_switchover(QTestState *from, QTestState *to,
+                                           const char *uri, const char *phase)
+{
+    migrate_set_capability(from, "pause-before-switchover", true);
+    migrate_set_capability(to, "pause-before-switchover", true);
+
+    migrate_set_parameter_int(from, "multifd-channels", 2);
+    migrate_set_parameter_int(to, "multifd-channels", 2);
+    migrate_set_capability(from, "multifd", true);
+    migrate_set_capability(to, "multifd", true);
+
+    migrate_incoming_qmp(to, uri, "{ 'exit-on-error': false }");
+
+    wait_for_serial("src_serial");
+    migrate_ensure_converge(from);
+
+    migrate_qmp(from, to, uri, NULL, "{}");
+
+    migration_event_wait(from, phase);
+    migrate_cancel(from);
+    migration_event_wait(from, "cancelling");
+
+    wait_for_migration_status(from, "cancelled",
+                              (const char * []) { "completed", NULL });
+
+    wait_for_migration_status(to, "failed",
+                              (const char * []) { "completed", NULL });
+}
+
+static void test_cancel_src_after_status(void *opaque)
+{
+    const char *test_path = opaque;
+    g_autofree char *phase = g_path_get_basename(test_path);
+    g_autofree char *uri = g_strdup_printf("unix:%s/migsocket", tmpfs);
+    QTestState *from, *to;
+    MigrateStart args = {
+        .hide_stderr = true,
+    };
+
+    if (test_migrate_start(&from, &to, "defer", &args)) {
+        return;
+    }
+
+    if (g_str_has_prefix(phase, "postcopy")) {
+        if (!ufd_version_check()) {
+            g_test_skip("No postcopy support. "
+                        "Cannot test migrate_cancel in postcopy states");
+            goto out;
+        }
+
+        test_cancel_src_after_postcopy(from, to, uri, phase);
+
+    } else if (g_str_equal(phase, "cancelling") ||
+               g_str_equal(phase, "cancelled")) {
+        test_cancel_src_after_cancelled(from, to, uri, phase);
+
+    } else if (g_str_equal(phase, "completed")) {
+        test_cancel_src_after_complete(from, to, uri, phase);
+
+    } else if (g_str_equal(phase, "failed")) {
+        test_cancel_src_after_failed(from, to, uri, phase);
+
+    } else if (g_str_equal(phase, "none")) {
+        test_cancel_src_after_none(from, to, uri, phase);
+
+    } else {
+        /* any state that comes before pre-switchover */
+        test_cancel_src_pre_switchover(from, to, uri, phase);
+    }
+
+out:
+    test_migrate_end(from, to, false);
+}
+
 int main(int argc, char **argv)
 {
     bool has_kvm, has_tcg;
@@ -4034,6 +4264,19 @@  int main(int argc, char **argv)
         }
     }
 
+    for (int i = MIGRATION_STATUS_NONE; i < MIGRATION_STATUS__MAX; i++) {
+        switch (i) {
+        case MIGRATION_STATUS_DEVICE: /* happens too fast */
+        case MIGRATION_STATUS_WAIT_UNPLUG: /* no support in tests */
+        case MIGRATION_STATUS_COLO: /* no support in tests */
+            continue;
+        default:
+            migration_test_add_suffix("/migration/cancel/src/after/",
+                                      MigrationStatus_str(i),
+                                      test_cancel_src_after_status);
+        }
+    }
+
     ret = g_test_run();
 
     g_assert_cmpint(ret, ==, 0);