#define QEMU_VM_FILE_MAGIC 0x5145564d
#define FILE_TEST_FILENAME "migfile"
#define FILE_TEST_OFFSET 0x1000
+#define QEMU_ENV_SRC "QTEST_QEMU_BINARY_SRC"
+#define QEMU_ENV_DST "QTEST_QEMU_BINARY_DST"
#if defined(__linux__)
#include <sys/syscall.h>
/* Postcopy specific fields */
void *postcopy_data;
bool postcopy_preempt;
+ bool postcopy_recovery_test_fail;
} MigrateCommon;
static int test_migrate_start(QTestState **from, QTestState **to,
const char *arch = qtest_get_arch();
const char *memory_size;
const char *machine_alias, *machine_opts = "";
+ g_autofree char *machine = NULL;
if (args->use_shmem) {
if (!g_file_test("/dev/shm", G_FILE_TEST_IS_DIR)) {
kvm_opts = ",dirty-ring-size=4096";
}
+ machine = resolve_machine_version(machine_alias, QEMU_ENV_SRC,
+ QEMU_ENV_DST);
+
+ g_test_message("Using machine type: %s", machine);
+
cmd_source = g_strdup_printf("-accel kvm%s -accel tcg "
"-machine %s,%s "
"-name source,debug-threads=on "
"-serial file:%s/src_serial "
"%s %s %s %s %s",
kvm_opts ? kvm_opts : "",
- machine_alias, machine_opts,
+ machine, machine_opts,
memory_size, tmpfs,
arch_opts ? arch_opts : "",
arch_source ? arch_source : "",
args->opts_source ? args->opts_source : "",
ignore_stderr);
if (!args->only_target) {
- *from = qtest_init(cmd_source);
+ *from = qtest_init_with_env(QEMU_ENV_SRC, cmd_source);
qtest_qmp_set_event_callback(*from,
migrate_watch_for_stop,
&got_src_stop);
"-incoming %s "
"%s %s %s %s %s",
kvm_opts ? kvm_opts : "",
- machine_alias, machine_opts,
+ machine, machine_opts,
memory_size, tmpfs, uri,
arch_opts ? arch_opts : "",
arch_target ? arch_target : "",
shmem_opts ? shmem_opts : "",
args->opts_target ? args->opts_target : "",
ignore_stderr);
- *to = qtest_init(cmd_target);
+ *to = qtest_init_with_env(QEMU_ENV_DST, cmd_target);
qtest_qmp_set_event_callback(*to,
migrate_watch_for_resume,
&got_dst_resume);
migrate_prepare_for_dirty_mem(from);
qtest_qmp_assert_success(to, "{ 'execute': 'migrate-incoming',"
- " 'arguments': { 'uri': 'tcp:127.0.0.1:0' }}");
+ " 'arguments': { "
+ " 'channels': [ { 'channel-type': 'main',"
+ " 'addr': { 'transport': 'socket',"
+ " 'type': 'inet',"
+ " 'host': '127.0.0.1',"
+ " 'port': '0' } } ] } }");
/* Wait for the first serial output from the source */
wait_for_serial("src_serial");
}
#endif
+static void wait_for_postcopy_status(QTestState *one, const char *status)
+{
+ wait_for_migration_status(one, status,
+ (const char * []) { "failed", "active",
+ "completed", NULL });
+}
+
+#ifndef _WIN32
+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");
+ 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]);
+}
+#endif /* _WIN32 */
+
static void test_postcopy_recovery_common(MigrateCommon *args)
{
QTestState *from, *to;
* migrate-recover command can only succeed if destination machine
* is in the paused state
*/
- wait_for_migration_status(to, "postcopy-paused",
- (const char * []) { "failed", "active",
- "completed", NULL });
+ wait_for_postcopy_status(to, "postcopy-paused");
+ wait_for_postcopy_status(from, "postcopy-paused");
+
+#ifndef _WIN32
+ if (args->postcopy_recovery_test_fail) {
+ /*
+ * Test when a wrong socket specified for recover, and then the
+ * ability to kick it out, and continue with a correct socket.
+ */
+ postcopy_recover_fail(from, to);
+ /* continue with a good recovery */
+ }
+#endif /* _WIN32 */
/*
* Create a new socket to emulate a new channel that is different
* Try to rebuild the migration channel using the resume flag and
* the newly created channel
*/
- wait_for_migration_status(from, "postcopy-paused",
- (const char * []) { "failed", "active",
- "completed", NULL });
migrate_qmp(from, uri, "{'resume': true}");
/* Restore the postcopy bandwidth to unlimited */
test_postcopy_recovery_common(&args);
}
+#ifndef _WIN32
+static void test_postcopy_recovery_double_fail(void)
+{
+ MigrateCommon args = {
+ .postcopy_recovery_test_fail = true,
+ };
+
+ test_postcopy_recovery_common(&args);
+}
+#endif /* _WIN32 */
+
#ifdef CONFIG_GNUTLS
static void test_postcopy_recovery_tls_psk(void)
{
test_file_common(&args, false);
}
+static void *test_mode_reboot_start(QTestState *from, QTestState *to)
+{
+ migrate_set_parameter_str(from, "mode", "cpr-reboot");
+ migrate_set_parameter_str(to, "mode", "cpr-reboot");
+
+ migrate_set_capability(from, "x-ignore-shared", true);
+ migrate_set_capability(to, "x-ignore-shared", true);
+
+ return NULL;
+}
+
+static void test_mode_reboot(void)
+{
+ g_autofree char *uri = g_strdup_printf("file:%s/%s", tmpfs,
+ FILE_TEST_FILENAME);
+ MigrateCommon args = {
+ .start.use_shmem = true,
+ .connect_uri = uri,
+ .listen_uri = "defer",
+ .start_hook = test_mode_reboot_start
+ };
+
+ test_file_common(&args, true);
+}
+
static void test_precopy_tcp_plain(void)
{
MigrateCommon args = {
dirtylimit_stop_vm(vm);
}
+static void migrate_dirty_limit_wait_showup(QTestState *from,
+ const int64_t period,
+ const int64_t value)
+{
+ /* Enable dirty limit capability */
+ migrate_set_capability(from, "dirty-limit", true);
+
+ /* Set dirty limit parameters */
+ migrate_set_parameter_int(from, "x-vcpu-dirty-limit-period", period);
+ migrate_set_parameter_int(from, "vcpu-dirty-limit", value);
+
+ /* Make sure migrate can't converge */
+ migrate_ensure_non_converge(from);
+
+ /* To check limit rate after precopy */
+ migrate_set_capability(from, "pause-before-switchover", true);
+
+ /* Wait for the serial output from the source */
+ wait_for_serial("src_serial");
+}
+
+/*
+ * This test does:
+ * source destination
+ * start vm
+ * start incoming vm
+ * migrate
+ * wait dirty limit to begin
+ * cancel migrate
+ * cancellation check
+ * restart incoming vm
+ * migrate
+ * wait dirty limit to begin
+ * wait pre-switchover event
+ * convergence condition check
+ *
+ * And see if dirty limit migration works correctly.
+ * This test case involves many passes, so it runs in slow mode only.
+ */
+static void test_migrate_dirty_limit(void)
+{
+ g_autofree char *uri = g_strdup_printf("unix:%s/migsocket", tmpfs);
+ QTestState *from, *to;
+ int64_t remaining;
+ uint64_t throttle_us_per_full;
+ /*
+ * We want the test to be stable and as fast as possible.
+ * E.g., with 1Gb/s bandwidth migration may pass without dirty limit,
+ * so we need to decrease a bandwidth.
+ */
+ const int64_t dirtylimit_period = 1000, dirtylimit_value = 50;
+ const int64_t max_bandwidth = 400000000; /* ~400Mb/s */
+ const int64_t downtime_limit = 250; /* 250ms */
+ /*
+ * We migrate through unix-socket (> 500Mb/s).
+ * Thus, expected migration speed ~= bandwidth limit (< 500Mb/s).
+ * So, we can predict expected_threshold
+ */
+ const int64_t expected_threshold = max_bandwidth * downtime_limit / 1000;
+ int max_try_count = 10;
+ MigrateCommon args = {
+ .start = {
+ .hide_stderr = true,
+ .use_dirty_ring = true,
+ },
+ .listen_uri = uri,
+ .connect_uri = uri,
+ };
+
+ /* Start src, dst vm */
+ if (test_migrate_start(&from, &to, args.listen_uri, &args.start)) {
+ return;
+ }
+
+ /* Prepare for dirty limit migration and wait src vm show up */
+ migrate_dirty_limit_wait_showup(from, dirtylimit_period, dirtylimit_value);
+
+ /* Start migrate */
+ migrate_qmp(from, uri, "{}");
+
+ /* Wait for dirty limit throttle begin */
+ throttle_us_per_full = 0;
+ while (throttle_us_per_full == 0) {
+ throttle_us_per_full =
+ read_migrate_property_int(from, "dirty-limit-throttle-time-per-round");
+ usleep(100);
+ g_assert_false(got_src_stop);
+ }
+
+ /* Now cancel migrate and wait for dirty limit throttle switch off */
+ migrate_cancel(from);
+ wait_for_migration_status(from, "cancelled", NULL);
+
+ /* Check if dirty limit throttle switched off, set timeout 1ms */
+ do {
+ throttle_us_per_full =
+ read_migrate_property_int(from, "dirty-limit-throttle-time-per-round");
+ usleep(100);
+ g_assert_false(got_src_stop);
+ } while (throttle_us_per_full != 0 && --max_try_count);
+
+ /* Assert dirty limit is not in service */
+ g_assert_cmpint(throttle_us_per_full, ==, 0);
+
+ args = (MigrateCommon) {
+ .start = {
+ .only_target = true,
+ .use_dirty_ring = true,
+ },
+ .listen_uri = uri,
+ .connect_uri = uri,
+ };
+
+ /* Restart dst vm, src vm already show up so we needn't wait anymore */
+ if (test_migrate_start(&from, &to, args.listen_uri, &args.start)) {
+ return;
+ }
+
+ /* Start migrate */
+ migrate_qmp(from, uri, "{}");
+
+ /* Wait for dirty limit throttle begin */
+ throttle_us_per_full = 0;
+ while (throttle_us_per_full == 0) {
+ throttle_us_per_full =
+ read_migrate_property_int(from, "dirty-limit-throttle-time-per-round");
+ usleep(100);
+ g_assert_false(got_src_stop);
+ }
+
+ /*
+ * The dirty limit rate should equals the return value of
+ * query-vcpu-dirty-limit if dirty limit cap set
+ */
+ g_assert_cmpint(dirtylimit_value, ==, get_limit_rate(from));
+
+ /* Now, we have tested if dirty limit works, let it converge */
+ migrate_set_parameter_int(from, "downtime-limit", downtime_limit);
+ migrate_set_parameter_int(from, "max-bandwidth", max_bandwidth);
+
+ /*
+ * Wait for pre-switchover status to check if migration
+ * satisfy the convergence condition
+ */
+ wait_for_migration_status(from, "pre-switchover", NULL);
+
+ remaining = read_ram_property_int(from, "remaining");
+ g_assert_cmpint(remaining, <,
+ (expected_threshold + expected_threshold / 100));
+
+ migrate_continue(from, "pre-switchover");
+
+ qtest_qmp_eventwait(to, "RESUME");
+
+ wait_for_serial("dest_serial");
+ wait_for_migration_complete(from);
+
+ test_migrate_end(from, to, true);
+}
+
static bool kvm_dirty_ring_supported(void)
{
#if defined(__linux__) && defined(HOST_X86_64)
bool has_uffd;
const char *arch;
g_autoptr(GError) err = NULL;
+ const char *qemu_src = getenv(QEMU_ENV_SRC);
+ const char *qemu_dst = getenv(QEMU_ENV_DST);
int ret;
g_test_init(&argc, &argv, NULL);
+ /*
+ * The default QTEST_QEMU_BINARY must always be provided because
+ * that is what helpers use to query the accel type and
+ * architecture.
+ */
+ if (qemu_src && qemu_dst) {
+ g_test_message("Only one of %s, %s is allowed",
+ QEMU_ENV_SRC, QEMU_ENV_DST);
+ exit(1);
+ }
+
has_kvm = qtest_has_accel("kvm");
has_tcg = qtest_has_accel("tcg");
qtest_add_func("/migration/postcopy/recovery/compress/plain",
test_postcopy_recovery_compress);
}
+#ifndef _WIN32
+ qtest_add_func("/migration/postcopy/recovery/double-failures",
+ test_postcopy_recovery_double_fail);
+#endif /* _WIN32 */
+
}
qtest_add_func("/migration/bad_dest", test_baddest);
qtest_add_func("/migration/precopy/file/offset/bad",
test_precopy_file_offset_bad);
+ /*
+ * Our CI system has problems with shared memory.
+ * Don't run this test until we find a workaround.
+ */
+ if (getenv("QEMU_TEST_FLAKY_TESTS")) {
+ qtest_add_func("/migration/mode/reboot", test_mode_reboot);
+ }
+
#ifdef CONFIG_GNUTLS
qtest_add_func("/migration/precopy/unix/tls/psk",
test_precopy_unix_tls_psk);
*/
if (g_test_slow()) {
qtest_add_func("/migration/auto_converge", test_migrate_auto_converge);
+ if (g_str_equal(arch, "x86_64") &&
+ has_kvm && kvm_dirty_ring_supported()) {
+ qtest_add_func("/migration/dirty_limit", test_migrate_dirty_limit);
+ }
}
qtest_add_func("/migration/multifd/tcp/plain/none",
test_multifd_tcp_none);
projects / mirror_qemu.git / blobdiff