diff mbox series

[v4,09/10] tests/qtest: make more migration pre-copy scenarios run non-live

Message ID 20230601161347.1803440-10-berrange@redhat.com (mailing list archive)
State New, archived
Headers show
Series tests/qtest: make migration-test massively faster | expand

Commit Message

Daniel P. Berrangé June 1, 2023, 4:13 p.m. UTC
There are 27 pre-copy live migration scenarios being tested. In all of
these we force non-convergence and run for one iteration, then let it
converge and wait for completion during the second (or following)
iterations. At 3 mbps bandwidth limit the first iteration takes a very
long time (~30 seconds).

While it is important to test the migration passes and convergence
logic, it is overkill to do this for all 27 pre-copy scenarios. The
TLS migration scenarios in particular are merely exercising different
code paths during connection establishment.

To optimize time taken, switch most of the test scenarios to run
non-live (ie guest CPUs paused) with no bandwidth limits. This gives
a massive speed up for most of the test scenarios.

For test coverage the following scenarios are unchanged

 * Precopy with UNIX sockets
 * Precopy with UNIX sockets and dirty ring tracking
 * Precopy with XBZRLE
 * Precopy with UNIX compress
 * Precopy with UNIX compress (nowait)
 * Precopy with multifd

On a test machine this reduces execution time from 13 minutes to
8 minutes.

Tested-by: Thomas Huth <thuth@redhat.com>
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
---
 tests/qtest/migration-test.c | 81 +++++++++++++++++++++++++++++-------
 1 file changed, 66 insertions(+), 15 deletions(-)

Comments

Juan Quintela June 1, 2023, 10:50 p.m. UTC | #1
Daniel P. Berrangé <berrange@redhat.com> wrote:
> There are 27 pre-copy live migration scenarios being tested. In all of
> these we force non-convergence and run for one iteration, then let it
> converge and wait for completion during the second (or following)
> iterations. At 3 mbps bandwidth limit the first iteration takes a very
> long time (~30 seconds).
>
> While it is important to test the migration passes and convergence
> logic, it is overkill to do this for all 27 pre-copy scenarios. The
> TLS migration scenarios in particular are merely exercising different
> code paths during connection establishment.
>
> To optimize time taken, switch most of the test scenarios to run
> non-live (ie guest CPUs paused) with no bandwidth limits. This gives
> a massive speed up for most of the test scenarios.
>
> For test coverage the following scenarios are unchanged
>
>  * Precopy with UNIX sockets
>  * Precopy with UNIX sockets and dirty ring tracking
>  * Precopy with XBZRLE
>  * Precopy with UNIX compress
>  * Precopy with UNIX compress (nowait)
>  * Precopy with multifd
>
> On a test machine this reduces execution time from 13 minutes to
> 8 minutes.
>
> Tested-by: Thomas Huth <thuth@redhat.com>
> Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>

Reviewed-by: Juan Quintela <quintela@redhat.com>
diff mbox series

Patch

diff --git a/tests/qtest/migration-test.c b/tests/qtest/migration-test.c
index 23fb61506c..0b9d045152 100644
--- a/tests/qtest/migration-test.c
+++ b/tests/qtest/migration-test.c
@@ -577,9 +577,12 @@  typedef struct {
         MIG_TEST_FAIL_DEST_QUIT_ERR,
     } result;
 
-    /* Optional: set number of migration passes to wait for */
+    /* Optional: set number of migration passes to wait for, if live==true */
     unsigned int iterations;
 
+    /* Optional: whether the guest CPUs should be running during migration */
+    bool live;
+
     /* Postcopy specific fields */
     void *postcopy_data;
     bool postcopy_preempt;
@@ -1385,8 +1388,6 @@  static void test_precopy_common(MigrateCommon *args)
         return;
     }
 
-    migrate_ensure_non_converge(from);
-
     if (args->start_hook) {
         data_hook = args->start_hook(from, to);
     }
@@ -1396,6 +1397,31 @@  static void test_precopy_common(MigrateCommon *args)
         wait_for_serial("src_serial");
     }
 
+    if (args->live) {
+        /*
+         * Testing live migration, we want to ensure that some
+         * memory is re-dirtied after being transferred, so that
+         * we exercise logic for dirty page handling. We achieve
+         * this with a ridiculosly low bandwidth that guarantees
+         * non-convergance.
+         */
+        migrate_ensure_non_converge(from);
+    } else {
+        /*
+         * Testing non-live migration, we allow it to run at
+         * full speed to ensure short test case duration.
+         * For tests expected to fail, we don't need to
+         * change anything.
+         */
+        if (args->result == MIG_TEST_SUCCEED) {
+            qtest_qmp_assert_success(from, "{ 'execute' : 'stop'}");
+            if (!got_src_stop) {
+                qtest_qmp_eventwait(from, "STOP");
+            }
+            migrate_ensure_converge(from);
+        }
+    }
+
     if (!args->connect_uri) {
         g_autofree char *local_connect_uri =
             migrate_get_socket_address(to, "socket-address");
@@ -1413,25 +1439,41 @@  static void test_precopy_common(MigrateCommon *args)
             qtest_set_expected_status(to, EXIT_FAILURE);
         }
     } else {
-        if (args->iterations) {
-            while (args->iterations--) {
+        if (args->live) {
+            if (args->iterations) {
+                while (args->iterations--) {
+                    wait_for_migration_pass(from);
+                }
+            } else {
                 wait_for_migration_pass(from);
             }
-        } else {
-            wait_for_migration_pass(from);
-        }
 
-        migrate_ensure_converge(from);
+            migrate_ensure_converge(from);
 
-        /* We do this first, as it has a timeout to stop us
-         * hanging forever if migration didn't converge */
-        wait_for_migration_complete(from);
+            /*
+             * We do this first, as it has a timeout to stop us
+             * hanging forever if migration didn't converge
+             */
+            wait_for_migration_complete(from);
 
-        if (!got_src_stop) {
-            qtest_qmp_eventwait(from, "STOP");
+            if (!got_src_stop) {
+                qtest_qmp_eventwait(from, "STOP");
+            }
+        } else {
+            wait_for_migration_complete(from);
+            /*
+             * Must wait for dst to finish reading all incoming
+             * data on the socket before issuing 'cont' otherwise
+             * it'll be ignored
+             */
+            wait_for_migration_complete(to);
+
+            qtest_qmp_assert_success(to, "{ 'execute' : 'cont'}");
         }
 
-        qtest_qmp_eventwait(to, "RESUME");
+        if (!got_dst_resume) {
+            qtest_qmp_eventwait(to, "RESUME");
+        }
 
         wait_for_serial("dest_serial");
     }
@@ -1449,6 +1491,8 @@  static void test_precopy_unix_plain(void)
     MigrateCommon args = {
         .listen_uri = uri,
         .connect_uri = uri,
+
+        .live = true,
     };
 
     test_precopy_common(&args);
@@ -1464,6 +1508,8 @@  static void test_precopy_unix_dirty_ring(void)
         },
         .listen_uri = uri,
         .connect_uri = uri,
+
+        .live = true,
     };
 
     test_precopy_common(&args);
@@ -1575,6 +1621,7 @@  static void test_precopy_unix_xbzrle(void)
         .start_hook = test_migrate_xbzrle_start,
 
         .iterations = 2,
+        .live = true,
     };
 
     test_precopy_common(&args);
@@ -1592,6 +1639,7 @@  static void test_precopy_unix_compress(void)
          * the previous iteration.
          */
         .iterations = 2,
+        .live = true,
     };
 
     test_precopy_common(&args);
@@ -1609,6 +1657,7 @@  static void test_precopy_unix_compress_nowait(void)
          * the previous iteration.
          */
         .iterations = 2,
+        .live = true,
     };
 
     test_precopy_common(&args);
@@ -2017,6 +2066,8 @@  static void test_multifd_tcp_none(void)
     MigrateCommon args = {
         .listen_uri = "defer",
         .start_hook = test_migrate_precopy_tcp_multifd_start,
+
+        .live = true,
     };
     test_precopy_common(&args);
 }