diff mbox series

[v5,2/2] qtest/migration: Use switchover-hold to speedup

Message ID 20230706124331.377939-3-peterx@redhat.com (mailing list archive)
State New, archived
Headers show
Series migration: switchover-hold flag | expand

Commit Message

Peter Xu July 6, 2023, 12:43 p.m. UTC
This solution is heavily based on Daniel's original approach here, but
hopefully a cleaner way to impl:

https://lore.kernel.org/r/20230601161347.1803440-11-berrange@redhat.com

The difference is we use the switchover-hold flag rather than tuning
bw+downtime to guide test convergence, comparing to use the magic offset.

This can achieve similar goal of previous patch "tests/qtest: massively
speed up migration-test" but without magic offset to write or monitoring.

With this flag, we can safely always run migration tests with full
speed (bw=0).

However for postcopy tests, when with above bw=0, it's easy to happen that
right after switching to postcopy there're merely no page left, so the
postcopy paths are not well tested.

To remedy that, don't wait for a full iteration but switch to postcopy in
the 1st iteration, adding a precopy bw limit (200MB/s for now, running
100ms) so it should guarantee enough pages left for postcopy.

One pity is that normally postcopy switchover happens after 1-2 rounds of
precopy, so qtest doesn't follow that anymore (while it was trying to).
However it also means previous postcopy tests never tested the case where
there're holes in pages (pages that never got migrated during precopy), now
we cover that too which is actually also a valid scenario for postcopy.

The initial solution can reduce migration-test time from 8min to 1min40s,
this patch can further reduce it from 1m40s to <1m per my local test.

While at it, add migrate_set_bandwidth_[pre|post]copy() and use them.

Signed-off-by: Peter Xu <peterx@redhat.com>
---
 tests/qtest/migration-test.c | 39 +++++++++++++++++++++++++++---------
 1 file changed, 29 insertions(+), 10 deletions(-)
diff mbox series

Patch

diff --git a/tests/qtest/migration-test.c b/tests/qtest/migration-test.c
index b9cc194100..d5584d07a9 100644
--- a/tests/qtest/migration-test.c
+++ b/tests/qtest/migration-test.c
@@ -433,16 +433,23 @@  static void migrate_set_parameter_bool(QTestState *who, const char *parameter,
 
 static void migrate_ensure_non_converge(QTestState *who)
 {
-    /* Can't converge with 1ms downtime + 3 mbs bandwidth limit */
-    migrate_set_parameter_int(who, "max-bandwidth", 3 * 1000 * 1000);
-    migrate_set_parameter_int(who, "downtime-limit", 1);
+    /* Hold off switchover for precopy only */
+    migrate_set_parameter_bool(who, "switchover-hold", true);
 }
 
 static void migrate_ensure_converge(QTestState *who)
 {
-    /* Should converge with 30s downtime + 1 gbs bandwidth limit */
-    migrate_set_parameter_int(who, "max-bandwidth", 1 * 1000 * 1000 * 1000);
-    migrate_set_parameter_int(who, "downtime-limit", 30 * 1000);
+    migrate_set_parameter_bool(who, "switchover-hold", false);
+}
+
+static void migrate_set_bandwidth_precopy(QTestState *who, int bw)
+{
+    migrate_set_parameter_int(who, "max-bandwidth", bw);
+}
+
+static void migrate_set_bandwidth_postcopy(QTestState *who, int bw)
+{
+    migrate_set_parameter_int(who, "max-postcopy-bandwidth", bw);
 }
 
 static void migrate_pause(QTestState *who)
@@ -736,6 +743,14 @@  static int test_migrate_start(QTestState **from, QTestState **to,
         unlink(shmem_path);
     }
 
+    /*
+     * By default, use full speed for precopy in qtests as that will reduce
+     * the time of testing. The default bandwidth (128MB/s) may be too slow
+     * in this case.  Specific test can overwrite this value after the
+     * function returns but before starting migration.
+     */
+    migrate_set_bandwidth_precopy(*from, 0);
+
     return 0;
 }
 
@@ -1168,9 +1183,13 @@  static int migrate_postcopy_prepare(QTestState **from_ptr,
     /* Wait for the first serial output from the source */
     wait_for_serial("src_serial");
 
+    /*
+     * Limit precopy to 200MB/s for 0.1 sec, so we guarantee to leave
+     * enough pages (total-20MB) for remote page fault processes later.
+     */
+    migrate_set_bandwidth_precopy(from, 200 * 1024 * 1024);
     migrate_qmp(from, uri, "{}");
-
-    wait_for_migration_pass(from);
+    usleep(100000);
 
     *from_ptr = from;
     *to_ptr = to;
@@ -1270,7 +1289,7 @@  static void test_postcopy_recovery_common(MigrateCommon *args)
     }
 
     /* Turn postcopy speed down, 4K/s is slow enough on any machines */
-    migrate_set_parameter_int(from, "max-postcopy-bandwidth", 4096);
+    migrate_set_bandwidth_postcopy(from, 4096);
 
     /* Now we start the postcopy */
     migrate_postcopy_start(from, to);
@@ -1314,7 +1333,7 @@  static void test_postcopy_recovery_common(MigrateCommon *args)
     migrate_qmp(from, uri, "{'resume': true}");
 
     /* Restore the postcopy bandwidth to unlimited */
-    migrate_set_parameter_int(from, "max-postcopy-bandwidth", 0);
+    migrate_set_bandwidth_postcopy(from, 0);
 
     migrate_postcopy_complete(from, to, args);
 }