[PULL 19/40] migration: Add tracepoints for downtime checkpoints

[Juan Quintela <quintela@redhat.com>]

From: Peter Xu <peterx@redhat.com>

This patch is inspired by Joao Martin's patch here:

https://lore.kernel.org/r/20230926161841.98464-1-joao.m.martins@oracle.com

Add tracepoints for major downtime checkpoints on both src and dst.  They
share the same tracepoint with a string showing its stage.

Besides the checkpoints in the previous patch, this patch also added
destination checkpoints.

On src, we have these checkpoints added:

  - src-downtime-start: right before vm stops on src
  - src-vm-stopped: after vm is fully stopped
  - src-iterable-saved: after all iterables saved (END sections)
  - src-non-iterable-saved: after all non-iterable saved (FULL sections)
  - src-downtime-stop: migration fully completed

On dst, we have these checkpoints added:

  - dst-precopy-loadvm-completes: after loadvm all done for precopy
  - dst-precopy-bh-*: record BH steps to resume VM for precopy
  - dst-postcopy-bh-*: record BH steps to resume VM for postcopy

On dst side, we don't have a good way to trace total time consumed by
iterable or non-iterable for now.  We can mark it by 1st time receiving a
FULL / END section, but rather than that let's just rely on the other
tracepoints added for vmstates to back up the information.

With this patch, one can enable "vmstate_downtime*" tracepoints and it'll
enable all tracepoints for downtime measurements necessary.

Drop loadvm_postcopy_handle_run_bh() tracepoint alongside, because they
service the same purpose, which was only for postcopy.  We then have
unified prefix for all downtime relevant tracepoints.

Co-developed-by: Joao Martins <joao.m.martins@oracle.com>
Signed-off-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
Message-ID: <20231030163346.765724-6-peterx@redhat.com>
---
 migration/migration.c  | 16 +++++++++++++++-
 migration/savevm.c     | 14 +++++++++-----
 migration/trace-events |  2 +-
 3 files changed, 25 insertions(+), 7 deletions(-)

diff --git a/migration/migration.c b/migration/migration.c
index 3e38294485..c334b9effd 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -103,6 +103,7 @@ static int close_return_path_on_source(MigrationState *s);
 
 static void migration_downtime_start(MigrationState *s)
 {
+    trace_vmstate_downtime_checkpoint("src-downtime-start");
     s->downtime_start = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
 }
 
@@ -117,6 +118,8 @@ static void migration_downtime_end(MigrationState *s)
     if (!s->downtime) {
         s->downtime = now - s->downtime_start;
     }
+
+    trace_vmstate_downtime_checkpoint("src-downtime-end");
 }
 
 static bool migration_needs_multiple_sockets(void)
@@ -151,7 +154,11 @@ static gint page_request_addr_cmp(gconstpointer ap, gconstpointer bp)
 
 int migration_stop_vm(RunState state)
 {
-    return vm_stop_force_state(state);
+    int ret = vm_stop_force_state(state);
+
+    trace_vmstate_downtime_checkpoint("src-vm-stopped");
+
+    return ret;
 }
 
 void migration_object_init(void)
@@ -495,6 +502,8 @@ static void process_incoming_migration_bh(void *opaque)
     Error *local_err = NULL;
     MigrationIncomingState *mis = opaque;
 
+    trace_vmstate_downtime_checkpoint("dst-precopy-bh-enter");
+
     /* If capability late_block_activate is set:
      * Only fire up the block code now if we're going to restart the
      * VM, else 'cont' will do it.
@@ -520,6 +529,8 @@ static void process_incoming_migration_bh(void *opaque)
      */
     qemu_announce_self(&mis->announce_timer, migrate_announce_params());
 
+    trace_vmstate_downtime_checkpoint("dst-precopy-bh-announced");
+
     multifd_load_shutdown();
 
     dirty_bitmap_mig_before_vm_start();
@@ -537,6 +548,7 @@ static void process_incoming_migration_bh(void *opaque)
     } else {
         runstate_set(global_state_get_runstate());
     }
+    trace_vmstate_downtime_checkpoint("dst-precopy-bh-vm-started");
     /*
      * This must happen after any state changes since as soon as an external
      * observer sees this event they might start to prod at the VM assuming
@@ -571,6 +583,8 @@ process_incoming_migration_co(void *opaque)
     ret = qemu_loadvm_state(mis->from_src_file);
     mis->loadvm_co = NULL;
 
+    trace_vmstate_downtime_checkpoint("dst-precopy-loadvm-completed");
+
     ps = postcopy_state_get();
     trace_process_incoming_migration_co_end(ret, ps);
     if (ps != POSTCOPY_INCOMING_NONE) {
diff --git a/migration/savevm.c b/migration/savevm.c
index 99ce42b6f3..bc98c2ea6f 100644
--- a/migration/savevm.c
+++ b/migration/savevm.c
@@ -1526,6 +1526,8 @@ int qemu_savevm_state_complete_precopy_iterable(QEMUFile *f, bool in_postcopy)
                                     end_ts_each - start_ts_each);
     }
 
+    trace_vmstate_downtime_checkpoint("src-iterable-saved");
+
     return 0;
 }
 
@@ -1592,6 +1594,8 @@ int qemu_savevm_state_complete_precopy_non_iterable(QEMUFile *f,
     json_writer_free(vmdesc);
     ms->vmdesc = NULL;
 
+    trace_vmstate_downtime_checkpoint("src-non-iterable-saved");
+
     return 0;
 }
 
@@ -2133,18 +2137,18 @@ static void loadvm_postcopy_handle_run_bh(void *opaque)
     Error *local_err = NULL;
     MigrationIncomingState *mis = opaque;
 
-    trace_loadvm_postcopy_handle_run_bh("enter");
+    trace_vmstate_downtime_checkpoint("dst-postcopy-bh-enter");
 
     /* TODO we should move all of this lot into postcopy_ram.c or a shared code
      * in migration.c
      */
     cpu_synchronize_all_post_init();
 
-    trace_loadvm_postcopy_handle_run_bh("after cpu sync");
+    trace_vmstate_downtime_checkpoint("dst-postcopy-bh-cpu-synced");
 
     qemu_announce_self(&mis->announce_timer, migrate_announce_params());
 
-    trace_loadvm_postcopy_handle_run_bh("after announce");
+    trace_vmstate_downtime_checkpoint("dst-postcopy-bh-announced");
 
     /* Make sure all file formats throw away their mutable metadata.
      * If we get an error here, just don't restart the VM yet. */
@@ -2155,7 +2159,7 @@ static void loadvm_postcopy_handle_run_bh(void *opaque)
         autostart = false;
     }
 
-    trace_loadvm_postcopy_handle_run_bh("after invalidate cache");
+    trace_vmstate_downtime_checkpoint("dst-postcopy-bh-cache-invalidated");
 
     dirty_bitmap_mig_before_vm_start();
 
@@ -2169,7 +2173,7 @@ static void loadvm_postcopy_handle_run_bh(void *opaque)
 
     qemu_bh_delete(mis->bh);
 
-    trace_loadvm_postcopy_handle_run_bh("return");
+    trace_vmstate_downtime_checkpoint("dst-postcopy-bh-vm-started");
 }
 
 /* After all discards we can start running and asking for pages */
diff --git a/migration/trace-events b/migration/trace-events
index 5820add1f3..e54f317e3b 100644
--- a/migration/trace-events
+++ b/migration/trace-events
@@ -17,7 +17,6 @@ loadvm_handle_recv_bitmap(char *s) "%s"
 loadvm_postcopy_handle_advise(void) ""
 loadvm_postcopy_handle_listen(const char *str) "%s"
 loadvm_postcopy_handle_run(void) ""
-loadvm_postcopy_handle_run_bh(const char *str) "%s"
 loadvm_postcopy_handle_resume(void) ""
 loadvm_postcopy_ram_handle_discard(void) ""
 loadvm_postcopy_ram_handle_discard_end(void) ""
@@ -50,6 +49,7 @@ vmstate_save(const char *idstr, const char *vmsd_name) "%s, %s"
 vmstate_load(const char *idstr, const char *vmsd_name) "%s, %s"
 vmstate_downtime_save(const char *type, const char *idstr, uint32_t instance_id, int64_t downtime) "type=%s idstr=%s instance_id=%d downtime=%"PRIi64
 vmstate_downtime_load(const char *type, const char *idstr, uint32_t instance_id, int64_t downtime) "type=%s idstr=%s instance_id=%d downtime=%"PRIi64
+vmstate_downtime_checkpoint(const char *checkpoint) "%s"
 postcopy_pause_incoming(void) ""
 postcopy_pause_incoming_continued(void) ""
 postcopy_page_req_sync(void *host_addr) "sync page req %p"
-- 
2.41.0