[v5,09/28] migration: allow fault thread to pause

Message ID 20171205065307.21853-10-peterx@redhat.com
State New
Headers show
Series
  • [v5,01/28] migration: better error handling with QEMUFile
Related show

Commit Message

Peter Xu Dec. 5, 2017, 6:52 a.m.
Allows the fault thread to stop handling page faults temporarily. When
network failure happened (and if we expect a recovery afterwards), we
should not allow the fault thread to continue sending things to source,
instead, it should halt for a while until the connection is rebuilt.

When the dest main thread noticed the failure, it kicks the fault thread
to switch to pause state.

Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Signed-off-by: Peter Xu <peterx@redhat.com>
---
 migration/migration.c    |  1 +
 migration/migration.h    |  1 +
 migration/postcopy-ram.c | 50 ++++++++++++++++++++++++++++++++++++++++++++----
 migration/savevm.c       |  3 +++
 migration/trace-events   |  2 ++
 5 files changed, 53 insertions(+), 4 deletions(-)

Patch

diff --git a/migration/migration.c b/migration/migration.c
index e3ce22dce4..90ff49a271 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -151,6 +151,7 @@  MigrationIncomingState *migration_incoming_get_current(void)
         qemu_mutex_init(&mis_current.rp_mutex);
         qemu_event_init(&mis_current.main_thread_load_event, false);
         qemu_sem_init(&mis_current.postcopy_pause_sem_dst, 0);
+        qemu_sem_init(&mis_current.postcopy_pause_sem_fault, 0);
         once = true;
     }
     return &mis_current;
diff --git a/migration/migration.h b/migration/migration.h
index b63cdfbfdb..2751b2dffc 100644
--- a/migration/migration.h
+++ b/migration/migration.h
@@ -64,6 +64,7 @@  struct MigrationIncomingState {
 
     /* notify PAUSED postcopy incoming migrations to try to continue */
     QemuSemaphore postcopy_pause_sem_dst;
+    QemuSemaphore postcopy_pause_sem_fault;
 };
 
 MigrationIncomingState *migration_incoming_get_current(void);
diff --git a/migration/postcopy-ram.c b/migration/postcopy-ram.c
index 032abfbf1a..31c290c884 100644
--- a/migration/postcopy-ram.c
+++ b/migration/postcopy-ram.c
@@ -485,6 +485,17 @@  static int ram_block_enable_notify(const char *block_name, void *host_addr,
     return 0;
 }
 
+static bool postcopy_pause_fault_thread(MigrationIncomingState *mis)
+{
+    trace_postcopy_pause_fault_thread();
+
+    qemu_sem_wait(&mis->postcopy_pause_sem_fault);
+
+    trace_postcopy_pause_fault_thread_continued();
+
+    return true;
+}
+
 /*
  * Handle faults detected by the USERFAULT markings
  */
@@ -535,6 +546,22 @@  static void *postcopy_ram_fault_thread(void *opaque)
             }
         }
 
+        if (!mis->to_src_file) {
+            /*
+             * Possibly someone tells us that the return path is
+             * broken already using the event. We should hold until
+             * the channel is rebuilt.
+             */
+            if (postcopy_pause_fault_thread(mis)) {
+                last_rb = NULL;
+                /* Continue to read the userfaultfd */
+            } else {
+                error_report("%s: paused but don't allow to continue",
+                             __func__);
+                break;
+            }
+        }
+
         ret = read(mis->userfault_fd, &msg, sizeof(msg));
         if (ret != sizeof(msg)) {
             if (errno == EAGAIN) {
@@ -574,18 +601,33 @@  static void *postcopy_ram_fault_thread(void *opaque)
                                                 qemu_ram_get_idstr(rb),
                                                 rb_offset);
 
+retry:
         /*
          * Send the request to the source - we want to request one
          * of our host page sizes (which is >= TPS)
          */
         if (rb != last_rb) {
             last_rb = rb;
-            migrate_send_rp_req_pages(mis, qemu_ram_get_idstr(rb),
-                                     rb_offset, qemu_ram_pagesize(rb));
+            ret = migrate_send_rp_req_pages(mis, qemu_ram_get_idstr(rb),
+                                            rb_offset, qemu_ram_pagesize(rb));
         } else {
             /* Save some space */
-            migrate_send_rp_req_pages(mis, NULL,
-                                     rb_offset, qemu_ram_pagesize(rb));
+            ret = migrate_send_rp_req_pages(mis, NULL,
+                                            rb_offset, qemu_ram_pagesize(rb));
+        }
+
+        if (ret) {
+            /* May be network failure, try to wait for recovery */
+            if (ret == -EIO && postcopy_pause_fault_thread(mis)) {
+                /* We got reconnected somehow, try to continue */
+                last_rb = NULL;
+                goto retry;
+            } else {
+                /* This is a unavoidable fault */
+                error_report("%s: migrate_send_rp_req_pages() get %d",
+                             __func__, ret);
+                break;
+            }
         }
     }
     trace_postcopy_ram_fault_thread_exit();
diff --git a/migration/savevm.c b/migration/savevm.c
index 1e5fc4f332..ee03fb5c32 100644
--- a/migration/savevm.c
+++ b/migration/savevm.c
@@ -2039,6 +2039,9 @@  static bool postcopy_pause_incoming(MigrationIncomingState *mis)
     mis->to_src_file = NULL;
     qemu_mutex_unlock(&mis->rp_mutex);
 
+    /* Notify the fault thread for the invalidated file handle */
+    postcopy_fault_thread_notify(mis);
+
     error_report("Detected IO failure for postcopy. "
                  "Migration paused.");
 
diff --git a/migration/trace-events b/migration/trace-events
index a4031cfe00..32f02cbdcc 100644
--- a/migration/trace-events
+++ b/migration/trace-events
@@ -101,6 +101,8 @@  open_return_path_on_source_continue(void) ""
 postcopy_start(void) ""
 postcopy_pause_return_path(void) ""
 postcopy_pause_return_path_continued(void) ""
+postcopy_pause_fault_thread(void) ""
+postcopy_pause_fault_thread_continued(void) ""
 postcopy_pause_continued(void) ""
 postcopy_pause_incoming(void) ""
 postcopy_pause_incoming_continued(void) ""