[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[Qemu-devel] [PULL 17/40] migration: allow src return path to pause
From: |
Juan Quintela |
Subject: |
[Qemu-devel] [PULL 17/40] migration: allow src return path to pause |
Date: |
Wed, 16 May 2018 01:39:54 +0200 |
From: Peter Xu <address@hidden>
Let the thread pause for network issues.
Reviewed-by: Dr. David Alan Gilbert <address@hidden>
Signed-off-by: Peter Xu <address@hidden>
Message-Id: <address@hidden>
Signed-off-by: Juan Quintela <address@hidden>
---
migration/migration.c | 35 +++++++++++++++++++++++++++++++++--
migration/migration.h | 1 +
migration/trace-events | 2 ++
3 files changed, 36 insertions(+), 2 deletions(-)
diff --git a/migration/migration.c b/migration/migration.c
index 4a7c02fd3c..f9c58d2511 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -1779,6 +1779,18 @@ static void migrate_handle_rp_req_pages(MigrationState
*ms, const char* rbname,
}
}
+/* Return true to retry, false to quit */
+static bool postcopy_pause_return_path_thread(MigrationState *s)
+{
+ trace_postcopy_pause_return_path();
+
+ qemu_sem_wait(&s->postcopy_pause_rp_sem);
+
+ trace_postcopy_pause_return_path_continued();
+
+ return true;
+}
+
/*
* Handles messages sent on the return path towards the source VM
*
@@ -1795,6 +1807,8 @@ static void *source_return_path_thread(void *opaque)
int res;
trace_source_return_path_thread_entry();
+
+retry:
while (!ms->rp_state.error && !qemu_file_get_error(rp) &&
migration_is_setup_or_active(ms->state)) {
trace_source_return_path_thread_loop_top();
@@ -1886,13 +1900,28 @@ static void *source_return_path_thread(void *opaque)
break;
}
}
- if (qemu_file_get_error(rp)) {
+
+out:
+ res = qemu_file_get_error(rp);
+ if (res) {
+ if (res == -EIO) {
+ /*
+ * Maybe there is something we can do: it looks like a
+ * network down issue, and we pause for a recovery.
+ */
+ if (postcopy_pause_return_path_thread(ms)) {
+ /* Reload rp, reset the rest */
+ rp = ms->rp_state.from_dst_file;
+ ms->rp_state.error = false;
+ goto retry;
+ }
+ }
+
trace_source_return_path_thread_bad_end();
mark_source_rp_bad(ms);
}
trace_source_return_path_thread_end();
-out:
ms->rp_state.from_dst_file = NULL;
qemu_fclose(rp);
return NULL;
@@ -2700,6 +2729,7 @@ static void migration_instance_finalize(Object *obj)
g_free(params->tls_creds);
qemu_sem_destroy(&ms->pause_sem);
qemu_sem_destroy(&ms->postcopy_pause_sem);
+ qemu_sem_destroy(&ms->postcopy_pause_rp_sem);
error_free(ms->error);
}
@@ -2731,6 +2761,7 @@ static void migration_instance_init(Object *obj)
params->has_xbzrle_cache_size = true;
qemu_sem_init(&ms->postcopy_pause_sem, 0);
+ qemu_sem_init(&ms->postcopy_pause_rp_sem, 0);
}
/*
diff --git a/migration/migration.h b/migration/migration.h
index 0ccdcb8ffe..32fd50e9be 100644
--- a/migration/migration.h
+++ b/migration/migration.h
@@ -200,6 +200,7 @@ struct MigrationState
/* Needed by postcopy-pause state */
QemuSemaphore postcopy_pause_sem;
+ QemuSemaphore postcopy_pause_rp_sem;
};
void migrate_set_state(int *state, int old_state, int new_state);
diff --git a/migration/trace-events b/migration/trace-events
index e23ec019be..cd971bf9fe 100644
--- a/migration/trace-events
+++ b/migration/trace-events
@@ -99,6 +99,8 @@ migration_thread_setup_complete(void) ""
open_return_path_on_source(void) ""
open_return_path_on_source_continue(void) ""
postcopy_start(void) ""
+postcopy_pause_return_path(void) ""
+postcopy_pause_return_path_continued(void) ""
postcopy_pause_continued(void) ""
postcopy_pause_incoming(void) ""
postcopy_pause_incoming_continued(void) ""
--
2.17.0
- [Qemu-devel] [PULL 06/40] migration: terminate_* can be called for other threads, (continued)
- [Qemu-devel] [PULL 06/40] migration: terminate_* can be called for other threads, Juan Quintela, 2018/05/15
- [Qemu-devel] [PULL 09/40] migration: Create multifd channels, Juan Quintela, 2018/05/15
- [Qemu-devel] [PULL 08/40] migration: Export functions to create send channels, Juan Quintela, 2018/05/15
- [Qemu-devel] [PULL 10/40] migration: Delay start of migration main routines, Juan Quintela, 2018/05/15
- [Qemu-devel] [PULL 11/40] migration: Transmit initial package through the multifd channels, Juan Quintela, 2018/05/15
- [Qemu-devel] [PULL 13/40] migration: let incoming side use thread context, Juan Quintela, 2018/05/15
- [Qemu-devel] [PULL 12/40] migration: Define MultifdRecvParams sooner, Juan Quintela, 2018/05/15
- [Qemu-devel] [PULL 07/40] migration: Be sure all recv channels are created, Juan Quintela, 2018/05/15
- [Qemu-devel] [PULL 14/40] migration: new postcopy-pause state, Juan Quintela, 2018/05/15
- [Qemu-devel] [PULL 16/40] migration: allow dst vm pause on postcopy, Juan Quintela, 2018/05/15
- [Qemu-devel] [PULL 17/40] migration: allow src return path to pause,
Juan Quintela <=
- [Qemu-devel] [PULL 18/40] migration: allow fault thread to pause, Juan Quintela, 2018/05/15
- [Qemu-devel] [PULL 19/40] qmp: hmp: add migrate "resume" option, Juan Quintela, 2018/05/15
- [Qemu-devel] [PULL 15/40] migration: implement "postcopy-pause" src logic, Juan Quintela, 2018/05/15
- [Qemu-devel] [PULL 20/40] migration: rebuild channel on source, Juan Quintela, 2018/05/15
- [Qemu-devel] [PULL 22/40] migration: wakeup dst ram-load-thread for recover, Juan Quintela, 2018/05/15
- [Qemu-devel] [PULL 23/40] migration: new cmd MIG_CMD_RECV_BITMAP, Juan Quintela, 2018/05/15
- [Qemu-devel] [PULL 21/40] migration: new state "postcopy-recover", Juan Quintela, 2018/05/15
- [Qemu-devel] [PULL 25/40] migration: new cmd MIG_CMD_POSTCOPY_RESUME, Juan Quintela, 2018/05/15
- [Qemu-devel] [PULL 24/40] migration: new message MIG_RP_MSG_RECV_BITMAP, Juan Quintela, 2018/05/15
- [Qemu-devel] [PULL 26/40] migration: new message MIG_RP_MSG_RESUME_ACK, Juan Quintela, 2018/05/15