From 14b1742eaaad1148c5b421eea0ae7e74d823e630 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Wed, 2 May 2018 18:47:21 +0800 Subject: migration: allow src return path to pause Let the thread pause for network issues. Reviewed-by: Dr. David Alan Gilbert Signed-off-by: Peter Xu Message-Id: <20180502104740.12123-6-peterx@redhat.com> Signed-off-by: Juan Quintela --- migration/migration.c | 35 +++++++++++++++++++++++++++++++++-- 1 file changed, 33 insertions(+), 2 deletions(-) (limited to 'migration/migration.c') 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); } /* -- cgit v1.2.3