* Peter Xu (pet...@redhat.com) wrote: > Let the thread pause for network issues. > > Signed-off-by: Peter Xu <pet...@redhat.com> > --- > 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 c729c5a..d0b9a86 100644 > --- a/migration/migration.c > +++ b/migration/migration.c > @@ -996,6 +996,7 @@ static void migrate_fd_cleanup(void *opaque) > block_cleanup_parameters(s); > > qemu_sem_destroy(&s->postcopy_pause_sem); > + qemu_sem_destroy(&s->postcopy_pause_rp_sem); > } > > void migrate_fd_error(MigrationState *s, const Error *error) > @@ -1140,6 +1141,7 @@ MigrationState *migrate_init(void) > error_free(s->error); > s->error = NULL; > qemu_sem_init(&s->postcopy_pause_sem, 0); > + qemu_sem_init(&s->postcopy_pause_rp_sem, 0); > > migrate_set_state(&s->state, MIGRATION_STATUS_NONE, > MIGRATION_STATUS_SETUP); > > @@ -1527,6 +1529,18 @@ 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 > * > @@ -1543,6 +1557,8 @@ 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(); > @@ -1634,13 +1650,28 @@ 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;
The recursion trick I suggested in the previous patch might also work here. but it's OK, so Reviewed-by: Dr. David Alan Gilbert <dgilb...@redhat.com> > + } > + } > + > 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; > diff --git a/migration/migration.h b/migration/migration.h > index 08b90e8..7aaab13 100644 > --- a/migration/migration.h > +++ b/migration/migration.h > @@ -157,6 +157,7 @@ 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 22a629e..a269eec 100644 > --- a/migration/trace-events > +++ b/migration/trace-events > @@ -98,6 +98,8 @@ 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) "" > -- > 2.7.4 > -- Dr. David Alan Gilbert / dgilb...@redhat.com / Manchester, UK