remus: resume immediately if libxl__xc_domain_save_done() completes

For example: if the secondary host is down, and we fail to send the data to
the secondary host. xc_domain_save() returns 0. So in the function
libxl__xc_domain_save_done(), rc is 0 (the helper program exits normally),
and retval is 0 (it is xc_domain_save()'s return value). In such case, we
just need to complete the stream.

Signed-off-by: Wen Congyang <wency@cn.fujitsu.com>
Reviewed-by: Andrew Cooper <andrew.cooper3@citrix.com>
Acked-by: Ian Campbell <ian.campbell@citrix.com>
[ ijc -- updated wording of comment as discussed ]

diff --git a/tools/libxl/libxl.h b/tools/libxl/libxl.h
index 7114491b039ee3132c8f40cf7ed899d78af23a91..156c0d50f8556b758372ce01df5f94aea2f9a70e 100644 (file)
--- a/tools/libxl/libxl.h
+++ b/tools/libxl/libxl.h
@@ -1215,6 +1215,11 @@ int libxl_domain_resume(libxl_ctx *ctx, uint32_t domid, int suspend_cancel,
                         const libxl_asyncop_how *ao_how)
                         LIBXL_EXTERNAL_CALLERS_ONLY;
 
+/*
+ * This function doesn't return unless something has gone wrong with
+ * the replication to the secondary. If this function returns then the
+ * caller should resume the (primary) domain.
+ */
 int libxl_domain_remus_start(libxl_ctx *ctx, libxl_domain_remus_info *info,
                              uint32_t domid, int send_fd, int recv_fd,
                              const libxl_asyncop_how *ao_how)

diff --git a/tools/libxl/libxl_stream_write.c b/tools/libxl/libxl_stream_write.c
index 80d9208062fc260616c0742854a465dee8190b57..21b4b51e4bab0bf7bbd86383e05a056f8150b893 100644 (file)
--- a/tools/libxl/libxl_stream_write.c
+++ b/tools/libxl/libxl_stream_write.c
@@ -354,8 +354,18 @@ void libxl__xc_domain_save_done(libxl__egc *egc, void *dss_void,
      * alive, and check_all_finished() may have torn it down around us.
      * If the stream is not still alive, we must not continue any work.
      */
-    if (libxl__stream_write_inuse(stream))
-        write_emulator_xenstore_record(egc, stream);
+    if (libxl__stream_write_inuse(stream)) {
+        if (dss->remus)
+            /*
+             * For remus, if libxl__xc_domain_save_done() completes,
+             * there was an error sending data to the secondary.
+             * Resume the primary ASAP. The caller doesn't care of the
+             * return value (Please refer to libxl__remus_teardown())
+             */
+            stream_complete(egc, stream, 0);
+        else
+            write_emulator_xenstore_record(egc, stream);
+    }
 }
 
 static void write_emulator_xenstore_record(libxl__egc *egc,