From d132157c9e0b6b990cd989662f5499644508de97 Mon Sep 17 00:00:00 2001
From: Nir Soffer <nsoffer@redhat.com>
Date: Thu, 28 Nov 2019 20:36:32 +0200
Subject: [PATCH] rhv-upload: Fix waiting for transfer

We were not considering failures while initializing the transfer. In
this case the transfer phase can change to PAUSED_SYSTEM or
FINISHED_FAILURE, and transfer_url will be None, which failed the
upload with a misleading error:

    RuntimeError: direct upload to host not supported, requires
    ovirt-engine >= 4.2 and only works when virt-v2v is run within the
    oVirt/RHV environment, eg. on an oVirt node

Change the wait loop to consider all cases:
- Transfer failed and was removed
- Transfer failed and will be removed soon
- Transfer paused by the system (cancel required)
- Unexpected transfer phase (cancel required)
- Timeout waiting for TRANSFERRING state (cancel required)

Reported-by: Xiaodai Wang

(cherry picked from commit 40e1844827e4d096b1919a2159f9effc41915a73
in virt-v2v)
---
 v2v/rhv-upload-plugin.py | 41 +++++++++++++++++++++++++++++++---------
 1 file changed, 32 insertions(+), 9 deletions(-)

diff --git a/v2v/rhv-upload-plugin.py b/v2v/rhv-upload-plugin.py
index 9b83d1cfa..14d4e37fb 100644
--- a/v2v/rhv-upload-plugin.py
+++ b/v2v/rhv-upload-plugin.py
@@ -185,20 +185,43 @@ def open(readonly):
     # Get a reference to the created transfer service.
     transfer_service = transfers_service.image_transfer_service(transfer.id)
 
-    # After adding a new transfer for the disk, the transfer's status
-    # will be INITIALIZING.  Wait until the init phase is over. The
-    # actual transfer can start when its status is "Transferring".
+    # Wait until transfer's phase change from INITIALIZING to TRANSFERRING. On
+    # errors transfer's phase can change to PAUSED_SYSTEM or FINISHED_FAILURE.
+    # If the transfer was paused, we need to cancel it to remove the disk,
+    # otherwise the system will remove the disk and transfer shortly after.
+
     endt = time.time() + timeout
     while True:
-        transfer = transfer_service.get()
-        if transfer.phase != types.ImageTransferPhase.INITIALIZING:
+        time.sleep(1)
+        try:
+            transfer = transfer_service.get()
+        except sdk.NotFoundError:
+            # The system has removed the disk and the transfer.
+            raise RuntimeError("transfer %s was removed" % transfer.id)
+
+        if transfer.phase == types.ImageTransferPhase.FINISHED_FAILURE:
+            # The system will remove the disk and the transfer soon.
+            raise RuntimeError(
+                "transfer %s has failed" % transfer.id)
+
+        if transfer.phase == types.ImageTransferPhase.PAUSED_SYSTEM:
+            transfer_service.cancel()
+            raise RuntimeError(
+                "transfer %s was paused by system" % transfer.id)
+
+        if transfer.phase == types.ImageTransferPhase.TRANSFERRING:
             break
-        if time.time() > endt:
+
+        if transfer.phase != types.ImageTransferPhase.INITIALIZING:
+            transfer_service.cancel()
             raise RuntimeError(
-                "timed out waiting for transfer %s status != INITIALIZING"
-                % transfer.id)
+                "unexpected transfer %s phase %s"
+                % (transfer.id, transfer.phase))
 
-        time.sleep(1)
+        if time.time() > endt:
+            transfer_service.cancel()
+            raise RuntimeError(
+                "timed out waiting for transfer %s" % transfer.id)
 
     # Now we have permission to start the transfer.
     if params['rhv_direct']:
-- 
2.26.2