[Libguestfs] [v2v PATCH v2] -o rhv-upload: wait for VM creation task

[Tomáš Golembiovský]

oVirt API call for VM creation finishes before the VM is actually
created. Entities may be still locked after virt-v2v terminates and if
user tries to perform (scripted) actions after virt-v2v those operations
may fail. To prevent this it is useful to monitor the task and wait for
the completion. This will also help to prevent some corner case
scenarios (that would be difficult to debug) when the VM creation job
fails after virt-v2v already termintates with success.

Thanks: Nir Soffer
Fixes: https://bugzilla.redhat.com/show_bug.cgi?id=1985827
Signed-off-by: Tomáš Golembiovský <tgolembi at redhat.com>
Reviewed-by: Arik Hadas <ahadas at redhat.com>
Reviewed-by: Nir Soffer <nsoffer at redhat.com>
---
 output/rhv-upload-createvm.py                 | 57 ++++++++++++++++++-
 .../ovirtsdk4/__init__.py                     | 10 +++-
 .../ovirtsdk4/types.py                        | 19 +++++++
 3 files changed, 84 insertions(+), 2 deletions(-)


Changes in v2:

- fixed tests
- changes suggested by Nir
- increased sleep time and decreased timeout


diff --git a/output/rhv-upload-createvm.py b/output/rhv-upload-createvm.py
index 50bb7e34..642f0720 100644
--- a/output/rhv-upload-createvm.py
+++ b/output/rhv-upload-createvm.py
@@ -19,12 +19,54 @@
 import json
 import logging
 import sys
+import time
+import uuid
 
 from urllib.parse import urlparse
 
 import ovirtsdk4 as sdk
 import ovirtsdk4.types as types
 
+
+def debug(s):
+    if params['verbose']:
+        print(s, file=sys.stderr)
+        sys.stderr.flush()
+
+
+def jobs_completed(system_service, correlation_id):
+    jobs_service = system_service.jobs_service()
+
+    try:
+        jobs = jobs_service.list(
+            search="correlation_id=%s" % correlation_id)
+    except sdk.Error as e:
+        debug(
+            "Error searching for jobs with correlation id %s: %s" %
+            (correlation_id, e))
+        # We don't know, assume that jobs did not complete yet.
+        return False
+
+    # STARTED is the only "in progress" status, anything else means the job
+    # has already terminated.
+    if all(job.status != types.JobStatus.STARTED for job in jobs):
+        failed_jobs = [(job.description, str(job.status))
+                       for job in jobs
+                       if job.status != types.JobStatus.FINISHED]
+        if failed_jobs:
+            raise RuntimeError(
+                "Failed to create a VM! Failed jobs: %r" % failed_jobs)
+        return True
+    else:
+        running_jobs = [(job.description, str(job.status)) for job in jobs]
+        debug("Some jobs with correlation id %s are running: %s" %
+              (correlation_id, running_jobs))
+        return False
+
+
+# Seconds to wait for the VM import job to complete in oVirt.
+timeout = 5 * 60
+
 # Parameters are passed in via a JSON doc from the OCaml code.
 # Because this Python code ships embedded inside virt-v2v there
 # is no formal API here.
@@ -67,6 +109,7 @@ system_service = connection.system_service()
 cluster = system_service.clusters_service().cluster_service(params['rhv_cluster_uuid'])
 cluster = cluster.get()
 
+correlation_id = str(uuid.uuid4())
 vms_service = system_service.vms_service()
 vm = vms_service.add(
     types.Vm(
@@ -77,5 +120,17 @@ vm = vms_service.add(
                 data=ovf,
             )
         )
-    )
+    ),
+    query={'correlation_id': correlation_id},
 )
+
+# Wait for the import job to finish.
+endt = time.monotonic() + timeout
+while True:
+    time.sleep(1)
+    if jobs_completed(system_service, correlation_id):
+        break
+    if time.monotonic() > endt:
+        raise RuntimeError(
+            "Timed out waiting for VM creation!"
+            " Jobs still running for correlation id %s" % correlation_id)
diff --git a/tests/test-v2v-o-rhv-upload-module/ovirtsdk4/__init__.py b/tests/test-v2v-o-rhv-upload-module/ovirtsdk4/__init__.py
index 0d8f33b3..e33d0714 100644
--- a/tests/test-v2v-o-rhv-upload-module/ovirtsdk4/__init__.py
+++ b/tests/test-v2v-o-rhv-upload-module/ovirtsdk4/__init__.py
@@ -59,6 +59,9 @@ class SystemService(object):
     def disks_service(self):
         return DisksService()
 
+    def jobs_service(self):
+        return JobsService()
+
     def image_transfers_service(self):
         return ImageTransfersService()
 
@@ -104,6 +107,11 @@ class DisksService(object):
         return DiskService(disk_id)
 
 
+class JobsService(object):
+    def list(self, search=None):
+        return [types.Job()]
+
+
 class ImageTransferService(object):
     def __init__(self):
         self._finalized = False
@@ -135,7 +143,7 @@ class StorageDomainsService(object):
 
 
 class VmsService(object):
-    def add(self, vm):
+    def add(self, vm, query=None):
         return vm
 
     def list(self, search=None):
diff --git a/tests/test-v2v-o-rhv-upload-module/ovirtsdk4/types.py b/tests/test-v2v-o-rhv-upload-module/ovirtsdk4/types.py
index 5707fa3e..38d89573 100644
--- a/tests/test-v2v-o-rhv-upload-module/ovirtsdk4/types.py
+++ b/tests/test-v2v-o-rhv-upload-module/ovirtsdk4/types.py
@@ -141,6 +141,25 @@ class Initialization(object):
         pass
 
 
+class JobStatus(Enum):
+    ABORTED = "aborted"
+    FAILED = "failed"
+    FINISHED = "finished"
+    STARTED = "started"
+    UNKNOWN = "unknown"
+
+    def __init__(self, image):
+        self._image = image
+
+    def __str__(self):
+        return self._image
+
+
+class Job(object):
+    description = "Fake job"
+    status = JobStatus.FINISHED
+
+
 class StorageDomain(object):
     def __init__(self, name=None):
         pass
-- 
2.35.1