1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
|
# frozen_string_literal: true
module BulkImports
class PipelineWorker # rubocop:disable Scalability/IdempotentWorker
include ApplicationWorker
NDJSON_PIPELINE_PERFORM_DELAY = 10.seconds
data_consistency :always
feature_category :importers
sidekiq_options retry: false, dead: false
worker_has_external_dependencies!
def perform(pipeline_tracker_id, stage, entity_id)
pipeline_tracker = ::BulkImports::Tracker
.with_status(:enqueued)
.find_by_id(pipeline_tracker_id)
if pipeline_tracker.present?
logger.info(
structured_payload(
entity_id: pipeline_tracker.entity.id,
pipeline_name: pipeline_tracker.pipeline_name
)
)
run(pipeline_tracker)
else
logger.error(
structured_payload(
entity_id: entity_id,
pipeline_tracker_id: pipeline_tracker_id,
message: 'Unstarted pipeline not found'
)
)
end
ensure
::BulkImports::EntityWorker.perform_async(entity_id, stage)
end
private
def run(pipeline_tracker)
if pipeline_tracker.entity.failed?
raise(Entity::FailedError, 'Failed entity status')
end
if ndjson_pipeline?(pipeline_tracker)
status = ExportStatus.new(pipeline_tracker, pipeline_tracker.pipeline_class.relation)
raise(Pipeline::ExpiredError, 'Pipeline timeout') if job_timeout?(pipeline_tracker)
raise(Pipeline::FailedError, status.error) if status.failed?
return reenqueue(pipeline_tracker) if status.started?
end
pipeline_tracker.update!(status_event: 'start', jid: jid)
context = ::BulkImports::Pipeline::Context.new(pipeline_tracker)
pipeline_tracker.pipeline_class.new(context).run
pipeline_tracker.finish!
rescue BulkImports::NetworkError => e
if e.retriable?(pipeline_tracker)
logger.error(
structured_payload(
entity_id: pipeline_tracker.entity.id,
pipeline_name: pipeline_tracker.pipeline_name,
message: "Retrying error: #{e.message}"
)
)
pipeline_tracker.update!(status_event: 'retry', jid: jid)
reenqueue(pipeline_tracker, delay: e.retry_delay)
else
fail_tracker(pipeline_tracker, e)
end
rescue StandardError => e
fail_tracker(pipeline_tracker, e)
end
def fail_tracker(pipeline_tracker, exception)
pipeline_tracker.update!(status_event: 'fail_op', jid: jid)
logger.error(
structured_payload(
entity_id: pipeline_tracker.entity.id,
pipeline_name: pipeline_tracker.pipeline_name,
message: exception.message
)
)
Gitlab::ErrorTracking.track_exception(
exception,
entity_id: pipeline_tracker.entity.id,
pipeline_name: pipeline_tracker.pipeline_name
)
end
def logger
@logger ||= Gitlab::Import::Logger.build
end
def ndjson_pipeline?(pipeline_tracker)
pipeline_tracker.pipeline_class.ndjson_pipeline?
end
def job_timeout?(pipeline_tracker)
(Time.zone.now - pipeline_tracker.entity.created_at) > Pipeline::NDJSON_EXPORT_TIMEOUT
end
def reenqueue(pipeline_tracker, delay: NDJSON_PIPELINE_PERFORM_DELAY)
self.class.perform_in(
delay,
pipeline_tracker.id,
pipeline_tracker.stage,
pipeline_tracker.entity.id
)
end
end
end
|
