Skip to content

Commit 9ba813f

Browse files
committed
[CHORE] Shorten one test comment to the voice of the surrounding file
Eight lines became five, with the notification argument and the reason the cases hold the handoff rather than the parking both kept. es_log_record_exporter_test passes 14 of 14 and clang-format 18.1.8 is clean. Signed-off-by: thc1006 <84045975+thc1006@users.noreply.github.com>
1 parent 2b20772 commit 9ba813f

1 file changed

Lines changed: 5 additions & 8 deletions

File tree

‎exporters/elasticsearch/test/es_log_record_exporter_test.cc‎

Lines changed: 5 additions & 8 deletions
Original file line numberDiff line numberDiff line change
@@ -440,14 +440,11 @@ std::shared_ptr<ParkedExport> StartParkedExport()
440440
}
441441
} // namespace
442442

443-
// A terminal error that arrives after the handler has been handed off, while the export is still
444-
// running, has to end the wait, which is the half the notification is responsible for. Without
445-
// these two, removing cv_.notify_all() keeps this file green.
446-
//
447-
// The handoff is what they hold, not the parking: the session publishes the handler before
448-
// SendRequest() returns, so the export need not have reached cv_.wait() when the callback is
449-
// delivered. Holding that would want a wait entry seam in production code, which is not worth the
450-
// API it would add.
443+
// A terminal error that arrives after the handler is handed off, while the export is still
444+
// running, has to end the wait. Without these two, removing cv_.notify_all() keeps this file
445+
// green. What they hold is the handoff rather than the parking: the session publishes the handler
446+
// before SendRequest() returns, so the export need not have reached cv_.wait() yet. Holding that
447+
// would want a wait-entry seam in production code, which is not worth the API.
451448
TEST_F(ElasticsearchLogsExporterSyncTests, AReadErrorAfterTheHandoffEndsTheExport)
452449
{
453450
auto parked = StartParkedExport();

0 commit comments

Comments
 (0)