ServiceX transformation fails for a few files with specific query

[alexander-held]

From the CMS ttbar notebook, slightly adapted:

if PIPELINE == "servicex_databinder":
    from servicex_databinder import DataBinder
    t0 = time.time()

    # query for events with at least 4 jets with 25 GeV, at least one b-tag, and exactly one electron or muon with pT > 25 GeV
    # returning columns required for subsequent processing
    query_string = """Where(
        lambda event: event.electron_pt.Where(lambda pT: pT > 25).Count() + event.muon_pt.Where(lambda pT: pT > 25).Count() == 1
        ).Where(lambda event: event.jet_pt.Where(lambda pT: pT > 25).Count() >= 4
        ).Where(lambda event: event.jet_btag.Where(lambda btag: btag > 0.5).Count() >= 1
        ).Select(
             lambda e: {"electron_pt": e.electron_pt, "muon_pt": e.muon_pt,
                        "jet_pt": e.jet_pt, "jet_eta": e.jet_eta, "jet_phi": e.jet_phi, "jet_mass": e.jet_mass, "jet_btag": e.jet_btag}
    )"""

    query_string = """Where(
        lambda event: event.electron_pt.Where(lambda pT: pT > 25).Count() + event.muon_pt.Where(lambda pT: pT > 25).Count() == 1
        ).Select(
             lambda e: {"electron_pt": e.electron_pt, "muon_pt": e.muon_pt,
                        "jet_pt": e.jet_pt, "jet_eta": e.jet_eta, "jet_phi": e.jet_phi, "jet_mass": e.jet_mass, "jet_btag": e.jet_btag}
    )"""

    sample_names = ["ttbar__nominal"]  # 1.5 TB, 7066 files
    sample_list = []

    for sample_name in sample_names:
        sample_list.append({"Name": sample_name, "RucioDID": f"user.ivukotic:user.ivukotic.{sample_name}", "Tree": "events", "FuncADL": query_string})

    databinder_config = {
                            "General": {
                                           "ServiceXBackendName": "uproot",
                                            "OutputDirectory": "outputs_databinder",
                                            "OutputFormat": "root",
                                            "IgnoreServiceXCache": SERVICEX_IGNORE_CACHE
                            },
                            "Sample": sample_list
                        }

    sx_db = DataBinder(databinder_config)
    out = sx_db.deliver()
    print(f"execution took {time.time() - t0:.2f} seconds")

fails for a single file. This seems to be query-related.

[alexander-held]

This may have been a transient issue.

[alexander-held]

Closing this as it has not happened since, presumably no longer a problem.