We present a new measurement of the deuterium-to-hydrogen ratio (D/H) in the Lyman limit absorption system at z = 3.572 toward Q1937-1009. Tytler, Fan & Buries (TFB) made the first extragalactic detection of deuterium in this absorption system, which remains the best location for a high-accuracy measurement of primordial D/H. Their detailed analysis of Keck spectra gave a low value of D/H = 2.3 +/- 0.3 +/- 0.3 x 10(-5) (1 sigma statistical and systematic errors). Now we present a new method to measure D/H in QSO absorption systems. We avoid many of the assumptions adopted by TFB; we allow extra parameters to treat the continuum uncertainties, include a variety of new absorption models that allow for undetected velocity structure, and use the improved measurement of the total hydrogen column density by Buries & Tytler. We find that all models, including contamination, give an upper limit of D/H < 3.9 x 10(-5) (95% confidence). Both this and previous analyses find contamination to be unlikely in this absorption system: a chi(2) analysis in models without contamination gives D/H = 3.3 +/- 0.3 x 10(-5) (67% confidence), which is higher but consistent with the earlier results of TFB, and a second measurement of D/H toward Q1009+2956. With calculations of standard big bang nucleosynthesis (SBBN) and the assumption that this measurement of D/H is representative of the primordial value, we find a high baryon-to-photon ratio, eta = 5.3 +/- 0.4 x 10(-10). This is consistent with primordial abundance determinations of He-4 in H II regions and Li-7 in the atmospheres of warm metal-poor Population II stars. We find a high value for the present-day baryon density, Omega(b)h(2) = 0.0193 +/- 0.0014, which is consistent with other inventories of baryonic matter, from low to high redshift: clusters of galaxies, the Lyman alpha forest & the cosmic microwave background.