To evaluate factors associated with failure in patients treated with DAIR (debridement, antibiotic therapy, and implant retention) for Staphylococcus aureus prosthetic joint infections (PJIs). We retrospectively analyzed consecutive patients with stable PJI due to S. aureus treated with DAIR at six hospitals between 2010 and 2014. Cox proportional hazards regression was used to study factors associated with treatment failure at 2 years. Of 154 eligible patients, 137 were included (mean age 73 ± 13 years; male 56%). The estimated success rate according to the Kaplan–Meier method was 76.2 [95% CI 68–83] at 2 years of follow-up. In multivariate analysis, longer duration of treatment (hazard ratio (HR) 0.78 [0.69–0.88]; p < 0.001) and combination therapy including rifampin (HR 0.08 [0.018–0.36]; p = 0.001) were independently associated with success, whereas active smoking was independently associated with failure (HR 3.6 [1.09–11.84]; p = 0.036). When the analysis was restricted to patients with early infection onset (< 3 months), early acute infection was also predictive of a better prognosis (HR 0.25 [0.09–0.7]; p = 0.009). Failure was not associated with time from prosthesis insertion to debridement, nor with duration of symptoms > 3 weeks and type of prosthesis (hip or knee). These results remained unchanged when the 14 patients under immunosuppressive therapy were removed from analysis. These data suggest that DAIR can be performed even if infection and symptoms are delayed but reserved to patients who are able to follow rifampin-based combination therapy for a prolonged duration that should not be different for hip and knee PJI.