Background Patella resurfacing in total knee arthroplasty is a contentious issue. The literature suggests that resurfacing of the patella is based on surgeon preference, and little is known about the role and timing of resurfacing and how this affects outcomes. Methods We analyzed 134,799 total knee arthroplasties using data from the Australian Orthopaedic Association National Joint Replacement Registry. Hazards ratios (HRs) were used to compare rates of early revision between patella resurfacing at the primary procedure (the resurfacing group, R) and primary arthroplasty without resurfacing (no-resurfacing group, NR). We also analyzed the outcomes of NR that were revised for isolated patella addition. Results At 5 years, the R group showed a lower revision rate than the NR group: cumulative per cent revision (CPR) 3.1% and 4.0%, respectively (HR 0.75, p < 0.001). Revisions for patellofemoral pain were more common in the NR group (17%) than in the R group (1%), and "patella only" revisions were more common in the NR group (29%) than in the R group (6%). Non-resurfaced knees revised for isolated patella addition had a higher revision rate than patella resurfacing at the primary procedure, with a 4-year CPR of 15% and 2.8%, respectively (HR 4.1, p < 0.001). Interpretation Rates of early revision of primary total knees were higher when the patella was not resurfaced, and suggest that surgeons may be inclined to resurface later if there is patellofemoral pain. However, 15% of non-resurfaced knees revised for patella addition are re-revised by 4 years. Our results suggest an early beneficial outcome for patella resurfacing at primary arthroplasty based on revision rates up to 5 years.