We introduce a Markov chain for sampling from the uniform distribution on a Riemannian manifold M, which we call the geodesic walk. We prove that the mixing time of this walk on any manifold with positive sectional curvature C x (u, v) bounded both aboveIn particular, this bound on the mixing time does not depend explicitly on the dimension of the manifold. In the special case that M is the boundary of a convex body, we give an explicit and computationally tractable algorithm for approximating the exact geodesic walk. As a consequence, we obtain an algorithm for sampling uniformly from the surface of a convex body that has running time bounded solely in terms of the curvature of the body. ‡ 2 is often very pessimistic and can be greatly improved in some important special cases (See Remark 8.11 in Section 8.2). Furthermore, in situations where one has access to better geodesic approximations, such as when symplectic integrators or exact geodesic integrators are available, our results imply computational costs that are much closer to the mixing time O * M 2 m 2 of the true geodesic walk.Remark 1.2. Note that the bound in [11] is better for chains with a bound on the diameter of K that is much smaller than 2 √ m 2 , while our bound is better in higher dimensions and when the bound on the inner radius of curvature of K is much smaller than 1 √ M 2 . Also, a practical implementation of the geodesic walk requires additional computational costs that depend on the method used to approximate geodesics.