To handle the high volume of requests, large-scale services are comprised of thousands of instances deployed in clouds. These services utilize diverse programming languages and are distributed across various nodes as encapsulated containers. Given their vast scale, even minor performance enhancements can lead to significant cost reductions. In this paper, we introduce Atys (Atys, known as the god of tracking and discovery, is often portrayed as a skilled hunter and scout in mythology), an efficient profiling framework specifically designed to identify hotspot functions within large-scale distributed services. Atys presents two key features. First, we propose a function selective pruning (FSP) strategy to enhance the efficiency of aggregating profiling results. Then, we develop a frequency dynamic adjustment (FDA) scheme that dynamically modifies sampling frequency based on service status, effectively minimizing profiling cost while keeping accuracy. Cluster-scale experiments on two benchmarks show that the FSP strategy achieves a 6.8% reduction in time with a mere 0.58% mean average percentage error (MAPE) in stack traces aggregation. Additionally, the FDA scheme ensures that the mean squared error (MSE) remains on par with that at high sampling rates, while achieving an 87.6% reduction in cost.