As cloud-native technologies continue to proliferate, fault diagnosis has become a critical aspect of online service systems. Operators tasked with fault diagnosis face the challenge of analyzing a wide range of monitoring metrics. These metrics often have missing data, adding complexity to the process. Their main goal is to locate faults among multiple components and find similar faults to develop effective solutions. However, prevailing methodologies fail to tightly integrate fault localization and fault correlation technologies, leading to suboptimal performance in root cause analysis. In this paper, we present a root cause analysis framework, SetRCA, that accurately localizes faults and offers interpretable identification of similar faults. To achieve this, we integrate the correlations between each pair of metrics with their temporal features for data interpolation using CP decomposition. Subsequently, the components in online service systems are ranked based on scores derived from the Personalized PageRank algorithm, using the filled data. Innovatively, the inclusion relationships between sets of abnormal metrics are employed to locate system faults. Ultimately, the solution is determined by examining the similarity between the current fault components and historical faults. An extensive study on two public datasets demonstrates the accuracy and interpretability of our proposed model.