Abstract: Modern network telemetry systems collect and analyze massive amounts of raw data in a space efficient manner. These require advanced capabilities such as drill down queries that allow iterative refinement of the search space. We present a first integral solution that (i) enables multiple measurement tasks inside the same data structure, (ii) supports specifying the time frame of interest as part of its queries, and (iii) is sketch-based and thus space efficient. Namely, our approach allows the user to define both the measurement task (e.g., heavy hitters, entropy estimation, count distinct, etc.) and the time frame of relevance (e.g., 5PM-6PM) at query time. Our approach provides accuracy guarantees and is the only space-efficient solution that offers such capabilities. Finally, we demonstrate how our system can be used for accurately pinpointing the start of a realistic DDoS attack.
0 Replies
Loading