换柱状图配色

mySkyline-v7.5.tex

@@ -925,7 +925,6 @@ For comparison, we evaluate the following execution schemes:
 	\item \textbf{Ours:} The proposed mechanism featuring contention-aware switching, global I/O plan ordering, and window merging.
 \end{enumerate}
 
-\subsubsection{Concurrency Scalability}
 \begin{figure*}[htb]
 	\centering
 	\subfigure[$\sigma=0.4$]{\label{fig:cc_exp1_3}
@@ -943,6 +942,7 @@ For comparison, we evaluate the following execution schemes:
 	\label{fig:cc_exp1}
 \end{figure*}
 
+\subsubsection{Concurrency Scalability}
 To evaluate the system's robustness under different workload characteristics, we conducted a sensitivity analysis by manipulating the Spatial Overlap Ratio ($\sigma$). We examined three distinct scenarios: low overlap ($\sigma=0.4$, simulating dispersed random queries), medium overlap ($\sigma=0.6$), and high overlap ($\sigma=0.8$, simulating hotspot analysis). Note that $\sigma=0.4$ is defined as a low overlap scenario because: when $\sigma \le 0.35$, the performance of the deterministic scheduling mode is even lower than that of the optimistic mode (See Sec.~\ref{sec:ModeSwitch}). So, the performance of our method is the same as the Baseline when $\sigma \le 0.35$. Fig.~\ref{fig:cc_exp1} illustrates the query latency trends as the number of concurrent clients increases from 1 to 64.
 
 The results reveal a fundamental divergence in how the two systems respond to data contention. As shown in Fig.~\ref{fig:cc_exp1}(a), when query footprints are spatially dispersed, the opportunities for physical I/O merging are minimal. Consequently, the performance of both systems is primarily constrained by the aggregate physical bandwidth of the storage cluster. Both approaches exhibit linear latency growth with respect to the client count. At $N=64$, the Baseline reaches a mean latency of approx. 37,000 ms, while our method records approx. 30,000 ms. Although our method maintains a slight performance edge due to the reduced read amplification provided by the I/O-aware index, it inevitably degrades to a linear query processing mode similar to the Baseline. This confirms that without spatial locality to leverage request collapsing, the system is bound by the hardware's I/O throughput limits.