Optimal Checkpoint Research Articles

Design and optimization of acetazolamide nanoparticle-laden contact lens using statistical experimental design for controlled ocular drug delivery

This study aims to formulate and evaluate Eudragit nanoparticles-laden hydrogel contact lenses for controlled delivery of acetazolamide (ACZ) using experimental design. Eudragit S-100 was selected for the preparation of nanoparticles. The optimization of Eudragit S100 concentration (X1), polyvinyl alcohol concentration (X2), and the sonication time (X3) was attempted by applying a central composite experimental design. Mean size of nanoparticles (nm), percent in vitro drug release and drug leaching from the ACZ-ENs laden contact lens were considered as dependent variables. Nanoparticles-laden contact lens was prepared through the direct loading method and characterized. Optimum check-point formulation was selected based on validated quadratic polynomial equations developed using response surface methodology. The optimized formulation of ACZ-ENs exhibited spherical shape with a size of 244.3 nm and a zeta potential of −13.2 mV. The entrapment efficiency of nanoparticles was found to be 82.7 ± 1.21%. Transparent contact lenses loaded ACZ-ENs were successfully prepared using the free radical polymerization technique. ACZ-ENs incorporated in contact lens exhibited a swelling of 83.4 ± 0.82% and transmittance of 80.1 ± 1.23%. ACZ-ENs showed a significantly lower burst release of the drug when incorporated in the contact lens and release was sustained over a period of 24 h. The sterilized formulation of ACZ-ENs laden contact lens did not show any sign of toxicity in rabbit eyes. ACZ-ENs incorporated in contact lens could be considered as a potential alternative in glaucoma patients due to their ability to provide sustained drug release and thus enhance patient compliance.

Optimal Checkpointing Strategy for Real-time Systems with Both Logical and Timing Correctness

Real-time systems are susceptible to adversarial factors such as faults and attacks, leading to severe consequences. This paper presents an optimal checkpoint scheme to bolster fault resilience in real-time systems, addressing both logical consistency and timing correctness. First, we partition message-passing processes into a directed acyclic graph (DAG) based on their dependencies, ensuring checkpoint logical consistency. Then, we identify the DAG’s critical path, representing the longest sequential path, and analyze the optimal checkpoint strategy along this path to minimize overall execution time, including checkpointing overhead. Upon fault detection, the system rolls back to the nearest valid checkpoints for recovery. Our algorithm derives the optimal checkpoint count and intervals, and we evaluate its performance through extensive simulations and a case study. Results show a 99.97% and 67.86% reduction in execution time compared to checkpoint-free systems in simulations and the case study, respectively. Moreover, our proposed strategy outperforms prior work and baseline methods, increasing deadline achievement rates by 31.41% and 2.92% for small-scale tasks and 78.53% and 4.15% for large-scale tasks.

Optimal Scheme Models with Imperfect Checkpoint

We propose optimal checkpointing models for dual and majority decision structures with imperfect checkpoints. In systems with high reliability, the process returns to the previous checkpoint when errors occur. However, in real-time systems, if the process always returns to the previous checkpoint, its process might not end in time. In this paper, we propose extended checkpoint models in which when errors occur, the process makes forward and backward recoveries, i.e., the process makes the same one again or returns to the first one with some probability. Using dual and majority decision structures as processing modules, these models are applied to constant and random tasks for the processing of objective works. Furthermore, it is shown that processing models are given by the more general forms using a K-out-of-n system. We formulate simultaneous renewal equations for imperfect models and solve them skillfully, using mathematical methods. The mean execution times until the process succeeds are obtained, and optimal policies to minimize them are derived analytically. These results include the former ones and would be useful for some practical checkpoint models.

Abstract 1836: Combining a novel retinoic acid receptor-γ agonist with immune checkpoint blockade represses lung cancer growth in vivo

Abstract All-trans-retinoic acid (ATRA), a pan-agonist for retinoic acid receptors (RARs), regulates diverse cellular functions including growth, differentiation and immune function. We report here that ATRA-treatment represses tumor growth in syngeneic, immunocompetent but not in immunodeficient mice. Tumor immune microenvironment was implicated since depletion of cytotoxic T lymphocytes antagonized these effects in syngeneic mice. Combining ATRA with immune checkpoint blockade did not inhibit lung cancer growth in mice. We sought to augment retinoid anti-tumor effects without affecting its pro-tumorigenicity. We previously reported that CD38 mediated resistance to checkpoint blockade in murine 344SQ lung cancer cells via RARα transcriptional activation of CD38 expression. Yet, combining the RARα antagonist (IRX6696) with anti-PD-L1 did not augment anti-tumorigenicity in transplanted 344SQ cells in syngeneic mice. Prior work implicated RARγ in regulating T cell response. Combining the novel RARγ agonist (IRX4647) with anti-PD-L1 statistically-significantly repressed 344SQ lung cancer cell growth in syngeneic mice. This line is relatively resistant to checkpoint blockade. Immunofluorescent analysis of these treated tumors revealed that combined IRX4647 and anti-PD-L1 treatments reduced CD38 expression in the tumor stroma relative to IRX4647 or anti-PD-L1 treatment alone. Statistically-significantly elevated helper (CD4+) T cells were detected in treated tumors along with increased IL-5 and IL-13 expression observed in plasma and tumors. These cytokines can activate helper T cells, altering lung cancer growth. These microenvironment effects were associated with in vivo anti-tumorigenicity. IRX4647-treatment did not appreciably alter in vitro growth of lung cancer cells although retinoid receptors expression profiles were affected. Pharmacokinetic study of IRX4647 found its plasma half-life was 6 hours. Combining an RARγ agonist with immune checkpoint blockade exerted superior anti-neoplastic efficacy against lung cancer versus an ATRA-based regimen. Given these findings we propose exploring activity of this RARγ agonist with an optimal checkpoint inhibitor in a lung cancer clinical trial. Citation Format: Cheng-Hsin Wei, Lu Huang, Blair Kreh, Xiuxia Liu, Liliya Tyutyunyk-Massey, Zibo Chen, Mi Shi, Vidyasagar Vuligonda, Martin Sanders, Serguei Kozlov, King Chan, Amir Horowitz, Mary Carrington, Patrick Hwu, Weiyi Peng, Ethan Dmitrovsky, Xi Liu. Combining a novel retinoic acid receptor-γ agonist with immune checkpoint blockade represses lung cancer growth in vivo [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2023; Part 1 (Regular and Invited Abstracts); 2023 Apr 14-19; Orlando, FL. Philadelphia (PA): AACR; Cancer Res 2023;83(7_Suppl):Abstract nr 1836.

Federated Learning with Research Prototypes: Application to Multi-Center MRI-based Detection of Prostate Cancer with Diverse Histopathology.

Early prostate cancer detection and staging from MRI is extremely challenging for both radiologists and deep learning algorithms, but the potential to learn from large and diverse datasets remains a promising avenue to increase their performance within and across institutions. To enable this for prototype-stage algorithms, where the majority of existing research remains, we introduce a flexible federated learning framework for cross-site training, validation, and evaluation of custom deep learning prostate cancer detection algorithms. We introduce an abstraction of prostate cancer groundtruth that represents diverse annotation and histopathology data. We maximize use of this groundtruth if and when they are available using UCNet, a custom 3D UNet that enables simultaneous supervision of pixel-wise, region-wise, and gland-wise classification. We leverage these modules to perform cross-site federated training using 1400+ heterogeneous multi-parameteric prostate MRI exams from two University hospitals. We observe a positive result, with significant improvements in cross-site generalization performance with negligible intra-site performance degradation for both lesion segmentation and per-lesion binary classification of clinically-significant prostate cancer. Cross-site lesion segmentation performance intersection-over-union (IoU) improved by 100%, while cross-site lesion classification performance overall accuracy improved by 9.5-14.8%, depending on the optimal checkpoint selected by each site. Federated learning can improve the generalization performance of prostate cancer detection models across institutions while protecting patient health information and institution-specific code and data. However, even more data and participating institutions are likely required to improve the absolute performance of prostate cancer classification models. To enable adoption of federated learning with limited re-engineering of federated components, we open-source our FLtools system at https://federated.ucsf.edu, including examples that can be easily adapted to other medical imaging deep learning projects.

Checkpointing Workflows à la Young/Daly Is Not Good Enough

This article revisits checkpointing strategies when workflows composed of multiple tasks execute on a parallel platform. The objective is to minimize the expectation of the total execution time. For a single task, the Young/Daly formula provides the optimal checkpointing period. However, when many tasks execute simultaneously, the risk that one of them is severely delayed increases with the number of tasks. To mitigate this risk, a possibility is to checkpoint each task more often than with the Young/Daly strategy. But is it worth slowing each task down with extra checkpoints? Does the extra checkpointing make a difference globally? This article answers these questions. On the theoretical side, we prove several negative results for keeping the Young/Daly period when many tasks execute concurrently, and we design novel checkpointing strategies that guarantee an efficient execution with high probability. On the practical side, we report comprehensive experiments that demonstrate the need to go beyond the Young/Daly period and to checkpoint more often for a wide range of application/platform settings.

Optimal checkpointing for adjoint multistage time-stepping schemes

We consider checkpointing strategies that minimize the number of recomputations needed when performing discrete adjoint computations using multistage time-stepping schemes that require computing several substeps within one complete time step. Specifically, we propose two algorithms that can generate optimal checkpointing schedules under weak assumptions. The first is an extension of the seminal Revolve algorithm adapted to multistage schemes. The second algorithm, named CAMS, is developed based on dynamic programming, and it requires the least number of recomputations when compared with other algorithms. The CAMS algorithm is made publicly available in a library with bindings to C and Python. Numerical results show that the proposed algorithms can deliver up to two times the speedup compared with that of classical Revolve. Moreover, we discuss the utilization of the CAMS library in mature scientific computing libraries and demonstrate the ease of using it in an adjoint workflow. The proposed algorithms have been adopted by the PETScTSAdjoint library. Their performance has been demonstrated with a large-scale PDE-constrained optimization problem on a leadership-class supercomputer. This work is a significant extension of the authors’ conference paper (Zhang and Constantinescu, 2021).

The optimal strategy balancing risk and speed predicts DNA damage checkpoint override times.

Checkpoints arrest biological processes allowing time for error correction. The phenomenon of checkpoint override (also known as checkpoint adaptation, slippage, or leakage), during cellular self-replication is biologically critical but currently lacks a quantitative, functional, or system-level understanding. To uncover fundamental laws governing error-correction systems, we derived a general theory of optimal checkpoint strategies, balancing the trade-off between risk and self-replication speed. Mathematically, the problem maps onto the optimization of an absorbing boundary for a random walk. We applied the theory to the DNA damage checkpoint (DDC) in budding yeast, an intensively researched model checkpoint. Using novel reporters for double-strand DNA breaks (DSBs), we first quantified the probability distribution of DSB repair in time including rare events and, secondly, the survival probability after override. With these inputs, the optimal theory predicted remarkably accurately override times as a function of DSB numbers, which we measured precisely for the first time. Thus, a first-principles calculation revealed undiscovered patterns underlying highly noisy override processes. Our multi-DSB measurements revise well-known past results and show that override is more general than previously thought.

Optimal Checkpointing Strategies for Iterative Applications

This work provides an optimal checkpointing strategy to protect iterative applications from fail-stop errors. We consider a general framework, where the application repeats the same execution pattern by executing consecutive iterations, and where each iteration is composed of several tasks. These tasks have different execution lengths and different checkpoint costs. Assume that there are <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">n</i> tasks and that task a <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">i</sub> , where 0 ≤ i <; <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">n</i> , has execution time t <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">i</sub> and checkpoint cost c <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">i</sub> . A naive strategy would checkpoint after each task. Another naive strategy would checkpoint at the end of each iteration. A strategy inspired by the Young/Daly formula would work for √{2 μc <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">ave</sub> } seconds, where μ is the application MTBF and c <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">ave</sub> is the average checkpoint time, and checkpoint at the end of the current task (and repeat). Another strategy, also inspired by the Young/Daly formula, would select the task a <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">min</sub> with smallest checkpoint cost c <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">min</sub> and would checkpoint after every p <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">th</sup> instance of that task, leading to a checkpointing period p T, where T = Σ <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">i=0</sub> <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">n-1</sup> a <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">i</sub> is the time per iteration. One would choose the period so that p T ≈ √{2 μc <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">min</sub> } to obey the Young/Daly formula. All these naive and Young/Daly strategies are suboptimal. Our main contribution is to show that the optimal checkpoint strategy is globally periodic, and to design a dynamic programming algorithm that computes the optimal checkpointing pattern. This pattern may well checkpoint many different tasks, and this across many different iterations. We show through simulations, both from synthetic and real-life application scenarios, that the optimal strategy outperforms the naive and Young/Daly strategies.

Optimal checkpoint strategies balancing risk and speed

Why biological quality-control systems fail is often mysterious. Checkpoints in yeast and animals are overridden (adapt) after prolonged arrests allowing self-replication to proceed despite the continued presence of errors. Although critical for biological systems, checkpoint adaptation is not understood quantitatively or at the system level by experiment or theory. To uncover potential patterns in checkpoint adaptation, we derived the mathematically optimal checkpoint strategy, balancing the trade-off between risk and opportunities for growth.

Fc-null anti-PD-1 monoclonal antibodies deliver optimal checkpoint blockade in diverse immune environments

BackgroundDespite extensive clinical use, the mechanisms that lead to therapeutic resistance to anti-programmed cell-death (PD)-1 monoclonal antibodies (mAbs) remain elusive. Here, we sought to determine how interactions between the Fc...

Optimizing checkpoint‐based fault‐tolerance in distributed stream processing systems: Theory to practice

AbstractFault‐tolerance is an essential part of a stream processing system that guarantees data analysis could continue even after failures. State‐of‐the‐art distributed stream processing systems use checkpointing to support fault‐tolerance for stateful computations where the state of the computations is periodically persisted. However, the frequency of performing checkpoints impacts the performance (utilization, latency, and throughput) of the system as the checkpointing process consumes resources and time that can be used for actual computations. In practice, systems are often configured to perform checkpoints based on crude values ignoring factors such as checkpoint and restart costs, leading to suboptimal performance. In our previous work, we proposed a theoretical optimal checkpoint interval that maximizes the system utilization for stream processing systems to minimize the impact of checkpointing on system performance. In this article, we investigate the practical benefits of our proposed theoretical optimal by conducting experiments in a real‐world cloud setting using different streaming applications; we use Apache Flink, a well‐known stream processing system for our experiments. The experiment results demonstrate that an optimal interval can achieve better utilization, confirming the practicality of the theoretical model when applied to real‐world applications. We observed utilization improvements from 10% to 200% for a range of failure rates from 0.3 failures per hour to 0.075 failures per minute. Moreover, we explore how performance measures: latency and throughput are affected by the optimal interval. Our observations demonstrate that significant improvements can be achieved using the optimal interval for both latency and throughput.

Realizing Best Checkpointing Control in Computing Systems

This article considers best checkpointing control realizable in real-world systems, whose mean time between failures (MTBFs) often fluctuate. The considered control scheme is based on equating aggregate checkpointing overhead over an activity sequence of interest (θ) and the expected rework amount after a failure recovery for best checkpointing, called “CHORE” (i.e., checkpointing overhead and rework equated), where θ starts from execution resumption after failure recovery and ends after restore from the following failure. CHORE lets its inter-checkpoint intervals in θ follow a pre-determined sequence independent of MTBF to aim at performance optimality and is shown analytically to keep overall execution time overhead upper bounded. When failure occurrences are tracked during job execution for real-time MTBF estimation, an enhanced CHORE (dubbed En-CHORE) is obtained to lower checkpointing overhead by skipping certain checkpoints at the beginning of each θ before taking checkpoints with the most desirable inter-checkpoint intervals determined on-the-fly for best checkpointing control. En-CHORE can outperform optimal checkpointing (which follows a fixed inter-checkpoint interval optimized for one constant global MTBF known a prior) both under synthetic random failures with local MTBF fluctuating markedly and under real failure traces of 22 real HPC systems (whose failure rates actually fluctuate over their trace time spans).

Research on Optimal Checkpointing-Interval for Flink Stream Processing Applications

Nowadays various distributed stream processing systems (DSPSs) are employed to process the ever-expanding real-time data. The DSPSs are highly susceptible to system failure, and the fault-tolerance issue is a major problem, which is getting lot of attention nowadays. Flink is a popular streaming computing framework that implements a lightweight, asynchronous checkpoint technique based on the barrier mechanism to ensure high efficiency in analysing the data. In a checkpoint-based fault-tolerance mechanism, a shorter checkpoint interval can increase runtime cost of streaming applications, while a longer one will increase recovery time of failure recovery. So, selecting an optimal checkpoint interval is critical to attain high efficiency of the streaming applications. Traditional optimal checkpoint interval mechanisms usually assume that the checkpointing delay and the fault recovery time are fixed. However, both factors have a strong relation to the intensity of the application’s workload. To obtain more optimal checkpoint interval under different workload intensities, this paper proposes a performance model to estimate the tuples processing latency and a recovery model to estimate the fault recovery time. With these two models, an optimal checkpoint interval can be arrived. These models and the interval optimisation interval are verified experimentally on Flink. The results show that the proposed model can recommend an optimal checkpoint interval according to the system reliability related indicators. This proposed system optimised recovery time and performs efficiently in applications with delay constraints.

Tight Bounds on Online Checkpointing Algorithms

The problem of online checkpointing is a classical problem with numerous applications that has been studied in various forms for almost 50 years. In the simplest version of this problem, a user has to maintain k memorized checkpoints during a long computation, where the only allowed operation is to move one of the checkpoints from its old time to the current time, and his goal is to keep the checkpoints as evenly spread out as possible at all times. Bringmann, Doerr, Neumann, and Sliacan studied this problem as a special case of an online/offline optimization problem in which the deviation from uniformity is measured by the natural discrepancy metric of the worst case ratio between real and ideal segment lengths. They showed this discrepancy is smaller than 1.59-o(1) for all k and smaller than ln 4-o(1)≈ 1.39 for the sparse subset of k ’s, which are powers of 2. In addition, they obtained upper bounds on the achievable discrepancy for some small values of k . In this article, we solve the main problems left open in the above-mentioned paper by proving that ln 4 is a tight upper and lower bound on the asymptotic discrepancy for all large k and by providing tight upper and lower bounds (in the form of provably optimal checkpointing algorithms, some of which are in fact better than those of Bringmann et al.) for all the small values of k ≤ 10. In the last part of the article, we describe some new applications of this online checkpointing problem.

Optimal equidistant checkpointing of fault tolerant systems subject to correlated failure

Checkpointing is a technique to back up work at periodic intervals so that if computation fails, it will not be necessary to restart from the beginning but will instead be able to restart from the latest checkpoint. Performing checkpointing operations requires time. Therefore, it is necessary to consider the tradeoff between the time to perform checkpointing operations and the time saved when computation restarts at a checkpoint. This article presents a method to model the impact of correlated failures on an application that performs a specified amount of computation and implements checkpointing operations at equidistant periods during this computation. We develop a Markov model and superimpose a correlated life distribution. Two cases are considered. The first assumes that reaching a checkpoint resets the failure distribution. The second allows the probability of failure to progress. We illustrate the approach through a series of examples. The results indicate that correlation can negatively impact checkpointing, necessitating more frequent checkpointing and increasing the total time required, but that the approach can still identify the optimal number of equidistant checkpoints, despite this correlation.

A utilization model for optimization of checkpoint intervals in distributed stream processing systems

State-of-the-art distributed stream processing systems such as Apache Flink and Storm have recently included checkpointing to provide fault-tolerance for stateful applications. This is a necessary eventuality as these systems head into the Exascale regime, and is evidently more efficient than replication as state size grows. However current systems use a nominal value for the checkpoint interval, indicative of assuming roughly 1 failure every 19 days, that does not take into account the salient aspects of the checkpoint process, nor the system scale, which can readily lead to inefficient system operation. To address this shortcoming, we provide a rigorous derivation of utilization – the fraction of total time available for the system to do useful work – that incorporates checkpoint interval, failure rate, checkpoint cost, failure detection and restart cost, depth of the system topology and message delay. Our model yields an elegant expression for utilization and provides an optimal checkpoint interval given these parameters, interestingly showing it to be dependent only on checkpoint cost and failure rate. We confirm the accuracy and efficacy of the model through simulations and experiments with Apache Flink. Observations of the simulations validate our theoretical model and demonstrate that utilization can be improved using the derived optimal checkpoint interval. Moreover, experimental results with Apache Flink show that we can obtain improvements in system utilization for every case we tested, especially as the system size increases. Our model provides a solid theoretical basis for the analysis and optimization of more elaborate checkpointing approaches.

MULTS: A multi-cloud fault-tolerant architecture to manage transient servers in cloud computing

The large-scale utilization of cloud computing resources has led to the emergence of cloud environment reliability as an important issue. In addition, cloud providers are negotiating unreliable virtual machines as a result of exploring unused resources offering them as transient servers - a lower price virtual machine service with resource revocations without user intervention. To increase the availability of transient servers, we propose a multi-cloud fault-tolerant architecture to provide a resilient environment using a scenario-based optimal checkpoint in a scheme to guarantee running processes with reduced user costs. The architecture combines a heuristic to extract information from a case-based reasoning and a statistical model to predict failure events helping to refine fault tolerance parameters. As a result, a cloud environment with better levels of reliability and reduced execution time is provided. Extensive simulations show high levels of accuracy reaching up to 92% survival prediction success rate and a gain of 74,58% of execution time reduction for long running applications. The results are promising, indicating that the proposed architecture can prevent revocation failures under realistic working conditions.

Compressive least-squares migration with on-the-fly Fourier transforms

Least-squares reverse time migration is a powerful approach for true-amplitude seismic imaging of complex geologic structures, but the successful application of this method is currently hindered by its enormous computational cost, as well as its high memory requirements for computing the gradient of the objective function. We have tackled these problems by introducing an algorithm for low-cost sparsity-promoting least-squares migration using on-the-fly Fourier transforms. We formulate the least-squares migration objective function in the frequency domain (FD) and compute gradients for randomized subsets of shot records and frequencies, thus significantly reducing data movement and the number of overall wave equations solves. By using on-the-fly Fourier transforms, we can compute an arbitrary number of monochromatic FD wavefields with a time-domain (TD) modeling code, instead of having to solve individual Helmholtz equations for each frequency, which becomes computationally infeasible when moving to high frequencies. Our numerical examples demonstrate that compressive imaging with on-the-fly Fourier transforms provides a fast and memory-efficient alternative to TD imaging with optimal checkpointing, whose memory requirements for a fixed background model and source wavelet are independent of the number of time steps. Instead, the memory and additional computational costs grow with the number of frequencies and determine the amount of subsampling artifacts and crosstalk. In contrast to optimal checkpointing, this offers the possibility to trade the memory and computational costs for image quality or a larger number of iterations and is advantageous in new computing environments such as the cloud, where computing is often cheaper than memory and data movement.

An optimal checkpointing model with online OCI adjustment for stream processing applications

SummaryCheckpoint‐based fault‐tolerant (FT) methods have been widely used to enhance the reliability of stream processing systems, but a checkpointing process usually introduces considerable overhead. It is a critical issue to choose the optimal checkpoint interval (OCI) that maximizes the processing efficiency. Traditional OCI models consider the recovery time equals to the execution time from the last checkpoint to the failure moment. However, for stream processing jobs, the recovery time is related to reprocessing workloads, depending on the real‐time input data before a failure. A new model is needed to choose the OCI for stream processing applications. Moreover, the input data rate of a stream processing job fluctuates over time. To solve these problems, we present a novel DSPS OCI (DOCI) model in this paper. We prove that it maximizes the processing efficiency for a given time. We propose an approach to dynamically adjust the OCI for an application to accommodate the workload fluctuations. We conduct simulation experiments to verify the effectiveness of our DOCI model and the efficiency of the online OCI adjustment algorithm. Experimental results with a real‐world dataset show that DOCI achieves an improvement on system efficiency by up to 32%, compared with existing FT approaches.