Search NASA⌕ Search

SEARCH · Search NASA

Results for “checkpointing”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 19 records

Lazy Checkpointing: Exploiting Temporal Locality in Failures to Mitigate Checkpointing Overheads on Extreme-Scale Systems, In: 2014 44th Annual IEEE/IFIP International Conference on Dependable Systems and Networks

Continuing increase in the computational power of supercomputers has enabled large-scale scientific applications in the areas of astrophysics, fusion, climate and combustion to run larger and longer-running simulations, facilitating deeper scientific insights. However, these long-running simulations are often interrupted by multiple system failures. Therefore, these applications rely on "check pointing'" as a resilience mechanism to store application state to permanent storage and recover from failures. Unfortunately, check pointing incurs excessive I/O overhead on supercomputers due to large size of checkpoints, resulting in a sub-optimal performance and resource utilization. In this paper, we devise novel mechanisms to show how check pointing overhead can be mitigated significantly by exploiting the temporal characteristics of system failures. We provide new insights and detailed quantitative understanding of the check pointing overheads and trade-offs on large-scale machines. Our prototype implementation shows the viability of our approach on extreme-scale machines.

Computer Science↗

Scalable Incremental Checkpointing using GPU-Accelerated De-Duplication

Writing large amounts of data concurrently to stable storage is a typical I/O pattern of many HPC workflows. This pattern introduces high I/O overheads and results in increased storage space utilization especially for workflows that need to capture the evolution of data structures with high frequency as checkpoints. In this context, many applications, such as graph pattern matching, perform sparse updates to large data structures between checkpoints. For these applications, incremental checkpointing techniques that save only the differences from one checkpoint to another can dramatically reduce the checkpoint sizes, I/O bottlenecks, and storage space utilization. However, such techniques are not without challenges: it is non-trivial to transparently determine what data has changed since a previous checkpoint and assemble the differences in a compact fashion that does not result in excessive metadata. State-of-art data reduction techniques (e.g., compression and de-duplication) have significant limitations when applied to modern HPC applications that leverage GPUs: slow at detecting the differences, generate a large amount of metadata to keep track of the differences, and ignore crucial spatiotemporal checkpoint data redundancy. This paper addresses these challenges by proposing a Merkle tree-based incremental checkpointing method to exploit GPUs' high memory bandwidth and massive parallelism. Experimental results at scale show a significant reduction of the I/O overhead and space utilization of checkpointing compared with state-of-the-art incremental checkpointing and compression techniques.

Tan, Nigel↗

Optimizing checkpoint data placement with guaranteed burst buffer endurance in large-scale hierarchical storage systems

Non-volatile devices, such as SSDs, will be an integral part of the deepening storage hierarchy on large-scale HPC systems. These devices can be on the compute nodes as part of a distributed burst buffer service or they can be external. Wherever they are located in the hierarchy, one critical design issue is the SSD endurance under the write-heavy workloads, such as the checkpoint I/O for scientific applications. For these environments, it is widely assumed that checkpoint operations can occur once every 60 min and for each checkpoint step as much as half of the system memory can be written out. Unfortunately, for large-scale HPC applications, the burst buffer SSDs can be worn out much more quickly given the extensive amount of data written at every checkpoint step. One possible solution is to control the amount of data written by reducing the checkpoint frequency. However, a direct effect caused by reduced checkpoint frequency is the increased vulnerability window of system failures and therefore potentially wasted computation time, especially for large-scale compute jobs.

Computer Science↗

Toward an optimal online checkpoint solution under a two-level HPC checkpoint model

The traditional single-level checkpointing method suffers from significant overhead on large-scale platforms. Hence, multilevel checkpointing protocols have been studied extensively in recent years. The multilevel checkpoint approach allows different levels of checkpoints to be set (each with different checkpoint overheads and recovery abilities), in order to further improve the fault tolerance performance of extreme-scale HPC applications. How to optimize the checkpoint intervals for each level, however, is an extremely difficult problem. In this paper, we construct an easy-to-use two-level checkpoint model. Checkpoint level 1 deals with errors with low checkpoint/recovery overheads such as transient memory errors, while checkpoint level 2 deals with hardware crashes such as node failures. Compared with previous optimization work, our new optimal checkpoint solution offers two improvements: (1) it is an online solution without requiring knowledge of the job length in advance, and (2) it shows that periodic patterns are optimal and determines the best pattern. We evaluate the proposed solution and compare it with the most up-to-date related approaches on an extreme-scale simulation testbed constructed based on a real HPC application execution. Simulation results show that our proposed solution outperforms other optimized solutions and can improve the performance significantly in some cases. Specifically, with the new solution the wall-clock time can be reduced by up to 25.3% over that of other state-of-the-art approaches. Lastly, a brute-force comparison with all possible patterns shows that our solution is always within 1% of the best pattern in the experiments.

97 MATHEMATICS AND COMPUTING↗

The unexpected virtue of almost: Exploiting MPI collective operations to approximately coordinate checkpoints

Summary Coordinated checkpoint/restart is currently the dominant approach to mitigating the impact of failures on important scientific applications running on large‐scale distributed systems. However, there is widespread evidence that coordinated checkpointing may no longer be viable on next‐generation systems. Uncoordinated checkpoint/restart attempts to address the shortcomings of coordinated checkpoint/restart by allowing application processes to checkpoint their state independently. However, eliminating coordination may significantly degrade application performance. In this paper, we propose an approach that leverages existing coordination in important scientific applications to approximately coordinate checkpoints. Specifically, we propose to extend MPI implementations to force checkpoints to occur immediately after the completion of a collective operation. We evaluate the performance implications of this approach using an existing validated simulation framework. Our results demonstrate that approximately coordinated checkpointing can significantly improve application performance relative to totally uncoordinated checkpointing. We also show that forcing checkpoints to occur following a collective operation has a small impact on the nominal checkpoint interval for several important workloads. As a whole, the results presented in this paper demonstrate that approximately coordinated checkpointing may provide significant performance benefits without significantly increasing the cost of failure recovery.

Levy, Scott↗

Asynchronous Checkpoint Migration with MRNet in the Scalable Checkpoint / Restart Library

Applications running on today's supercomputers tolerate failures by periodically saving their state in checkpoint files on stable storage, such as a parallel file system. Although this approach is simple, the overhead of writing the checkpoints can be prohibitive, especially for large-scale jobs. In this paper, we present initial results of an enhancement to our Scalable Checkpoint/Restart Library (SCR). We employ MRNet, a tree-based overlay network library, to transfer checkpoints from the compute nodes to the parallel file system asynchronously. This enhancement increases application efficiency by removing the need for an application to block while checkpoints are transferred to the parallel file system. We show that the integration of SCR with MRNet can reduce the time spent in I/O operations by as much as 15x. However, our experiments exposed new scalability issues with our initial implementation. We discuss the sources of the scalability problems and our plans to address them.

97 MATHEMATICS AND COMPUTING↗

Evaluating Online Global Recovery with Fenix Using Application-Aware In-Memory Checkpointing Techniques

Exascale systems promise the potential for computation at unprecedented scales and resolutions, but achieving exascale by the end of this decade presents significant challenges. A key challenge is due to the very large number of cores and components and the resulting mean time between failures (MTBF) in the order of hours or minutes. Since the typical run times of target scientific applications are longer than this MTBF, fault tolerance techniques will be essential. An important class of failures that must be addressed is process or node failures. While checkpoint/restart (C/R) is currently the most widely accepted technique for addressing processor failures, coordinated, stable-storage-based global C/R might be unfeasible at exascale when the time to checkpoint exceeds the expected MTBF. This paper explores transparent recovery via implicitly coordinated, diskless, application-driven checkpointing as a way to tolerate process failures in MPI applications at exascale. The discussed approach leverages User Level Failure Mitigation (ULFM), which is being proposed as an MPI extension to allow applications to create policies for tolerating process failures. Specifically, this paper demonstrates how different implementations of application-driven in-memory checkpoint storage and recovery compare in terms of performance and scalability. We also experimentally evaluate the effectiveness and scalability of the Fenix online global recovery framework on a production system -the Titan Cray XK7 at ORNL- and demonstrate the ability of Fenix to tolerate dynamically injected failures using the execution of four benchmarks and mini-applications with different behaviors.

97 MATHEMATICS AND COMPUTING↗

A survey on checkpointing strategies: Should we always checkpoint à la Young/Daly?

The Young/Daly formula provides an approximation of the optimal checkpointing period for a parallel application executing on a supercomputing platform. It was originally designed to handle fail-stop errors for preemptible tightly-coupled applications, but has been extended to other application and resilience frameworks. Here, we provide some background and survey various scenarios to assess the usefulness and limitations of the formula, both for preemptible applications and workflow applications represented as a graph of tasks. We also discuss scenarios with uncertainties, and extend the study to silent errors. We exhibit cases where the optimal period is of a different order than that dictated by the Young/Daly formula, and finally we explain how checkpointing can be further combined with replication.

97 MATHEMATICS AND COMPUTING↗

DNA damage checkpoint recovery and cancer development

Cell cycle checkpoints were initially presumed to function as a regulator of cell cycle machinery in response to different genotoxic stresses, and later found to play an important role in the process of tumorigenesis by acting as a guard against DNA over-replication. As a counterpart of checkpoint activation, the checkpoint recovery machinery is working in opposition, aiming to reverse the checkpoint activation and resume the normal cell cycle. The DNA damage response (DDR) and oncogene induced senescence (OIS) are frequently found in precancerous lesions, and believed to constitute a barrier to tumorigenesis, however, the DDR and OIS have been observed to be diminished in advanced cancers of most tissue origins. These findings suggest that when progressing from pre-neoplastic lesions to cancer, DNA damage checkpoint barriers are overridden. How the DDR checkpoint is bypassed in this process remains largely unknown. Activated cytokine and growth factor-signaling pathways were very recently shown to suppress the DDR and to promote uncontrolled cell proliferation in the context of oncovirus infection. In recent decades, data from cell line and tumor models showed that a group of checkpoint recovery proteins function in promoting tumor progression; data from patient samples also showed overexpression of checkpoint recovery proteins in human cancer tissues and a correlation with patients' poor prognosis. In this review, the known cell cycle checkpoint recovery proteins and their roles in DNA damage checkpoint recovery are reviewed, as well as their implications in cancer development. This review also provides insight into the mechanism by which the DDR suppresses oncogene-driven tumorigenesis and tumor progression. - Highlights: • DNA damage checkpoint works as a barrier to cancer initiation. • DDR machinary response to genotoxic and oncogenic stress in similar way. • Checkpoint recovery pathways provide active signaling in cell cycle control. • Checkpoint recovery pathway plays a role in overriding tumor barrier in tumorigenesis. • Recovery protein dysregulation and human cancer development is correlated.

60 APPLIED LIFE SCIENCES↗

Combined Radiation Therapy and Immune Checkpoint Blockade Therapy for Breast Cancer

Purpose: Treatment with checkpoint inhibitors has shown durable responses in a number of solid tumors, including melanoma, lung, and renal cell carcinoma. However, most breast cancers are resistant to monotherapy with checkpoint inhibitors. Radiation therapy (RT) has been shown to have a number of immunostimulatory effects, including priming the immune system, recruiting immune cells to the tumor environment, and altering the immunosuppressive effects of the tumor microenvironment. RT therefore represents a promising adjuvant therapy to checkpoint blockade in breast cancer. Methods and Materials: We review the data from the checkpoint blockade studies on breast cancer reported to date, the mechanisms by which RT potentiates immune responses, the preclinical and clinical data of checkpoint blockade and RT combinations, and the landscape of current clinical trials of RT and immune checkpoint inhibitor combinations in breast cancer. Results: Clinical trials with checkpoint blockade therapy have demonstrated response rates of up to 19% in breast cancer, and many of the responses are durable. Preclinical data indicate that RT combined with checkpoint inhibition synergizes not only to enhance antitumor efficacy but also to induce responses outside of the radiation field. Thus multiple clinical trials are currently investigating the combination of checkpoint inhibition with RT. Conclusions: The use of combination strategies that incorporate chemotherapy and/or local strategies such as RT may be needed to augment responses to immune therapy in breast cancer. Preclinical and clinical results show that RT in combination with checkpoint blockade may be a promising therapeutic option in breast cancer.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Detailed Modeling and Evaluation of a Scalable Multilevel Checkpointing System

High-performance computing (HPC) systems are growing more powerful by utilizing more components. As the system mean time before failure correspondingly drops, applications must checkpoint frequently to make progress. But, at scale, the cost of checkpointing becomes prohibitive. A solution to this problem is multilevel checkpointing, which employs multiple types of checkpoints in a single run. Moreover, lightweight checkpoints can handle the most common failure modes, while more expensive checkpoints can handle severe failures. We designed a multilevel checkpointing library, the Scalable Checkpoint/Restart (SCR) library, that writes lightweight checkpoints to node-local storage in addition to the parallel file system. We present probabilistic Markov models of SCR's performance. We show that on future large-scale systems, SCR can lead to a gain in machine efficiency of up to 35 percent, and reduce the load on the parallel file system by a factor of two. In addition, we predict that checkpoint scavenging, or only writing checkpoints to the parallel file system on application termination, can reduce the load on the parallel file system by 20 × on today's systems and still maintain high application efficiency.

97 MATHEMATICS AND COMPUTING↗

Asynchronous Two-Level Checkpointing Scheme for Large-Scale Adjoints in the Spectral-Element Solver Nek5000

Adjoints are an important computational tool for large-scale sensitivity evaluation, uncertainty quantification, and derivative-based optimization. An essential component of their performance is the storage/recomputation balance in which efficient checkpointing methods play a key role. We introduce a novel asynchronous two-level adjoint checkpointing scheme for multistep numerical time discretizations targeted at large-scale numerical simulations. The checkpointing scheme combines bandwidth-limited disk checkpointing and binomial memory checkpointing. Based on assumptions about the target petascale systems, which we later demonstrate to be realistic on the IBM Blue Gene/Q system Mira, we create a model of the expected performance of our checkpointing approach and validate it using the highly scalable Navier-Stokes spectralelement solver Nek5000 on small to moderate subsystems of the Mira supercomputer. In turn, this allows us to predict optimal algorithmic choices when using all of Mira. We also demonstrate that two-level checkpointing is significantly superior to single-level checkpointing when adjoining a large number of time integration steps. To our knowledge, this is the first time two-level checkpointing had been designed, implemented, tuned, and demonstrated on fluid dynamics codes at large scale of 50k+ cores.

Adjoints↗

McrEngine: A Scalable Checkpointing System Using Data-Aware Aggregation and Compression

High performance computing (HPC) systems use checkpoint-restart to tolerate failures. Typically, applications store their states in checkpoints on a parallel file system (PFS). As applications scale up, checkpoint-restart incurs high overheads due to contention for PFS resources. The high overheads force large-scale applications to reduce checkpoint frequency, which means more compute time is lost in the event of failure. We alleviate this problem through a scalable checkpoint-restart system, mcrEngine. McrEngine aggregates checkpoints from multiple application processes with knowledge of the data semantics available through widely-used I/O libraries, e.g., HDF5 and netCDF, and compresses them. Our novel scheme improves compressibility of checkpoints up to 115% over simple concatenation and compression. Our evaluation with large-scale application checkpoints show that mcrEngine reduces checkpointing overhead by up to 87% and restart overhead by up to 62% over a baseline with no aggregation or compression.

Islam, Tanzima Zerin↗

Detailed Modeling, Design, and Evaluation of a Scalable Multi-level Checkpointing System

High-performance computing (HPC) systems are growing more powerful by utilizing more hardware components. As the system mean-time-before-failure correspondingly drops, applications must checkpoint more frequently to make progress. However, as the system memory sizes grow faster than the bandwidth to the parallel file system, the cost of checkpointing begins to dominate application run times. A potential solution to this problem is to use multi-level checkpointing, which employs multiple types of checkpoints with different costs and different levels of resiliency in a single run. The goal is to design light-weight checkpoints to handle the most common failure modes and rely on more expensive checkpoints for less common, but more severe failures. While this approach is theoretically promising, it has not been fully evaluated in a large-scale, production system context. To this end we have designed a system, called the Scalable Checkpoint/Restart (SCR) library, that writes checkpoints to storage on the compute nodes utilizing RAM, Flash, or disk, in addition to the parallel file system. We present the performance and reliability properties of SCR as well as a probabilistic Markov model that predicts its performance on current and future systems. We show that multi-level checkpointing improves efficiency on existing large-scale systems and that this benefit increases as the system size grows. In particular, we developed low-cost checkpoint schemes that are 100x-1000x faster than the parallel file system and effective against 85% of our system failures. This leads to a gain in machine efficiency of up to 35%, and it reduces the the load on the parallel file system by a factor of two on current and future systems.

99 GENERAL AND MISCELLANEOUS↗

Reliable and Efficient Distributed Checkpointing System for Grid Environments

In Fine-Grained Cycle Sharing (FGCS) systems, machine owners voluntarily share their unused CPU cycles with guest jobs, as long as their performance degradation is tolerable. However, unpredictable evictions of guest jobs lead to fluctuating completion times. Checkpoint-recovery is an attractive mechanism for recovering from such “failures”. Today’s FGCS systems often use expensive, high-performance dedicated checkpoint servers. However, in geographically distributed clusters, this may incur high checkpoint transfer latencies. Here we present a distributed checkpointing system called FALCON that uses available disk resources of the FGCS machines as shared checkpoint repositories. However, an unavailable storage host may lead to loss of checkpoint data. Therefore, we model the failures of a storage host and develop a prediction algorithm for choosing reliable checkpoint repositories. We experiment with FALCON in the university-wide Condor testbed at Purdue and show improved and consistent performance for guest jobs in the presence of irregular resource availability.

checkpoint↗

RNA interference regulates the cell cycle checkpoint through the RNA export factor, Ptr1, in fission yeast

Highlights: Black-Right-Pointing-Pointer RNAi is linked to the cell cycle checkpoint in fission yeast. Black-Right-Pointing-Pointer Ptr1 co-purifies with Ago1. Black-Right-Pointing-Pointer The ptr1-1 mutation impairs the checkpoint but does not affect gene silencing. Black-Right-Pointing-Pointer ago1{sup +} and ptr1{sup +} regulate the cell cycle checkpoint via the same pathway. Black-Right-Pointing-Pointer Mutations in ago1{sup +} and ptr1{sup +} lead to the nuclear accumulation of poly(A){sup +} RNAs. -- Abstract: Ago1, an effector protein of RNA interference (RNAi), regulates heterochromatin silencing and cell cycle arrest in fission yeast. However, the mechanism by which Ago1 controls cell cycle checkpoint following hydroxyurea (HU) treatment has not been elucidated. In this study, we show that Ago1 and other RNAi factors control cell cycle checkpoint following HU treatment via a mechanism independent of silencing. While silencing requires dcr1{sup +}, the overexpression of ago1{sup +} alleviated the cell cycle defect in dcr1{Delta}. Ago1 interacted with the mRNA export factor, Ptr1. The ptr1-1 mutation impaired cell cycle checkpoint but gene silencing was unaffected. Genetic analysis revealed that the regulation of cell cycle checkpoint by ago1{sup +} is dependent on ptr1{sup +}. Nuclear accumulation of poly(A){sup +} RNAs was detected in mutants of ago1{sup +} and ptr1{sup +}, suggesting there is a functional link between the cell cycle checkpoint and RNAi-mediated RNA quality control.

60 APPLIED LIFE SCIENCES↗

On The Theory of Speculative Checkpointing: Time and Energy Considerations

Collective checkpoint-rollback is the most popular approach to dealing with fail-stop errors on high-performance computing (HPC) platforms. Prior work has focused on choosing checkpoint intervals that minimize the total cost of checkpoint-rollback. In this paper, we introduce the notion of speculative checkpointing, where we probabilistically skip some checkpoints. Careful choice of check- points to be taken or skipped has the potential to further reduce the total checkpoint-rollback overhead. We mathematically formulate the overall checkpoint-rollback cost in the presence of speculation. We consider the choice of speculation being a fixed probability or a probability distribution. We formulate two criteria to be minimized: total execution time and approximate total energy. We derive the criteria for beneficial speculative checkpointing for exponential and arbitrary failure distributions. Further, we analyze the joint optimization of energy and time to mathematically express the trade-offs.

Subasi, Omer↗