More Like this

1. Building Fast Recoverable Persistent Data Structures with Montage

   https://doi.org/10.4230/LIPIcs.DISC.2020.52  

   Wen, Haosen; Cai, Wentao; Du, Mingzhe; Valpey, Benjamin; Scott, Michael L. (October 2020, Leibniz international proceedings in informatics)

   null (Ed.)

   The recent emergence of fast, dense, nonvolatile main memory suggests that certain long-lived data structures might remain in their natural, pointer-rich format across program runs and hardware reboots. Operations on such structures must be instrumented with explicit write-back and fence instructions to ensure consistency in the wake of a crash. Techniques to minimize the cost of this instrumentation are an active topic of current research. We present what we believe to be the first general-purpose approach to building buffered durably linearizable persistent data structures, and a system, Montage, to support that approach. Montage is built on top of the Ralloc nonblocking persistent allocator. It employs a slow-ticking epoch clock, and ensures that no operation appears to span an epoch boundary. If a crash occurs in epoch e, all work performed in epochs e and e-1 is lost, but all work from prior epochs is preserved. We describe the implementation of Montage, argue its correctness, and report on experiments confirming excellent performance for operations on queues, sets/mappings, and general graphs. 

   more » « less
2. Fast Nonblocking Persistence for Concurrent Data Structures

   https://doi.org/10.4230/LIPIcs.DISC.2021.14  

   Cai, Wentao; Wen, Haosen; Maksimovski, Vladimir; Du, Mingzhe; Sanna, Rafaello; Abdallah, Shreif; Scott, Michael L. (October 2021, 35th Intl. Symp. on Distributed Computing (DISC))

   null (Ed.)

   We present a fully lock-free variant of our recent Montage system for persistent data structures. The variant, nbMontage, adds persistence to almost any nonblocking concurrent structure without introducing significant overhead or blocking of any kind. Like its predecessor, nbMontage is buffered durably linearizable: it guarantees that the state recovered in the wake of a crash will represent a consistent prefix of pre-crash execution. Unlike its predecessor, nbMontage ensures wait-free progress of the persistence frontier, thereby bounding the number of recent updates that may be lost on a crash, and allowing a thread to force an update of the frontier (i.e., to perform a sync operation) without the risk of blocking. As an extra benefit, the helping mechanism employed by our wait-free sync significantly reduces its latency. Performance results for nonblocking queues, skip lists, trees, and hash tables rival custom data structures in the literature – dramatically faster than achieved with prior general-purpose systems, and generally within 50% of equivalent non-persistent structures placed in DRAM. 

   more » « less
3. Buffered Persistence in B+ Trees

   https://doi.org/10.1145/3698801  

   Du, Mingzhe; Scott, Michael_L (December 2024, Proceedings of the ACM on Management of Data)

   Non-volatile Memory (NVM) offers the opportunity to build large, durable B+ trees with markedly higher performance and faster post-crash recovery than is possible with traditional disk- or flash-based persistence. Unfortunately, cache flush and fence instructions, required for crash consistency and failure atomicity on many machines, introduce substantial overhead not present in non-persistent trees, and force additional NVM reads and writes. The overhead is particularly pronounced in workloads that benefit from cache reuse due to good temporal locality or small working sets---traits commonly observed in real-world applications. In this paper, we propose a buffered durable B+ tree (BD+Tree) that improves performance and reduces NVM traffic viarelaxedpersistence. Execution of a BD+Tree is divided intoepochsof a few milliseconds each; if a crash occurs in epoche,the tree recovers to its state as of the end of epoche-2. (The persistence boundary can always be made current with an explicit sync operation, which quickly advances the epoch by 2.) NVM writes within an epoch are aggregated for delayed persistence, thereby increasing cache reuse and reducing traffic to NVM. In comparison to state-of-the-art persistent B+ trees, our micro-benchmark experiments show that BD+Tree can improve throughput by up to 2.4x and reduce NVM writes by up to 90% when working sets are small or workloads exhibit strong temporal locality. On real-world workloads that benefit from cache reuse, BD+Tree realizes throughput improvements of 1.1--2.4x and up to a 99% decrease in NVM writes. Even on uniform workloads, with working sets that significantly exceed cache capacity, BD+Tree still improves throughput by 1--1.3x. The performance advantage of BD+Tree increases with larger caches, suggesting ongoing benefits as CPUs evolve toward gigabyte cache capacities. 

   more » « less
4. Understanding and optimizing persistent memory allocation

   https://doi.org/10.1145/3381898.3397212  

   Cai, Wentao; Wen, Haosen; Beadle, H. Alan; Kjellqvist, Chris; Hedayati, Mohammad; Scott, Michael L. (June 2020, International Symposium on Memory Management)

   The proliferation of fast, dense, byte-addressable nonvolatile memory suggests that data might be kept in pointer-rich “in-memory” format across program runs and even process and system crashes. For full generality, such data requires dynamic memory allocation, and while the allocator could in principle be “rolled into” each data structure, it is desirableto make it a separate abstraction. Toward this end, we introduce _recoverability_, a correctness criterion for persistent allocators, together with a nonblocking allocator, _Ralloc,_ that satisfies this criterion. Ralloc is based on the _LRMalloc_ of Leite and Rocha, with four key innovations: First, we persist just enough information during normal operation to permit a garbage collection (GC) pass to correctly reconstruct the heap in the wake of a full-system crash. Second, we introduce the notion of _filter functions_, which identify the locations of pointers within persistent blocks to mitigate the limitations of conservative GC. Third, we reorganize the layout of the heap to facilitate the incremental allocation of physical space. Fourth, we employ position-independent (offset-based) pointers to allow persistent regions to be mapped at an arbitrary address. Experiments show Ralloc to be performance-competitive with both _Makalu_, the state-of-the-art lock-based persistent allocator, and such transient allocators as LRMalloc and JEMalloc. In particular, reliance on GC and offline metadata reconstruction allows Ralloc to pay almost nothing for persistence during normal operation. 

   more » « less
5. Understanding and optimizing persistent memory allocation

   https://doi.org/10.1145/3332466.3374502  

   Cai, Wentao; Wen, Haosen; Beadle, H. Alan; Hedayati, Mohammad; Scott, Michael L. (February 2020, ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming)

   The proliferation of fast, dense, byte-addressable nonvolatile memory suggests the possibility of keeping data in pointer-rich “in-memory” format across program runs and even crashes. For full generality, such data requires dynamic memory allocation. Toward this end, we introduce _recoverability_, a correctness criterion for persistent allocators, together with a nonblocking allocator, _Ralloc_, that satisfies this criterion. Ralloc is based on _LRMalloc_, with three key innovations. First, we persist just enough information during normal operation to permit reconstruction of the heap after a full-system crash. Our reconstruction mechanism performs garbage collection (GC) to identify and remedy any failure-induced memory leaks. Second, in support of GC, we introduce the notion of _filter functions_, which identify the locations of pointers within persistent blocks. Third, to allow persistent regions to be mapped at an arbitrary address, we employ the position-independent pointer representation of Chen et al., both in data and in allocator metadata. Experiments show that Ralloc provides scalable performance competitive to that of both _Makalu_, the state-of-the-art lock-based persistent allocator, and the best transient allocators (e.g.,_JEMalloc_). 

   more » « less