Post-crash log processing for fuzzy checkpointing main memory databases

Li, X.; Eich, Margaret H.

doi:10.1109/icde.1993.344071

Cited by 25 publications

(23 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Li et al [17] also suggest run-time optimizations for reduc ing log size by using shadow pages for updates but also require all shadow updates as well as the log buffer to reside in non volatile memory. Lehman and Carey's recovery algorithm [14] also requires presence of non-volatile RAM to be able to store log tails.…”

Section: Related Workmentioning

confidence: 99%

Rethinking main memory OLTP recovery

Malviya¹,

Weisberg²,

Madden³

et al. 2014

2014 IEEE 30th International Conference on Data Engineering

101

View full text Add to dashboard Cite

Abstract-Fine-grained, record-oriented write-ahead logging, as exemplified by systems like ARIES, has been the gold standard for relational database recovery. In this paper, we show that in modern high-throughput transaction processing systems, this is no longer the optimal way to recover a database system. In particular, as transaction throughputs get higher, ARIEs-style logging starts to represent a non-trivial fraction of the overall transaction execution time.We propose a lighter weight, coarse-grained command logging technique which only records the transactions that were executed on the database. It then does recovery by starting from a trans actionally consistent checkpoint and replaying the commands in the log as if they were new transactions. By avoiding the overhead of fine-grained logging of before and after images (both CPU complexity as well as substantial associated 110), command logging can yield significantly higher throughput at run-time.Recovery times for command logging are higher compared to an ARIEs-style physiological logging approach, but with the advent of high-availability techniques that can mask the outage of a recovering node, recovery speeds have become secondary in importance to run-time performance for most applications.We evaluated our approach on an implementation of TPC C in a main memory database system (VoltDB), and found that command logging can offer 1.5 x higher throughput than a main memory optimized implementation of ARIEs-style physiological logging.

show abstract

Section: Related Workmentioning

confidence: 99%

Rethinking main memory OLTP recovery

Malviya¹,

Weisberg²,

Madden³

et al. 2014

2014 IEEE 30th International Conference on Data Engineering

101

View full text Add to dashboard Cite

show abstract

“…As fuzzy checkpointing in MMDB has little synchronization with executing transactions, a consecutive fuzzy checkpointing has been considered in some previous MMDB recovery methods [14,11]. That is, the end chkpt of a checkpoint becomes the begin chkpt of the next checkpoint.…”

Section: Applying To Segmented Mmdbmentioning

confidence: 99%

“…Table 2 shows some parameters and their default values. They are derived from [11] and [14]. For the simplicity, the recovery time of the last complete checkpoint is considered.…”

Section: Performance Evaluationmentioning

confidence: 99%

“…To preserve data against crashes, we need a recovery method that restores MMDB to a consistent state. Many researches have been done in the past for recovery methods in MMDB [2,4,7,8,10,11,14].…”

Section: Introductionmentioning

confidence: 99%

“…As fuzzy checkpointing flushes dirty pages asynchronously against transaction activities, the quiescence of transactions is not required. However, only physical logging scheme was considered in fuzzy checkpointing due to asynchronous flushing in the past MMDB recovery works [5,11,12]. Physical logging causes a recovery time of MMDB to be longer than logical logging.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Accommodating logical logging under fuzzy checkpointing in main memory databases

Woo

Kim

Lee

Proceedings of the 1997 International Database Engineering and Applications Symposium (Cat. No.97TB100166)

View full text Add to dashboard Cite

show abstract

The architecture of the Dalí main memory storage manager

Bohannon¹,

Rastogi²,

Silberschatz

et al. 2002

Bell Labs Tech. J.

View full text Add to dashboard Cite

In a 32‐yr‐old man, an infratentorial cystic lesion with a mural nodule was interpreted to be either a hemangioblastoma or a cystic astrocytoma on CT scan. Intraoperative crush cytology revealed it to be a choroid plexus papilloma (CPP). The utility of crush cytology in the rapid diagnosis of central nervous system (CNS) tumors and the differential diagnosis of CNS papillary lesions are highlighted in this report. Diagn. Cytopathol. 2001;25:165–167. © 2001 Wiley‐Liss, Inc.

show abstract

Post-crash log processing for fuzzy checkpointing main memory databases

Cited by 25 publications

References 8 publications

Rethinking main memory OLTP recovery

Rethinking main memory OLTP recovery

Accommodating logical logging under fuzzy checkpointing in main memory databases

The architecture of the Dalí main memory storage manager

Contact Info

Product

Resources

About