Opportunities for optimism in contended main-memory multicore transactions

نویسندگان

چکیده

Main-memory multicore transactional systems have achieved excellent performance using single-version optimistic concurrency control (OCC), especially on uncontended workloads. Nevertheless, based other protocols, such as hybrid OCC/ locking and variations multiversion (MVCC), are reported to outperform the best OCC systems, with increasing contention. This paper shows that implementation choices unrelated can explain some of these differences. Our evaluation strengths weaknesses OCC, MVCC, TicToc under varying workloads contention levels, importance several called basis factors. Given sensible factor choices, does not collapse high-contention TPC-C. We also present two optimization techniques, deferred updates timestamp splitting, dramatically improve both MVCC. These techniques known, but we apply them in a new context highlight their potency: when combined, they lead gains $$4.74\times $$ for MVCC $$5.01\times TPC-C workload.

برای دانلود باید عضویت طلایی داشته باشید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Phase Reconciliation for Contended In-Memory Transactions

Multicore main-memory database performance can collapse when many transactions contend on the same data. Contending transactions are executed serially—either by locks or by optimistic concurrency control aborts—in order to ensure that they have serializable effects. This leaves many cores idle and performance poor. We introduce a new concurrency control technique, phase reconciliation, that sol...

متن کامل

Fast Transactions for Multicore In-Memory Databases

Though modern multicore machines have sufficient RAM and processors to manage very large in-memory databases, it is not clear what the best strategy for dividing work among cores is. Should each core handle a data partition, avoiding the overhead of concurrency control for most transactions (at the cost of increasing it for crosspartition transactions)? Or should cores access a shared data stru...

متن کامل

Fast Transactions for Multicore In - Memory Databases by Stephen Lyle

Though modern multicore machines have sufficient RAM and processors to manage very large in-memory databases, it is not clear what the best strategy for dividing work among cores is. Should each core handle a data partition, avoiding the overhead of concurrency control for most transactions (at the cost of increasing it for crosspartition transactions)? Or should cores access a shared data stru...

متن کامل

Speedy transactions in multicore in-memory databases Citation

Silo is a new in-memory database that achieves excellent performance and scalability on modern multicore machines. Silo was designed from the ground up to use system memory and caches efficiently. For instance, it avoids all centralized contention points, including that of centralized transaction ID assignment. Silo’s key contribution is a commit protocol based on optimistic concurrency control...

متن کامل

The Main Memory System: Challenges and Opportunities

The memory system is a fundamental performance and energy bottleneck in almost all computing systems. Recent system design, application, and technology trends that require more capacity, bandwidth, efficiency, and predictability out of the memory system make it an even more important system bottleneck. At the same time, DRAM technology is experiencing difficult technology scaling challenges tha...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: The Vldb Journal

سال: 2022

ISSN: ['0949-877X', '1066-8888']

DOI: https://doi.org/10.1007/s00778-021-00719-9