Evolution of a Communication System for Distributed Transaction Processing in Raid
نویسندگان
چکیده
This paper identifies the basic services required from a communication subsystem to support transaction processing in a distributed, reliable, reconfigurable, and replicated database environment. These services include multicasting, remote procedure calls (RPC), inexpensive datagram services, and efficient local interprocess communication (IPC). We show the evolution of the various versions of Raid communication software and our experience with them. rile show how several ideas such as lightweight protocols, simple naming, memory mapping and shared memory, physical multicasting, direct control passing, and adaptability fulfill the needs for transaction processing. rüe present performance data on these ideas and study their impact on transaction processing. We also use the results of these studies to design and implement a new communication scheme. This scheme has reduced the overhead of communication in Raid distributed database system by up to 70. This research is supported by NASA and AIRMICS under grant number NAG-l-676, NSF grant IRI-8821398, and AT&L @ Computing Systems, Vol. 4 ' No. 3 ' Summer 1991 277
منابع مشابه
Implementation of RAID
This paper describes the implementation of RAID, a robust and adaptable distributed system for transaction processing. RAID is a message-passing system, with several server processes on each site. A high-level, layered communications package provides a clean, location independent interface between servers. RAID processes concurrent updates and retrievals on multiple sites. The servers manage co...
متن کاملAdapting Distributed Database Systems for High Availability
The availability offered by current data replication and update algorithms varies with dynamically changing conditions which include the network configuration and system load. With dynamic adaptability, systems can switch to an appropriate mechanism to improve perFormance and availability, In this paper, we present an algorithm to estimate the overall availability of transaction processing in a...
متن کاملDynamic Multiple Parity (DMP) Disk Array for Serial Transaction Processing
ÐThe performance of today's database systems is usually limited by the speed of their I/O devices. Fast I/O systems can be built from an array of low cost disks working in parallel. This kind of disk architecture is called RAID (Redundant Arrays of Inexpensive Disks). RAID promises improvement over SLED (Single Large Expensive Disks) in performance, reliability, power consumption, and scalabili...
متن کاملTransaction Processing and Consistency Control of Replicated Copies during Failures in Distributed Databases
Consistency of replicated copies is difficult to maintain and recover during multiple failures of sites and network communication in a distributed database system. Transaction processing must continue as long as a single copy is available. But in a multiple failure environment, each operational site must make correct decisions about which copy to update and which one will be updated by the reco...
متن کاملA Model for Adaptable Concurrency Control
This research presents a model for an adaptable system that allows on-line switc:hing of classes of algorithms for database transaction processing. The basic idea is to identify conditions on the state of processing that will maintain consistency during the switch from one class to another. The classes of concurrency control algorithms and the formalism of history for transaction processing and...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
- Computing Systems
دوره 4 شماره
صفحات -
تاریخ انتشار 1991