Fast sensor data insertion using memory logging

نویسندگان

  • Hideyuki KAWASHIMA
  • Motomichi TOYAMA
  • Yuichiro ANZAI
چکیده

The sensor database system to which new sensor data frequently arrive should provide fresh data to its clients. Toward this end, fast sensor data insertion to the database is essential. The bottleneck of the conventional sensor data insertion is disk logging that writes a log record to disk before accessing buffer pool in memory. The purpose of this paper is to show fast sensor data insertion using memory logging that writes a log record to neighboring nodes’ memory. We further propose multiple memory logging which improves the speed of memory logging and the persistence of the memory log records. To accomplish speed improvement, we try two approaches, (1) UDP(User Datagram Protocol), and (2) BPF(Berkeley Packet Filter). To accomplish persistence improvement, we introduce several log servers and a log server manager that manages them. The result of our experiment shows that single memory logging is about 5.20 time and multiple memory logging is about 1.67 times faster than disk logging in the maximum case.

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

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Low Bandwidth Call Trace Logging for Sensor Networks

Call traces can provide detailed insight into the operation of distributed embedded systems. Developers inspect traces to understand and debug systems using manual and automatic techniques such as data mining. Correlation of traces between nodes provides a network level view of system. These traces are typically gathered by logging a globally unique identifier for each called function. Unfortun...

متن کامل

Asynchronous Logging and Fast Recovery for a Large-Scale Distributed In-Memory Storage

Large-scale interactive applications and online graph analytic processing require very fast data access to many small data objects. DXRAM addresses these challenges by keeping all data always in memory of potentially many nodes aggregated in a data center. Data loss in case of node failures is prevented by an asynchronous logging on flash disks. In this paper we present the architecture of a no...

متن کامل

Practical Schemes using Logs for Lightweight Recoverable DSM

In the existing Fault-Tolerant Software Distributed Shared Memory (FT-SDSM) with the message logging, the logs are used only to recover the failed nodes. In our previous work, we have implemented a lightweight logging protocol, called remote logging, on the SDSM for fault tolerance, which incurs low logging overhead with a fast network and a remote memory for back-up data. In this paper, we pro...

متن کامل

Lightweight Message Logging Protocol for Distributed Sensor Networks

Among a lot of rollback-recovery protocols developed for providing fault-tolerance for long-running distributed applications, sender-based message logging with checkpointing is one of the most lightweight fault-tolerance techniques to be capable of being applied in this field, significantly decreasing high failure-free overhead of synchronous logging by using message sender's volatile memory as...

متن کامل

LIS is More: Improved Diagnostic Logging in Sensor Networks with Log Instrumentation Specifications

Detailed diagnostic data is a prerequisite for debugging problems and understanding runtime performance in distributed embedded wireless systems. Severe bandwidth limitations, tight timing constraints, and limited program text space hinder the application of standard diagnostic tools within this domain. Our work introduces the Log Instrumentation Specification (LIS) that drives insertion of low...

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

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2002