• Journal of Information Processing Systems
• /
• v.9 no.2
• /
• pp.205-216
• /
• 2013

In this paper, we analyze a technique for building a high-availability (HA) cluster system. We propose what we have termed the 'Selective Replication Manager (SRM),' which improves the throughput performance and reduces the latency of disk devices by means of a Distributed Replicated Block Device (DRBD), which is integrated in the recent Linux Kernel (version 2.6.33 or higher) and that still provides HA and failover capabilities. The proposed technique can be applied to any disk replication and database system with little customization and with a reasonably low performance overhead. We demonstrate that this approach using SRM increases the disk replication speed and reduces latency by 17% and 7%, respectively, as compared to the existing DRBD solution. This approach represents a good effort to increase HA with a minimum amount of risk and cost in terms of commodity hardware.

• Journal of IKEEE
• /
• v.20 no.2
• /
• pp.167-170
• /
• 2016

Replica bit-line technique is used for making enable signal of sense amplifier which accurately tracks bit-line of SRAM. However, threshold voltage variation in the replica bit-line circuit changes the cell current, which results in variation of the sense amplifier enable time, $T_{SAE}$. The variation of $T_{SAE}$ makes the sensing operation unstable. In this paper, in addition to conventional replica bit-line delay ($RBL_{conv}$), dual replica bit-line delay (DRBD) and multi-stage dual replica bit-line delay (MDRBD) which are used for reducing $T_{SAE}$ variation are briefly introduced, and the maximum possible number of on-cell which can satisfy $6{\sigma}$ sensing yield is determined through simulation at a supply voltage of 0.6V with 14nm FinFET technology. As a result, it is observed that performance of DRBD and MDRBD is improved 24.4% and 48.3% than $RBL_{conv}$ and energy consumption is reduced which 8% and 32.4% than $RBL_{conv}$.

• Proceedings of the Korea Contents Association Conference
• /
• 2008.05a
• /
• pp.529-533
• /
• 2008

Mission Computer performs important role both managing a whole system and dealing with a specific mission in avionics system. In general, the fault of SPOF(Single Point Of Failure) in unity system can lead to failure of whole system. It can cause a failure of a mission and also can threaten to the life of the pilot. So, in this paper, we design the HA(High-availability) system so that dealing with the failure. And we use HA software like Heartbeat, Fake, DRBD and Bonding to managing HA system.

• Proceedings of the Korea Contents Association Conference
• /
• 2008.05a
• /
• pp.547-550
• /
• 2008

Recently, changes in the environment of user-centric internet service such as blog, UCC and IPTV and ubiquitous computing based on web service are needed to high availability system platform. High availability system is to provide safe service continuously even if system failure occurs in clustering system at the network. And it is necessary to synchronize data for reliable service in high availability system. In this paper, I implement DRBD(Disk Replicated Block Device) which is synchronization technique for data of local disks in high availability system.

• The Journal of the Korea Contents Association
• /
• v.8 no.8
• /
• pp.47-56
• /
• 2008

MC(Mission Computer) performs important function in avionics system which tactic data processing, image processing and managing navigation system etc. In general, the fault of SPOF(Single Point Of Failure) in unity system can lead to failure of whole system. It can cause a failure of a mission and also can threaten to the life of the pilot. So, in this paper, we design the HA(Hight-availability) system so that dealing with the failure. And we use HA software like Heartbeat, Fake, DRBD and Bonding to manage HA system. Also we analyze the performance of HA system using the FDT(Fault Detection Time) for fast fault detection and MTTR(Mean Time To Repair) for mission continuity.