• IEMEK Journal of Embedded Systems and Applications
• /
• v.14 no.2
• /
• pp.63-69
• /
• 2019

Recently, ultra-low latency flash storage devices such as Z-SSD and Optane SSD were introduced with the significant technological improvement in the storage devices which provide much faster response time than today's other NVMe SSDs. With such ultra-low latency, $10{\mu}s$, storage devices the cost of context switch could be an overhead during interrupt-driven I/O completion process. As an interrupt-driven I/O completion process could bring an interrupt handling overhead, polling or hybrid-polling for the I/O completion is known to perform better. In this paper, we analyze tail latency problem in a polling process caused by process scheduling in data center environment where multiple applications run simultaneously under one system and we introduce our adaptive polling selection technique which dynamically selects efficient processing method between two techniques according to the system's conditions.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37B no.12
• /
• pp.1208-1218
• /
• 2012

Disseminating broadcast information stably and reliably in IEEE 802.11-like CSMA wireless networks requires that a source should seek collision-free transmission to multiple receivers and keep track of the reception state of the multiple receivers. We propose a simple yet efficient feedback scheme for stable reliable broadcast in wireless networks, called 2-polling feedback, where the state of two receivers are checked by a source before its broadcast transmission attempt We present a performance analysis of the class of reliable broadcast feedback schemes in terms of two performance metrics (packet transmission delay and packet stable time). The analysis results show that the proposed 2-polling feedback scheme outperforms the current existing classes of feedback schemes in the literature, i.e., all-polling feedback and 1-polling feedback. The 2-polling feedback scheme has lower asymptotic complexity than the all-polling feedback, and has the same asymptotic complexity as the 1-polling feedback but exhibits almost 50 % reduction in packet stable time.

• Proceedings of the Korean Information Science Society Conference
• /
• 2000.10c
• /
• pp.183-185
• /
• 2000

본 논문에서는 SNMP를 이용한 Nerwork Management System(NMS)이 Network을 사용하는 Application에 영향을 주지 않도록 하는 Polling 전략과 Model을 설계하였다. 제안된 System은 Network의 각 Client 정보를 처리하는 Agent와 Data 수집 및 제어를 담당하는 Server로 구성된다. Agent는 SNMP Agent 부분과 Network 상태를 Monitoring 하는 SubManager로 구성되어, Server는 SNMP Agent와의 Polling 및 Polling 정책을 결정하는 부분으로 구성된다. 제안 Model은 SNMP를 이용한 NMS를 도입할 경우, 기존 Network Service에 영향을 주지 않도록 하는 것이 목적이다. 제안된 System에 대한 성능평가를 위해 실존하는 Network을 대상으로 SNMP의 Polling 및 Service의 부하량을 측정하였다.

• Journal of the Korean Statistical Society
• /
• v.26 no.3
• /
• pp.355-363
• /
• 1997

In queueing theory, polling systems have been widely studied as a way of serving several stations in cyclic order. In this paper we consider Markov-modulated Poisson process which is useful for approximating a superposition of heterogeneous arrivals. We derive the mean waiting time of each station in a polling system where the arrival process is modeled by a Markov-modulated Poisson process.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.10c
• /
• pp.322-324
• /
• 2004

IEEf 802.11 Point Coordination Function (PCF) mode is defined to support time bounded traffic, such as VoIP in wireless LANs. The poll scheduling plays an important role in IEEE 802.11 PCF mode operation. This paper proposed a Multicast Polling Scheme to increase the performance of wireless LANs. Moreover, we proposed a polling schedule scheme for our proposed multipoll to serve real-time traffic. The results show that the proposed mechanism is more efficient than the original IEEE 802.11 PCF.

• Journal of applied mathematics & informatics
• /
• v.16 no.1_2
• /
• pp.469-481
• /
• 2004

In this paper, we investigate the mean queue length and the mean packet delay of a dynamic bandwidth allocation(DBA) scheme in an Ethernet passive optical network(EPON). We focus on the interleaved polling system with a gated service discipline. We assume that input packets arrive at an optical network unit(ONU) according to Poisson process. We use a continuous time queueing model in order to find the queue length distribution of the gated interleaved polling system with the first stage input queue and the second stage transmission queue. We give some numerical results to investigate the mean queue lengths and mean packet delays for the symmetric polling system with statistically identical stations.

• 한국정보통신설비학회:학술대회논문집
• /
• 2008.08a
• /
• pp.249-252
• /
• 2008

This paper presents a new dynamically adaptable polling scheme for efficient support of real-time traffic over an IEEE 802.11 wireless LAN network. The poll scheduling plays an important role in IEEE 802.11 PCF. However, the current version of the polling list management scheme proposed in the IEEE802.11 standard is inefficient when a variable number of mobile stations have variable packets to transmit. If Point Coordinator has an exact information on the station status, it is possible to efficiently perform polling. In this thesis, we suggest an adaptable polling scheme to meet requirements of the stations. In our scheme, each station transmits packets including a piggyback information to inform that it wants to receive a poll in the next polling duration. Simulation results indicate that our scheme may reduces the packet discard ratio and real-time packet transfer delay.

• Proceedings of the IEEK Conference
• /
• summer
• /
• pp.313-316
• /
• 2004

This paper presents a new dynamically adaptable polling scheme for efficient support of real-time traffic over an IEEE 802.11 wireless LAN network. The poll scheduling plays an important role in IEEE 802.11 PCF. However, the current version of the polling list management scheme proposed in the IEEE802.11 standard is inefficient when a variable number of mobile stations have variable packets to transmit. If Point Coordinator(PC) has an exact information on the station status, it is possible to efficiently perform polling. In this thesis. we suggest an adaptable polling scheme to meet requirements of the stations. In our scheme, each station transmits packets including a piggyback information to inform that it wants to receive a poll in the next polling duration. Simulation results indicate that our scheme may reduces the packet discard ratio and real-time packet transfer delay.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.2A
• /
• pp.80-89
• /
• 2005

In IEEE 802.11 and 802.11e for ad hoc networks, DCF and EDCA use a contention-based protocol called CSMA/CA, which is simple to implement efficient when the system is light loaded. But the performance of CSMA/CA decreases dramatically when the system load is heavy because of increasing collisions. In PCF and HCF modes, stations are controlled by a base station by polling, no collision ever occurs. However, when the system load is light, the performance is poor because few stations have data to transfer. More important, PCF and HCF can not be used in the ad hoc networks. In this paper, we address a priority-based distributed polling mechanism (PDPM) that implements polling scheme into DCF or EDCA modes for ad hoc networks by adding a polling approach before every contention-based procedure. PDPM takes the advantages of polling mechanism that avoids most of collisions in a high load condition. At the same time, it also keeps the contention-based mechanism for a light loaded condition. PDPM provides quality of service (QoS) with fewer collisions and higher throughput compared with IEEE 802.11e.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.32 no.7B
• /
• pp.455-462
• /
• 2007

The GTS(Guaranteed Time Slot) of IEEE802.15.4 standard, which is the contention free access mechanism, has some problems such as the limited number of deployed devices, the low channel utilization and the service confirm delay. The proposed Cyclic-CFA(Contention Free Access) scheme is a modified polling algorithm that allows a large number of devices to be served Contention Free Access without polling packets. The Cyclic-CFA scheme improves the channel utilization dramatically and also reduces service delay time.