TY - GEN
T1 - Method for measuring the packet processing time of Internet workstations with the detection of interrupt coalescence
AU - Salehin, Khondaker M.
AU - Rojas-Cessa, Roberto
N1 - Publisher Copyright:
© 2016 IEEE.
PY - 2016/7/28
Y1 - 2016/7/28
N2 - The packet processing time (PPT) of an end host (i.e., workstation) is the time elapsed between the arrival of a packet at the data-link layer and the time the packet is processed at the application layer (RFCs 2679). A recent work presented an active scheme to measure PPT over Internet paths using a packet-pair based probing structure considering its importance as a network parameter in the Internet. However, the existing scheme does not consider the effect of interrupt coalescence (IC) in network interface cards (NICs), which are configured with an IC under high transmission speeds. In this paper, we propose an enhancement to the existing scheme for measuring PPT when there is an IC available in the NIC of the workstation under test. The enhanced scheme first detects IC and then measures PPT using the measured gaps of the probing structure. We evaluated the enhanced scheme through testbed experiments using two different workstations and under different transmission speeds, i.e., 10, 100, and 1000 Mb/s. Our results show that the proposed scheme consistently measures PPT with high efficacy.
AB - The packet processing time (PPT) of an end host (i.e., workstation) is the time elapsed between the arrival of a packet at the data-link layer and the time the packet is processed at the application layer (RFCs 2679). A recent work presented an active scheme to measure PPT over Internet paths using a packet-pair based probing structure considering its importance as a network parameter in the Internet. However, the existing scheme does not consider the effect of interrupt coalescence (IC) in network interface cards (NICs), which are configured with an IC under high transmission speeds. In this paper, we propose an enhancement to the existing scheme for measuring PPT when there is an IC available in the NIC of the workstation under test. The enhanced scheme first detects IC and then measures PPT using the measured gaps of the probing structure. We evaluated the enhanced scheme through testbed experiments using two different workstations and under different transmission speeds, i.e., 10, 100, and 1000 Mb/s. Our results show that the proposed scheme consistently measures PPT with high efficacy.
KW - Active measurement
KW - Internet path
KW - compound probe
KW - end-to-end delay
KW - high-speed link
KW - interrupt coalescence
KW - packet pair
KW - packet processing time
UR - http://www.scopus.com/inward/record.url?scp=84991577929&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84991577929&partnerID=8YFLogxK
U2 - 10.1109/HPSR.2016.7525658
DO - 10.1109/HPSR.2016.7525658
M3 - Conference contribution
AN - SCOPUS:84991577929
T3 - IEEE International Conference on High Performance Switching and Routing, HPSR
SP - 142
EP - 147
BT - 2016 IEEE 17th International Conference on High Performance Switching and Routing, HPSR 2016
PB - IEEE Computer Society
T2 - 17th IEEE International Conference on High Performance Switching and Routing, HPSR 2016
Y2 - 14 June 2016 through 17 June 2016
ER -