TY - GEN
T1 - Motivating and modeling SIP offload
AU - Zou, Jia
AU - Dai, Yiqi
N1 - Funding Information:
G.D., G.L and S.B. conceived and led the project, S.B. monitored the literature, G.L. supervised most of the experimental work, B.D., C.M., C.C and A.J. carried out the fabrication of the CZTSSe samples and devices. The I(V) and IQE data were collected by C.C., C.M. and G.L. The optical measurements to derive Eg and photoluminescence were performed by G.R and S.S. The C(V) measurements were performed by G.R. The STEM analysis was conducted by B.D. The XRD refinement analysis was conducted by A.L. The CL measurements were performed by F.D., S.B. and G.D wrote the manuscript, with contributions and feedback from all co-authors; In particular, S.S. wrote the review section, and A.W. reviewed the section. The work at Bath was supported by the EPSRC (Grant No. EP/K016288/1 and EP/L017792/1) and the ERC (Starting Grant 27757).
PY - 2007
Y1 - 2007
N2 - Session Initiation Protocol (SIP) is one building block for IP Multimedia Subsystem (IMS) and Next Generation Network (NGN), and is becoming ubiquitous in Internet telephony services. Therefore, the performance issue of SIP servers is becoming crucial In this paper, SIP stack processing is identified to be CPU-bound in nature and dominates the system overhead for common SIP server scenarios. These facts provide motivations for the idea of SIP offload. We also find that current protocol offload models have not considered program parallelism and can not analyze throughput and latency in together, which makes them difficult to apply to SIP offload. Therefore, a new model is proposed based on 7 ratios capturing fundamental properties of the protocol stack and offload scheme. The model can be applied in prediction of performance gains, selection of parameters for adaptive offloading schemes, and estimation of software or hardware characteristics using observed performance results.
AB - Session Initiation Protocol (SIP) is one building block for IP Multimedia Subsystem (IMS) and Next Generation Network (NGN), and is becoming ubiquitous in Internet telephony services. Therefore, the performance issue of SIP servers is becoming crucial In this paper, SIP stack processing is identified to be CPU-bound in nature and dominates the system overhead for common SIP server scenarios. These facts provide motivations for the idea of SIP offload. We also find that current protocol offload models have not considered program parallelism and can not analyze throughput and latency in together, which makes them difficult to apply to SIP offload. Therefore, a new model is proposed based on 7 ratios capturing fundamental properties of the protocol stack and offload scheme. The model can be applied in prediction of performance gains, selection of parameters for adaptive offloading schemes, and estimation of software or hardware characteristics using observed performance results.
KW - 3G IMS
KW - Model
KW - NGN
KW - Offload
KW - Parallelism
KW - SIP
UR - http://www.scopus.com/inward/record.url?scp=40949155286&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=40949155286&partnerID=8YFLogxK
U2 - 10.1109/ICCCN.2007.4317906
DO - 10.1109/ICCCN.2007.4317906
M3 - Conference contribution
AN - SCOPUS:40949155286
SN - 9781424412518
T3 - Proceedings - International Conference on Computer Communications and Networks, ICCCN
SP - 741
EP - 746
BT - Proceedings of 16th International Conference on Computer Communications and Networks 2007, ICCCN 2007
T2 - 16th International Conference on Computer Communications and Networks 2007, ICCCN 2007
Y2 - 13 August 2007 through 16 August 2007
ER -