TY - GEN
T1 - Understanding on-device bufferbloat for cellular upload
AU - Guo, Yihua
AU - Qian, Feng
AU - Chen, Qi Alfred
AU - Morley Mao, Z.
AU - Sen, Subhabrata
PY - 2016/11/14
Y1 - 2016/11/14
N2 - Despite the extensive characterization of the growth of cellular network traffic, we observe two important trends not yet thoroughly investigated. First, fueled by the LTE technology and applications involving wearable devices and device-Todevice (D2D) communication, device upload traffic is increasingly popular. Second, the multi-Tasking and multiwindow features of modern mobile devices allow many concurrent TCP connections, resulting in potentially complex interactions. Motivated by these new observations, we conduct to our knowledge the first comprehensive characterization of cellular upload traffic and investigate its interaction with other concurrent traffic. In particular, we reveal rather poor performance associated with applications running concurrently with cellular upload traffic, due to excessive ondevice buffering (i.e., on-device bufferbloat). This leads to significant performance degradation on real mobile applications, e.g., 66% of download throughput degradation and more than doubling of page load times. We further systematically study a wide range of solutions for mitigating ondevice bufferbloat, and provide concrete recommendations by proposing a system called QCUT to control the firmware buffer occupancy from the OS kernel.
AB - Despite the extensive characterization of the growth of cellular network traffic, we observe two important trends not yet thoroughly investigated. First, fueled by the LTE technology and applications involving wearable devices and device-Todevice (D2D) communication, device upload traffic is increasingly popular. Second, the multi-Tasking and multiwindow features of modern mobile devices allow many concurrent TCP connections, resulting in potentially complex interactions. Motivated by these new observations, we conduct to our knowledge the first comprehensive characterization of cellular upload traffic and investigate its interaction with other concurrent traffic. In particular, we reveal rather poor performance associated with applications running concurrently with cellular upload traffic, due to excessive ondevice buffering (i.e., on-device bufferbloat). This leads to significant performance degradation on real mobile applications, e.g., 66% of download throughput degradation and more than doubling of page load times. We further systematically study a wide range of solutions for mitigating ondevice bufferbloat, and provide concrete recommendations by proposing a system called QCUT to control the firmware buffer occupancy from the OS kernel.
KW - Bufferbloat
KW - Cellular Networks
KW - Radio Firmware
KW - Upload
UR - http://www.scopus.com/inward/record.url?scp=85000605935&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85000605935&partnerID=8YFLogxK
U2 - 10.1145/2987443.2987490
DO - 10.1145/2987443.2987490
M3 - Conference contribution
AN - SCOPUS:85000605935
T3 - Proceedings of the ACM SIGCOMM Internet Measurement Conference, IMC
SP - 303
EP - 317
BT - IMC 2016 - Proceedings of the 2016 ACM Internet Measurement Conference
PB - Association for Computing Machinery
T2 - 2016 ACM Internet Measurement Conference, IMC 2016
Y2 - 14 November 2016 through 16 November 2016
ER -