Interferences among wireless signals hinder concurrent transmissions such that the throughput of wireless networks decreases. It is well known that link scheduling is an effective way to improve throughput and decrease transmission delay of wireless networks. SINR (Signal to Interference plus Noise Ratio) model accurately describes the inherent characteristics of wireless signal propagation. Therefore, in this paper, an online distributed link scheduling (OLD_LS) algorithm with a constant approximation factor under the SINR model is proposed. Here, online means that nodes can join in and leave from wireless networks. Nodes joining in or leaving from networks arbitrarily reflects the dynamic characteristics of wireless networks. OLD_LS partitions the network region into hexagons and localizes the SINR model, which is a global interference model. A leader election (LE) subroutine in dynamic networks is proposed in this paper. It is shown that if the dynamic rate of nodes is less than 1/ε, LE elects a leader with a high probability and the time complexity is O(logn+logR). Where,ε is a constant and satisfies ε≤5(1-2^1-α/2)/6, with α being the path loss exponent, n is the number of senders and R is the longest link length. To the best of our knowledge, the algorithm proposed in this paper is the first online distributed link scheduling algorithm for dynamic wireless networks.