This letter considers a wireless M2M communication scenario with a massive number of M2M devices. Each device needs to send its reports within a given deadline and with certain reliability, e. g. 99.99%. A pool of resources available to all M2M devices is periodically available for transmission. The number of transmissions required by an M2M device within the pool is random due to two reasons - random number of arrived reports since the last reporting opportunity and requests for retransmission due to random channel errors. We show how to dimension the pool of M2M-dedicated resources in order to guarantee the desired reliability of the report delivery within the deadline. The fact that the pool of resources is used by a massive number of devices allows to base the dimensioning on the central limit theorem. The results are interpreted in the context of LTE, but they are applicable to any M2M communication system.