Dynamic replication and migration of data objects with hot-spot and cold-spot statuses across storage data centers

A data replication strategy with tenant performance and provider economic profit guarantees in Cloud data centers

“…It is regarded as an assigned budget value for DCs in Gill and Singh (2016) and modelled in terms of time in Lin et al (2013). In this context, only some strategies (Wu et al, 2013;Zeng et al, 2016;Tos et al, 2017;Casas et al, 2017;Liu and Shen, 2017;Mansouri and Buyya, 2019) model the replication cost and the provider profit as monetary costs while satisfying a tenant RT SLO. Furthermore, they often only consider a per-query replication that immediately responds to any query load or popularity change, but may generate higher RTs and increase overhead costs.…”

“…(ii) Some data replication strategies are based on techniques that achieve specific tenant SLOs. Examples of these techniques are: compression (Liu and Shen, 2016a) for data durability, or for reducing replication bandwidth (Xu et al, 2015), multi-failure resilient scheme (Liu and Shen, 2016b) for enhancing availability, de-duplication (Nicolae, 2015) for reducing data transfer, prefetching (Mansouri and Javidi, 2018), data migration (Mansouri and Buyya, 2019), parallel downloading (Mansouri et al, 2017), data mining (Hamrouni and Charrada, 2015), supervised learning (Bui et al, 2016), overheating similarity of nodes (Sun et al, 2018), partitioning (Zhou and Fan, 2017) for ensuring performance and fragmentation for optimal security (Ali et al, 2018). On the other hand, many corporations, e.g., Facebook, as well as many replication strategies (Bui et al, 2016) are based on the erasure coding technique rather than/in addition to data replication.…”

“…(iii) Although most of the replication strategies cited above have been proposed for a single cloud provider, other replication strategies are deployed across multiple cloud providers (Wu et al, 2013;Mansouri and Buyya, 2019;Abu-Libdeh et al, 2010;Bessani et al, 2011). SpanStore (Wu et al, 2013) spans DCs across multiple cloud providers.…”

“…Pricing discrepancies are exploited in order to minimize costs when considering fault tolerance and latency requirements. Authors in Liu and Shen (2017) and Mansouri and Buyya (2019) focused on the costs of Get/Put operation of data sets. The resource price difference is exploited in Mansouri and Buyya (2019) to minimize the monetary cost of replication with the assumption that the workload on objects is known in advance.…”

“…Authors in Liu and Shen (2017) and Mansouri and Buyya (2019) focused on the costs of Get/Put operation of data sets. The resource price difference is exploited in Mansouri and Buyya (2019) to minimize the monetary cost of replication with the assumption that the workload on objects is known in advance. The work of Liu and Shen (2017) avoids, as in Abu-Libdeh et al (2010), the vendor lock-in problem, i.e., a tenant may not be free to switch from one provider to another.…”