Optimizing virtual machine live storage migration in heterogeneous storage environment

Abstract

Virtual machine (VM) live storage migration techniques significantly increase the mobility and manageability of virtual machines in the era of cloud computing. On the other hand, as solid state drives (SSDs) become increasingly popular in data centers, VM live storage migration will inevitably encounter heterogeneous storage environments. Nevertheless, conventional migration mechanisms do not consider the speed discrepancy and SSD's wear-out issue, which not only causes significant performance degradation but also shortens SSD's lifetime. This paper, for the first time, addresses the efficiency of VM live storage migration in heterogeneous storage environments from a multi-dimensional perspective, i.e., user experience, device wearing, and manageability. We derive a flexible metric (migration cost), which captures various design preference. Based on that, we propose and prototype three new storage migration strategies, namely: 1) Low Redundancy (LR), which generates the least amount of redundant writes; 2) Source-based Low Redundancy (SLR), which keeps the balance between IO performance and write redundancy; and 3) Asynchronous IO Mirroring, which seeks the highest IO performance. The evaluation of our prototyped system shows that our techniques outperform existing live storage migration by a significant margin. Furthermore, by adaptively mixing our proposed schemes, the cost of massive VM live storage migration can be even lower than that of only using the best of individual mechanism.

A Survey on the Use of Preferences for Virtual Machine Placement in Cloud Data Centers

“…Migration cost/overhead [42,47,93,99] • VMs with lower migration overhead are more preferred to migrate.…”

“…Availability/ Reliability [5,99] • Include the degree of PM wear-and-tear (e.g., due to frequent PM ON/OFF cycles) in weighted function.…”

“…Next-Fit and First-Fit Decreasing [23], Opportunistic-Fit [27], Multiple Heuristics [78], repacking algorithm [71] Other Fair proportional scheduler [13] Bin packing [14] - [31] Distributed bartering algorithm [75] Random search (biased statistical sampling) [79] Random search (biased statistical sampling) [84] Bruteforce [87], Constraints-based model [91], NA [99], A framework [57,60], cloud broker [3] Table 2: Existing Approaches that handle preferences in VMP For VMP, preferences have been expressed as a utility function of the administrator for different combinations of SLA satisfaction, reliability and energy [20] and as breaking tie mechanism for final solutions of the MOP [50]. Also, preferences have been used to correlate two VMs to be placed on the same PM based on historical experience and thus minimizing number of active PMs [51] .…”

Challenges and New Solutions for Live Migration of Virtual Machines in Cloud Computing Environments

“…They have faster I/O speed than mechanical Hard Disk Drive (HDD). Zhou et al [206] try to solve the I/O speed disparity problem when migrating VM images between SSD and HDD. They design three migration strategies for different situations: (1) Low Redundancy (LR) mechanism.…”

“…1. Because only one type of computation task is offloaded to an edge cloud data center within a period of time by a UE, we assume that the VMs have a stable memory dirty rate D m and disk dirty rate D s . They are configured based on some previous practical tests [203,206,2]. The network bandwidth available for VM migration is 100MB/s.…”