AbstractThis paper presents a novel Network Request Scheduler (NRS) for a large-scale, LustreTM
storage system. It proposes a quantum-based, Object Based Round Robin (OBRR) NRS algorithm that
reorders the execution of I/O requests per data object, presenting a workload to backend storage
that can be optimized more easily. According to the drawback of static deadlines in large-scale workloads,
it proposes a novel two-level deadline setting strategy that not only avoids starvation, but also
guarantees that urgent I/O requests are serviced in a specified time period. Via a series
of simulation experiments using a Lustre simulator, it demonstrates that I/O performance increases
as much as 40% when using the OBRR NRS algorithm, and the two-level deadline setting strategy can avoid
starvation and ensure that urgent I/O requests are serviced in the required time.
[1]
Adrien Lèbre,et al.
I/O Scheduling Service for Multi-Application Clusters
,
2006,
2006 IEEE International Conference on Cluster Computing.
[2]
Seetharami R. Seelam,et al.
Enhancements to Linux I/O Scheduling
,
2005
.
[3]
Robert B. Ross,et al.
REACTIVE SCHEDULING FOR PARALLEL I/O SYSTEMS
,
2000
.
[4]
J. R. Santos,et al.
Ext 4 block and inode allocator improvements
,
2010
.
[5]
Andrew A. Chien,et al.
Input/Output Characteristics of Scalable Parallel Applications
,
1995,
SC.
[6]
Carla Schlatter Ellis,et al.
File-Access Characteristics of Parallel Scientific Workloads
,
1996,
IEEE Trans. Parallel Distributed Syst..