IO Priority: Related Work

Labeling I/O requests globally:

Differentiated storage services 
SOSP 2011 M. Mesnier, F. Chen, T. Luo, and J. B. Akers.
Applications label IO requests. The label then propagates with the requests from the file system to a block device using the SCSI protocol.

Diagnosing performance changes by comparing request flows. NSDI 2011
Diagnosing performance changes by comparing request flows SIGMETRICS 2006
Explicit labels for IO requests in distributed system.

QoS for Storage Systems:

A Fresh Approach to File System Quality of Service NOSSDAV 97
A Practical Learning Approach for Dynamic Storage Bandwidth Allocation IWQoS2003
Providing QoS guarantees for disk I/O. Multimeida Systems, 57-68 Feb 2000
Travelling to Rome: QoS specification for automated stoarage system management, IWQoS 2001

Multi-tenant storage control:

Proportional allocations of resources for distributed storage accesses. FAST 2009
Proportional share scheduling for distributed storage systems. FAST 2007

Performance Insulation for Shared Storage Servers. FAST 2007

Performance Differentiation for storage systems using adaptive control. ACM Transactions on Storage

Performance Isolation and Fairness for multi-tenant cloud storage
David Shue, Michael J. Freedman, and Anees Shaikh.
OSDI, 2012
   
System level max-min fairness at the key-value store level.
Assume well-provisioned network, do not deal with in-network resource sharing.  
They mainly deal with: where to place datasets, where to replicate datasets, how to allocate weights to each node, and how to do faire queuing locally to ensure DRF even though some datasets are more (dynamically) popular than others. (They use DRF so they do deal with multiple resources, namely bytes received, bytes sent, and requests. bytes bound by network/storage, requests bound by interrupts???)