🤖 AI Summary
This work addresses performance inconsistency and global I/O throttling failure in disaggregated storage clusters caused by cross-generational heterogeneous hardware and skewed access patterns. To this end, the authors propose IORM, a multi-stage distributed I/O resource manager featuring four key innovations: a hardware-transparent I/O accounting mechanism, a datasheet-based hardware-aware cost model, a quantum throttling policy supporting micro-bursts and credit carryover, and a distributed adaptive feedback controller capable of dynamically reallocating quotas. Experimental evaluation demonstrates that IORM supports 100 concurrent tenant volumes on an 8-node cluster, achieves throttling error below 5% under extreme sequential access skew, eliminates tenant interference entirely, and restores full throughput within 15 seconds following a storage node failure.
📝 Abstract
Shared-nothing disaggregated storage clusters that serve both latency-sensitive databases and opaque block-volume workloads face two governance problems unsolved by existing schedulers: maintaining consistent performance across heterogeneous hardware generations, and enforcing global I/O limits when access patterns skew to a subset of storage nodes. We present the I/O Resource Manager (IORM), a multi-stage distributed scheduler deployed in production within Oracle Exadata Exascale. IORM combines three mechanisms: a hardware-aware cost modeler that normalizes I/O accounting using datasheet-derived fixed costs to make limits invariant across hardware generations; a quantum-based rate limiter with bounded carry-forward credits that accommodates database micro-bursts while enforcing long-term SLOs; and a distributed adaptive feedback controller that redistributes unused entitlements across the cluster to resolve topological access skew. Beyond design, we share operational lessons from production deployment. On an 8-node test cluster running up to 100 concurrent tenant volumes, IORM converges within 5\% of provisioned limits under extreme sequential skew, scales without inter-tenant interference, and recovers full throughput within 15 seconds of a storage-node failure.