2 posts tagged with "sharding"

This week, the Leios team conducted comprehensive experiments examining protocol variants, conflict handling, and bandwidth requirements. The team also completed the analysis of nine candidate Leios variants with different sharding strategies, performed detailed conflict experiments at 100 TPS, and validated bandwidth requirements across multiple throughput scenarios.

Simulation analysis of protocol variants​

• Completed a comprehensive analysis of nine candidate variants of Leios, examining three basic variants and three sharding strategies:
  • Basic variants: Full, Full without IBs, Full with transaction references
  • Sharding strategies: unsharded, sharded, overcollateralized 1x
• Identified significant differences in spatial and temporal efficiencies across variants:
  • Full with transaction references achieved the highest spatial efficiency (95.999-96.466%)
  • Full without IBs demonstrated the fastest time to the ledger (43.052-43.057s)
  • Sharded variants generally showed improved spatial efficiency but increased latency
• Documented detailed findings in the analysis notebook.

Conflict experiments​

• Conducted experiments exploring the effect of conflicting transactions at 100 TPS using the simplest Leios variant
• Tested scenarios with 0%, 25%, and 50% of transactions conflicting with other transactions
• Key findings from the conflict analysis:
  • Spatial efficiency can be as low as 55% due to occasional IB production before the previous reception
  • All non-conflicted transactions reach the ledger within 75 seconds
  • NIC bandwidth of 20 Mb/s is sufficient for protocol operation
  • Four vCPU cores provide adequate processing capacity
  • Large IBs (up to 2 MB) diffuse globally within five seconds
  • IB traffic does not interfere with other protocol message types.

Bandwidth experiments​

• Completed experiments exploring bandwidth limitations at 100 TPS and 300 TPS documented in the bandwidth analysis
• Validated protocol parameters for high performance: mini-mainnet topology, 1-2 IB/s, 10 slot/stage, 328 kB/IB maximum, 1.5 EB/stage, and multiple shards
• Key performance findings:
  • Achieved 80% spatial efficiency across tested scenarios
  • All transactions reach the ledger within two minutes
  • 30 Mbps NIC bandwidth is sufficient for Leios node operation
  • Four-core vCPU provides adequate processing capacity
  • Insensitive results to inter-nodal link bandwidths above 50 Mb/s
  • Even 10 Mb/s links show minimal impact on protocol performance.

Rust simulation improvements​

• Added support for IB equivocation (work in progress, evaluating impact)
• Implemented minor usability improvements to the CLI tool
• Added sharding support to the 'full without IBs' variant of Leios.

CDDL Version 1​

• finalized and merged a first version of the CDDLs for the current variants in discussion for CIP, here in PR-396.

This week, the Leios team made significant progress in simulation capabilities, with a successful comparison of Rust and Haskell simulations across 90 scenarios. A mainnet-scale analysis of Leios on a realistic 3,000-node network revealed unexpected performance benefits from network topology. Insights from sharding performance analysis provided important optimization strategies. Finally, the team refined both simulation implementations for greater realism and comparability, while the formal methods team developed initial trace verification tools for Short Leios.

Simulation comparison​

• Compared 90 scenarios between Rust and Haskell simulations at tag leios-2025w11
• Recent fixes and adjustments enabled meaningful comparison between simulations
• Identified issues requiring further investigation.

Analysis of mainnet-scale simulation​

• Completed the first analysis of Leios on a mainnet-scale network simulation using the Rust simulator
• Discovered that a 3,000-node mainnet-scale network transports IBs faster than an artificial 100-node network
• Identified 'shortcut' edges in larger networks as a likely factor in the improved transport speed.

Performance analysis of sharding​

• Created computational models to analyze the relationship between the fraction of shards without an IB and the expected number of extra IBs
• Evaluated performance characteristics of the simplest sharding scheme.

Haskell simulation​

• Fixed a bug in the relay protocol that prevented full diffusion of votes
• Adjusted the priority of certified EBs for inclusion in RBs
• Added support for an output log format that shares a common subset with the Rust simulator
• Analyzed TCP realism in comparison to idealized diffusion:
  • Discovered that higher IB rates and sizes improve diffusion times
  • Identified ledger state access as a significant source of latency.

Rust simulation​

• Expanded logs to include total IB size and parent ID of RBs
• Implemented the same EB selection strategy as in the Haskell simulation
• Added validation of IB headers before propagation to neighbors
• Investigating lower congestion in the Rust simulation compared to Haskell.

Formal methods​

• Developed the initial trace verifier for Short Leios simulation traces in leios-trace-verifier.

Research​

• Progressing on ledger design by exploring options and trade-offs
• Analyzing how concurrent input blocks in Leios create unique ledger-level challenges not present in Praos
• Evaluating approaches that balance multiple properties, including:
  • Conflict avoidance in the blockchain
  • Guaranteed fee payment for block producers
  • Transaction eligibility and inclusion speed
  • User experience regarding fee payment
• Investigating sharding-based solutions with various optimization strategies
• Planning to share more detailed findings at Leios public meeting by the end of March
• Targeting a comprehensive recommendation for implementors by the end of April.

From Short Leios to Full Leios​

• Planning the simulation roadmap for transitioning from Short Leios (currently implemented) to Full Leios
• Developing implementation guidelines for simulators to incorporate the pipeline referencing scheme specified in the papers
• Identifying key components needed to simulate the complete ledger inclusion guarantees of Full Leios.