2 posts tagged with "cddl"

This week, the Leios team achieved significant milestones in protocol development and analysis, successfully demonstrating high-throughput capabilities and exploring new protocol variants. The team completed comprehensive experiments with the Stracciatella variant, conducted analytical analysis of Linear Leios throughput efficiency, and implemented new simulation capabilities.

HIGH-THROUGHPUT DEMONSTRATION​

• Successfully completed experiments demonstrating 1,000+ TPS capability with the Stracciatella variant of Leios.
• Achieved spatial efficiency better than 95% with transaction lifecycle times under two minutes.
• Validated protocol performance under extreme throughput conditions significantly beyond current Cardano capacity.
• Documented detailed findings in the Stracciatella analysis notebook.

PROTOCOL VARIANTS ANALYSIS​

Stracciatella Variant​

• Completed comprehensive analysis of the Stracciatella variant (no IBs, transaction references in EBs, two-stage pipeline).
• Key findings:
  • 5 slot/stage performs less well but scales better than 8 slot/stage.
  • Only minimal fraction of transactions fail to reach ledger, likely due to EB expiration.
  • Network usage is slightly heavy while CPU usage appears suspiciously light.
  • Congestion appears at 1,000+ TPS throughput levels.

Linear Leios Throughput Efficiency​

• Conducted analytical analysis of Linear Leios variant's probability of including certified EBs on-chain.
• Results show Linear Leios could achieve approximately 500 times the throughput of Praos at over 50% network resource efficiency.
• 500 times Praos throughput would exceed 1,000 historically typical transactions per second.
• Generated comprehensive throughput and efficiency visualizations available in the analysis repository.

CDDL SPECIFICATIONS​

• Added CDDL specifications for Linear and Stracciatella protocol variants.

SIMULATION IMPROVEMENTS​

Rust Simulation​

• Implemented first pass at Linear Leios variant in Rust simulation.
• Enhanced simulation capabilities for protocol variant testing and analysis.
• Continued optimization of simulation performance for high-throughput scenarios.

Small Transaction Experiments​

• Completed analysis of small-transaction, high-throughput experiments with 300-byte non-Plutus transactions.
• Key findings:
  • 1,000 tx/s with 300 B/tx is feasible in Leios variants.
  • Clear time vs space tradeoff between variants.
  • full-with-ib-references uses space more efficiently than full-without-ibs.
  • full-without-ibs has shorter transaction lifecycle than full-with-ib-references.
  • 2 CPU cores are sufficient for high-throughput operation.
  • Network usage remains modest under high load.
• Supporting materials available in analysis documentation and analysis notebook.

NEXT STEPS​

• Continue investigation of protocol variants for CIP convergence.
• Expand simulation capabilities for additional protocol variants.
• Refine performance optimization strategies for high-throughput scenarios.
• Complete documentation of protocol variant comparisons and recommendations.

This week, the Leios team conducted extensive experiments using the previously developed network topologies to study transaction and input block throughput limits under realistic conditions. The team also conducted empirical bandwidth measurements between data centers, advanced formal methods capabilities, and created initial CDDL specifications for core Leios components.

CDDL specification draft​

• Created initial CDDL specifications for core Leios components:
  • Input blocks with VRF lottery and single IB/slot limits
  • Endorser blocks as a new aggregation block type
  • Ranking blocks as Conway extension with optional certificates
  • BLS voting system with persistent/non-persistent voters and key registration
• Followed crypto-benchmarks implementation approach while maintaining Conway CDDL compatibility
• Established foundational structures in the first draft covering common base components
• Future iterations will add detailed specifications for design variants, including full sharding, overcollateralization, and protocol extensions.

Formal methods​

• Added support for Late IB inclusion to the formal specification of Full-Short Leios
• Profiled leios-trace-verifier performance, identifying that approximately 60% of execution time is spent in garbage collection
• Improved performance significantly by switching to --nonmoving-gc garbage collection strategy.

Bandwidth measurements​

• Conducted empirical bandwidth measurements using iperf3 between data centers in North America and Europe
• Measured bidirectional connections across multiple cloud providers (OVH, AWS, CenturyLink)
• Results ranged from 95 Mbps to 973 Mbps, depending on geographic distance and the provider
• Identified 100 Mbps as a conservative lower bound for inter-datacenter connections
• Observed 5-20% reduction in individual link speeds when multiple simultaneous connections are active.

Large-scale network experiments​

• Conducted comprehensive experiments using both the 750-node and 10,000-node network topologies with Haskell and Rust simulations
• Studied transaction and IB throughput limits for realistic scenarios up to 300 TPS and 32 IB/s
• Key findings from the 750-node mini-mainnet experiments are documented in analysis results and summary slides:
  • The 750-node mini-mainnet serves as a suitable replacement for the 10,000-node pseudo mainnet for performance measurements
  • Substantial agreement between Haskell and Rust simulations for mini-mainnet scenarios
  • Block propagation times under one second, consistent with empirical observations from pooltool.io
  • Protocol can support 25 MB/s throughput with 1 Gb/s links before degradation
  • Mean transaction time from mempool to ledger is approximately 150 seconds
  • Achieved 80% disk-space efficiency with ~20% network traffic overhead
  • Six-core VM is sufficient for peak demand at 300 TPS, with average demand under two cores
• Results from 10,000-node pseudo-mainnet experiments are available in analysis documentation and presentation slides:
  • Average transaction lifecycle of 100 seconds from mempool to ledger
  • Approximately 80% efficiency for both disk and network usage
  • Six CPU cores are sufficient for peak load handling even at high TPS rates
  • Block propagation time averaged under one second across the large network.