4 posts tagged with "bandwidth"

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 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.

Weekly Meeting​

• Discussed Ethereum's blob approach and its relevance to Leios.
• Considered Leios for storing unstructured, transient data.
• Identified potential use cases and next steps for protocol modeling.

Meeting with Spyros​

• Spyros worked on network simulation for Leios using Peernet.
• Focused on bandwidth as a limiting factor and explored block generation frequency limits.

Structuring Repository for Open-source​

• Added basic instructions for Code of Conduct, Contribution guidelines, and coding standards.
• Restructured code to merge leios and leios-sim packages.

Weekly Meeting​

• Discussed Ethereum's blob approach and its relevance to Leios.
• Considered Leios for storing unstructured, transient data.
• Identified potential use cases and next steps for protocol modeling.

Meeting with Spyros​

• Spyros worked on network simulation for Leios using Peernet.
• Focused on bandwidth as a limiting factor and explored block generation frequency limits.

Structuring Repository for Open-source​

• Added basic instructions for Code of Conduct, Contribution guidelines, and coding standards.
• Restructured code to merge leios and leios-sim packages.