Skip to main content

· One min read
Carlos LopezDeLara

· 2 min read
Michael Karg

High level summary

  • Benchmarking: GHC 9.6.3 benchmarks for node 8.7.2 have been performed.
  • Development: Additional features for our reporting pipeline, while simultaneously reducing dependency footprint.
  • Tracing: Implementation for cardano-tracer to work on handles instead of files; work on New Tracing Quickstart document has begun.
  • Nomad cluster: We're preparing an upgrade to the latest Nomad version.

Low level overview

Benchmarking

We've performed a full set of GHC 9.6.3 benchmarks for node 8.7.2. For recommending GHC9.6 as a default build platform for cardano-node - from a performance perspective - we observe only one residual issue. As a way to address this, we've decided to create a reproduction benchmark targeting the affected component.

Development

Our reporting pipeline will be expanded to support a wider range of rendering formats, as well as report templates. As the pipeline is part of our workbench - and thus gets downloaded and built when entering the workbench shell - it's good practice to keep a small dependency footprint. When reworking the pipeline, we aim to simultaneously reduce dependencies.

Tracing

So far, cardano-tracer has internally been using files, or file names, for the purpose of logging trace messages it receives via forwarding. This is simple, but induces quite some overhead at runtime: files have to be opened and closed for each message. Using and managing open file handles inside cardano-tracer does remove that overhead, but unsurprisingly introduces some complexity into the application code. Currently, we're working on implementing that change.

Furthermore, we're working on a Quickstart document for the new tracing system, with end users as its intended audience. It will contain recommended production use setup(s), and how to efficiently configure and run them step by step. Additionally, it will provide a brief, but comprehensive overview over the features at the user's disposal.

Nomad backend

On the Nomad cluster, we've experienced undesired system behaviour when the heartbeat between the Nomad server and a client is interrupted temporarily - although the Nomad job itself is still 100% functional. A Nomad upgrade to the latest version promises to fix that, but it turn comes with other issues. We're currently working on adapting our automation and deployment around those known issues, before we can eventually apply the upgrade.

· One min read
Kostas Dermentzis

High level summary

The DBSync team has prepared and tested a new db-sync version for mainnet, we have continued our integration and update for Conway and have extended its modularity.

Lower level summary

  • We attempt to turn db-sync into a modular project that can run with wither low or high recourses #1610 #1613 #1590

  • Moving the flags above to a config file #1609

  • Optimizations #1595 #1607

  • Conway Support and updates #1581 #1573 #1570

· One min read
Sebastian Nagel

High-level Summary

This week, the Hydra team conducted yearly roadmapping sessions, introduced a breaking API change to eliminate JSON encoding of transactions (refer to issue #1213 for details), completed off-chain logic for incremental decommits through, and implemented a hydra-explorer backend.

What did the team achieve this week

  • Conducted yearly roadmapping sessions
  • Merged a breaking API change to drop JSON encoding of transactions #1213 - contact us if you were relying on this.
  • Completed off-chain logic for incremental decommits #1223
  • Implemented a hydra-explorer backend #1235

What are the goals of next week

  • Publish the monthly report
  • Prepare PRs for hydra clients to switch to CBOR due to the changed API (see above)
  • Enhance the model testing framework to cover close/contest (needed to fix a bug and incremental decommit development)
  • Fix new bugs (all minors) and finish things before starting new

· One min read
Damian Nadales

High level summary

This week the team continued working on the second iteration of the Ledger DB API for UTxO-HD, as well as on Genesis. We incorporated further improvements to the onboarding documentation, and wrote a document explaining a specific subtlety of our chain orders. For Conway, we integrated DReps and initial delegates injection, which will allow the Performance and Tracing team to run benchmarks for this era.