Fix Rx/Tx statistics overwrite in multi-replica deployments #1035
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
In multi-replica Kubernetes deployments, each replica overwrites database byte counts instead of accumulating them, causing incorrect statistics.
Changes
Delta-based accumulation
peerStatsmap with mutex)Storage.AddByteCounts(publicKey, rxDelta, txDelta)using SQL UPDATE with additionCounter reset handling
Memory management
Implementation
Before:
After:
Each replica independently tracks its connected peers and contributes deltas to the shared database, enabling correct cumulative totals across all replicas.
Warning
Firewall rules blocked me from connecting to one or more addresses (expand for details)
I tried to connect to the following addresses, but was blocked by firewall rules:
dns.ffmuc.netCo-authored-by: Goliath-ifaceassert -W g_.a /tmp/go-build1930920028/b188/ -data-downloader /home/REDACTED/go//opt/hostedtoolcache/go/1.24.11/x64/pkg/tool/linux_amd64/vet rt =0 -data-downloader-buildtags` (dns block)
Original prompt
💬 We'd love your input! Share your thoughts on Copilot coding agent in our 2 minute survey.