---
title: Efficiency and cost
description: Fewer bucket requests, less memory, and the s3bench harness over upstream denoland/celld.
---

Every bucket request and every resident megabyte is your bill. These patches cut both, with measurements you can re-run in `tools/s3bench/`. Bucket-posture group commit has its own [fleet section](/project/what-cello-adds/fleet-durability). Each entry names its fork patch number.

## Spend fewer bucket requests

- `0054` — Eviction skips visibility LISTs it can prove locally; see [storage](/project/what-cello-adds/storage). Measured on 200 short-lived Durable Objects (6 writes each, `CELLO_DURABILITY=bucket`): 12 Class-A requests per cell before, 9 after.
- `0055` — A lone fleet node slows its posture-repair scan: while a `maintain` pass finds no eligible peer, the wait before the next pass doubles from one second up to the 30 s maintenance tick. The flat retry cost a lone node about 2.6M LIST plus 2.6M GET a month doing nothing. A degraded ensemble that lost all its followers still retries at once, so it re-recruits the moment one returns.
- `0056` — Concurrent bucket-posture writes on one cell share ownership reads; see [storage](/project/what-cello-adds/storage). Measured on one hot cell with 16 concurrent writers: GET `cells/*/own.json` 1550 → 553 at the same throughput.
- `0057` — Eviction deletes the superseded per-cell L0/L1 objects behind the handoff snapshot; see [storage](/project/what-cello-adds/storage). Measured on the 200-agent shape: stored `cells/` bytes 2.47 MB → 0.57 MB, objects 1800 → 400.
- `0061` — Warm eviction guards HEAD instead of LIST (see [storage](/project/what-cello-adds/storage)): one Class-B HEAD replaces one Class-A LIST.
- `0071` — Idle bundle GC goes quiet (see [fleet and durability](/project/what-cello-adds/fleet-durability)): an idle bucket node costs one discovery LIST and then nothing until it writes, instead of one LIST per 30 s tick (~2880 Class-A a day). Also fixes the bucket hot-cell double-write (per-cell L0s beside every bundle flush).
- `0078` — Lazy handoff for short chains: an eviction skips the full-database handoff snapshot when the cell's restorable chain was born in this epoch, every acked row is already per-cell, and the chain holds at most 16 objects (`HANDOFF_CHAIN_MAX_OBJECTS`) — a successor restores the short L0 chain instead, a bounded number of Class-B GETs replacing one Class-A PUT plus a full-database upload per eviction. Modelled on ClickHouse MergeTree's lazy merges; cells restored from an older epoch and longer chains still snapshot. Measured (200 agents × 6 writes, bucket, release builds): Class A 1934 → 1734 (−10%), write p50 unchanged at 210 ms.

## Hold less memory and start faster

- `0065` — The sampler tick returns glibc free pages past `CELLO_C_TRIM_MB` (default 8, was a 32 MiB const). Measured post-drain RSS 72.0 → 61.9 MiB on the agent-50 s3bench shape. See [configuration](/reference/configuration).
- `0066` — `CELLO_SQLITE_CACHE_KB` caps the per-connection SQLite page cache (default 2000, the stock ceiling: no behavior change).
- `0067` — A deployment generation projects its `/bundle` tree once instead of once per isolate; read-only semantics unchanged.
- `0102` — Hydration counting is O(1) (see [storage](/project/what-cello-adds/storage)): an 8.9 GB whale's fill no longer walks the whole cut per faulted read.

## Measure it yourself

- `0058` — A reproducible S3 request-cost harness in `tools/s3bench/`: `proxy.py` logs one JSON line per request in front of the S3 endpoint, `count.py` classifies the log into `METHOD x key-family` counts with an R2 Class A/B summary, `stored.py` inventories stored `cells/` objects and bytes, `app/` is a minimal Worker + SQLite Durable Object app, and `run.sh` drives the agent workload (or one hot cell with `HOT=1`) against a local RustFS container. New files only; nothing under `tools/` runs in CI.
- `0069` — The s3bench agent workload drives its agents concurrently — one thread and connection per agent on its own phase — so arrivals look like independent clients and cross-cell group commit can batch. The serial walk kept at most one cell in flight and could never batch.
- `0072` — The s3bench drivers report per-turn latency (`mean`, `p50`, `p95`, `p99`, nearest-rank, whole ms) next to the request counts, so ack-latency regressions show beside the savings.
- `0076` — `run.sh` defaults `CELLO_BIN` to `target/release/cello` and refuses to start while another `cello-s3bench-*` container is up (unless `S3BENCH_ALLOW_PARALLEL=1`), after debug-vs-release and dueling-harness skews polluted two `.11` measurements.

For how Cello tests correctness — conformance, TLA+, hostile-schedule simulation — read [how Cello is tested](/concepts/testing).
