[murex971]

Changes how the cross-shard projection rewrite plan is stored and passed around.

• Route::projection_rewrite_plan and PostRouteRewrite::plan are now Option<Arc<ProjectionRewritePlan>> instead of an inline ProjectionRewritePlan.
• On the common path (direct-to-shard queries, or no rewrite needed) the plan is None.
• build only creates a plan when the rewrite added helper columns. ProjectionRewritePlan no longer derives Clone.

[codecov]

Codecov Report

❌ Patch coverage is 98.46154% with 1 line in your changes missing coverage. Please review.

Files with missing lines	Patch %	Lines
pgdog/src/backend/pool/connection/aggregate.rs	95.83%	1 Missing ⚠️

📢 Thoughts on this report? Let us know!

[github-actions]

Bencher Report

Project	PgDog
Branch	project-rewrite-refactor
Testbed	Intel v1

Click to view all benchmark results

Benchmark	Throughput	Benchmark Result operations / second (ops/s) x 1e3 (Result Δ%)	Lower Boundary operations / second (ops/s) x 1e3 (Limit %)	cpu-per-txn	Benchmark Result Measure (units) (Result Δ%)	Upper Boundary Measure (units) (Limit %)
pooler-v3	📈 view plot 🚷 view threshold	16.99 ops/s x 1e3 (+0.00%) Baseline: 16.99 ops/s x 1e3	16.82 ops/s x 1e3 (99.00%)	📈 view plot 🚷 view threshold	40.77 units (+0.29%) Baseline: 40.65 units	41.06 units (99.30%)

🐰 View full continuous benchmarking report in Bencher

[github-actions]

Metal bench failed. 1 of 150 measures outside bounds.

suite	throughput	cpu/txn	user cycles/txn	user instr/txn	kernel cycles/txn	ctx/txn
pooler		28.17 (-1.5% ± 0.8%)	27,863 (-1.3% ± 1.2%)	35,236 (-0.3% ± 0.02%)	38,941 (-1.9% ± 1.3%)
lb		29.19 (-1.9% ± 1.0%)	29,159 (-1.3% ± 1.3%)	36,091 (-0.3% ± 0.03%)	40,100 (-2.9% ± 1.6%)
sharding-w2		52.75 (+0.5%)	67,121 (+0.1%)	72,441 (-0.2%)	60,596 (+0.5%)	1.412 (-0.3%)
sharding-w8	159,545 (-0.9%)	45.6 (-0.2%)	65,483 (-1.6%)	56,139 (-0.2%)	51,899 (+1.5%)	0.1517 (+7.1%), bound +3%

Counters per txn

suite	frontend stall	l1i refill	backend stall
pooler	13,774 (-2.2% ± 2.5%)	3,172 (-1.8% ± 1.1%)	2,669 (-0.4% ± 1.2%)
lb	14,474 (-2.4% ± 2.6%)	3,239 (-1.6% ± 1.2%)	2,951 (+0.4% ± 2.0%)
sharding-w2	38,457 (+1.8%)	5,371 (-0.0%)	6,672 (-5.4%)
sharding-w8	35,855 (-3.9%)	4,944 (-1.4%)	9,805 (+4.9%)

Microbench: all 135 measures within bounds.

• extended_cached: 15 of 15 benches faster, median -4.3% ± 0.5%
• extended_cold: 15 of 15 benches faster, median -4.1% ± 0.6%
• simple_cold: 15 of 15 benches faster, median -4.7% ± 0.4%

lb flamegraph vs d74cf08

Open interactive for hover, zoom and search.

Open interactive.

microbench flamegraph vs d74cf08

Open interactive for hover, zoom and search.

Open interactive.

pooler flamegraph vs d74cf08

Open interactive for hover, zoom and search.

Open interactive.

sharding-w2 flamegraph vs d74cf08

Open interactive for hover, zoom and search.

Open interactive.

sharding-w8 flamegraph vs d74cf08

Open interactive for hover, zoom and search.

Open interactive.

Logs

lb, microbench, pooler, sharding-w2, sharding-w8, verdict.json

Compared 773bb04 with d74cf08.

[github-actions]

Bencher Report

Project	PgDog
Branch	project-rewrite-refactor
Testbed	Intel v1

⚠️ WARNING: Truncated view!

The full continuous benchmarking report exceeds the maximum length allowed on this platform.

🚨 3 Alerts

🐰 View full continuous benchmarking report in Bencher