3 people d92c563b9e perf(ecstore): keep decode scratch buffers inline (#6002) ...

Keep common shard-indexed decode scratch vectors inline while preserving heap fallback for larger supported erasure layouts. Consume scratch iterators directly at the stripe-state boundary to avoid reallocating.

Co-authored-by: heihutu <[email protected]>

2026-08-12 15:40:32 +00:00

..

bitrot.rs

perf(ecstore): reduce inline GET fixed costs (#5985)

2026-08-12 19:29:46 +08:00

decode_reader.rs

…

decode.rs

perf(ecstore): keep decode scratch buffers inline (#6002)

2026-08-12 15:40:32 +00:00

encode.rs

perf(ecstore): reduce small PUT fixed costs (#5987)

2026-08-12 20:07:40 +08:00

erasure.rs

perf(ecstore): reduce small PUT fixed costs (#5987)

2026-08-12 20:07:40 +08:00

heal.rs

…

mod.rs

…