Files
qdrant/lib/segment/src/common
xzfc bde40eb44a UniversalReadPipeline (#8798)
* UniversalReadPipeline

* Performance: cache pointers in MmapFile

The previous commit removed `MmapFile::read_batch` method override. So,
`MmapFile` now re-uses the default `UniversalRead::read_batch` impl,
which is implemented using `UniversalReadPipeline` interface.

Unsurprisingly, it caused a slowdown in the benchmarks, particularly
this one:

    cargo bench -p common --bench universal_io -- mmap/8bytes/read_batch_full

This commit reclaims the performance back.

* remove unfulfilled lint

* Review suggestions

---------

Co-authored-by: Luis Cossío <luis.cossio@outlook.com>
Co-authored-by: Roman Titov <ffuugoo@users.noreply.github.com>
2026-05-08 13:47:43 +02:00
..
2025-03-21 11:38:56 +01:00
2026-05-08 13:46:42 +02:00
2026-03-26 17:52:01 +01:00
2025-09-29 11:31:11 +02:00