Christian Schwarz 2edbc07733 experiment: demonstrate that std-fs performs better because it hits the page cache ...

... by forcing each write system call to go to disk

test_bulk_insert[neon-release-pg14-tokio-epoll-uring].wal_written: 346 MB
test_bulk_insert[neon-release-pg14-tokio-epoll-uring].wal_recovery: 92.559 s

test_bulk_insert[neon-release-pg14-std-fs].wal_written: 346 MB
test_bulk_insert[neon-release-pg14-std-fs].wal_recovery: 81.998 s

=> 10%ish worse instead of 2x

2024-03-13 15:07:46 +00:00

..

benches

bench_walredo: use tokio multi-threaded runtime (#6743)

2024-02-16 16:31:54 +01:00

client

storage controller: robustness improvements (#7027)

2024-03-07 17:10:03 +00:00

compaction

Minor improvements to tiered compaction (#7020)

2024-03-05 16:26:51 +01:00

ctl

pageserver: optimise disk io for vectored get (#6780)

2024-02-28 12:06:00 +00:00

pagebench

pageserver: optimise disk io for vectored get (#6780)

2024-02-28 12:06:00 +00:00

src

experiment: demonstrate that std-fs performs better because it hits the page cache

2024-03-13 15:07:46 +00:00

test_data

Add walingest test (#5892)

2023-11-28 12:50:53 -05:00

Cargo.toml

Add new compaction abstraction, simulator, and implementation. (#6830)

2024-02-27 17:15:46 +01:00