Julian Stecklina b6c266c880 vmm: avoid creating large temporary vector during migration ...

... by just passing the iterator along. For large VMs this bitmap is
gigantic. A 12TB VM has 384MB of dirty bitmap.

With all these optimizations from the previous commits in place, we
see quite the improvement when it comes to scanning the dirty bitmap.

For a bitmap with 1% bits (randomly) set, dirty_log() takes:

Original code: 2166ms (100.0%)
New code:       382ms ( 17.6%)

on my system. The sparser the dirty bitmap the faster. Scanning an
empty bitmap is 100x faster. For a 5% populated bitmap we are still 3x
faster.

If someone wants to play with this, there is a benchmark harness here:
https://github.com/blitz/chv-bitmap-bench

On-behalf-of: SAP julian.stecklina@sap.com
Signed-off-by: Julian Stecklina <julian.stecklina@cyberus-technology.de>

2025-11-17 14:34:54 +00:00

..

src

vmm: avoid creating large temporary vector during migration

2025-11-17 14:34:54 +00:00

build.rs

build: Add "fuzzing" as a valid cfg(..) attribute

2024-05-08 08:10:28 +00:00

Cargo.toml

build: Bump the non-rust-vmm group across 2 directories with 25 updates

2025-10-21 09:20:56 +00:00