News for hackers. Stuff that matters.

A comment on io_uring, libaio performance across Linux kernels and an unexpected IOMMU trap. Parent comment

Re:io_uring, libaio performance across Linux kernels and an ... by jcalvinowens on Tuesday March 24, 2026 @12:48PM (#47505564)
Thanks for sharing this.

Was the iommu using strict or lazy invalidation? I think lazy is the default but I'm not sure how long that's been true.

[ Parent | on HN ]
Re:io_uring, libaio performance across Linux kernels and an ... by eivanov89 on Tuesday March 24, 2026 @01:00PM (#47505772)
We compared IOMMU fully disabled vs enabled. When it is enabled, I expect it to be lazy (should be the default for IOMMU). Note, that we recommend to use passthrough to completely bypass translation for most devices independent on strict/lazy mode.
[ Parent | on HN ]