Skip to content

Conversation

Gregy
Copy link

@Gregy Gregy commented Dec 18, 2016

This modification resulted in large performance gain on my system (5x faster). Reasoning behind this change is that we should not call the kernel with each sector (512b) and instead accumulate more data before sending it.

Please review the change carefully, this is my first encounter with golang and I do not understand it very well (but I used this code to successfully recover my 2T WD drive)

This modification resulted in large performance gain on my system (5x faster).
@wolfgang-noichl
Copy link

No performance benefit for me, but works.

@maxisvk
Copy link

maxisvk commented Feb 13, 2019

test with Intel G5400 change from ~950Kb/s to ~10Mb/s. Also cpu is always at 100% so with faster cpu gain can be better.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants