mgutt Posted March 28, 2021 Share Posted March 28, 2021 Depending on the performance of the HDD and position of the data on the plattern, the writing speed of the parity varies: I think the write speed could be better by raising the chunk/block size, so the amount of re-positionings of the Read-Write-Head is reduced. What is the actual size? Did the Limeteach developers already tested a bigger size? Quote Link to comment
i-chat Posted April 18, 2021 Share Posted April 18, 2021 I’m not very sure on how this works, but by increasing blocksize would that not also mitigate some of the SMR-issues based on what i know, with smr a track will be destroyed if the adjacent track is written and thus has to be re-written. This kind of is why smr is stil oké for linear writes but not for random writes. I would feel that file-system and parity calculation tuning. MAY somewhat mitigate the smr-drawback Quote Link to comment
Recommended Posts
Join the conversation
You can post now and register later. If you have an account, sign in now to post with your account.
Note: Your post will require moderator approval before it will be visible.