Rob Norris
Rob Norris
I did a light fio run on a small Celeron J3455 [Goldmont] board with SSE4.2 but no AVX. Using a single-vdev tmpfs-backed pool, no compression: * `generic`: ~3.7MB/s * `pclmulqdq`:...
I highly doubt #15588 will have anything to do with it - it doesn't change TRIM.
Extra for your todo list: `Location:` can now be relative ([7231#7.1.2](https://tools.ietf.org/html/rfc7231#section-7.1.2)). Update: My mistake. I was crashing out in `_split_url`, saw the regex and didn't look deeper. If I had...
[Fast dedup stack rebased to master 3c941d181]
@amotin [last push](https://github.com/openzfs/zfs/compare/83010659ad6ca7749ced0f2d8547168b50496a62..6a9bed1ab57122f72d48f2d11b9a5ebcef5838e1) switches from storing count of blocks to count of bytes, as discussed. Note that it still operates on whole blocks internally, it just changes what we store,...
@adamdmoss > * The changes still need to be taken to completion (ifdefs/xxx) > * I'm concerned about how much this has been exercised, especially when separated from the other...
[Fast dedup stack rebased to master c98295eed]
Alright, so we now have large blocks, and it looks good I think. To clarify some of the above comments, by design, we never write across a block boundary, and...
Alright, big push today: - on-disk formats should now be endian-safe: all u64-based, and use the BF64_* macros to break it down. Untested on a big-endian machine (who has those?)...
Last push fixes that we weren't updating the log stats at checkpoint, which could lead to `zpool status -D` reporting a much larger count of entries until the logs are...