Brian Behlendorf
Brian Behlendorf
Indeed they are according to `/sys/block` output above. The `physical_block_size=4k` and `logical_block_size=512` so I think ZFS is doing the right think by defaulting to 4k (ashift=12) in order avoid a...
If possible could you dump the stack from the `txg_sync` process when this happens.
@cwedgwood It's definitely been a challenging area to get working and is not heavily stress tested on a wide range of kernels. It was working reliably with older zfs releases...
> we'll need to determine how/where to do the preallocation of the ZVOL's blocks (see zvol_prealloc() in illumos); I took a look at [mkswap.c](https://github.com/karelzak/util-linux/blob/master/disk-utils/mkswap.c) and aside from writing a unique...
Systemd umounts dataset under encrypted root because it thinks the encryption root key is not loaded
Let's start by reopening this issue. Do I understand correctly that you were not observing this with 20.04 and ZFS v0.8.5? @aerusso @rlaager any thoughts?
It does seem like ZFS is incorrectly returning `EAGAIN` for `sendfile(2)`. Would it be possible for you to see if this is reproducible with the latest code from the master...
@AeonJJohnson we have made a couple fixes in this area (4b5c9d9f976375ca4f075a533d2b6f0c9a14cf4a 0aacde2e9a818942f4e25ab765b3a4849aac6de8 32366649d3164e994def7e5a26765ca6bc1e2315) over the last year or so, if you can reproduce this on demand I think it'd be...
The intent is to convert everything to `ZFS_MODULE_PARAM` and `ZFS_MODULE_PARAM_CALL`. This is currently the case for all of the common code, however some of the platform specific code may still...
The following new module options were added fir OpenZFS 2.0. They're all described in the man pages but not yet added to this documentation. I've opened PR #76 which which...
I agree, I think some manually testing would be probably sufficient to let us make forward progress on this. Some (or all) of the tests I mentioned in this https://github.com/openzfs/zfs/pull/9600#discussion_r359002431...