Derek Su

> > > If one wants to take a snapshot of the volume, it can execute `dmsetup suspend` and the filesystem is automatically frozen ([code](https://elixir.bootlin.com/linux/latest/source/drivers/md/dm.c#L2693)). In addition to preventing the...

When starting a v1 volume engine, there is a big [controller lock](https://github.com/longhorn/longhorn-engine/blob/master/pkg/controller/control.go#L709-L710) for protecting the controller creation, and the [WriteAt](https://github.com/longhorn/longhorn-engine/blob/master/pkg/controller/control.go#L853) and [ReadAt](https://github.com/longhorn/longhorn-engine/blob/master/pkg/controller/control.go#L914) are also safeguarded by the big lock. Unlike...

@WebberHuang1118 Not implemented because of the concerns mentioned in https://github.com/longhorn/longhorn/issues/2187#issuecomment-1735473718.

The feature will be added into the [Longhorn CLI](https://github.com/longhorn/longhorn/issues/7927) later.

We've improved the rebuilding performance by multiple threads, large block size and skipping unnecessary block checksum calculation. Then, the main bottleneck is disk IO. Do we need to change the...

I can sometimes see the message in demsg before the machine is somehow restarted in kernel 5.15.0 ``` [ 2922.561981] nvme nvme8: Removing ctrl: NQN "nqn.2023-01.io.longhorn.spdk:pvc-c2467c90-c3ef-4fee-9803-4ba3237a4c99-e-0" [ 2958.093090] nvme nvme4:...

> Let's update the 1.6.0 doc first to mention this known issue. Remove that until we clarify the cause. Added a doc for the issue and made some PRs for...

The root cause is spdk_tgt constantly emits ``` [2024-01-16 05:17:25.641866] ctrlr.c: 178:nvmf_ctrlr_keep_alive_poll: *NOTICE*: Disconnecting host nqn.2014-08.org.nvmexpress:uuid:00000000-0000-0000-0000-ac1f6be298ca from subsystem nqn.2023-01.io.longhorn.spdk:pvc-d24ca15c-6fab-4039-a889-651f07aa0072-e-0 due to keep alive timeout. [2024-01-16 05:17:26.639906] ctrlr.c: 178:nvmf_ctrlr_keep_alive_poll: *NOTICE*: Disconnecting...

This is a nvme-cli upstream issue and caused by a problematic spdk_tgt. Need a further investigation. Move to v1.7. WDYT? @innobead

> Longhorn supports system backup which stores all resources into the backup target. You can check [this](https://longhorn.io/docs/1.5.3/advanced-resources/system-backup-restore/) for details. > > > I think it is necessary to warn of...