On Thursday, July 04, 2019, at 8:03 PM, K. R. Sanborn wrote: > One way to deal with the pool import, is to manually run them sequentially. > It will take longer, but it's more controlled. I did it, things were the same.
> Next, since these are in essence R/O files, I'd disable "atime" in the > dataset level. I didn't think it was relevant (BTW, it's turned off). > Last, I'd look at the "primarycache" options. If your use case has the files read / streamed occasionally, then perhaps using "primarycache=metadata" might make sense. Especially if the files read are flushed out of RAM cache / ARC so quickly that it makes no sense to put them there in the first place. Well, it does, I mean there are more frequently used objects and cache helps there. ------------------------------------------ openzfs: openzfs-developer Permalink: https://openzfs.topicbox.com/groups/developer/T10533b84f9e1cfc5-M7e109a2cd513c3a78caca14c Delivery options: https://openzfs.topicbox.com/groups/developer/subscription
