flex Posted December 12, 2023 Share Posted December 12, 2023 Was checking my ssd smart data and noticed that a brand new drive I just installed had 303TB written to it. I've checked online and found that this was an old issue which should have been fixed in 6.9. I'm currently running 6.12.4. looking at iotop, the only out of the ordinary writes I see are from [btfrs-transcations]. Would like assistance in preventing the death of ssd in a few more months at this rate. I've seen spikes of writes go up to 500MB/s. I am running plex but transcoding is done in RAM. I thought it was excessive logs by nginx, I moved that to a different cache drive but no change. Can provide any logs/data as needed Quote Link to comment
Kilrah Posted December 12, 2023 Share Posted December 12, 2023 There are things with logs that may cause excessive writes, but nowhere near that much. Most likely a misconfiguration wither for transcode location of simply the amount of stuff you download to cache before moving. Quote Link to comment
flex Posted December 13, 2023 Author Share Posted December 13, 2023 That was actually the first thing I checked. After switching to ZFS and having less docker containers running. I ran an iotop and now the main culprit is nginx: worker process writing/reading a few GBS since I started the command 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.