# atop, loadavg, ebpf, ps and HDD issue

Before testing read/write on a HDD, check below items first:
1. Any `dev sd[x]` error in dmesg or jounalctl
2. loadavg and atop/htop and D status process

Because if the HDD is completely broken, the touch/cat and any read/write cmd might be blocked by kernel which is watiing for HDD response ( which is impossible )

## Related docs
* [atop](https://www.atoptool.nl/)
* [atop on stackoverflow](https://serverfault.com/questions/169676/how-to-check-disk-i-o-utilization-per-process)
* [Troubleshooting High I/O Wait in Linux](https://bencane.com/2012/08/06/troubleshooting-high-io-wait-in-linux/)
* `iostat -x 2 5`
* `for x in `seq 1 1 10`; do ps -eo state,pid,cmd | grep "^D"; echo "----"; sleep 5; done` : dump D state process

* [Brendan Gregg's Blog - Linux Load Averages: Solving the Mystery](https://www.brendangregg.com/blog/2017-08-08/linux-load-averages.html)
* [How to get process load avg without tools](https://unix.stackexchange.com/questions/404820/how-to-get-process-load-avg-without-tools)