We have an automatic check using checkarray being performed every Sunday of the month at 12:57 pm, but it is degrading the server, e.g. loadavg increases from ~5 to ~100 in minutes and makes the server unusable. >From the Linux Raid mailing list and the internet, we found similar issues: - Configure speed of checkarray in mdadm? https://marc.info/?l=linux-raid&m=124138136430340&w=2 checking md device parity (forced resync) - is it necessary? https://marc.info/?l=linux-raid&m=115744679317060&w=2 - Importance of checkarray: https://serverfault.com/questions/199096/linux-software-raid-runs-checkarray-on-the-first-sunday-of-the-month-why - mdcheck: slow system issues: https://marc.info/?l=linux-raid&m=158557483523833&w=2 - MDADM CONSISTENCY CHECKS: https://wmbuck.net/blog/?p=825 (Similar issue) And some suggested lowering the value in '/sys/block/md127/md/sync_speed_max'. There is also some discussion about disabling mdcheck/checkrarray https://serverfault.com/a/199125. Given the information above, I would like to ask: 1 - What is the importance of mdcheck/checkarray in RAID 1 configuration? 2 - What are the risks of disabling this functionality? 3 - Does a decrease in sync_speed_max reduce performance degradation, and how does this change affect the overall system? Note: Debian-based OS Note: Server is running on RAID 1. Note: The same level of degradation seen in checkarray was seen using mdcheck. Thanks for considering my questions, Gilson Urbano
