md mdcheck/checkarray degrading server

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



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



[Index of Archives]     [Linux RAID Wiki]     [ATA RAID]     [Linux SCSI Target Infrastructure]     [Linux Block]     [Linux IDE]     [Linux SCSI]     [Linux Hams]     [Device Mapper]     [Device Mapper Cryptographics]     [Kernel]     [Linux Admin]     [Linux Net]     [GFS]     [RPM]     [git]     [Yosemite Forum]


  Powered by Linux