[clug] Is a weekly RAID scrub too much?
Eyal Lebedinsky
eyal at eyal.emu.id.au
Fri Feb 24 11:35:59 UTC 2017
I was idly browsing when I came upon an announcement from Toshiba of a new NAS HDD family:
https://toshiba.semicon-storage.com/ap-en/product/storage-products/client-hdd/mn05aca-mn04acaxxx.html
I took a look at the spec
https://toshiba.semicon-storage.com/content/dam/toshiba-ss/asia-pacific/docs/product/storage/product-manual/cHDD-MN05ACA_MN04ACA_Product-overview.pdf
and there I see
"Rated Annual Workload (Total TB Transferred per Year, R/W) 180 TB/year".
and this is the same for the three models 4/6/8TB.
Doing the math: a weekly scrub will read 52*8=416TB a year, more than twice the designed load.
Even a monthly scrub will use up more than half the workload.
Is the scrub doing more harm than good by shortening the service life of the disk?
Does smart self-test count as data read too? I do these too...
Some modern disks record the read/write volume, take the Seagate ST4000DM000. smartctl says:
9 Power_On_Hours -O--CK 099 099 000 - 1059
240 Head_Flying_Hours ------ 100 253 000 - 1038h+23m+23.410s
241 Total_LBAs_Written ------ 100 253 000 - 23806990167
242 Total_LBAs_Read ------ 100 253 000 - 81453441961
So about 50TB I/O, and this (4TB) disk is was used only intermittently in the RAID while I wait for
a replacement of a failed disk (44 days total). The data-sheet specifies just 55TB/year workload,
even for the larger 8TB model.
Will this data be used to deny warranty service or is this just a guideline?
Are these kind of disks simply unsuitable for RAID?
Just looking for more things to worry about :-)
--
Eyal Lebedinsky (eyal at eyal.emu.id.au)
More information about the linux
mailing list