Re: [ceph-users] Scrubbing question

Le 26/11/2015 15:53, Tomasz Kuzemko a écrit : > ECC will not be able to recover the data, but it will always be able to > detect that data is corrupted. No. That's a theoretical impossibility as the detection is done by some kind of hash over the memory content which brings the possibility of hash

Re: [ceph-users] Scrubbing question

ECC will not be able to recover the data, but it will always be able to detect that data is corrupted. AFAIK under Linux this results in immediate halt of system, so it would not be able to report bad checksum data during deep-scrub. -- Tomasz Kuzemko tomasz.kuze...@corp.ovh.com W dniu 26.11.2015

Re: [ceph-users] Scrubbing question

Hi, We don't use ECC modules but the ECC doesn't mean you're safe. See the presentation I linked earlier: https://www.nsc.liu.se/lcsc2007/presentations/LCSC_2007-kelemen.pdf>https://www.nsc.liu.se/lcsc2007/presentations/LCSC_2007-kelemen.pdf

Re: [ceph-users] Scrubbing question

Hi, I have also seen inconsistent PGs despite md5 being the same on all objects, however all my hardware uses ECC RAM, which as I understand should prevent this type of error. To be clear - in your case you were using ECC or non-ECC module? -- Tomasz Kuzemko tomasz.kuze...@ovh.net W dniu 26.11.20

Re: [ceph-users] Scrubbing question

Hi, On 11/25/2015 06:41 PM, Robert LeBlanc wrote: Since the one that is different is not your primary for the pg, then pg repair is safe. Ok, that's clear thanks. I think we managed to identify the root cause of the scrubbing errors even if the files are identical. It seems to be a hardware is

Re: [ceph-users] Scrubbing question

-BEGIN PGP SIGNED MESSAGE- Hash: SHA256 Since the one that is different is not your primary for the pg, then pg repair is safe. - Robert LeBlanc PGP Fingerprint 79A2 9CA4 6CC4 45DD A904 C70E E654 3BB2 FA62 B9F1 On Wed, Nov 25, 2015 at 2:42 AM, Major Csaba wrote: > Hi,

[ceph-users] Scrubbing question

Hi, I have some magic deep scrubbing error, and can't find the reason. The system contains 5 nodes with 20 OSDs in total and everything works fine, except these scrubbing errors. Sometimes the deep-scrub finds inconsistencies, but not exactly clear why. The content of the objects are exactly