Re:Silent Data Corruption Is Real
by blablabloe on Monday March 13, 2017 @10:59AM
(#13858319)
When a double-parity error is detected, the operating system should halt. Maybe that didn't happen properly.
Tripple parity errors may go undetected, but how likely is that.
Re:Silent Data Corruption Is Real
by mrb on Tuesday March 14, 2017 @11:49AM
(#13868506)
I saw dozens of ECC errors in the IPMI log, and dozens of MCAs in dmesg. So the memory was failing so badly that it is probably there were 3+ bit errors.
I wonder what 'really' happened.