# # config file for mcelog # For further options, see the mcelog manpage and documentation # # Filter out known broken events by default filter = yes # don't log memory errors individually #filter-memory-errors = yes # output in undecoded raw format to be easier machine readable #raw = yes [server] # An upstream bug prevents this from being disabled # Only allow root to connect by default client-user = root # Path to socket client uses to connect socket-path = /var/run/mcelog-client [dimm] # Enable DIMM-tracking dimm-tracking-enabled = yes # Disable DIMM DMI pre-population unless supported on your system dmi-prepopulate = no # execute these triggers when the rate of corrected or uncorrected # errors per DIMM exceeds the threshold # The default of 10/24h was reasonable for server quality # DDR3 DIMMs as of 2009/10. Newer systems can benefit from # more aggressive page offline when corrected errors are seen # See: # https://www.intel.com/content/dam/www/public/us/en/documents/intel-and-samsung-mrt-improving-memory-reliability-at-data-centers.pdf # for details. uc-error-trigger = dimm-error-trigger uc-error-threshold = 1 / 24h ce-error-trigger = dimm-error-trigger ce-error-threshold = 2 / 24h [socket] # Memory error accounting per socket socket-tracing-enabled = yes mem-uc-error-threshold = 100 / 24h mem-ce-error-trigger = socket-memory-error-trigger mem-ce-error-threshold = 100 / 24h mem-ce-error-log = yes [cache] # Attempt to off-line CPUs causing cache errors cache-threshold-trigger = cache-error-trigger cache-threshold-log = yes [page] # Try to soft-offline a 4K page if it exceeds the threshold memory-ce-threshold = 10 / 24h memory-ce-trigger = page-error-trigger memory-ce-log = yes memory-ce-action = soft [trigger] # Maximum number of running triggers children-max = 2 directory = /etc/mcelog/triggers