From Noah.org
Revision as of 04:18, 14 January 2014 by Root (Talk | contribs)

(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to: navigation, search

See also mcelog.

EDAC stands for "Error Detection and Correction".

The EDAC project is a set of Linux kernel modules that expose hardware errors such as PCI bus errors and ECC parity errors in RAM memory modules. EDAC is part of the mainstream Linux kernel. See also the EDAC Wiki.

Errors are visible in userspace through the sysfs filesystem under /sys/devices/system/edac directory. There are also userspace utilities available through edac-utils.

This example scans for correctable and uncorrectable errors (ce_count and ue_count) reported by the hardware memory controller.

grep . /sys/devices/system/edac/mc/mc?/[uc]e_count

The same results can be obtained with nice formatting by using the edac-util tool.

edac-util --report=full

There is also a utility called edac-ctl, which may be of interest. It lets you find the name and model of the mainboard and DIMM labels.