This article will explain about the UE correct that could cause RE to crash/reload.
EDAC Logs:
[ 2.384725] EDAC sbridge MC0: HANDLING MCE MEMORY ERROR[ 2.384727] EDAC sbridge MC0: CPU 0: Machine Check Event: 0 Bank 7: ac00000000010092[ 2.384731] EDAC sbridge MC0: PROCESSOR 0:306f2 TIME 1760827210 SOCKET 0 APIC 0[ 2.384736] EDAC DEBUG: get_memory_error_data: SAD interleave package: 1 = CPU socket 0, HA 0, shiftup: 1[ 2.384740] EDAC DEBUG: get_memory_error_data: TAD#0: address 0x000000001ec80200 < 0x000000007fffffff, socket interleave 0, channel interleave 2 (offset 0x00000000), index 0, base ch: 2, ch mask: 0x04[ 2.384743] EDAC DEBUG: get_memory_error_data: RIR#0, limit: 31.999 GB (0x00000007ffffffff), way: 4[ 2.384744] EDAC DEBUG: get_memory_error_data: RIR#0: channel address 0x0f640100 < 0x7ffffffff, RIR interleave 2, index 0[ 2.384747] EDAC DEBUG: sbridge_mce_output_error: recoverable area:DRAM err_code:0001:0092 socket:0 ha:0 channel_mask:4 rank:0[ 2.384752] EDAC MC0: 0 UE memory read error on CPU_SrcID#0_Ha#0_Chan#2_DIMM#0 (channel:2 slot:0 page:0x1ec80 offset:0x200 grain:32 - recoverable area:DRAM err_code:0001:0092 socket:0 ha:0 channel_mask:4 rank:0)[ 2.384759] microcode: Microcode Update Driver: v2.01 <[email protected]>, Peter Oruba
On RE, the EDAC (Error Detection and Correction) subsystem detected an error in the memory controller (MC0). As it is an Uncorrectable (UE) memory errors, indicating a hardware fault, likely a failing DIMM on the RE. ECC memory cannot repair this fault.
Any further memory access in this area could cause:
Workaround:
In a MW, reload the affected routing-engine to recover from this state. Then monitor it for the next 24 hours.
Collect commands below output to check further whether the same DIMM/channel has produced repeated errors — repeated uncorrectable errors = failing DIMM.
If logs are still persisting, please open a case with JTAC Support.