add sys_devices_system_edac_mc charts info (#11589)
Ilya Mashchenko committed
Sep 29, 2021 at 09:28 UTC
1b22cba80bc2047b8a392a67aac6c0b7176053ec
1 file changed
+27
web/gui/dashboard_info.js
+27
@@ -738,6 +738,21 @@ netdataDashboard.submenu = {
738
info: 'Non-Uniform Memory Access (NUMA) is a hierarchical memory design the memory access time is dependent on locality. Under NUMA, a processor can access its own local memory faster than non-local memory (memory local to another processor or memory shared between processors). The individual metrics are described in the <a href="https://www.kernel.org/doc/Documentation/numastat.txt" target="_blank">Linux kernel documentation</a>.'
739
},
740
741
+ 'mem.ecc': {
742
+ info: '<p><a href="https://en.wikipedia.org/wiki/ECC_memory" target="_blank">ECC memory</a> '+
743
+ 'is a type of computer data storage that uses an error correction code (ECC) to detect '+
744
+ 'and correct n-bit data corruption which occurs in memory. '+
745
+ 'Typically, ECC memory maintains a memory system immune to single-bit errors: '+
746
+ 'the data that is read from each word is always the same as the data that had been written to it, '+
747
+ 'even if one of the bits actually stored has been flipped to the wrong state.</p>'+
748
+ '<p>Memory errors can be classified into two types: '+
749
+ '<b>Soft errors</b>, which randomly corrupt bits but do not leave physical damage. '+
750
+ 'Soft errors are transient in nature and are not repeatable, can be because of electrical or '+
751
+ 'magnetic interference. '+
752
+ '<b>Hard errors</b>, which corrupt bits in a repeatable manner because '+
753
+ 'of a physical/hardware defect or an environmental problem.'
754
+ },
755
+
756
'ip.ecn': {
757
info: '<a href="https://en.wikipedia.org/wiki/Explicit_Congestion_Notification" target="_blank">Explicit Congestion Notification (ECN)</a> '+
758
'is an extension to the IP and to the TCP that allows end-to-end notification of network congestion without dropping packets. '+
@@ -1322,6 +1337,18 @@ netdataDashboard.context = {
1337
info: 'The amount of memory with physical corruption problems, identified by <a href="https://en.wikipedia.org/wiki/ECC_memory" target="_blank">ECC</a> and set aside by the kernel so it does not get used.'
1338
},
1339
1340
+ 'mem.ecc_ce': {
1341
+ info: 'The number of correctable (single-bit) ECC errors. '+
1342
+ 'These errors do not affect the normal operation of the system '+
1343
+ 'because they are still being corrected. '+
1344
+ 'Periodic correctable errors may indicate that one of the memory modules is slowly failing.'
1345
+ },
1346
+
1347
+ 'mem.ecc_ue': {
1348
+ info: 'The number of uncorrectable (multi-bit) ECC errors. '+
1349
+ 'An uncorrectable error is a fatal issue that will typically lead to an OS crash.'
1350
+ },
1351
+
1352
'mem.cachestat_ratio': {
1353
info: 'When the processor needs to read or write a location in main memory, it checks for a corresponding entry in the page cache. If the entry is there, a page cache hit has occurred and the read is from the cache. If the entry is not there, a page cache miss has occurred and the kernel allocates a new entry and copies in data from the disk. Netdata calculates the percentage of accessed files that are cached on memory. <a href="https://github.com/iovisor/bcc/blob/master/tools/cachestat.py#L126-L138" target="_blank">The ratio</a> is calculated counting the accessed cached pages (without counting dirty pages and pages added because of read misses) divided by total access without dirty pages.'
1354
},