add proc_mdstat charts info (#11537)
* add proc_mdstat charts info
Ilya Mashchenko committed
Sep 21, 2021 at 12:07 UTC
f7175f032675cd4524a393d94e3829f605b1eca6
1 file changed
+41
-1
web/gui/dashboard_info.js
+41
-1
@@ -135,7 +135,12 @@ netdataDashboard.menu = {
135
136
'mdstat': {
137
title: 'MD arrays',
138
- icon: '<i class="fas fa-hdd"></i>'
138
+ icon: '<i class="fas fa-hdd"></i>',
139
+ info: '<p>RAID devices are virtual devices created from two or more real block devices. '+
140
+ '<a href="https://man7.org/linux/man-pages/man4/md.4.html" target="_blank">Linux Software RAID</a> devices are '+
141
+ 'implemented through the md (Multiple Devices) device driver.</p>'+
142
+ '<p>Netdata monitors the current status of MD arrays reading <a href="https://raid.wiki.kernel.org/index.php/Mdstat" target="_blank">/proc/mdstat</a> and '+
143
+ '<code>/sys/block/%s/md/mismatch_cnt</code> files.</p>'
144
},
145
146
'sensors': {
@@ -1235,6 +1240,41 @@ netdataDashboard.context = {
1240
info: 'Counters of file accesses. <code>Reference</code> is when there is a file access and the file is not present in the directory cache. <code>Miss</code> is when there is file access and the file is not found in the filesystem. <code>Slow</code> is when there is a file access and the file is present in the filesystem but not in the directory cache. Read more about <a href="https://www.kernel.org/doc/htmldocs/filesystems/the_directory_cache.html" target="_blank">directory cache</a>.'
1241
},
1242
1243
+ 'md.health': {
1244
+ info: 'Number of failed devices per MD array. '+
1245
+ 'Netdata retrieves this data from the <b>[n/m]</b> field of the md status line. '+
1246
+ 'It means that ideally the array would have <b>n</b> devices however, currently, <b>m</b> devices are in use. '+
1247
+ '<code>failed disks</code> is <b>n-m</b>.'
1248
+ },
1249
+ 'md.disks': {
1250
+ info: 'Number of devices in use and in the down state. '+
1251
+ 'Netdata retrieves this data from the <b>[n/m]</b> field of the md status line. '+
1252
+ 'It means that ideally the array would have <b>n</b> devices however, currently, <b>m</b> devices are in use. '+
1253
+ '<code>inuse</code> is <b>m</b>, <code>down</code> is <b>n-m</b>.'
1254
+ },
1255
+ 'md.status': {
1256
+ info: 'Completion progress of the ongoing operation.'
1257
+ },
1258
+ 'md.expected_time_until_operation_finish': {
1259
+ info: 'Estimated time to complete the ongoing operation. '+
1260
+ 'The time is only an approximation since the operation speed will vary according to other I/O demands.'
1261
+ },
1262
+ 'md.operation_speed': {
1263
+ info: 'Speed of the ongoing operation. '+
1264
+ 'The system-wide rebuild speed limits are specified in <code>/proc/sys/dev/raid/{speed_limit_min,speed_limit_max}</code> files. '+
1265
+ 'These options are good for tweaking rebuilt process and may increase overall system load, cpu and memory usage.'
1266
+ },
1267
+ 'md.mismatch_cnt': {
1268
+ info: 'When performing <b>check</b> and <b>repair</b>, and possibly when performing <b>resync</b>, md will count the number of errors that are found. '+
1269
+ 'A count of mismatches is recorded in the <code>sysfs</code> file <code>md/mismatch_cnt</code>. '+
1270
+ 'This value is the number of sectors that were re-written, or (for <b>check</b>) would have been re-written. '+
1271
+ 'It may be larger than the number of actual errors by a factor of the number of sectors in a page. '+
1272
+ 'Mismatches can not be interpreted very reliably on RAID1 or RAID10, especially when the device is used for swap. '+
1273
+ 'On a truly clean RAID5 or RAID6 array, any mismatches should indicate a hardware problem at some level - '+
1274
+ 'software issues should never cause such a mismatch. '+
1275
+ 'For details, see <a href="https://man7.org/linux/man-pages/man4/md.4.html" target="_blank">md(4)</a>.'
1276
+ },
1277
+
1278
// ------------------------------------------------------------------------
1279
// network interfaces
1280