Changes between Version 28 and Version 29 of Public/User_Guide/PaS

Timestamp:

Oct 27, 2020, 2:17:11 PM (5 years ago)

Author:

Jochen Kreutz

Comment:

HW and SW sections updated to reflect current system status

Public/User_Guide/PaS

@@ -3 +3 @@
 This page is intended to give a short overview on known issues and to provide potential solutions and workarounds to the issues seen.
 
-''Last update: 2020-09-23''
+''Last update: 2020-10-27''
 {{{#!comment highlighted red text
 [[span(style=color: #FF0000, System maintenance from Monday, 2020-09-07 to Friday, 2020-09-11, no user access !)]]
@@ -15 +15 @@
 === CM nodes ===
 
-* dp-cn[01,09,10]: nodes currently reserved for special use case during working hours 
-* dp-cn33: memory issues (#2464)
-* dp-cn49: configuration change required (#2291)
-* dp-cn50: node not reachable (#2488)
+* dp-cn25: node shows Unknown SPS FW Health (#2495)
+       
 
 === DAM nodes ===
 
 * dp-dam03: node currently reserved for special use case (#2242)
-* dp-dam04: showing low streams performance (#2401)
-* dp-dam05: node currently reserved for special use case
-* dp-dam07: showing problems with its FPGA (#2353)
-* dp-dam[09,10]: nodes currently reserved for special use case during working hours
 
 
@@ -35 +29 @@
 }}}
 
-* dp-esb05: node hangs in state "Idle+Completing"
 * dp-esb11: wrong GPU Link Speed detected (#2358)
 * dp-esb24: CentOS8 Testbed (#2396)
-* dp-esb39: energy meter reading issues (#2432)
 * dp-esb52: energy meter reading issues (#2433)
-* dp-esb61: node not reachable (#2469)
-* dp-esb71: energy meter reading issues (#2432)
-* dp-esb73: energy meter reading issues (#2433)
 
 
 === SDV nodes ===
 
-* deeper-sdv01: node reachable via nework, but marked as down in SLURM
+* deeper-sdv[01-16]: currently offline after removing Extoll network 
 * nfgw[01,02]: node reachable via nework, but marked as down in SLURM
 * knl01: NVMe issues (#2011)
-* ml-gpu02: memory issues reported with MCE (#2489)
-
 
 
 == Software issues ==
-
-=== Modular jobs failing ===
-
-- users reported failing jobs that are doing MPI on more than one module using the gateways
-- the problem is being investigated
-
 
 === SLURM jobs ===