Cluster Status(Ganglia) TDG Rocks CPU last hour C 09:40 TDG Rocks Network last hour Show Hosts: yes O no O TDG Rocks load one last hour sorted descending I columns4 comp-pvfs-0-1. local comp-pvfs-0-2.local conp-pvfs-0-3. local comp-pvfs-0-5. local os:2O9:40 09:209:40 0s:2o:40 d load_one last hour (now 17. 00) 口1。 ad: one1 ast hour(now17,0 D load_one last hour (now 15. 00) a load_one last hour (now 14.00) commp-pvfs-0-15. local comp-pvfs-0-10. local comp-pvfs-0-12. local 2009:40 20 d load one last hour (now 14, 00) 口1。 adone1 ast hour(now14.00) 口1o4done1 ast hour 13.00 d loadone last hour (now 13. 00) comp-pvfs-0-13. local conp-pvfs-0- comp-pvfs-0-4,local comp-pvfs-0-6. local 09:2008:40 09:20.09:40 09:200:40 09:20.09:40 a load_one last hour (now 13. 00) n load_one last hour (now 13.00) D load one last Hour (now 12.00) d load one last hour (now 12.00) comp-pvfs-0-9, local commp-pvfs-0-8, local comp-pvfs-0-19. local pvfs-0-18. local
Cluster Status (Ganglia)
Cluster Top This page is a version of the standard"top"command for your cluster. This page presents process information from each node in the cluster. It is useful for monitoring the precise activity of your nodes The Cluster Top differs from standard top in several respects. Most importantly, each row has a "Host"designation and a" attribute that specifies its age. Since taking a process measurement itself requires resources, compute nodes report process data only once every 60 seconds on average. a process row with tn=30 means the host reported information about that process 30 seconds ago
Cluster Top • This page is a version of the standard "top" command for your cluster. This page presents process information from each node in the cluster. It is useful for monitoring the precise activity of your nodes. • The Cluster Top differs from standard top in several respects. Most importantly, each row has a "HOST" designation and a "TN" attribute that specifies its age. Since taking a process measurement itself requires resources, compute nodes report process data only once every 60 seconds on average. A process row with TN=30 means the host reported information about that process 30 seconds ago
Cluster Top TDG Rocks Cluster Top ROCKS Mon, 19 Apr 2004 10: 29: 05+0800 Physical Job Assignments Show only processes by user HOST PID USER CMD CPU [MEM [SIZE DATA [SHARED vM Up I 50 comp-pufs-0-34local 28228 0101 1499 asiandataNM2 99.90 224 848 50comp-pvfs-0-29. local2812901011499 asiandataINi99.900.052402248441068 omp-pvfs-0-54.local 2110 01011499 asiandataNM 99.90 0.05 232 1068 comp-pwfs-0-62local 1 512 comp-pvfs-0-36.local 01011499 asiandataNM 240 14 comp-pwfs-0-33local 01011499 asiandataonlyNs99900.052162208201040 14 comp-pwfs-0-33local 8790 01011499 asiandataonlyNs 99.90 0.05 216216 49 comp-pwfs-0-58local 12240 01011499 asiandataonlyNs 99.90 0.05 216 212 1032 comp-pvts-0-55local 16056 yang 99900.03 228 716 7comp-pvfs-0-51.1ocal35891011499 asiandataonlyNs99.900.052162168201036 77 comp-pwfs-0-44local 1217 01011499 asiandataloop22 99.90 0.05 6 comp-pvfs-0-45local 1 187 braun r4.5 99.90 0736 085601368 comp-pvfs-0-55.local 16023 yang 0.03 488 7comp-pvfs-0-511ocal368701011499 asiandataonlyNs99370.052162208201040 65 comp-pvfs-0-32local 17916 yang si 99.37 0.03 6 20 comp-pvfs-0-46local 6970 braun 1 99 0.07368085601368
Cluster Top
Cluster Top Process Columns The age of the information in this row, in seconds HOST The node in the cluster on which this process is running PID The Process ID. A non-negative integer, unique among all processes on this node USER The username of this processes CMD The command name of this process, without arguments %CPU The percentage of available CPu cycles occupied by this process. This is always an approximate figure, which is more accurate for longer running processes
Cluster Top • Process Columns – TN • The age of the information in this row, in seconds. – HOST • The node in the cluster on which this process is running. – PID • The Process ID. A non-negative integer, unique among all processes on this node. – USER • The username of this processes. – CMD • The command name of this process, without arguments. – %CPU • The percentage of available CPU cycles occupied by this process. This is always an approximate figure, which is more accurate for longer running processes
Cluster Top %MEM The percentage of available physical memory occupied by this process SIZE The size of the text"memory segment of this process, in kilobytes. This approximately relates the size of the executable itself(depending on the Bss segment) DATA Approximately the size of all dynamically allocated memory of this process, in kilobytes Includes the Heap and Stack of th e process. Defined as the resident shared" size where resident is the total amount of physical memory used, and shared is defined below Includes the text segment as well if this process has no children SHARED The size of the shared memory belonging to this process, in kilobytes. Defined as an page of this process'physical memory that is referenced by another process Includes shared libraries such as the standard libc and loader The total virtual memory size used by this process, in kilobytes
Cluster Top – %MEM • The percentage of available physical memory occupied by this process. – SIZE • The size of the "text" memory segment of this process, in kilobytes. This approximately relates the size of the executable itself (depending on the BSS segment). – DATA • Approximately the size of all dynamically allocated memory of this process, in kilobytes. Includes the Heap and Stack of the process. Defined as the "resident" - "shared" size, where resident is the total amount of physical memory used, and shared is defined below. Includes the text segment as well if this process has no children. – SHARED • The size of the shared memory belonging to this process, in kilobytes. Defined as any page of this process' physical memory that is referenced by another process. Includes shared libraries such as the standard libc and loader. – VM • The total virtual memory size used by this process, in kilobytes