mirror of
https://github.com/ClusterCockpit/cc-specifications.git
synced 2024-12-25 13:09:05 +01:00
Introduce resolution variants and stats
Add statistics across topology
This commit is contained in:
Jan Eitzinger
parent
fc69a29b34
commit
183002ab19
@ -47,6 +47,10 @@
|
||||
"description": "Metric unit",
|
||||
"type": "string"
|
||||
},
|
||||
"scope": {
|
||||
"description": "Native measurement resolution",
|
||||
"type": "string"
|
||||
},
|
||||
"timestep": {
|
||||
"description": "Frequency of timeseries points",
|
||||
"type": "integer"
|
||||
|
||||
@ -6,155 +6,163 @@
|
||||
"properties": {
|
||||
"mem_used": {
|
||||
"description": "Memory capacity used (required)",
|
||||
"#ref": "https://github.com/ClusterCockpit/cc-specifications/blob/master/schema/json/job-metric-data.schema.json"
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"node": {
|
||||
"#ref": "https://github.com/ClusterCockpit/cc-specifications/blob/master/schema/json/job-metric-data.schema.json"
|
||||
}
|
||||
}
|
||||
},
|
||||
"flops_any": {
|
||||
"description": "Total flop rate with DP flops scaled up (required)",
|
||||
"#ref": "https://github.com/ClusterCockpit/cc-specifications/blob/master/schema/json/job-metric-data.schema.json"
|
||||
"properties": {
|
||||
"node": {
|
||||
"#ref": "https://github.com/ClusterCockpit/cc-specifications/blob/master/schema/json/job-metric-data.schema.json"
|
||||
},
|
||||
"socket": {
|
||||
"#ref": "https://github.com/ClusterCockpit/cc-specifications/blob/master/schema/json/job-metric-data.schema.json"
|
||||
},
|
||||
"memoryDomain": {
|
||||
"#ref": "https://github.com/ClusterCockpit/cc-specifications/blob/master/schema/json/job-metric-data.schema.json"
|
||||
},
|
||||
"core": {
|
||||
"#ref": "https://github.com/ClusterCockpit/cc-specifications/blob/master/schema/json/job-metric-data.schema.json"
|
||||
},
|
||||
"hwthread": {
|
||||
"#ref": "https://github.com/ClusterCockpit/cc-specifications/blob/master/schema/json/job-metric-data.schema.json"
|
||||
}
|
||||
}
|
||||
},
|
||||
"mem_bw": {
|
||||
"description": "Main memory bandwidth (required)",
|
||||
"#ref": "https://github.com/ClusterCockpit/cc-specifications/blob/master/schema/json/job-metric-data.schema.json"
|
||||
"properties": {
|
||||
"node": {
|
||||
"#ref": "https://github.com/ClusterCockpit/cc-specifications/blob/master/schema/json/job-metric-data.schema.json"
|
||||
},
|
||||
"socket": {
|
||||
"#ref": "https://github.com/ClusterCockpit/cc-specifications/blob/master/schema/json/job-metric-data.schema.json"
|
||||
},
|
||||
"memoryDomain": {
|
||||
"#ref": "https://github.com/ClusterCockpit/cc-specifications/blob/master/schema/json/job-metric-data.schema.json"
|
||||
}
|
||||
}
|
||||
},
|
||||
"net_bw": {
|
||||
"description": "Total fast interconnect network bandwidth (required)",
|
||||
"#ref": "https://github.com/ClusterCockpit/cc-specifications/blob/master/schema/json/job-metric-data.schema.json"
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"node": {
|
||||
"#ref": "https://github.com/ClusterCockpit/cc-specifications/blob/master/schema/json/job-metric-data.schema.json"
|
||||
}
|
||||
}
|
||||
},
|
||||
"file_bw": {
|
||||
"description": "Total file IO bandwidth (required)",
|
||||
"#ref": "https://github.com/ClusterCockpit/cc-specifications/blob/master/schema/json/job-metric-data.schema.json"
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"node": {
|
||||
"#ref": "https://github.com/ClusterCockpit/cc-specifications/blob/master/schema/json/job-metric-data.schema.json"
|
||||
}
|
||||
}
|
||||
},
|
||||
"ipc": {
|
||||
"description": "Instructions executed per cycle",
|
||||
"#ref": "https://github.com/ClusterCockpit/cc-specifications/blob/master/schema/json/job-metric-data.schema.json"
|
||||
},
|
||||
"cpu_used": {
|
||||
"description": "CPU active core utilization",
|
||||
"#ref": "https://github.com/ClusterCockpit/cc-specifications/blob/master/schema/json/job-metric-data.schema.json"
|
||||
},
|
||||
"cpu_load": {
|
||||
"description": "CPU requested core utilization (load 1m)",
|
||||
"#ref": "https://github.com/ClusterCockpit/cc-specifications/blob/master/schema/json/job-metric-data.schema.json"
|
||||
},
|
||||
"flops_dp": {
|
||||
"description": "Double precision flop rate",
|
||||
"#ref": "https://github.com/ClusterCockpit/cc-specifications/blob/master/schema/json/job-metric-data.schema.json"
|
||||
},
|
||||
"flops_sp": {
|
||||
"description": "Single precision flops rate",
|
||||
"#ref": "https://github.com/ClusterCockpit/cc-specifications/blob/master/schema/json/job-metric-data.schema.json"
|
||||
},
|
||||
"vectorization_ratio": {
|
||||
"description": "Fraction of arithmetic instructions using SIMD instructions",
|
||||
"#ref": "https://github.com/ClusterCockpit/cc-specifications/blob/master/schema/json/job-metric-data.schema.json"
|
||||
},
|
||||
"cpu_power": {
|
||||
"description": "CPU power consumption",
|
||||
"#ref": "https://github.com/ClusterCockpit/cc-specifications/blob/master/schema/json/job-metric-data.schema.json"
|
||||
},
|
||||
"mem_power": {
|
||||
"description": "Memory power consumption",
|
||||
"#ref": "https://github.com/ClusterCockpit/cc-specifications/blob/master/schema/json/job-metric-data.schema.json"
|
||||
},
|
||||
"acc_utilization": {
|
||||
"description": "GPU utilization",
|
||||
"#ref": "https://github.com/ClusterCockpit/cc-specifications/blob/master/schema/json/job-metric-data.schema.json"
|
||||
},
|
||||
"acc_mem_used": {
|
||||
"description": "GPU memory capacity used",
|
||||
"#ref": "https://github.com/ClusterCockpit/cc-specifications/blob/master/schema/json/job-metric-data.schema.json"
|
||||
},
|
||||
"acc_power": {
|
||||
"description": "GPU power consumption",
|
||||
"#ref": "https://github.com/ClusterCockpit/cc-specifications/blob/master/schema/json/job-metric-data.schema.json"
|
||||
},
|
||||
"clock": {
|
||||
"description": "Average core frequency",
|
||||
"#ref": "https://github.com/ClusterCockpit/cc-specifications/blob/master/schema/json/job-metric-data.schema.json"
|
||||
},
|
||||
"eth_read_bw": {
|
||||
"description": "Ethernet read bandwidth",
|
||||
"#ref": "https://github.com/ClusterCockpit/cc-specifications/blob/master/schema/json/job-metric-data.schema.json"
|
||||
},
|
||||
"eth_write_bw": {
|
||||
"description": "Ethernet write bandwidth",
|
||||
"#ref": "https://github.com/ClusterCockpit/cc-specifications/blob/master/schema/json/job-metric-data.schema.json"
|
||||
},
|
||||
"pfs_read_bw": {
|
||||
"description": "Parallel file system read bandwidth",
|
||||
"#ref": "https://github.com/ClusterCockpit/cc-specifications/blob/master/schema/json/job-metric-data.schema.json"
|
||||
},
|
||||
"pfs_write_bw": {
|
||||
"description": "Parallel file system write bandwidth",
|
||||
"#ref": "https://github.com/ClusterCockpit/cc-specifications/blob/master/schema/json/job-metric-data.schema.json"
|
||||
},
|
||||
"pfs_read_req": {
|
||||
"description": "Parallel file system read requests",
|
||||
"#ref": "https://github.com/ClusterCockpit/cc-specifications/blob/master/schema/json/job-metric-data.schema.json"
|
||||
},
|
||||
"pfs_write_req": {
|
||||
"description": "Parallel file system write requests",
|
||||
"#ref": "https://github.com/ClusterCockpit/cc-specifications/blob/master/schema/json/job-metric-data.schema.json"
|
||||
},
|
||||
"pfs_inodes": {
|
||||
"description": "Parallel file system inodes used",
|
||||
"#ref": "https://github.com/ClusterCockpit/cc-specifications/blob/master/schema/json/job-metric-data.schema.json"
|
||||
},
|
||||
"pfs_accesses": {
|
||||
"description": "Parallel file system open and close",
|
||||
"#ref": "https://github.com/ClusterCockpit/cc-specifications/blob/master/schema/json/job-metric-data.schema.json"
|
||||
},
|
||||
"pfs_fsync": {
|
||||
"description": "Parallel file system fsync",
|
||||
"#ref": "https://github.com/ClusterCockpit/cc-specifications/blob/master/schema/json/job-metric-data.schema.json"
|
||||
},
|
||||
"pfs_create": {
|
||||
"description": "Parallel file system create",
|
||||
"#ref": "https://github.com/ClusterCockpit/cc-specifications/blob/master/schema/json/job-metric-data.schema.json"
|
||||
},
|
||||
"pfs_open": {
|
||||
"description": "Parallel file system open",
|
||||
"#ref": "https://github.com/ClusterCockpit/cc-specifications/blob/master/schema/json/job-metric-data.schema.json"
|
||||
},
|
||||
"pfs_close": {
|
||||
"description": "Parallel file system close",
|
||||
"#ref": "https://github.com/ClusterCockpit/cc-specifications/blob/master/schema/json/job-metric-data.schema.json"
|
||||
},
|
||||
"pfs_seek": {
|
||||
"description": "Parallel file system seek",
|
||||
"#ref": "https://github.com/ClusterCockpit/cc-specifications/blob/master/schema/json/job-metric-data.schema.json"
|
||||
},
|
||||
"fs_read_bw": {
|
||||
"description": "Local file system read bandwidth",
|
||||
"#ref": "https://github.com/ClusterCockpit/cc-specifications/blob/master/schema/json/job-metric-data.schema.json"
|
||||
},
|
||||
"fs_write_bw": {
|
||||
"description": "Local file system write bandwidth",
|
||||
"#ref": "https://github.com/ClusterCockpit/cc-specifications/blob/master/schema/json/job-metric-data.schema.json"
|
||||
},
|
||||
"fs_inodes": {
|
||||
"description": "Local file system inodes used",
|
||||
"#ref": "https://github.com/ClusterCockpit/cc-specifications/blob/master/schema/json/job-metric-data.schema.json"
|
||||
},
|
||||
"fs_accesses": {
|
||||
"description": "Local file system open and close",
|
||||
"#ref": "https://github.com/ClusterCockpit/cc-specifications/blob/master/schema/json/job-metric-data.schema.json"
|
||||
},
|
||||
"ic_rcv_packets": {
|
||||
"description": "Network interconnect read packets",
|
||||
"#ref": "https://github.com/ClusterCockpit/cc-specifications/blob/master/schema/json/job-metric-data.schema.json"
|
||||
},
|
||||
"ic_send_packets": {
|
||||
"description": "Network interconnect send packet",
|
||||
"#ref": "https://github.com/ClusterCockpit/cc-specifications/blob/master/schema/json/job-metric-data.schema.json"
|
||||
},
|
||||
"ic_read_bw": {
|
||||
"description": "Network interconnect read bandwidth",
|
||||
"#ref": "https://github.com/ClusterCockpit/cc-specifications/blob/master/schema/json/job-metric-data.schema.json"
|
||||
},
|
||||
"ic_write_bw": {
|
||||
"description": "Network interconnect write bandwidth",
|
||||
"#ref": "https://github.com/ClusterCockpit/cc-specifications/blob/master/schema/json/job-metric-data.schema.json"
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
|
||||
@ -21,8 +21,8 @@
|
||||
"type": "string"
|
||||
},
|
||||
"partition": {
|
||||
"description": "The cluster partition to which the job was submitted",
|
||||
"type": "string"
|
||||
"description": "The cluster partition id to which the job was submitted",
|
||||
"type": "integer"
|
||||
},
|
||||
"arrayJobId": {
|
||||
"description": "The unique identifier of an array job",
|
||||
|
||||
@ -41,6 +41,129 @@
|
||||
}
|
||||
}
|
||||
},
|
||||
"statisticsSeries": {
|
||||
"type": "object",
|
||||
"description": "Statistics series across topology",
|
||||
"properties": {
|
||||
"min": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"type": "number",
|
||||
"minimum": 0
|
||||
},
|
||||
"minItems": 3
|
||||
},
|
||||
"max": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"type": "number",
|
||||
"minimum": 0
|
||||
},
|
||||
"minItems": 3
|
||||
},
|
||||
"mean": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"type": "number",
|
||||
"minimum": 0
|
||||
},
|
||||
"minItems": 3
|
||||
},
|
||||
"percentiles": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"10": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"type": "number",
|
||||
"minimum": 0
|
||||
},
|
||||
"minItems": 3
|
||||
},
|
||||
"20": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"type": "number",
|
||||
"minimum": 0
|
||||
},
|
||||
"minItems": 3
|
||||
},
|
||||
"30": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"type": "number",
|
||||
"minimum": 0
|
||||
},
|
||||
"minItems": 3
|
||||
},
|
||||
"40": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"type": "number",
|
||||
"minimum": 0
|
||||
},
|
||||
"minItems": 3
|
||||
},
|
||||
"50": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"type": "number",
|
||||
"minimum": 0
|
||||
},
|
||||
"minItems": 3
|
||||
},
|
||||
"60": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"type": "number",
|
||||
"minimum": 0
|
||||
},
|
||||
"minItems": 3
|
||||
},
|
||||
"70": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"type": "number",
|
||||
"minimum": 0
|
||||
},
|
||||
"minItems": 3
|
||||
},
|
||||
"80": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"type": "number",
|
||||
"minimum": 0
|
||||
},
|
||||
"minItems": 3
|
||||
},
|
||||
"90": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"type": "number",
|
||||
"minimum": 0
|
||||
},
|
||||
"minItems": 3
|
||||
},
|
||||
"25": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"type": "number",
|
||||
"minimum": 0
|
||||
},
|
||||
"minItems": 3
|
||||
},
|
||||
"75": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"type": "number",
|
||||
"minimum": 0
|
||||
},
|
||||
"minItems": 3
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"series": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
@ -54,6 +177,7 @@
|
||||
},
|
||||
"statistics": {
|
||||
"type": "object",
|
||||
"description": "Statistics across time dimension",
|
||||
"properties": {
|
||||
"avg": {
|
||||
"description": "Series average",
|
||||
|
||||
Loading…
Reference in New Issue
Block a user