fix(controller,apiserver,xcecli): expose job CPU peak and efficiency to the apiserver and xcecli (bug-1736)
The controller computed run usage (CPU time, memory, CPU peak and efficiency, LSF bjobs -l definitions) but the capnp Job struct had no field for it, so the job pushed to the apiserver never carried it, and snapshots (the same struct) dropped it: a job restored from a checkpoint lost its accumulated usage. - controller.capnp: Job.runUsage @13 (JobRunusage); old entries decode with no run usage. - apiserver: map run_usage into JobInfo; max_mem, avg_mem, used_mem, cpu_time, peak_cpu, peak_cpu_time, peak_cpu_duration, mem_efficiency, avg_cpu_efficiency, peak_cpu_efficiency become queryable columns. - xcecli: -o fields MAX_MEM, AVG_MEM, MEM_EFFICIENCY, CPU_PEAK, CPU_PEAK_DURATION, CPU_EFFICIENCY, CPU_PEAK_EFFICIENCY (CPU_TIME now renders too), and a MEMORY USAGE / CPU USAGE block in jobs list -l. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
This commit is contained in:
parent
e2472aa73c
commit
1cedd7f791
GPG key ID:
80533536B0EB651C
9 changed files with 466 additions and 56 deletions
|
|
@ -546,18 +546,29 @@ type JobInfo struct {
|
|||
ReserveTime int64 `json:"reserve_time"`
|
||||
Duration int `json:"duration"`
|
||||
CPUTime int `json:"cpu_time"`
|
||||
ExitStatus Jsonb `json:"exit_status"` //change type, JSONB as []byte
|
||||
ExecHosts Jsonb `json:"exec_hosts"` //change type, JSONB as []byte
|
||||
ExecUID int `json:"exec_uid"`
|
||||
ExecHome string `json:"exec_home"`
|
||||
ExecCWD string `json:"exec_cwd"`
|
||||
ExecUser string `json:"exec_user"` //name change
|
||||
ChargedSaap string `json:"charged_saap"`
|
||||
RunTime int `json:"run_time"`
|
||||
RunTimeEstimation int `json:"run_time_estimation"`
|
||||
PendingReason Jsonb `json:"pending_reason"` //change type, JSONB as []byte
|
||||
PIDInfo Jsonb `json:"pid_info"` // JSONB as []byte
|
||||
JobRusage Jsonb `json:"job_rusage"` // JSONB as []byte
|
||||
// Run usage (bug-1736), from the controller's accumulated job usage with
|
||||
// LSF bjobs -l definitions; zero until the first usage report.
|
||||
MaxMem float64 `json:"max_mem"` // MB
|
||||
AvgMem float64 `json:"avg_mem"` // MB
|
||||
UsedMem float64 `json:"used_mem"` // MB, latest
|
||||
PeakCPU float64 `json:"peak_cpu"` // highest cores used at once
|
||||
PeakCPUTime int `json:"peak_cpu_time"` // peak_cpu rounded
|
||||
PeakCPUDuration float64 `json:"peak_cpu_duration"` // seconds, the interval that set the peak
|
||||
MemEfficiency float64 `json:"mem_efficiency"` // percent of the rusage[mem] request
|
||||
AvgCPUEfficiency float64 `json:"avg_cpu_efficiency"` // percent, cpu_time / elapsed / slots
|
||||
PeakCPUEfficiency float64 `json:"peak_cpu_efficiency"` // percent, peak_cpu / slots
|
||||
ExitStatus Jsonb `json:"exit_status"` //change type, JSONB as []byte
|
||||
ExecHosts Jsonb `json:"exec_hosts"` //change type, JSONB as []byte
|
||||
ExecUID int `json:"exec_uid"`
|
||||
ExecHome string `json:"exec_home"`
|
||||
ExecCWD string `json:"exec_cwd"`
|
||||
ExecUser string `json:"exec_user"` //name change
|
||||
ChargedSaap string `json:"charged_saap"`
|
||||
RunTime int `json:"run_time"`
|
||||
RunTimeEstimation int `json:"run_time_estimation"`
|
||||
PendingReason Jsonb `json:"pending_reason"` //change type, JSONB as []byte
|
||||
PIDInfo Jsonb `json:"pid_info"` // JSONB as []byte
|
||||
JobRusage Jsonb `json:"job_rusage"` // JSONB as []byte
|
||||
}
|
||||
|
||||
type JobExecHosts struct {
|
||||
|
|
@ -598,25 +609,18 @@ type JobAdditionalFields struct {
|
|||
FromHost string `json:"from_host"`
|
||||
ExecHosts string `json:"exec_hosts"`
|
||||
|
||||
StartTime int64 `json:"start_time"`
|
||||
EndTime int64 `json:"end_time"`
|
||||
JobRusage Jsonb `json:"job_rusage"`
|
||||
MaxMem float64 `json:"max_mem"`
|
||||
AvgMem float64 `json:"avg_mem"`
|
||||
UsedMem float64 `json:"used_mem"`
|
||||
CPUTime int `json:"cpu_time"`
|
||||
PeakCPUTime int `json:"peak_cpu_time"`
|
||||
PeakCPUDuration float64 `json:"peak_cpu_duration"`
|
||||
MemEfficiency float64 `json:"mem_efficiency"` // Memory efficiency in percentage
|
||||
AvgCPUEfficiency float64 `json:"avg_cpu_efficiency"` // Average CPU efficiency in percentage
|
||||
PeakCPUEfficiency float64 `json:"peak_cpu_efficiency"` // Peak CPU efficiency in percentage
|
||||
NumHosts int `json:"num_hosts"` // Number of hosts used by the job
|
||||
FirstHost string `json:"first_host"` // First host where the job ran
|
||||
AllocSlot string `json:"alloc_slots"` // Allocated slot information
|
||||
PIDInfo Jsonb `json:"pid_info"`
|
||||
Pids []int `json:"pids"` // List of process IDs associated with the job
|
||||
Pgids []int `json:"pgids"` // List of process group IDs associated with the job
|
||||
InteractiveJobURL string `json:"interactive_job_url"`
|
||||
StartTime int64 `json:"start_time"`
|
||||
EndTime int64 `json:"end_time"`
|
||||
JobRusage Jsonb `json:"job_rusage"`
|
||||
// max_mem/avg_mem/used_mem/cpu_time/peak_cpu*/..._efficiency are
|
||||
// JobInfo columns now (bug-1736).
|
||||
NumHosts int `json:"num_hosts"` // Number of hosts used by the job
|
||||
FirstHost string `json:"first_host"` // First host where the job ran
|
||||
AllocSlot string `json:"alloc_slots"` // Allocated slot information
|
||||
PIDInfo Jsonb `json:"pid_info"`
|
||||
Pids []int `json:"pids"` // List of process IDs associated with the job
|
||||
Pgids []int `json:"pgids"` // List of process group IDs associated with the job
|
||||
InteractiveJobURL string `json:"interactive_job_url"`
|
||||
// CoreLimit/MemLimit: JobInfo has no equivalent field (these are
|
||||
// submission-time resource limits, not job-state fields), but xcecli's
|
||||
// JobFieldsMap accepts them as valid -o/-l display fields (bug-1674) --
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue