mirror of
https://github.com/ClusterCockpit/cc-backend
synced 2024-12-26 05:19:05 +01:00
commit
036685cbe7
@ -10,7 +10,6 @@ import (
|
||||
"encoding/json"
|
||||
"errors"
|
||||
"fmt"
|
||||
"math"
|
||||
"strconv"
|
||||
"sync"
|
||||
"time"
|
||||
@ -18,7 +17,6 @@ import (
|
||||
"github.com/ClusterCockpit/cc-backend/internal/auth"
|
||||
"github.com/ClusterCockpit/cc-backend/internal/graph/model"
|
||||
"github.com/ClusterCockpit/cc-backend/internal/metricdata"
|
||||
"github.com/ClusterCockpit/cc-backend/internal/util"
|
||||
"github.com/ClusterCockpit/cc-backend/pkg/log"
|
||||
"github.com/ClusterCockpit/cc-backend/pkg/lrucache"
|
||||
"github.com/ClusterCockpit/cc-backend/pkg/schema"
|
||||
@ -318,7 +316,7 @@ func (r *JobRepository) FindConcurrentJobs(
|
||||
stopTime = startTime + int64(job.Duration)
|
||||
}
|
||||
|
||||
// Add 5m overlap for jobs start time at the end
|
||||
// Add 200s overlap for jobs start time at the end
|
||||
startTimeTail := startTime + 10
|
||||
stopTimeTail := stopTime - 200
|
||||
startTimeFront := startTime + 200
|
||||
@ -338,8 +336,7 @@ func (r *JobRepository) FindConcurrentJobs(
|
||||
}
|
||||
|
||||
items := make([]*model.JobLink, 0, 10)
|
||||
minStart := int64(math.MaxInt64)
|
||||
maxStart := int64(0)
|
||||
queryString := fmt.Sprintf("cluster=%s", job.Cluster)
|
||||
|
||||
for rows.Next() {
|
||||
var id, jobId, startTime sql.NullInt64
|
||||
@ -350,9 +347,7 @@ func (r *JobRepository) FindConcurrentJobs(
|
||||
}
|
||||
|
||||
if id.Valid {
|
||||
minStart = util.Min(minStart, startTime.Int64)
|
||||
maxStart = util.Max(maxStart, startTime.Int64)
|
||||
|
||||
queryString += fmt.Sprintf("&jobId=%d", int(jobId.Int64))
|
||||
items = append(items,
|
||||
&model.JobLink{
|
||||
ID: fmt.Sprint(id.Int64),
|
||||
@ -376,9 +371,7 @@ func (r *JobRepository) FindConcurrentJobs(
|
||||
}
|
||||
|
||||
if id.Valid {
|
||||
minStart = util.Min(minStart, startTime.Int64)
|
||||
maxStart = util.Max(maxStart, startTime.Int64)
|
||||
|
||||
queryString += fmt.Sprintf("&jobId=%d", int(jobId.Int64))
|
||||
items = append(items,
|
||||
&model.JobLink{
|
||||
ID: fmt.Sprint(id.Int64),
|
||||
@ -388,8 +381,6 @@ func (r *JobRepository) FindConcurrentJobs(
|
||||
}
|
||||
|
||||
cnt := len(items)
|
||||
queryString := fmt.Sprintf("cluster=%s&startTime=%d-%d&node=%s",
|
||||
job.Cluster, minStart, maxStart, hostname)
|
||||
|
||||
return &model.JobLinkResultList{
|
||||
ListQuery: &queryString,
|
||||
|
@ -1,4 +1,10 @@
|
||||
ALTER TABLE configuration ADD COLUMN value_new varchar(255);
|
||||
INSERT INTO configuration (value_new) SELECT value FROM configuration;
|
||||
ALTER TABLE configuration DROP COLUMN value;
|
||||
ALTER TABLE configuration RENAME COLUMN value_new TO value;
|
||||
CREATE TABLE IF NOT EXISTS configuration_new (
|
||||
username varchar(255),
|
||||
confkey varchar(255),
|
||||
value varchar(255),
|
||||
PRIMARY KEY (username, confkey),
|
||||
FOREIGN KEY (username) REFERENCES user (username) ON DELETE CASCADE ON UPDATE NO ACTION);
|
||||
|
||||
INSERT INTO configuration_new SELECT * FROM configuration;
|
||||
DROP TABLE configuration;
|
||||
ALTER TABLE configuration_new RENAME TO configuration;
|
||||
|
@ -1,4 +1,10 @@
|
||||
ALTER TABLE configuration ADD COLUMN value_new TEXT;
|
||||
INSERT INTO configuration (value_new) SELECT value FROM configuration;
|
||||
ALTER TABLE configuration DROP COLUMN value;
|
||||
ALTER TABLE configuration RENAME COLUMN value_new TO value;
|
||||
CREATE TABLE IF NOT EXISTS configuration_new (
|
||||
username varchar(255),
|
||||
confkey varchar(255),
|
||||
value text,
|
||||
PRIMARY KEY (username, confkey),
|
||||
FOREIGN KEY (username) REFERENCES user (username) ON DELETE CASCADE ON UPDATE NO ACTION);
|
||||
|
||||
INSERT INTO configuration_new SELECT * FROM configuration;
|
||||
DROP TABLE configuration;
|
||||
ALTER TABLE configuration_new RENAME TO configuration;
|
||||
|
@ -263,11 +263,11 @@ func buildStringCondition(field string, cond *model.StringInput, query sq.Select
|
||||
return query.Where(field+" LIKE ?", fmt.Sprint("%", *cond.Contains, "%"))
|
||||
}
|
||||
if cond.In != nil {
|
||||
queryUsers := make([]string, len(cond.In))
|
||||
queryElements := make([]string, len(cond.In))
|
||||
for i, val := range cond.In {
|
||||
queryUsers[i] = val
|
||||
queryElements[i] = val
|
||||
}
|
||||
return query.Where(sq.Or{sq.Eq{"job.user": queryUsers}})
|
||||
return query.Where(sq.Or{sq.Eq{field: queryElements}})
|
||||
}
|
||||
return query
|
||||
}
|
||||
|
@ -184,6 +184,9 @@ func buildFilterPresets(query url.Values) map[string]interface{} {
|
||||
}
|
||||
}
|
||||
}
|
||||
if query.Get("node") != "" {
|
||||
filterPresets["node"] = query.Get("node")
|
||||
}
|
||||
if query.Get("numNodes") != "" {
|
||||
parts := strings.Split(query.Get("numNodes"), "-")
|
||||
if len(parts) == 2 {
|
||||
@ -205,7 +208,13 @@ func buildFilterPresets(query url.Values) map[string]interface{} {
|
||||
}
|
||||
}
|
||||
if query.Get("jobId") != "" {
|
||||
if len(query["jobId"]) == 1 {
|
||||
filterPresets["jobId"] = query.Get("jobId")
|
||||
filterPresets["jobIdMatch"] = "eq"
|
||||
} else {
|
||||
filterPresets["jobId"] = query["jobId"]
|
||||
filterPresets["jobIdMatch"] = "in"
|
||||
}
|
||||
}
|
||||
if query.Get("arrayJobId") != "" {
|
||||
if num, err := strconv.Atoi(query.Get("arrayJobId")); err == nil {
|
||||
|
@ -27,7 +27,7 @@
|
||||
resources { hostname, hwthreads, accelerators },
|
||||
metaData,
|
||||
userData { name, email },
|
||||
concurrentJobs { items { id, jobId }, count }
|
||||
concurrentJobs { items { id, jobId }, count, listQuery }
|
||||
}
|
||||
`)
|
||||
|
||||
@ -118,11 +118,12 @@
|
||||
{/if}
|
||||
</Col>
|
||||
{#if $jobMetrics.data && $initq.data}
|
||||
{#if $initq.data.job.concurrentJobs != null}
|
||||
{#if $initq.data.job.concurrentJobs.items.length != 0}
|
||||
{#if authlevel > roles.manager}
|
||||
<Col>
|
||||
<h5>Concurrent Jobs <Icon name="info-circle" style="cursor:help;" title="Shared jobs running on the same node with overlapping runtimes"/></h5>
|
||||
<ul>
|
||||
<li><a href="/monitoring/jobs/?{$initq.data.job.concurrentJobs.listQuery}" target="_blank">See All</a></li>
|
||||
{#each $initq.data.job.concurrentJobs.items as pjob, index}
|
||||
<li><a href="/monitoring/job/{pjob.id}" target="_blank">{pjob.jobId}</a></li>
|
||||
{/each}
|
||||
|
@ -23,7 +23,7 @@
|
||||
const ccconfig = getContext('cc-config')
|
||||
const clusters = getContext('clusters')
|
||||
const client = getContextClient();
|
||||
const query = gql`query($cluster: String!, $nodes: [String!], $from: Time!, $to: Time!) {
|
||||
const nodeMetricsQuery = gql`query($cluster: String!, $nodes: [String!], $from: Time!, $to: Time!) {
|
||||
nodeMetrics(cluster: $cluster, nodes: $nodes, from: $from, to: $to) {
|
||||
host
|
||||
subCluster
|
||||
@ -42,9 +42,9 @@
|
||||
}
|
||||
}`;
|
||||
|
||||
$: nodesQuery = queryStore({
|
||||
$: nodeMetricsData = queryStore({
|
||||
client: client,
|
||||
query: query,
|
||||
query: nodeMetricsQuery,
|
||||
variables: {
|
||||
cluster: cluster,
|
||||
nodes: [hostname],
|
||||
@ -53,8 +53,44 @@
|
||||
}
|
||||
});
|
||||
|
||||
let itemsPerPage = ccconfig.plot_list_jobsPerPage;
|
||||
let page = 1;
|
||||
let paging = { itemsPerPage, page };
|
||||
let sorting = { field: "startTime", order: "DESC" };
|
||||
$: filter = [
|
||||
{cluster: { eq: cluster }},
|
||||
{node: { eq: hostname }},
|
||||
{state: 'running'}
|
||||
// {startTime: {
|
||||
// from: from.toISOString(),
|
||||
// to: to.toISOString()
|
||||
// }}
|
||||
];
|
||||
|
||||
const nodeJobsQuery = gql`
|
||||
query (
|
||||
$filter: [JobFilter!]!
|
||||
$sorting: OrderByInput!
|
||||
$paging: PageRequest!
|
||||
) {
|
||||
jobs(filter: $filter, order: $sorting, page: $paging) {
|
||||
# items {
|
||||
# id
|
||||
# jobId
|
||||
# }
|
||||
count
|
||||
}
|
||||
}
|
||||
`;
|
||||
|
||||
$: nodeJobsData = queryStore({
|
||||
client: client,
|
||||
query: nodeJobsQuery,
|
||||
variables: { paging, sorting, filter }
|
||||
});
|
||||
|
||||
let metricUnits = {}
|
||||
$: if ($nodesQuery.data) {
|
||||
$: if ($nodeMetricsData.data) {
|
||||
let thisCluster = clusters.find(c => c.name == cluster)
|
||||
if (thisCluster) {
|
||||
for (let metric of thisCluster.metricConfig) {
|
||||
@ -67,7 +103,7 @@
|
||||
}
|
||||
}
|
||||
|
||||
// $: console.log($nodesQuery?.data?.nodeMetrics[0].metrics)
|
||||
const dateToUnixEpoch = rfc3339 => Math.floor(Date.parse(rfc3339) / 1000)
|
||||
</script>
|
||||
|
||||
<Row>
|
||||
@ -82,6 +118,18 @@
|
||||
<InputGroupText>{hostname} ({cluster})</InputGroupText>
|
||||
</InputGroup>
|
||||
</Col>
|
||||
<Col>
|
||||
{#if $nodeJobsData.fetching }
|
||||
<Spinner/>
|
||||
{:else}
|
||||
{#if $nodeJobsData.data}
|
||||
Currently running jobs on this node: { $nodeJobsData.data.jobs.count }
|
||||
[ <a href="/monitoring/jobs/?cluster={cluster}&state=running&node={hostname}" target="_blank">View in Job List</a> ]
|
||||
{:else}
|
||||
No currently running jobs.
|
||||
{/if}
|
||||
{/if}
|
||||
</Col>
|
||||
<Col>
|
||||
<TimeSelection
|
||||
bind:from={from}
|
||||
@ -92,9 +140,9 @@
|
||||
<br/>
|
||||
<Row>
|
||||
<Col>
|
||||
{#if $nodesQuery.error}
|
||||
<Card body color="danger">{$nodesQuery.error.message}</Card>
|
||||
{:else if $nodesQuery.fetching || $initq.fetching}
|
||||
{#if $nodeMetricsData.error}
|
||||
<Card body color="danger">{$nodeMetricsData.error.message}</Card>
|
||||
{:else if $nodeMetricsData.fetching || $initq.fetching}
|
||||
<Spinner/>
|
||||
{:else}
|
||||
<PlotTable
|
||||
@ -102,18 +150,18 @@
|
||||
let:width
|
||||
renderFor="node"
|
||||
itemsPerRow={ccconfig.plot_view_plotsPerRow}
|
||||
items={$nodesQuery.data.nodeMetrics[0].metrics
|
||||
.map(m => ({ ...m, disabled: checkMetricDisabled(m.name, cluster, $nodesQuery.data.nodeMetrics[0].subCluster)}))
|
||||
items={$nodeMetricsData.data.nodeMetrics[0].metrics
|
||||
.map(m => ({ ...m, disabled: checkMetricDisabled(m.name, cluster, $nodeMetricsData.data.nodeMetrics[0].subCluster)}))
|
||||
.sort((a, b) => a.name.localeCompare(b.name))}>
|
||||
|
||||
<h4 style="text-align: center; padding-top:15px;">{item.name} {metricUnits[item.name]}</h4>
|
||||
{#if item.disabled === false && item.metric}
|
||||
<MetricPlot
|
||||
width={width} height={300} metric={item.name} timestep={item.metric.timestep}
|
||||
cluster={clusters.find(c => c.name == cluster)} subCluster={$nodesQuery.data.nodeMetrics[0].subCluster}
|
||||
cluster={clusters.find(c => c.name == cluster)} subCluster={$nodeMetricsData.data.nodeMetrics[0].subCluster}
|
||||
series={item.metric.series} />
|
||||
{:else if item.disabled === true && item.metric}
|
||||
<Card style="margin-left: 2rem;margin-right: 2rem;" body color="info">Metric disabled for subcluster <code>{item.name}:{$nodesQuery.data.nodeMetrics[0].subCluster}</code></Card>
|
||||
<Card style="margin-left: 2rem;margin-right: 2rem;" body color="info">Metric disabled for subcluster <code>{item.name}:{$nodeMetricsData.data.nodeMetrics[0].subCluster}</code></Card>
|
||||
{:else}
|
||||
<Card style="margin-left: 2rem;margin-right: 2rem;" body color="warning">No dataset returned for <code>{item.name}</code></Card>
|
||||
{/if}
|
||||
|
@ -34,6 +34,7 @@
|
||||
let filters = {
|
||||
projectMatch: filterPresets.projectMatch || 'contains',
|
||||
userMatch: filterPresets.userMatch || 'contains',
|
||||
jobIdMatch: filterPresets.jobIdMatch || 'eq',
|
||||
|
||||
cluster: filterPresets.cluster || null,
|
||||
partition: filterPresets.partition || null,
|
||||
@ -47,6 +48,7 @@
|
||||
project: filterPresets.project || '',
|
||||
jobName: filterPresets.jobName || '',
|
||||
|
||||
node: filterPresets.node || null,
|
||||
numNodes: filterPresets.numNodes || { from: null, to: null },
|
||||
numHWThreads: filterPresets.numHWThreads || { from: null, to: null },
|
||||
numAccelerators: filterPresets.numAccelerators || { from: null, to: null },
|
||||
@ -74,6 +76,8 @@
|
||||
let items = []
|
||||
if (filters.cluster)
|
||||
items.push({ cluster: { eq: filters.cluster } })
|
||||
if (filters.node)
|
||||
items.push({ node: { contains: filters.node } })
|
||||
if (filters.partition)
|
||||
items.push({ partition: { eq: filters.partition } })
|
||||
if (filters.states.length != allJobStates.length)
|
||||
@ -85,7 +89,7 @@
|
||||
if (filters.duration.from || filters.duration.to)
|
||||
items.push({ duration: { from: filters.duration.from, to: filters.duration.to } })
|
||||
if (filters.jobId)
|
||||
items.push({ jobId: { eq: filters.jobId } })
|
||||
items.push({ jobId: { [filters.jobIdMatch]: filters.jobId } })
|
||||
if (filters.arrayJobId != null)
|
||||
items.push({ arrayJobId: filters.arrayJobId })
|
||||
if (filters.numNodes.from != null || filters.numNodes.to != null)
|
||||
@ -114,6 +118,8 @@
|
||||
let opts = []
|
||||
if (filters.cluster)
|
||||
opts.push(`cluster=${filters.cluster}`)
|
||||
if (filters.node)
|
||||
opts.push(`node=${filters.node}`)
|
||||
if (filters.partition)
|
||||
opts.push(`partition=${filters.partition}`)
|
||||
if (filters.states.length != allJobStates.length)
|
||||
@ -125,6 +131,15 @@
|
||||
// } else {
|
||||
opts.push(`startTime=${dateToUnixEpoch(filters.startTime.from)}-${dateToUnixEpoch(filters.startTime.to)}`)
|
||||
// }
|
||||
if (filters.jobId.length != 0)
|
||||
if (filters.jobIdMatch != 'in') {
|
||||
opts.push(`jobId=${filters.jobId}`)
|
||||
} else {
|
||||
for (let singleJobId of filters.jobId)
|
||||
opts.push(`jobId=${singleJobId}`)
|
||||
}
|
||||
if (filters.jobIdMatch != 'eq')
|
||||
opts.push(`jobIdMatch=${filters.jobIdMatch}`)
|
||||
for (let tag of filters.tags)
|
||||
opts.push(`tag=${tag}`)
|
||||
if (filters.duration.from && filters.duration.to)
|
||||
@ -272,6 +287,12 @@
|
||||
</Info>
|
||||
{/if}
|
||||
|
||||
{#if filters.node != null }
|
||||
<Info icon="hdd-stack" on:click={() => (isResourcesOpen = true)}>
|
||||
Node: {filters.node}
|
||||
</Info>
|
||||
{/if}
|
||||
|
||||
{#if filters.stats.length > 0}
|
||||
<Info icon="bar-chart" on:click={() => (isStatsOpen = true)}>
|
||||
{filters.stats.map(stat => `${stat.text}: ${stat.from} - ${stat.to}`).join(', ')}
|
||||
@ -318,6 +339,7 @@
|
||||
bind:numNodes={filters.numNodes}
|
||||
bind:numHWThreads={filters.numHWThreads}
|
||||
bind:numAccelerators={filters.numAccelerators}
|
||||
bind:namedNode={filters.node}
|
||||
bind:isNodesModified={isNodesModified}
|
||||
bind:isHwthreadsModified={isHwthreadsModified}
|
||||
bind:isAccsModified={isAccsModified}
|
||||
|
@ -16,8 +16,9 @@
|
||||
export let isNodesModified = false
|
||||
export let isHwthreadsModified = false
|
||||
export let isAccsModified = false
|
||||
export let namedNode = null
|
||||
|
||||
let pendingNumNodes = numNodes, pendingNumHWThreads = numHWThreads, pendingNumAccelerators = numAccelerators
|
||||
let pendingNumNodes = numNodes, pendingNumHWThreads = numHWThreads, pendingNumAccelerators = numAccelerators, pendingNamedNode = namedNode
|
||||
|
||||
const findMaxNumAccels = clusters => clusters.reduce((max, cluster) => Math.max(max,
|
||||
cluster.subClusters.reduce((max, sc) => Math.max(max, sc.topology.accelerators?.length || 0), 0)), 0)
|
||||
@ -76,7 +77,9 @@
|
||||
Select number of utilized Resources
|
||||
</ModalHeader>
|
||||
<ModalBody>
|
||||
<h6>Number of Nodes</h6>
|
||||
<h6>Named Node</h6>
|
||||
<input type="text" class="form-control" bind:value={pendingNamedNode}>
|
||||
<h6 style="margin-top: 1rem;">Number of Nodes</h6>
|
||||
<DoubleRangeSlider
|
||||
on:change={({ detail }) => {
|
||||
pendingNumNodes = { from: detail[0], to: detail[1] }
|
||||
@ -117,7 +120,8 @@
|
||||
numNodes ={ from: pendingNumNodes.from, to: pendingNumNodes.to }
|
||||
numHWThreads = { from: pendingNumHWThreads.from, to: pendingNumHWThreads.to }
|
||||
numAccelerators = { from: pendingNumAccelerators.from, to: pendingNumAccelerators.to }
|
||||
dispatch('update', { numNodes, numHWThreads, numAccelerators })
|
||||
namedNode = pendingNamedNode
|
||||
dispatch('update', { numNodes, numHWThreads, numAccelerators, namedNode })
|
||||
}}>
|
||||
Close & Apply
|
||||
</Button>
|
||||
@ -126,13 +130,15 @@
|
||||
pendingNumNodes = { from: null, to: null }
|
||||
pendingNumHWThreads = { from: null, to: null }
|
||||
pendingNumAccelerators = { from: null, to: null }
|
||||
pendingNamedNode = null
|
||||
numNodes = { from: pendingNumNodes.from, to: pendingNumNodes.to }
|
||||
numHWThreads = { from: pendingNumHWThreads.from, to: pendingNumHWThreads.to }
|
||||
numAccelerators = { from: pendingNumAccelerators.from, to: pendingNumAccelerators.to }
|
||||
isNodesModified = false
|
||||
isHwthreadsModified = false
|
||||
isAccsModified = false
|
||||
dispatch('update', { numNodes, numHWThreads, numAccelerators })
|
||||
namedNode = pendingNamedNode
|
||||
dispatch('update', { numNodes, numHWThreads, numAccelerators, namedNode})
|
||||
}}>Reset</Button>
|
||||
<Button on:click={() => (isOpen = false)}>Close</Button>
|
||||
</ModalFooter>
|
||||
|
Loading…
Reference in New Issue
Block a user