"errors"
"flag"
"fmt"
- "git.arvados.org/arvados.git/lib/config"
"git.arvados.org/arvados.git/sdk/go/arvados"
"git.arvados.org/arvados.git/sdk/go/arvadosclient"
"git.arvados.org/arvados.git/sdk/go/keepclient"
"github.com/sirupsen/logrus"
)
+const timestampFormat = "2006-01-02T15:04:05"
+
type nodeInfo struct {
// Legacy (records created by Arvados Node Manager with Arvados <= 1.4.3)
Properties struct {
return nil
}
-func parseFlags(prog string, args []string, loader *config.Loader, logger *logrus.Logger, stderr io.Writer) (exitCode int, uuids arrayFlags, resultsDir string, cache bool, err error) {
+func (c *command) parseFlags(prog string, args []string, logger *logrus.Logger, stderr io.Writer) (exitCode int, err error) {
+ var beginStr, endStr string
flags := flag.NewFlagSet("", flag.ContinueOnError)
flags.SetOutput(stderr)
flags.Usage = func() {
fmt.Fprintf(flags.Output(), `
Usage:
- %s [options ...] <uuid> ...
+ %s [options ...] [UUID ...]
+
+ This program analyzes the cost of Arvados container requests and calculates
+ the total cost across all requests. At least one UUID or a timestamp range
+ must be specified.
- This program analyzes the cost of Arvados container requests. For each uuid
- supplied, it creates a CSV report that lists all the containers used to
- fulfill the container request, together with the machine type and cost of
- each container. At least one uuid must be specified.
+ When the '-output' option is specified, a set of CSV files with cost details
+ will be written to the provided directory. Each file is a CSV report that lists
+ all the containers used to fulfill the container request, together with the
+ machine type and cost of each container.
- When supplied with the uuid of a container request, it will calculate the
+ When supplied with the UUID of a container request, it will calculate the
cost of that container request and all its children.
- When supplied with the uuid of a collection, it will see if there is a
- container_request uuid in the properties of the collection, and if so, it
+ When supplied with the UUID of a collection, it will see if there is a
+ container_request UUID in the properties of the collection, and if so, it
will calculate the cost of that container request and all its children.
- When supplied with a project uuid or when supplied with multiple container
- request or collection uuids, it will create a CSV report for each supplied
- uuid, as well as a CSV file with aggregate cost accounting for all supplied
- uuids. The aggregate cost report takes container reuse into account: if a
- container was reused between several container requests, its cost will only
- be counted once.
+ When supplied with a project UUID or when supplied with multiple container
+ request or collection UUIDs, it will calculate the total cost for all
+ supplied UUIDs.
- To get the node costs, the progam queries the Arvados API for current cost
- data for each node type used. This means that the reported cost always
- reflects the cost data as currently defined in the Arvados API configuration
- file.
+ When supplied with a 'begin' and 'end' timestamp (format:
+ %s), it will calculate the cost for all top-level container
+ requests whose containers finished during the specified interval.
+
+ The total cost calculation takes container reuse into account: if a container
+ was reused between several container requests, its cost will only be counted
+ once.
Caveats:
- - the Arvados API configuration cost data may be out of sync with the cloud
- provider.
- - when generating reports for older container requests, the cost data in the
- Arvados API configuration file may have changed since the container request
- was fulfilled. This program uses the cost data stored at the time of the
+
+ - This program uses the cost data from config.yml at the time of the
execution of the container, stored in the 'node.json' file in its log
- collection.
- - if a container was run on a preemptible ("spot") instance, the cost data
+ collection. If the cost data was not correctly configured at the time the
+ container was executed, the output from this program will be incorrect.
+
+ - If a container was run on a preemptible ("spot") instance, the cost data
reported by this program may be wildly inaccurate, because it does not have
access to the spot pricing in effect for the node then the container ran. The
UUID report file that is generated when the '-output' option is specified has
a column that indicates the preemptible state of the instance that ran the
container.
- In order to get the data for the uuids supplied, the ARVADOS_API_HOST and
+ - This program does not take into account overhead costs like the time spent
+ starting and stopping compute nodes that run containers, the cost of the
+ permanent cloud nodes that provide the Arvados services, the cost of data
+ stored in Arvados, etc.
+
+ - When provided with a project UUID, subprojects will not be considered.
+
+ In order to get the data for the UUIDs supplied, the ARVADOS_API_HOST and
ARVADOS_API_TOKEN environment variables must be set.
This program prints the total dollar amount from the aggregate cost
- accounting across all provided uuids on stdout.
-
- When the '-output' option is specified, a set of CSV files with cost details
- will be written to the provided directory.
+ accounting across all provided UUIDs on stdout.
Options:
-`, prog)
+`, prog, timestampFormat)
flags.PrintDefaults()
}
loglevel := flags.String("log-level", "info", "logging `level` (debug, info, ...)")
- flags.StringVar(&resultsDir, "output", "", "output `directory` for the CSV reports")
- flags.BoolVar(&cache, "cache", true, "create and use a local disk cache of Arvados objects")
+ flags.StringVar(&c.resultsDir, "output", "", "output `directory` for the CSV reports")
+ flags.StringVar(&beginStr, "begin", "", fmt.Sprintf("timestamp `begin` for date range operation (format: %s)", timestampFormat))
+ flags.StringVar(&endStr, "end", "", fmt.Sprintf("timestamp `end` for date range operation (format: %s)", timestampFormat))
+ flags.BoolVar(&c.cache, "cache", true, "create and use a local disk cache of Arvados objects")
err = flags.Parse(args)
if err == flag.ErrHelp {
err = nil
exitCode = 2
return
}
- uuids = flags.Args()
+ c.uuids = flags.Args()
- if len(uuids) < 1 {
+ if (len(beginStr) != 0 && len(endStr) == 0) || (len(beginStr) == 0 && len(endStr) != 0) {
+ flags.Usage()
+ err = fmt.Errorf("When specifying a date range, both begin and end must be specified")
+ exitCode = 2
+ return
+ }
+
+ if len(beginStr) != 0 {
+ var errB, errE error
+ c.begin, errB = time.Parse(timestampFormat, beginStr)
+ c.end, errE = time.Parse(timestampFormat, endStr)
+ if (errB != nil) || (errE != nil) {
+ flags.Usage()
+ err = fmt.Errorf("When specifying a date range, both begin and end must be of the format %s %+v, %+v", timestampFormat, errB, errE)
+ exitCode = 2
+ return
+ }
+ }
+
+ if (len(c.uuids) < 1) && (len(beginStr) == 0) {
flags.Usage()
err = fmt.Errorf("error: no uuid(s) provided")
exitCode = 2
return
}
logger.SetLevel(lvl)
- if !cache {
+ if !c.cache {
logger.Debug("Caching disabled\n")
}
return
var tmpCsv string
var tmpTotalCost float64
var totalCost float64
+ fmt.Printf("Processing %s\n", uuid)
var crUUID = uuid
if strings.Contains(uuid, "-4zz18-") {
if err != nil {
return nil, fmt.Errorf("error loading cr object %s: %s", uuid, err)
}
+ if len(cr.ContainerUUID) == 0 {
+ // Nothing to do! E.g. a CR in 'Uncommitted' state.
+ logger.Infof("No container associated with container request %s, skipping\n", crUUID)
+ return nil, nil
+ }
var container arvados.Container
err = loadObject(logger, ac, crUUID, cr.ContainerUUID, cache, &container)
if err != nil {
topNode, err := getNode(arv, ac, kc, cr)
if err != nil {
- return nil, fmt.Errorf("error getting node %s: %s", cr.UUID, err)
+ logger.Errorf("Skipping container request %s: error getting node %s: %s", cr.UUID, cr.UUID, err)
+ return nil, nil
}
tmpCsv, totalCost = addContainerLine(logger, topNode, cr, container)
csv += tmpCsv
if err != nil {
return nil, fmt.Errorf("error querying container_requests: %s", err.Error())
}
- logger.Infof("Collecting child containers for container request %s", crUUID)
+ logger.Infof("Collecting child containers for container request %s (%s)", crUUID, container.FinishedAt)
for _, cr2 := range childCrs.Items {
logger.Info(".")
node, err := getNode(arv, ac, kc, cr2)
if err != nil {
- return nil, fmt.Errorf("error getting node %s: %s", cr2.UUID, err)
+ logger.Errorf("Skipping container request %s: error getting node %s: %s", cr2.UUID, cr2.UUID, err)
+ continue
}
logger.Debug("\nChild container: " + cr2.ContainerUUID + "\n")
var c2 arvados.Container
return
}
-func costanalyzer(prog string, args []string, loader *config.Loader, logger *logrus.Logger, stdout, stderr io.Writer) (exitcode int, err error) {
- exitcode, uuids, resultsDir, cache, err := parseFlags(prog, args, loader, logger, stderr)
+func (c *command) costAnalyzer(prog string, args []string, logger *logrus.Logger, stdout, stderr io.Writer) (exitcode int, err error) {
+ exitcode, err = c.parseFlags(prog, args, logger, stderr)
+
if exitcode != 0 {
return
}
- if resultsDir != "" {
- err = ensureDirectory(logger, resultsDir)
+ if c.resultsDir != "" {
+ err = ensureDirectory(logger, c.resultsDir)
if err != nil {
exitcode = 3
return
}
}
+ uuidChannel := make(chan string)
+
// Arvados Client setup
arv, err := arvadosclient.MakeArvadosClient()
if err != nil {
ac := arvados.NewClientFromEnv()
+ // Populate uuidChannel with the requested uuid list
+ go func() {
+ defer close(uuidChannel)
+ for _, uuid := range c.uuids {
+ uuidChannel <- uuid
+ }
+
+ if !c.begin.IsZero() {
+ initialParams := arvados.ResourceListParams{
+ Filters: []arvados.Filter{{"container.finished_at", ">=", c.begin}, {"container.finished_at", "<", c.end}, {"requesting_container_uuid", "=", nil}},
+ Order: "created_at",
+ }
+ params := initialParams
+ for {
+ // This list variable must be a new one declared
+ // inside the loop: otherwise, items in the API
+ // response would get deep-merged into the items
+ // loaded in previous iterations.
+ var list arvados.ContainerRequestList
+
+ err := ac.RequestAndDecode(&list, "GET", "arvados/v1/container_requests", nil, params)
+ if err != nil {
+ logger.Errorf("Error getting container request list from Arvados API: %s\n", err)
+ break
+ }
+ if len(list.Items) == 0 {
+ break
+ }
+
+ for _, i := range list.Items {
+ uuidChannel <- i.UUID
+ }
+ params.Offset += len(list.Items)
+ }
+
+ }
+ }()
+
cost := make(map[string]float64)
- for _, uuid := range uuids {
+
+ for uuid := range uuidChannel {
+ fmt.Printf("Considering %s\n", uuid)
if strings.Contains(uuid, "-j7d0g-") {
// This is a project (group)
- cost, err = handleProject(logger, uuid, arv, ac, kc, resultsDir, cache)
+ cost, err = handleProject(logger, uuid, arv, ac, kc, c.resultsDir, c.cache)
if err != nil {
exitcode = 1
return
} else if strings.Contains(uuid, "-xvhdp-") || strings.Contains(uuid, "-4zz18-") {
// This is a container request
var crCsv map[string]float64
- crCsv, err = generateCrCsv(logger, uuid, arv, ac, kc, resultsDir, cache)
+ crCsv, err = generateCrCsv(logger, uuid, arv, ac, kc, c.resultsDir, c.cache)
if err != nil {
err = fmt.Errorf("error generating CSV for uuid %s: %s", uuid, err.Error())
exitcode = 2
var csv string
csv = "# Aggregate cost accounting for uuids:\n"
- for _, uuid := range uuids {
+ for _, uuid := range c.uuids {
csv += "# " + uuid + "\n"
}
csv += "TOTAL," + strconv.FormatFloat(total, 'f', 8, 64) + "\n"
- if resultsDir != "" {
+ if c.resultsDir != "" {
// Write the resulting CSV file
- aFile := resultsDir + "/" + time.Now().Format("2006-01-02-15-04-05") + "-aggregate-costaccounting.csv"
+ aFile := c.resultsDir + "/" + time.Now().Format("2006-01-02-15-04-05") + "-aggregate-costaccounting.csv"
err = ioutil.WriteFile(aFile, []byte(csv), 0644)
if err != nil {
err = fmt.Errorf("error writing file with path %s: %s", aFile, err.Error())
projects / arvados.git / blobdiff