package diagnostics
import (
+ "archive/tar"
"bytes"
"context"
+ _ "embed"
"flag"
"fmt"
"io"
"strings"
"time"
+ "git.arvados.org/arvados.git/lib/cmd"
"git.arvados.org/arvados.git/sdk/go/arvados"
"git.arvados.org/arvados.git/sdk/go/ctxlog"
"github.com/sirupsen/logrus"
type Command struct{}
-func (cmd Command) RunCommand(prog string, args []string, stdin io.Reader, stdout, stderr io.Writer) int {
+func (Command) RunCommand(prog string, args []string, stdin io.Reader, stdout, stderr io.Writer) int {
var diag diagnoser
f := flag.NewFlagSet(prog, flag.ContinueOnError)
f.StringVar(&diag.projectName, "project-name", "scratch area for diagnostics", "name of project to find/create in home project and use for temporary/test objects")
f.StringVar(&diag.logLevel, "log-level", "info", "logging level (debug, info, warning, error)")
+ f.StringVar(&diag.dockerImage, "docker-image", "", "image to use when running a test container (default: use embedded hello-world image)")
f.BoolVar(&diag.checkInternal, "internal-client", false, "check that this host is considered an \"internal\" client")
f.BoolVar(&diag.checkExternal, "external-client", false, "check that this host is considered an \"external\" client")
f.IntVar(&diag.priority, "priority", 500, "priority for test container (1..1000, or 0 to skip)")
f.DurationVar(&diag.timeout, "timeout", 10*time.Second, "timeout for http requests")
- err := f.Parse(args)
- if err == flag.ErrHelp {
- return 0
- } else if err != nil {
- fmt.Fprintln(stderr, err)
- return 2
+ if ok, code := cmd.ParseFlags(f, prog, args, "", stderr); !ok {
+ return code
}
diag.logger = ctxlog.New(stdout, "text", diag.logLevel)
diag.logger.SetFormatter(&logrus.TextFormatter{DisableTimestamp: true, DisableLevelTruncation: true, PadLevelText: true})
}
}
+// docker save hello-world > hello-world.tar
+//go:embed hello-world.tar
+var HelloWorldDockerImage []byte
+
type diagnoser struct {
stdout io.Writer
stderr io.Writer
logLevel string
priority int
projectName string
+ dockerImage string
checkInternal bool
checkExternal bool
timeout time.Duration
}
func (diag *diagnoser) debugf(f string, args ...interface{}) {
- diag.logger.Debugf(f, args...)
+ diag.logger.Debugf(" ... "+f, args...)
}
func (diag *diagnoser) infof(f string, args ...interface{}) {
- diag.logger.Infof(f, args...)
+ diag.logger.Infof(" ... "+f, args...)
}
func (diag *diagnoser) warnf(f string, args ...interface{}) {
- diag.logger.Warnf(f, args...)
+ diag.logger.Warnf(" ... "+f, args...)
}
func (diag *diagnoser) errorf(f string, args ...interface{}) {
}
diag.done[id] = true
- diag.infof("%4d: %s", id, title)
+ diag.logger.Infof("%4d: %s", id, title)
t0 := time.Now()
err := fn()
- elapsed := fmt.Sprintf("%.0dms", time.Now().Sub(t0)/time.Millisecond)
+ elapsed := fmt.Sprintf("%d ms", time.Now().Sub(t0)/time.Millisecond)
if err != nil {
diag.errorf("%4d: %s (%s): %s", id, title, elapsed, err)
} else {
- diag.debugf("%4d: %s (%s): ok", id, title, elapsed)
+ diag.logger.Debugf("%4d: %s (%s): ok", id, title, elapsed)
}
}
var cluster arvados.Cluster
cfgpath := "arvados/v1/config"
+ cfgOK := false
diag.dotest(20, fmt.Sprintf("getting exported config from https://%s/%s", client.APIHost, cfgpath), func() error {
ctx, cancel := context.WithDeadline(context.Background(), time.Now().Add(diag.timeout))
defer cancel()
return err
}
diag.debugf("Collections.BlobSigning = %v", cluster.Collections.BlobSigning)
+ cfgOK = true
return nil
})
return nil
})
+ if !cfgOK {
+ diag.errorf("cannot proceed without cluster config -- aborting without running any further tests")
+ return
+ }
+
// uncomment to create some spurious errors
// cluster.Services.WebDAVDownload.ExternalURL.Host = "0.0.0.0:9"
}()
}
+ // Read hello-world.tar to find image ID, so we can upload it
+ // as "sha256:{...}.tar"
+ var imageSHA2 string
+ {
+ tr := tar.NewReader(bytes.NewReader(HelloWorldDockerImage))
+ for {
+ hdr, err := tr.Next()
+ if err == io.EOF {
+ break
+ }
+ if err != nil {
+ diag.errorf("internal error/bug: cannot read embedded docker image tar file: %s", err)
+ return
+ }
+ if s := strings.TrimSuffix(hdr.Name, ".json"); len(s) == 64 && s != hdr.Name {
+ imageSHA2 = s
+ }
+ }
+ if imageSHA2 == "" {
+ diag.errorf("internal error/bug: cannot find {sha256}.json file in embedded docker image tar file")
+ return
+ }
+ }
+ tarfilename := "sha256:" + imageSHA2 + ".tar"
+
diag.dotest(100, "uploading file via webdav", func() error {
ctx, cancel := context.WithDeadline(context.Background(), time.Now().Add(diag.timeout))
defer cancel()
if collection.UUID == "" {
return fmt.Errorf("skipping, no test collection")
}
- req, err := http.NewRequestWithContext(ctx, "PUT", cluster.Services.WebDAVDownload.ExternalURL.String()+"c="+collection.UUID+"/testfile", bytes.NewBufferString("testfiledata"))
+ req, err := http.NewRequestWithContext(ctx, "PUT", cluster.Services.WebDAVDownload.ExternalURL.String()+"c="+collection.UUID+"/"+tarfilename, bytes.NewReader(HelloWorldDockerImage))
if err != nil {
return fmt.Errorf("BUG? http.NewRequest: %s", err)
}
})
davurl := cluster.Services.WebDAV.ExternalURL
+ davWildcard := strings.HasPrefix(davurl.Host, "*--") || strings.HasPrefix(davurl.Host, "*.")
diag.dotest(110, fmt.Sprintf("checking WebDAV ExternalURL wildcard (%s)", davurl), func() error {
if davurl.Host == "" {
return fmt.Errorf("host missing - content previews will not work")
}
- if !strings.HasPrefix(davurl.Host, "*--") && !strings.HasPrefix(davurl.Host, "*.") && !cluster.Collections.TrustAllContent {
+ if !davWildcard && !cluster.Collections.TrustAllContent {
diag.warnf("WebDAV ExternalURL has no leading wildcard and TrustAllContent==false - content previews will not work")
}
return nil
})
for i, trial := range []struct {
- needcoll bool
- status int
- fileurl string
+ needcoll bool
+ needWildcard bool
+ status int
+ fileurl string
}{
- {false, http.StatusNotFound, strings.Replace(davurl.String(), "*", "d41d8cd98f00b204e9800998ecf8427e-0", 1) + "foo"},
- {false, http.StatusNotFound, strings.Replace(davurl.String(), "*", "d41d8cd98f00b204e9800998ecf8427e-0", 1) + "testfile"},
- {false, http.StatusNotFound, cluster.Services.WebDAVDownload.ExternalURL.String() + "c=d41d8cd98f00b204e9800998ecf8427e+0/_/foo"},
- {false, http.StatusNotFound, cluster.Services.WebDAVDownload.ExternalURL.String() + "c=d41d8cd98f00b204e9800998ecf8427e+0/_/testfile"},
- {true, http.StatusOK, strings.Replace(davurl.String(), "*", strings.Replace(collection.PortableDataHash, "+", "-", -1), 1) + "testfile"},
- {true, http.StatusOK, cluster.Services.WebDAVDownload.ExternalURL.String() + "c=" + collection.UUID + "/_/testfile"},
+ {false, false, http.StatusNotFound, strings.Replace(davurl.String(), "*", "d41d8cd98f00b204e9800998ecf8427e-0", 1) + "foo"},
+ {false, false, http.StatusNotFound, strings.Replace(davurl.String(), "*", "d41d8cd98f00b204e9800998ecf8427e-0", 1) + tarfilename},
+ {false, false, http.StatusNotFound, cluster.Services.WebDAVDownload.ExternalURL.String() + "c=d41d8cd98f00b204e9800998ecf8427e+0/_/foo"},
+ {false, false, http.StatusNotFound, cluster.Services.WebDAVDownload.ExternalURL.String() + "c=d41d8cd98f00b204e9800998ecf8427e+0/_/" + tarfilename},
+ {true, true, http.StatusOK, strings.Replace(davurl.String(), "*", strings.Replace(collection.PortableDataHash, "+", "-", -1), 1) + tarfilename},
+ {true, false, http.StatusOK, cluster.Services.WebDAVDownload.ExternalURL.String() + "c=" + collection.UUID + "/_/" + tarfilename},
} {
diag.dotest(120+i, fmt.Sprintf("downloading from webdav (%s)", trial.fileurl), func() error {
+ if trial.needWildcard && !davWildcard {
+ diag.warnf("skipping collection-id-in-vhost test because WebDAV ExternalURL has no leading wildcard")
+ return nil
+ }
ctx, cancel := context.WithDeadline(context.Background(), time.Now().Add(diag.timeout))
defer cancel()
if trial.needcoll && collection.UUID == "" {
if resp.StatusCode != trial.status {
return fmt.Errorf("unexpected response status: %s", resp.Status)
}
- if trial.status == http.StatusOK && string(body) != "testfiledata" {
- return fmt.Errorf("unexpected response content: %q", body)
+ if trial.status == http.StatusOK && !bytes.Equal(body, HelloWorldDockerImage) {
+ excerpt := body
+ if len(excerpt) > 128 {
+ excerpt = append([]byte(nil), body[:128]...)
+ excerpt = append(excerpt, []byte("[...]")...)
+ }
+ return fmt.Errorf("unexpected response content: len %d, %q", len(body), excerpt)
}
return nil
})
return err
}
if len(vmlist.Items) < 1 {
- return fmt.Errorf("no VMs found")
+ diag.warnf("no VMs found")
+ } else {
+ vm = vmlist.Items[0]
}
- vm = vmlist.Items[0]
return nil
})
ctx, cancel := context.WithDeadline(context.Background(), time.Now().Add(diag.timeout))
defer cancel()
if vm.UUID == "" {
- return fmt.Errorf("skipping, no vm available")
+ diag.warnf("skipping, no vm available")
+ return nil
}
webshelltermurl := cluster.Services.Workbench1.ExternalURL.String() + "virtual_machines/" + vm.UUID + "/webshell/testusername"
diag.debugf("url %s", webshelltermurl)
ctx, cancel := context.WithDeadline(context.Background(), time.Now().Add(diag.timeout))
defer cancel()
if vm.UUID == "" {
- return fmt.Errorf("skipping, no vm available")
+ diag.warnf("skipping, no vm available")
+ return nil
}
u := cluster.Services.WebShell.ExternalURL
webshellurl := u.String() + vm.Hostname + "?"
diag.dotest(160, "running a container", func() error {
if diag.priority < 1 {
- diag.debugf("skipping, caller requested priority<1 (%d)", diag.priority)
+ diag.infof("skipping (use priority > 0 if you want to run a container)")
return nil
}
if project.UUID == "" {
return fmt.Errorf("skipping, no project to work in")
}
+ timestamp := time.Now().Format(time.RFC3339)
+ ctrCommand := []string{"echo", timestamp}
+ if diag.dockerImage == "" {
+ if collection.UUID == "" {
+ return fmt.Errorf("skipping, no test collection to use as docker image")
+ }
+ diag.dockerImage = collection.PortableDataHash
+ ctrCommand = []string{"/hello"}
+ }
+
var cr arvados.ContainerRequest
ctx, cancel := context.WithDeadline(context.Background(), time.Now().Add(diag.timeout))
defer cancel()
- timestamp := time.Now().Format(time.RFC3339)
err := client.RequestAndDecodeContext(ctx, &cr, "POST", "arvados/v1/container_requests", nil, map[string]interface{}{"container_request": map[string]interface{}{
"owner_uuid": project.UUID,
"name": fmt.Sprintf("diagnostics container request %s", timestamp),
- "container_image": "arvados/jobs",
- "command": []string{"echo", timestamp},
+ "container_image": diag.dockerImage,
+ "command": ctrCommand,
"use_existing": false,
"output_path": "/mnt/output",
"output_name": fmt.Sprintf("diagnostics output %s", timestamp),