storage SAT: wait for smartctl self-test completion, add human-readable resource summary

smartctl -t short only launches the self-test and returns immediately
("Testing has begun"); unlike nvme device-self-test --wait, it has no
blocking mode. Validate/Load runs closed the task and produced reports
before the drive actually finished the test. Now poll smartctl -a until
the test completes (or times out) and report the real result.

Also add a per-disk "Resource" section with pseudographic progress bars
for uptime (vs 5y design life), bytes written (vs 1 DWPD x 5y budget),
and bytes read (percent from SMART attribute 242), all rendered in
human-scaled units (days/years, TB/PB) instead of raw hour/byte counts.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
This commit is contained in:
Mikhail Chusavitin
2026-07-01 14:54:48 +03:00
parent 8575cf06f8
commit 5bfaecd417
2 changed files with 229 additions and 7 deletions
+55
View File
@@ -746,6 +746,25 @@ func (s *System) RunStorageAcceptancePack(ctx context.Context, baseDir string, e
key := filepath.Base(devPath) + "_" + strings.ReplaceAll(job.name, "-", "_")
fmt.Fprintf(&summary, "%s_rc=%d\n", key, rc)
fmt.Fprintf(&summary, "%s_status=%s\n", key, status)
// smartctl -t short only launches the self-test on the drive firmware and
// returns immediately ("Testing has begun"); unlike `nvme device-self-test
// --wait`, smartctl has no blocking mode, so we must poll the drive
// ourselves until the self-test actually finishes.
if job.name == "smartctl-self-test-short" && err == nil {
statusName := "smartctl-self-test-status"
statusOut := waitForSmartctlSelfTest(ctx, verboseLog, devPath, logFunc)
deviceOutputs[statusName] = statusOut
statusFile := fmt.Sprintf("%s-%02d-%s.log", prefix, cmdIndex+2, statusName)
if writeErr := os.WriteFile(filepath.Join(runDir, statusFile), statusOut, 0644); writeErr != nil {
return "", writeErr
}
sStatus, sRC := classifySATResult(statusName, statusOut, nil)
stats.Add(sStatus)
sKey := filepath.Base(devPath) + "_" + strings.ReplaceAll(statusName, "-", "_")
fmt.Fprintf(&summary, "%s_rc=%d\n", sKey, sRC)
fmt.Fprintf(&summary, "%s_status=%s\n", sKey, sStatus)
}
}
reportText := GenerateDiskReportText(index+1, devPath, deviceOutputs, time.Now().UTC())
_ = os.WriteFile(filepath.Join(runDir, "disk-"+prefix+"-report.txt"), []byte(reportText), 0644)
@@ -1181,6 +1200,42 @@ func runSATCommandCtx(ctx context.Context, verboseLog, name string, cmd []string
return out, err
}
// smartctlSelfTestPollInterval/Timeout bound how long we poll the drive after
// launching `smartctl -t short`, which SMART/ATA specs put at ~2 minutes.
const (
smartctlSelfTestPollInterval = 5 * time.Second
smartctlSelfTestTimeout = 4 * time.Minute
)
// waitForSmartctlSelfTest polls `smartctl -a` until the short self-test
// started on devPath finishes (or the timeout/context elapses) and returns
// the final output, which reflects the actual test result rather than the
// "Testing has begun" launch acknowledgement.
func waitForSmartctlSelfTest(ctx context.Context, verboseLog, devPath string, logFunc func(string)) []byte {
deadline := time.Now().Add(smartctlSelfTestTimeout)
var last []byte
for {
out, _ := runSATCommandCtx(ctx, verboseLog, "smartctl-self-test-status", []string{"smartctl", "-a", devPath}, nil, nil)
last = out
if ctx.Err() != nil {
return last
}
lower := bytes.ToLower(out)
if !bytes.Contains(lower, []byte("self-test routine in progress")) &&
!bytes.Contains(lower, []byte("% of test remaining")) {
return last
}
if time.Now().After(deadline) {
return last
}
select {
case <-ctx.Done():
return last
case <-time.After(smartctlSelfTestPollInterval):
}
}
}
func listStorageDevices() ([]string, error) {
out, err := satExecCommand("lsblk", "-dn", "-o", "NAME,TYPE,TRAN").Output()
if err != nil {