syncthing/vendor/github.com/prometheus/procfs/stat.go
Jakob Borg 916ec63af6 cmd/stdiscosrv: New discovery server (fixes #4618)
This is a new revision of the discovery server. Relevant changes and
non-changes:

- Protocol towards clients is unchanged.

- Recommended large scale design is still to be deployed nehind nginx (I
  tested, and it's still a lot faster at terminating TLS).

- Database backend is leveldb again, only. It scales enough, is easy to
  setup, and we don't need any backend to take care of.

- Server supports replication. This is a simple TCP channel - protect it
  with a firewall when deploying over the internet. (We deploy this within
  the same datacenter, and with firewall.) Any incoming client announces
  are sent over the replication channel(s) to other peer discosrvs.
  Incoming replication changes are applied to the database as if they came
  from clients, but without the TLS/certificate overhead.

- Metrics are exposed using the prometheus library, when enabled.

- The database values and replication protocol is protobuf, because JSON
  was quite CPU intensive when I tried that and benchmarked it.

- The "Retry-After" value for failed lookups gets slowly increased from
  a default of 120 seconds, by 5 seconds for each failed lookup,
  independently by each discosrv. This lowers the query load over time for
  clients that are never seen. The Retry-After maxes out at 3600 after a
  couple of weeks of this increase. The number of failed lookups is
  stored in the database, now and then (avoiding making each lookup a
  database put).

All in all this means clients can be pointed towards a cluster using
just multiple A / AAAA records to gain both load sharing and redundancy
(if one is down, clients will talk to the remaining ones).

GitHub-Pull-Request: https://github.com/syncthing/syncthing/pull/4648
2018-01-14 08:52:31 +00:00

220 lines
6.1 KiB
Go

package procfs
import (
"bufio"
"fmt"
"io"
"os"
"strconv"
"strings"
)
// CPUStat shows how much time the cpu spend in various stages.
type CPUStat struct {
User float64
Nice float64
System float64
Idle float64
Iowait float64
IRQ float64
SoftIRQ float64
Steal float64
Guest float64
GuestNice float64
}
// SoftIRQStat represent the softirq statistics as exported in the procfs stat file.
// A nice introduction can be found at https://0xax.gitbooks.io/linux-insides/content/interrupts/interrupts-9.html
// It is possible to get per-cpu stats by reading /proc/softirqs
type SoftIRQStat struct {
Hi uint64
Timer uint64
NetTx uint64
NetRx uint64
Block uint64
BlockIoPoll uint64
Tasklet uint64
Sched uint64
Hrtimer uint64
Rcu uint64
}
// Stat represents kernel/system statistics.
type Stat struct {
// Boot time in seconds since the Epoch.
BootTime uint64
// Summed up cpu statistics.
CPUTotal CPUStat
// Per-CPU statistics.
CPU []CPUStat
// Number of times interrupts were handled, which contains numbered and unnumbered IRQs.
IRQTotal uint64
// Number of times a numbered IRQ was triggered.
IRQ []uint64
// Number of times a context switch happened.
ContextSwitches uint64
// Number of times a process was created.
ProcessCreated uint64
// Number of processes currently running.
ProcessesRunning uint64
// Number of processes currently blocked (waiting for IO).
ProcessesBlocked uint64
// Number of times a softirq was scheduled.
SoftIRQTotal uint64
// Detailed softirq statistics.
SoftIRQ SoftIRQStat
}
// NewStat returns kernel/system statistics read from /proc/stat.
func NewStat() (Stat, error) {
fs, err := NewFS(DefaultMountPoint)
if err != nil {
return Stat{}, err
}
return fs.NewStat()
}
// Parse a cpu statistics line and returns the CPUStat struct plus the cpu id (or -1 for the overall sum).
func parseCPUStat(line string) (CPUStat, int64, error) {
cpuStat := CPUStat{}
var cpu string
count, err := fmt.Sscanf(line, "%s %f %f %f %f %f %f %f %f %f %f",
&cpu,
&cpuStat.User, &cpuStat.Nice, &cpuStat.System, &cpuStat.Idle,
&cpuStat.Iowait, &cpuStat.IRQ, &cpuStat.SoftIRQ, &cpuStat.Steal,
&cpuStat.Guest, &cpuStat.GuestNice)
if err != nil && err != io.EOF {
return CPUStat{}, -1, fmt.Errorf("couldn't parse %s (cpu): %s", line, err)
}
if count == 0 {
return CPUStat{}, -1, fmt.Errorf("couldn't parse %s (cpu): 0 elements parsed", line)
}
cpuStat.User /= userHZ
cpuStat.Nice /= userHZ
cpuStat.System /= userHZ
cpuStat.Idle /= userHZ
cpuStat.Iowait /= userHZ
cpuStat.IRQ /= userHZ
cpuStat.SoftIRQ /= userHZ
cpuStat.Steal /= userHZ
cpuStat.Guest /= userHZ
cpuStat.GuestNice /= userHZ
if cpu == "cpu" {
return cpuStat, -1, nil
}
cpuID, err := strconv.ParseInt(cpu[3:], 10, 64)
if err != nil {
return CPUStat{}, -1, fmt.Errorf("couldn't parse %s (cpu/cpuid): %s", line, err)
}
return cpuStat, cpuID, nil
}
// Parse a softirq line.
func parseSoftIRQStat(line string) (SoftIRQStat, uint64, error) {
softIRQStat := SoftIRQStat{}
var total uint64
var prefix string
_, err := fmt.Sscanf(line, "%s %d %d %d %d %d %d %d %d %d %d %d",
&prefix, &total,
&softIRQStat.Hi, &softIRQStat.Timer, &softIRQStat.NetTx, &softIRQStat.NetRx,
&softIRQStat.Block, &softIRQStat.BlockIoPoll,
&softIRQStat.Tasklet, &softIRQStat.Sched,
&softIRQStat.Hrtimer, &softIRQStat.Rcu)
if err != nil {
return SoftIRQStat{}, 0, fmt.Errorf("couldn't parse %s (softirq): %s", line, err)
}
return softIRQStat, total, nil
}
// NewStat returns an information about current kernel/system statistics.
func (fs FS) NewStat() (Stat, error) {
// See https://www.kernel.org/doc/Documentation/filesystems/proc.txt
f, err := os.Open(fs.Path("stat"))
if err != nil {
return Stat{}, err
}
defer f.Close()
stat := Stat{}
scanner := bufio.NewScanner(f)
for scanner.Scan() {
line := scanner.Text()
parts := strings.Fields(scanner.Text())
// require at least <key> <value>
if len(parts) < 2 {
continue
}
switch {
case parts[0] == "btime":
if stat.BootTime, err = strconv.ParseUint(parts[1], 10, 64); err != nil {
return Stat{}, fmt.Errorf("couldn't parse %s (btime): %s", parts[1], err)
}
case parts[0] == "intr":
if stat.IRQTotal, err = strconv.ParseUint(parts[1], 10, 64); err != nil {
return Stat{}, fmt.Errorf("couldn't parse %s (intr): %s", parts[1], err)
}
numberedIRQs := parts[2:]
stat.IRQ = make([]uint64, len(numberedIRQs))
for i, count := range numberedIRQs {
if stat.IRQ[i], err = strconv.ParseUint(count, 10, 64); err != nil {
return Stat{}, fmt.Errorf("couldn't parse %s (intr%d): %s", count, i, err)
}
}
case parts[0] == "ctxt":
if stat.ContextSwitches, err = strconv.ParseUint(parts[1], 10, 64); err != nil {
return Stat{}, fmt.Errorf("couldn't parse %s (ctxt): %s", parts[1], err)
}
case parts[0] == "processes":
if stat.ProcessCreated, err = strconv.ParseUint(parts[1], 10, 64); err != nil {
return Stat{}, fmt.Errorf("couldn't parse %s (processes): %s", parts[1], err)
}
case parts[0] == "procs_running":
if stat.ProcessesRunning, err = strconv.ParseUint(parts[1], 10, 64); err != nil {
return Stat{}, fmt.Errorf("couldn't parse %s (procs_running): %s", parts[1], err)
}
case parts[0] == "procs_blocked":
if stat.ProcessesBlocked, err = strconv.ParseUint(parts[1], 10, 64); err != nil {
return Stat{}, fmt.Errorf("couldn't parse %s (procs_blocked): %s", parts[1], err)
}
case parts[0] == "softirq":
softIRQStats, total, err := parseSoftIRQStat(line)
if err != nil {
return Stat{}, err
}
stat.SoftIRQTotal = total
stat.SoftIRQ = softIRQStats
case strings.HasPrefix(parts[0], "cpu"):
cpuStat, cpuID, err := parseCPUStat(line)
if err != nil {
return Stat{}, err
}
if cpuID == -1 {
stat.CPUTotal = cpuStat
} else {
for int64(len(stat.CPU)) <= cpuID {
stat.CPU = append(stat.CPU, CPUStat{})
}
stat.CPU[cpuID] = cpuStat
}
}
}
if err := scanner.Err(); err != nil {
return Stat{}, fmt.Errorf("couldn't parse %s: %s", f.Name(), err)
}
return stat, nil
}