Upgrade the cluster with one command, over the agents' own streams
Every upgrade so far has been a script of mine copying a binary to each machine over ssh, restarting it and polling until it came back — which is the job, but not something the product could do, and which needed ssh into every node. `sudo llmgw ctl upgrade VERSION` on the control plane does it. This machine first: the release for its platform, checked against the release's checksums, the old binary kept beside it, llmgw-server restarted, and a wait until every node that was ready has reconnected. Then each node in turn: the control plane tells its agent the version over the stream it already holds; the agent fetches and checks the release itself, swaps it in with a rename, answers, and exits with status 75 so systemd starts the new binary. Engines keep running, as for any agent restart, and are adopted again. A node is done when it is back on the new version, ready, with as many ready replicas as before; one that is not within the timeout stops the run before the next node, so a bad release reaches one machine. Nodes already on the version are skipped, so running it again resumes. The fetch-and-verify is one package now, shared with onboarding's idea of what a release version looks like. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
This commit is contained in:
1 parent
3bf4b7b709
commit
116e75f8cb
19 files changed
+1082
-90
No files matched your search
@@ -8,6 +8,7 @@ import (
|
||||
"encoding/hex"
|
||||
"errors"
|
||||
"fmt"
|
||||
"gitea.mynodes.xyz/ilker/llmgw/internal/release"
|
||||
"io"
|
||||
"log/slog"
|
||||
"maps"
|
||||
@@ -18,6 +19,7 @@ import (
|
||||
"os"
|
||||
"os/exec"
|
||||
"path/filepath"
|
||||
"runtime"
|
||||
"slices"
|
||||
"strconv"
|
||||
"strings"
|
||||
@@ -1119,6 +1121,8 @@ func (a *Agent) handle(ctx context.Context, msg *llmgwv1.ControlMessage, out cha
|
||||
a.removeWeights(m.RemoveWeights.GetPaths())
|
||||
case *llmgwv1.ControlMessage_Provision:
|
||||
a.setProvision(m.Provision)
|
||||
case *llmgwv1.ControlMessage_Upgrade:
|
||||
go a.upgrade(ctx, m.Upgrade, out)
|
||||
case *llmgwv1.ControlMessage_Logs:
|
||||
reply := a.logsReply(m.Logs)
|
||||
// Off the receive loop: a full send queue must not stop commands being
|
||||
@@ -1874,3 +1878,49 @@ func (a *Agent) sampleNVLink(hb *llmgwv1.Heartbeat) {
|
||||
m := discoverIMEX(ctx)
|
||||
hb.Imex = &llmgwv1.IMEX{State: m.State, Channels: int32(m.Channels)}
|
||||
}
|
||||
|
||||
// upgradeExit is the exit status after an upgrade: non-zero, so systemd's
|
||||
// Restart=on-failure starts the new binary, and distinct, so the journal says
|
||||
// why the agent went.
|
||||
const upgradeExit = 75
|
||||
|
||||
// exitForUpgrade ends the process; a variable so a test can see it called
|
||||
// rather than have its own process end.
|
||||
var exitForUpgrade = func() { os.Exit(upgradeExit) }
|
||||
|
||||
// upgradeTarget is the binary an upgrade replaces; a variable so a test
|
||||
// replaces a file of its own rather than the test binary running it.
|
||||
var upgradeTarget = os.Executable
|
||||
|
||||
// upgrade replaces this agent's binary with a release and restarts into it.
|
||||
//
|
||||
// Engines are not touched: an agent restart leaves them running and adopts
|
||||
// them again, which is what makes upgrading a node something that can be done
|
||||
// while it serves.
|
||||
func (a *Agent) upgrade(ctx context.Context, m *llmgwv1.UpgradeAgent, out chan<- *llmgwv1.AgentMessage) {
|
||||
reply := &llmgwv1.UpgradeReply{RequestId: m.GetRequestId(), Version: m.GetVersion()}
|
||||
send := func() {
|
||||
select {
|
||||
case out <- &llmgwv1.AgentMessage{Msg: &llmgwv1.AgentMessage_Upgrade{Upgrade: reply}}:
|
||||
case <-ctx.Done():
|
||||
}
|
||||
}
|
||||
a.log.Info("upgrading", "to", m.GetVersion(), "from", a.cfg.Version)
|
||||
self, err := upgradeTarget()
|
||||
if err == nil {
|
||||
dctx, cancel := context.WithTimeout(ctx, 10*time.Minute)
|
||||
_, err = release.Install(dctx, nil, m.GetReleases(), m.GetVersion(), runtime.GOOS, runtime.GOARCH, self)
|
||||
cancel()
|
||||
}
|
||||
if err != nil {
|
||||
reply.Error = err.Error()
|
||||
a.log.Error("upgrade failed; still running the old version", "to", m.GetVersion(), "err", err)
|
||||
send()
|
||||
return
|
||||
}
|
||||
send()
|
||||
a.log.Info("upgraded; restarting into the new version", "to", m.GetVersion())
|
||||
// A moment for the reply to leave before the stream goes.
|
||||
time.Sleep(500 * time.Millisecond)
|
||||
exitForUpgrade()
|
||||
}
|
||||
Reference in new issue
Block a user