Thanks to visit codestin.com
Credit goes to github.com

Skip to content
Merged
Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
49 commits
Select commit Hold shift + click to select a range
c09c9b9
WIP: agent reinitialization
SasSwart Apr 21, 2025
476fe71
fix assignment to nil map
SasSwart Apr 21, 2025
8c8bca6
fix: ensure prebuilt workspace agent tokens are reused when a prebuil…
SasSwart Apr 23, 2025
7ce4eea
test agent reinitialization
SasSwart Apr 24, 2025
52ac64e
remove defunct metric
SasSwart Apr 24, 2025
362db7c
Remove todo
SasSwart Apr 25, 2025
dcc7379
test that we trigger workspace agent reinitialization under the right…
SasSwart Apr 28, 2025
ff66b3f
slight improvements to a test
SasSwart Apr 28, 2025
efff5d9
review notes to improve legibility
SasSwart Apr 28, 2025
cebd5db
add an integration test for prebuilt workspace agent reinitialization
SasSwart Apr 29, 2025
2679138
Merge remote-tracking branch 'origin/main' into jjs/prebuilds-agent-r…
SasSwart Apr 29, 2025
9feebef
enable the premium license in a prebuilds integration test
SasSwart Apr 29, 2025
b117b5c
encapsulate WaitForReinitLoop for easier testing
SasSwart Apr 30, 2025
a22b414
introduce unit testable abstraction layers
SasSwart Apr 30, 2025
9bbd2c7
test workspace claim pubsub
SasSwart May 1, 2025
5804201
add tests for agent reinitialization
SasSwart May 1, 2025
7e8dcee
review notes
SasSwart May 1, 2025
725f97b
Merge remote-tracking branch 'origin/main' into jjs/prebuilds-agent-r…
SasSwart May 1, 2025
a9b1567
make fmt lint
SasSwart May 1, 2025
21ee970
remove go mod replace
SasSwart May 1, 2025
e54d7e7
remove defunct logging
SasSwart May 1, 2025
2799858
update dependency on terraform-provider-coder
SasSwart May 2, 2025
1d93003
update dependency on terraform-provider-coder
SasSwart May 2, 2025
763fc12
go mod tidy
SasSwart May 2, 2025
0f879c7
make -B gen
SasSwart May 2, 2025
61784c9
dont require ids to InsertPresetParameters
SasSwart May 2, 2025
604eb27
dont require ids to InsertPresetParameters
SasSwart May 2, 2025
bf4d2cf
fix: set the running agent token
dannykopping May 2, 2025
38b4f0d
fix: use http client without timeout like we do in connectRPCVersion
dannykopping May 5, 2025
20df538
review notes
SasSwart May 6, 2025
4bb3b68
Merge remote-tracking branch 'origin/main' into jjs/prebuilds-agent-r…
SasSwart May 7, 2025
83972db
bump provisionerd proto version
SasSwart May 7, 2025
146b158
fix: fetch the previous agent when we need its token for prebuilt wor…
SasSwart May 12, 2025
5eb16cd
Merge remote-tracking branch 'origin/main' into jjs/prebuilds-agent-r…
SasSwart May 12, 2025
730d803
make -B lint
SasSwart May 12, 2025
150adc0
Test GetWorkspaceAgentsByBuildID
SasSwart May 12, 2025
b4ecf10
Rename GetWorkspaceAgentsByWorkspaceAndBuildNumber
SasSwart May 12, 2025
3fa3edf
make gen
SasSwart May 12, 2025
7e45919
fix a race condition
SasSwart May 12, 2025
a632508
Merge remote-tracking branch 'origin/main' into jjs/prebuilds-agent-r…
SasSwart May 12, 2025
72125ec
Merge remote-tracking branch 'origin/main' into jjs/prebuilds-agent-r…
SasSwart May 13, 2025
b65eea7
fix provisionerdserver test for prebuild claims
SasSwart May 13, 2025
e1339f3
fix race conditions
SasSwart May 13, 2025
c1a8ba6
Merge remote-tracking branch 'origin/main' into jjs/prebuilds-agent-r…
SasSwart May 13, 2025
5363dcc
Make TestReinitializeAgent more robust
SasSwart May 13, 2025
7ad9b6d
fix tests
SasSwart May 14, 2025
394571d
make -B gen
SasSwart May 14, 2025
890747b
remove a potential race in reinitialization testing in TestCompleteJob
SasSwart May 14, 2025
b3870db
fix a potential race in TestReinit
SasSwart May 14, 2025
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
introduce unit testable abstraction layers
  • Loading branch information
SasSwart committed Apr 30, 2025
commit a22b4143e1e224accd982fdba2a7f758a43b37c4
102 changes: 102 additions & 0 deletions coderd/prebuilds/claim.go
Original file line number Diff line number Diff line change
@@ -0,0 +1,102 @@
package prebuilds

import (
"context"
"fmt"
"net/http"

"github.com/google/uuid"
"golang.org/x/xerrors"

"cdr.dev/slog"
"github.com/coder/coder/v2/coderd/database/pubsub"
"github.com/coder/coder/v2/coderd/httpapi"
"github.com/coder/coder/v2/codersdk"
"github.com/coder/coder/v2/codersdk/agentsdk"
)

func PublishWorkspaceClaim(ctx context.Context, ps pubsub.Pubsub, workspaceID, userID uuid.UUID) error {
channel := agentsdk.PrebuildClaimedChannel(workspaceID)
if err := ps.Publish(channel, []byte(userID.String())); err != nil {
return xerrors.Errorf("failed to trigger prebuilt workspace agent reinitialization: %w", err)
}
return nil
}

func ListenForWorkspaceClaims(ctx context.Context, logger slog.Logger, ps pubsub.Pubsub, workspaceID uuid.UUID) (func(), <-chan agentsdk.ReinitializationEvent, error) {
reinitEvents := make(chan agentsdk.ReinitializationEvent, 1)
cancelSub, err := ps.Subscribe(agentsdk.PrebuildClaimedChannel(workspaceID), func(inner context.Context, id []byte) {
select {
case <-ctx.Done():
return
case <-inner.Done():
return
default:
Comment thread
SasSwart marked this conversation as resolved.
Outdated
}

claimantID, err := uuid.ParseBytes(id)
if err != nil {
logger.Error(ctx, "invalid prebuild claimed channel payload", slog.F("input", string(id)))
return
}
// TODO: turn this into a <- uuid.UUID
reinitEvents <- agentsdk.ReinitializationEvent{
Message: fmt.Sprintf("prebuild claimed by user: %s", claimantID),
Reason: agentsdk.ReinitializeReasonPrebuildClaimed,
}
})
if err != nil {
return func() {}, nil, xerrors.Errorf("failed to subscribe to prebuild claimed channel: %w", err)
}
defer cancelSub()
return func() { cancelSub() }, reinitEvents, nil
}

func StreamAgentReinitEvents(ctx context.Context, logger slog.Logger, rw http.ResponseWriter, r *http.Request, reinitEvents <-chan agentsdk.ReinitializationEvent) {
sseSendEvent, sseSenderClosed, err := httpapi.ServerSentEventSender(rw, r)

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

We can fix this later, but I think this might be inappropriate at this layer.
This seems like a detail of the HTTP API, and we aren't testing this directly so I'd argue this code could go back to coderd/workspaceagents.go.

if err != nil {
httpapi.Write(ctx, rw, http.StatusInternalServerError, codersdk.Response{
Message: "Internal error setting up server-sent events.",
Detail: err.Error(),
})
return
}
// Prevent handler from returning until the sender is closed.
defer func() {
<-sseSenderClosed
}()

// An initial ping signals to the requester that the server is now ready
// and the client can begin servicing a channel with data.
_ = sseSendEvent(codersdk.ServerSentEvent{
Type: codersdk.ServerSentEventTypePing,
})

for {
select {
case <-ctx.Done():
return
case reinitEvent := <-reinitEvents:
err = sseSendEvent(codersdk.ServerSentEvent{
Type: codersdk.ServerSentEventTypeData,
Data: reinitEvent,
})
if err != nil {
logger.Warn(ctx, "failed to send SSE response to trigger reinit", slog.Error(err))
Comment thread
SasSwart marked this conversation as resolved.
Outdated
}
}
}
}

type MockClaimCoordinator interface{}

type ClaimListener interface{}
type PostgresClaimListener struct{}

type AgentReinitializer interface{}
type SSEAgentReinitializer struct{}

type ClaimCoordinator interface {
ClaimListener
AgentReinitializer
}
Comment thread
SasSwart marked this conversation as resolved.
Outdated
8 changes: 3 additions & 5 deletions coderd/provisionerdserver/provisionerdserver.go
Original file line number Diff line number Diff line change
Expand Up @@ -16,8 +16,6 @@ import (
"sync/atomic"
"time"

"github.com/coder/coder/v2/codersdk/agentsdk"

"github.com/google/uuid"
"github.com/sqlc-dev/pqtype"
semconv "go.opentelemetry.io/otel/semconv/v1.14.0"
Expand All @@ -39,6 +37,7 @@ import (
"github.com/coder/coder/v2/coderd/database/pubsub"
"github.com/coder/coder/v2/coderd/externalauth"
"github.com/coder/coder/v2/coderd/notifications"
"github.com/coder/coder/v2/coderd/prebuilds"
"github.com/coder/coder/v2/coderd/promoauth"
"github.com/coder/coder/v2/coderd/schedule"
"github.com/coder/coder/v2/coderd/telemetry"
Expand Down Expand Up @@ -1750,9 +1749,8 @@ func (s *server) CompleteJob(ctx context.Context, completed *proto.CompletedJob)
slog.F("user", input.PrebuildClaimedByUser.String()),
slog.F("workspace_id", workspace.ID))

channel := agentsdk.PrebuildClaimedChannel(workspace.ID)
if err := s.Pubsub.Publish(channel, []byte(input.PrebuildClaimedByUser.String())); err != nil {
s.Logger.Error(ctx, "failed to trigger prebuilt workspace agent reinitialization", slog.Error(err))
if err := prebuilds.PublishWorkspaceClaim(ctx, s.Pubsub, workspace.ID, input.PrebuildClaimedByUser); err != nil {
Comment thread
SasSwart marked this conversation as resolved.
Outdated
s.Logger.Error(ctx, "failed to publish workspace claim event", slog.Error(err))
}
}
case *proto.CompletedJob_TemplateDryRun_:
Expand Down
69 changes: 4 additions & 65 deletions coderd/workspaceagents.go
Original file line number Diff line number Diff line change
Expand Up @@ -35,6 +35,7 @@ import (
"github.com/coder/coder/v2/coderd/httpmw"
"github.com/coder/coder/v2/coderd/httpmw/loggermw"
"github.com/coder/coder/v2/coderd/jwtutils"
"github.com/coder/coder/v2/coderd/prebuilds"
"github.com/coder/coder/v2/coderd/rbac"
"github.com/coder/coder/v2/coderd/rbac/policy"
"github.com/coder/coder/v2/coderd/telemetry"
Expand Down Expand Up @@ -1180,76 +1181,14 @@ func (api *API) workspaceAgentReinit(rw http.ResponseWriter, r *http.Request) {

log.Info(ctx, "agent waiting for reinit instruction")

prebuildClaims := make(chan uuid.UUID, 1)
cancelSub, err := api.Pubsub.Subscribe(agentsdk.PrebuildClaimedChannel(workspace.ID), func(inner context.Context, id []byte) {
select {
case <-ctx.Done():
return
case <-inner.Done():
return
default:
}

parsed, err := uuid.ParseBytes(id)
if err != nil {
log.Error(ctx, "invalid prebuild claimed channel payload", slog.F("input", string(id)))
return
}
prebuildClaims <- parsed
})
cancel, reinitEvents, err := prebuilds.ListenForWorkspaceClaims(ctx, log, api.Pubsub, workspace.ID)
Comment thread
SasSwart marked this conversation as resolved.
Outdated
if err != nil {
log.Error(ctx, "failed to subscribe to prebuild claimed channel", slog.Error(err))
httpapi.InternalServerError(rw, xerrors.New("failed to subscribe to prebuild claimed channel"))
return
}
defer cancelSub()

sseSendEvent, sseSenderClosed, err := httpapi.ServerSentEventSender(rw, r)
if err != nil {
httpapi.Write(ctx, rw, http.StatusInternalServerError, codersdk.Response{
Message: "Internal error setting up server-sent events.",
Detail: err.Error(),
})
return
}
// Prevent handler from returning until the sender is closed.
defer func() {
cancel()
<-sseSenderClosed
}()
// Synchronize cancellation from SSE -> context, this lets us simplify the
// cancellation logic.
go func() {
select {
case <-ctx.Done():
case <-sseSenderClosed:
cancel()
}
}()

// An initial ping signals to the request that the server is now ready
// and the client can begin servicing a channel with data.
_ = sseSendEvent(codersdk.ServerSentEvent{
Type: codersdk.ServerSentEventTypePing,
})

for {
select {
case <-ctx.Done():
return
case user := <-prebuildClaims:
err = sseSendEvent(codersdk.ServerSentEvent{
Type: codersdk.ServerSentEventTypeData,
Data: agentsdk.ReinitializationEvent{
Message: fmt.Sprintf("prebuild claimed by user: %s", user),
Reason: agentsdk.ReinitializeReasonPrebuildClaimed,
},
})
if err != nil {
log.Warn(ctx, "failed to send SSE response to trigger reinit", slog.Error(err))
}
}
}
defer cancel()
prebuilds.StreamAgentReinitEvents(ctx, log, rw, r, reinitEvents)
}

// convertProvisionedApps converts applications that are in the middle of provisioning process.
Expand Down
2 changes: 1 addition & 1 deletion codersdk/agentsdk/agentsdk.go
Original file line number Diff line number Diff line change
Expand Up @@ -776,8 +776,8 @@ func WaitForReinitLoop(ctx context.Context, logger slog.Logger, client *Client)
reinitEvent, err := client.WaitForReinit(ctx)
if err != nil {
logger.Error(ctx, "failed to wait for agent reinitialization instructions", slog.Error(err))
continue
}
reinitEvents <- *reinitEvent
select {
case <-ctx.Done():
close(reinitEvents)
Expand Down