Refuse build steps under a free-space floor and release workspaces, so the build modules stop filling a build node's disk (issue 1839)
mesh/delivery-group group fix/1839-build-floor checking: 1 of 2 member(s) ready
mesh/delivery superseded: a newer head of the same pull request
mesh/check failed: novox: the check ran past its bound of 30m0s, stuck at: test the unit level of novox/mesh-catalog#458 on novox | 3ca48ff23005 on 89…
mesh/delivery-group group fix/1839-build-floor checking: 1 of 2 member(s) ready
mesh/delivery superseded: a newer head of the same pull request
mesh/check failed: novox: the check ran past its bound of 30m0s, stuck at: test the unit level of novox/mesh-catalog#458 on novox | 3ca48ff23005 on 89…
mesh-build-go, mesh-build-node and mesh-build-image refuse every fetch, test and build, and say unhealthy, while their work or cache filesystem has less than 20 GiB free (build-agent's floor), so the builder chooses another node instead of filling this one. Each serves build_<x>_release, removing a workspace once its caller's last step answered; a failed fetch removes its own; a workspace never released goes two hours after its last use (ADR 0509) in place of a day, never while a step holds it. Pins mesh-sdk's fix/1839-build-floor (buildstep.Floor, buildstep.Workspaces).
This commit is contained in:
@@ -59,8 +59,14 @@ type Module struct {
|
||||
// unhealthy, while it is missing or older than BubblewrapLeast. Nil probes nothing.
|
||||
Bubblewrap func(ctx context.Context) (string, error)
|
||||
|
||||
mu sync.Mutex // guards Recipe
|
||||
install sync.Mutex // one install at a time
|
||||
// Floor refuses every step while the work or toolchain cache filesystem has less free than it (issue 1839); main
|
||||
// sets floorOf(node), and a zero Floor checks nothing.
|
||||
Floor buildstep.Floor
|
||||
|
||||
spacesOnce sync.Once
|
||||
workspaces *buildstep.Workspaces
|
||||
mu sync.Mutex // guards Recipe
|
||||
install sync.Mutex // one install at a time
|
||||
}
|
||||
|
||||
func (m *Module) recipe() Recipe {
|
||||
@@ -122,6 +128,7 @@ func (m *Module) Start(ctx context.Context) {
|
||||
if err := m.Prepare(ctx); err != nil && m.Say != nil {
|
||||
m.Say("the toolchain: %v", err)
|
||||
}
|
||||
m.CleanWorkspaces(m.now())
|
||||
select {
|
||||
case <-ctx.Done():
|
||||
return
|
||||
@@ -138,6 +145,9 @@ func (m *Module) Health(ctx context.Context) health.Answer {
|
||||
if err != nil {
|
||||
return health.Unhealthy(err.Error())
|
||||
}
|
||||
if err := m.room(); err != nil {
|
||||
return health.Unhealthy(err.Error())
|
||||
}
|
||||
return health.Healthy(fmt.Sprintf("node %s installed, the version the module builds with (recipe %s)", installed, m.recipe().Version()))
|
||||
}
|
||||
|
||||
@@ -150,6 +160,10 @@ func (m *Module) Long(tool string, run func(ctx context.Context, args map[string
|
||||
if err := m.Prepare(ctx); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
if err := m.room(); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
defer m.holdArg(args)()
|
||||
return run(ctx, args)
|
||||
})
|
||||
if err != nil {
|
||||
@@ -166,6 +180,10 @@ func (m *Module) Short(run func(ctx context.Context, args map[string]any) (any,
|
||||
if err := m.Prepare(m.Ctx); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
if err := m.room(); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
defer m.holdArg(args)()
|
||||
return run(m.Ctx, args)
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user