Files
gis/internal/landscape/compute_test.go
Bakhtiyar Issakhmetov 4051506b95 fix(landscape): guard redelivery, detach terminal writes, bound workers
F2: Execute had no status guard, so a redelivered or stale message reran a
finished run. Runs that are neither queued nor running are logged and acked
without work; "running" still executes so a worker that crashed mid-run
recovers.

F4: failRun, finishNodeFailed and MarkRunFailed wrote the terminal status on
the caller's context, which is exactly the context that is already cancelled
when the run failed because of a shutdown or a sibling node — the write was
refused and the run stayed stuck in "running". They now write on a
context.WithoutCancel copy with a 10s timeout; the consumer's best-effort
MarkRunFailed does the same.

F5: peak memory scaled with the host's core count. LP_MAX_WORKERS (default 8)
is now the total window-worker budget of a run and LP_MAX_NODES (default 2) the
node fan-out; each node gets max(1, workers/nodes) through the new
landscape.ComputeWithWorkers. Compute and service.ComputeFunc keep their
signatures: Compute delegates with MaxWorkersPerNode, and a legacy ComputeFunc
handed to NewLandscapeService is wrapped.

F6: the stage loop used a plain errgroup, so a failing node let its siblings
run to completion. It now uses errgroup.WithContext and passes the group
context into runNode, cancelling siblings mid-compute.

F7: wrap every float32 product in an explicit conversion so the compiler
cannot fuse it into an FMA, keeping the kernels bit-identical to numpy's
per-op rounding.

F8: README's builder package list now matches the Dockerfile (adds g++), and
the Landscape section documents the memory model and the two new knobs.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-05 14:44:34 +05:00

253 lines
8.2 KiB
Go

package landscape
import (
"context"
"fmt"
"os"
"path/filepath"
"testing"
"gis/internal/raster"
)
func grid(w, h int) raster.Grid {
return raster.Grid{Width: w, Height: h, GeoTransform: [6]float64{0, 30, 0, 0, 0, -30}, ProjectionWKT: "EPSG:32642"}
}
func constRaster(w, h int, v float64) []float64 {
d := make([]float64, w*h)
for i := range d {
d[i] = v
}
return d
}
func TestCompute_E_TilesWindowsAndWritesEveryPixel(t *testing.T) {
fio := newFakeIO()
g := grid(10, 7)
z := constRaster(10, 7, 2)
u := constRaster(10, 7, 4)
z[0] = -9999 // pixel 0 invalid
fio.put("z.tif", g, z)
fio.put("u.tif", g, u)
node, _ := NodeByCode("10")
p := DefaultParams()
p.WindowSize = 4 // forces partial windows (10x7 with 4x4 tiles)
out, err := Compute(context.Background(), fio, node, map[string]string{OutZIntegrated: "z.tif", OutUIntegrated: "u.tif"}, "/out", p)
if err != nil {
t.Fatal(err)
}
path := out[OutE]
if path != filepath.Join("/out", OutE+".tif") {
t.Fatalf("unexpected output path %q", path)
}
res := fio.files[path]
if res.grid != g {
t.Fatal("output grid must copy the first input's grid")
}
if res.opts != raster.DefaultWriterOptions() {
t.Fatalf("output created with %+v, want raster.DefaultWriterOptions() = %+v", res.opts, raster.DefaultWriterOptions())
}
for i, v := range res.data {
want := 4.0
if i == 0 {
want = -9999
}
if v != want {
t.Fatalf("pixel %d = %v want %v", i, v, want)
}
}
}
func TestCompute_FailsOnGridMismatch(t *testing.T) {
fio := newFakeIO()
fio.put("z.tif", grid(10, 7), constRaster(10, 7, 2))
fio.put("u.tif", grid(9, 7), constRaster(9, 7, 4))
node, _ := NodeByCode("10")
_, err := Compute(context.Background(), fio, node, map[string]string{OutZIntegrated: "z.tif", OutUIntegrated: "u.tif"}, "/out", DefaultParams())
if err == nil {
t.Fatal("expected grid mismatch error")
}
if _, created := fio.files[filepath.Join("/out", OutE+".tif")]; created {
t.Fatal("no output must be created on mismatch")
}
}
func TestCompute_FailsOnMissingInput(t *testing.T) {
fio := newFakeIO()
fio.put("z.tif", grid(2, 2), constRaster(2, 2, 2))
node, _ := NodeByCode("10")
if _, err := Compute(context.Background(), fio, node, map[string]string{OutZIntegrated: "z.tif"}, "/out", DefaultParams()); err == nil {
t.Fatal("expected error for missing input group")
}
}
func TestCompute_MultiOutputNode(t *testing.T) {
fio := newFakeIO()
g := grid(3, 1)
paths := map[string]string{}
for i, s := range []string{SlotPIrrigation, SlotPSnow, SlotPCrop, SlotPPasture, SlotPTourism} {
paths[s] = s + ".tif"
fio.put(paths[s], g, constRaster(3, 1, float64(i+1)))
}
paths[OutE] = "e.tif"
fio.put("e.tif", g, constRaster(3, 1, 3))
node, _ := NodeByCode("20")
out, err := Compute(context.Background(), fio, node, paths, "/o", DefaultParams())
if err != nil {
t.Fatal(err)
}
if len(out) != 5 {
t.Fatalf("want 5 outputs, got %d", len(out))
}
if fio.files[out[OutCTourism]].data[0] != 3 || fio.files[out[OutCIrrigation]].data[0] != 1 {
t.Fatal("min(P, E) not applied per output")
}
}
// TestCompute_MultiOutputNode_TiledWindows runs the 6-input/5-output node 20
// with a window size much smaller than the raster, so per-worker output
// buffers are reused across windows of differing pixel counts (partial
// windows at the raster's right/bottom edges).
func TestCompute_MultiOutputNode_TiledWindows(t *testing.T) {
fio := newFakeIO()
w, h := 5, 3
g := grid(w, h)
paths := map[string]string{}
for i, s := range []string{SlotPIrrigation, SlotPSnow, SlotPCrop, SlotPPasture, SlotPTourism} {
paths[s] = s + ".tif"
fio.put(paths[s], g, constRaster(w, h, float64(i+1)))
}
paths[OutE] = "e.tif"
fio.put("e.tif", g, constRaster(w, h, 3))
node, _ := NodeByCode("20")
p := DefaultParams()
p.WindowSize = 2 // 5x3 with 2x2 tiles: several differently-sized windows
out, err := Compute(context.Background(), fio, node, paths, "/o2", p)
if err != nil {
t.Fatal(err)
}
codes := []string{OutCIrrigation, OutCSnow, OutCCrop, OutCPasture, OutCTourism}
for i, code := range codes {
want := min(i+1, 3) // min(P_sector, E=3)
res := fio.files[out[code]]
for px, v := range res.data {
if v != float64(want) {
t.Fatalf("%s pixel %d = %v want %v", code, px, v, want)
}
}
}
}
// TestCompute_ZeroParamsUsesDefaults exercises Compute with a completely
// zero-valued Params, relying on WithDefaults to fill in WindowSize and the
// other node-independent knobs.
func TestCompute_ZeroParamsUsesDefaults(t *testing.T) {
fio := newFakeIO()
g := grid(4, 4)
fio.put("z.tif", g, constRaster(4, 4, 2))
fio.put("u.tif", g, constRaster(4, 4, 3))
node, _ := NodeByCode("10")
out, err := Compute(context.Background(), fio, node, map[string]string{OutZIntegrated: "z.tif", OutUIntegrated: "u.tif"}, "/z", Params{})
if err != nil {
t.Fatal(err)
}
for _, v := range fio.files[out[OutE]].data {
if v != 3 {
t.Fatalf("pixel = %v want 3", v)
}
}
}
// TestCompute_NegativeWindowSizeClampedToDefault guards against
// raster.Windows looping forever on a non-positive window size: WithDefaults
// only fills in a zero value, so Compute must clamp negatives itself.
func TestCompute_NegativeWindowSizeClampedToDefault(t *testing.T) {
fio := newFakeIO()
g := grid(2, 2)
fio.put("z.tif", g, constRaster(2, 2, 2))
fio.put("u.tif", g, constRaster(2, 2, 3))
node, _ := NodeByCode("10")
p := DefaultParams()
p.WindowSize = -5
out, err := Compute(context.Background(), fio, node, map[string]string{OutZIntegrated: "z.tif", OutUIntegrated: "u.tif"}, "/neg", p)
if err != nil {
t.Fatal(err)
}
if fio.files[out[OutE]].data[0] != 3 {
t.Fatal("unexpected result")
}
}
// TestCompute_FailureMidRunReturnsError simulates a read failure partway
// through a run (the fake fails every ReadFloat64 against u.tif from the
// first call on) and checks Compute surfaces the error instead of returning
// a partial result.
func TestCompute_FailureMidRunReturnsError(t *testing.T) {
fio := newFakeIO()
g := grid(10, 7)
fio.put("z.tif", g, constRaster(10, 7, 2))
fio.put("u.tif", g, constRaster(10, 7, 4))
fio.failReadAfterN("u.tif", 0) // fail starting from the very first read
node, _ := NodeByCode("10")
p := DefaultParams()
p.WindowSize = 4
if _, err := Compute(context.Background(), fio, node, map[string]string{OutZIntegrated: "z.tif", OutUIntegrated: "u.tif"}, "/out-fail", p); err == nil {
t.Fatal("expected error from simulated read failure")
}
}
// TestRemoveOutputs_DeletesFiles unit-tests the cleanup helper Compute uses
// after a failed run, against the real filesystem (the fake IO above has no
// on-disk files to assert against).
func TestRemoveOutputs_DeletesFiles(t *testing.T) {
dir := t.TempDir()
var paths []string
for i := 0; i < 3; i++ {
p := filepath.Join(dir, fmt.Sprintf("out%d.tif", i))
if err := os.WriteFile(p, []byte("data"), 0o644); err != nil {
t.Fatal(err)
}
paths = append(paths, p)
}
removeOutputs(paths)
for _, p := range paths {
if _, err := os.Stat(p); !os.IsNotExist(err) {
t.Fatalf("expected %s to be removed, stat err = %v", p, err)
}
}
}
// TestComputeWithWorkers_RespectsCap checks the caller's worker budget bounds
// the pool: each pool worker opens one reader per input and holds a buffer per
// input and output, so the open count bounds peak memory. checkGrids opens one
// extra set of handles before the pool starts, hence the (workers+1) bound.
func TestComputeWithWorkers_RespectsCap(t *testing.T) {
node, _ := NodeByCode("10")
inputs := len(node.Inputs)
for _, workers := range []int{1, 2, 4, 0, -3} {
t.Run(fmt.Sprintf("workers=%d", workers), func(t *testing.T) {
fio := newFakeIO()
g := grid(64, 64)
fio.put("z.tif", g, constRaster(64, 64, 2))
fio.put("u.tif", g, constRaster(64, 64, 4))
p := DefaultParams()
p.WindowSize = 8 // 64 windows, so the pool is never window-bound
if _, err := ComputeWithWorkers(context.Background(), fio, node,
map[string]string{OutZIntegrated: "z.tif", OutUIntegrated: "u.tif"}, "/out", p, workers); err != nil {
t.Fatal(err)
}
effective := max(1, workers)
if got, limit := fio.openCount(), (effective+1)*inputs; got > limit {
t.Fatalf("opened %d readers with workers=%d, want at most %d", got, workers, limit)
}
if fio.openCount() < inputs {
t.Fatalf("opened %d readers, want at least one set of %d", fio.openCount(), inputs)
}
})
}
}