feat(runners): set job container memory below runner

scripts/gitea-actions/deploy-runner-config.xsh

@@ -19,7 +19,9 @@ HOSTS = {
 }
 
 DEFAULT_MEM_FRACTION = 0.75
+DEFAULT_JOB_MEM_FRACTION = 0.9
 MIN_RUNNER_MEM_MIB = 1024
+MIN_JOB_MEM_MIB = 128
 
 
 def parse_mem_fraction(argv):
@@ -35,6 +37,20 @@ def parse_mem_fraction(argv):
         raise SystemExit("--mem-fraction must be > 0 and <= 1")
     return fraction
 
+
+def parse_job_mem_fraction(argv):
+    fraction = DEFAULT_JOB_MEM_FRACTION
+    for arg in argv[1:]:
+        if arg.startswith("--job-mem-fraction="):
+            _, value = arg.split("=", 1)
+            try:
+                fraction = float(value)
+            except ValueError as exc:
+                raise SystemExit(f"Invalid --job-mem-fraction value: {value}") from exc
+    if fraction <= 0 or fraction > 1:
+        raise SystemExit("--job-mem-fraction must be > 0 and <= 1")
+    return fraction
+
 def ssh(host, cmd):
     proc = subprocess.run(
         [
@@ -184,6 +200,25 @@ def upsert_service_deploy_memory(compose_text, service_names, value):
     return "\n".join(lines) + "\n"
 
 
+def upsert_compose_env_var(compose_text, var_name, var_value, anchor_line):
+    lines = compose_text.splitlines()
+    new_line = f"      - {var_name}={var_value}"
+    replaced = False
+
+    for idx, line in enumerate(lines):
+        stripped = line.strip()
+        if stripped.startswith(f"- {var_name}="):
+            lines[idx] = new_line
+            replaced = True
+
+    if not replaced:
+        for idx, line in enumerate(lines):
+            if line.strip() == anchor_line.strip():
+                lines.insert(idx + 1, new_line)
+
+    return "\n".join(lines) + "\n"
+
+
 def parse_mem_value_to_mib(raw_value):
     value = raw_value.strip().lower()
     if not value:
@@ -258,7 +293,7 @@ def find_service_memory_value(compose_text, service_names):
     return None
 
 
-def build_compose(compose_text, runner_mem_limit):
+def build_compose(compose_text, runner_mem_limit, job_mem_limit):
     updated = compose_text
 
     volume_line = "      - ./daemon.json:/etc/docker/daemon.json:ro"
@@ -268,7 +303,15 @@ def build_compose(compose_text, runner_mem_limit):
 
     force_pull_line = "      - GITEA_RUNNER_JOB_CONTAINER_FORCE_PULL=${GITEA_RUNNER_JOB_CONTAINER_FORCE_PULL:-false}"
     add_cfg_env = "      - CONFIG_FILE=/config.yaml"
-    if add_cfg_env not in updated and force_pull_line in updated:
+    if force_pull_line in updated:
+        updated = upsert_compose_env_var(updated, "CONFIG_FILE", "/config.yaml", force_pull_line)
+        updated = upsert_compose_env_var(
+            updated,
+            "GITEA_RUNNER_JOB_CONTAINER_OPTIONS",
+            f"--memory={job_mem_limit} --memory-swap={job_mem_limit}",
+            force_pull_line,
+        )
+    elif add_cfg_env not in updated:
         updated = updated.replace(force_pull_line, force_pull_line + "\n" + add_cfg_env)
 
     runner_services = {"act_runner_1", "act_runner_2", "runner1", "runner2"}
@@ -321,8 +364,10 @@ def current_runner_baseline_mib(host, compose_text):
 
 
 mem_fraction = parse_mem_fraction(sys.argv)
+job_mem_fraction = parse_job_mem_fraction(sys.argv)
 
 print(f"Runner mem fraction: {mem_fraction:.2f}")
+print(f"Job mem fraction: {job_mem_fraction:.2f}")
 print("Fetching canonical runner config template")
 rc, template = ssh(TEMPLATE_HOST, f"cat {TEMPLATE_PATH}")
 if rc != 0 or not template.strip():
@@ -360,7 +405,15 @@ with tempfile.TemporaryDirectory() as tmpdir:
         print(f"runner_mem_baseline={baseline_source}")
         print(f"runner_mem_limit={runner_mem_limit} ({runner_mem_mib} MiB)")
 
-        new_compose = build_compose(compose, runner_mem_limit)
+        job_mem_mib = int(runner_mem_mib * job_mem_fraction)
+        if job_mem_mib < MIN_JOB_MEM_MIB:
+            job_mem_mib = MIN_JOB_MEM_MIB
+        if job_mem_mib >= runner_mem_mib and runner_mem_mib > 1:
+            job_mem_mib = runner_mem_mib - 1
+        job_mem_limit = f"{job_mem_mib}m"
+        print(f"job_mem_limit={job_mem_limit} ({job_mem_mib} MiB)")
+
+        new_compose = build_compose(compose, runner_mem_limit, job_mem_limit)
 
         rc, _ = ssh(host, f"mkdir -p {root}/backups")
         rc, _ = ssh(host, f"cp -f {root}/compose.yml {root}/backups/compose.yml.{now}")
@@ -388,6 +441,8 @@ with tempfile.TemporaryDirectory() as tmpdir:
         print(out.strip())
         rc, out = ssh(host, f"grep -n 'CONFIG_FILE=/config.yaml' {root}/compose.yml")
         print(out.strip())
+        rc, out = ssh(host, f"grep -n 'GITEA_RUNNER_JOB_CONTAINER_OPTIONS=' {root}/compose.yml")
+        print(out.strip())
         rc, out = ssh(host, f"grep -n 'memory:' {root}/compose.yml")
         print(out.strip())