fix(scheduler): stop re-dispatching running jobs (bug-1498) + resval double-free (bug-1497)
bug-1498 (re-dispatch): sched_job_is_ready() was a stub returning 1, so any job lingering in the fcfs pendJobs queue was always elected. A dispatched job was never marked non-PEND (the controller defers its schedStartJob notify to the not-yet-implemented apply pump, controller/job.c), so fcfs_update_job re-enqueued it on every job update and the election thread re-dispatched the running job — the worker got conflicting signals and the job was SIGTERM'd. - sched_job_is_ready: elect only PEND, non-suspended jobs - sched_commit_decision (dispatch): mark the job JOB_STAT_RUN on dispatch so it leaves the PEND set and is no longer re-electable - fcfs_update_job: dedup via ordq_peek before enqueue bug-1497 (double-free): sched_update's resval paths transferred ownership of rv->val to sharedInst/w->resvals but left the request pointer set, so sched_pend_update_killer double-freed it -> use-after-free in build_host_eval_ctx. Clear rv->val = NULL on transfer. Tests: new scheduler/testsuite/test_redispatch.c (8 cases): sched_job_is_ready PEND gating + dispatch-commit marks the job RUN. Full scheduler meson suite green. Live-verified: a `sleep 60` job is elected exactly once, runs the full duration and exits 0 (`completed successfully`); before the fix it was re-dispatched at ~11s and killed (SIGTERM 143). Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
lei.chen
parent
07ab05671d
commit
ee7dee0ed4
5 changed files with 381 additions and 2 deletions
|
|
@ -14643,5 +14643,81 @@
|
|||
],
|
||||
"occurrences": 1,
|
||||
"last_seen": "2026-08-03"
|
||||
},
|
||||
{
|
||||
"id": "bug-1496",
|
||||
"timestamp": "2026-08-03",
|
||||
"error_message": "AppImage daemon binaries hardcode /nix/store absolute paths in DT_NEEDED (sqlite) and DT_RUNPATH (all libs), so they fail to load on hosts without /nix/store (t2/t3): \"error while loading shared libraries: libsqlite3.so/libcap.so.2/libm.so.6 cannot open shared object file\".",
|
||||
"file": "src/tools/appimage/ (entry.sh), xce.nix build",
|
||||
"root_cause": "Daemons (xce_controller/xcecd/xce_scheduler/xce_apiserver) are built by nix with DT_RUNPATH = /nix/store/<hash>/lib absolute paths, and xcecd has DT_NEEDED = /nix/store/<hash>-sqlite/lib/libsqlite3.so (absolute). AppImage packaging does NOT rewrite these, so the binaries are NOT self-contained: they depend on the build machine's /nix/store. t1 happens to have /nix/store (nix env) so it works; t2/t3 without it fail.",
|
||||
"fix": "VERIFIED FIX (pilot): use patchelf to make binaries self-contained \u2014 collect non-glibc deps into lib/ dir; patchelf --set-rpath $ORIGIN/lib on the binary; patchelf --set-rpath $ORIGIN on every lib/*.so (lib-to-lib deps also have absolute RUNPATH); replace sqlite absolute DT_NEEDED with short name; set interpreter to system /lib64/ld-linux (glibc stays on host). Verified on t2 (no /nix/store): self-contained xcecd loaded all 12 non-glibc libs and connected to t1 controller. NOT YET integrated into AppImage package.sh \u2014 pending.",
|
||||
"tags": [
|
||||
"appimage",
|
||||
"rpath",
|
||||
"dt-needed",
|
||||
"self-contained",
|
||||
"nix-store-dependency",
|
||||
"verified-fix-pilot"
|
||||
],
|
||||
"related_bugs": [],
|
||||
"occurrences": 1,
|
||||
"last_seen": "2026-08-03"
|
||||
},
|
||||
{
|
||||
"id": "bug-1497",
|
||||
"timestamp": "2026-08-03",
|
||||
"error_message": "scheduler ASAN: heap-use-after-free in build_host_eval_ctx (resource.c:170) \u2014 scheduling thread reads worker resvals freed by sched_pend_update_killer. Scheduler crashes (ASAN abort) after scheduling a job.",
|
||||
"file": "src/scheduler/src/scheduler.c (sched_handle_resvals XCE_SCHED_OP_UPDATE_RESVALS / _FULL)",
|
||||
"root_cause": "Ownership conflict: sched_handle_resvals does zarray_put(&w->resvals, r->idx, rv->val) (and &sched->sharedInst in the FULL path), transferring rv->val to the zarray whose killer (kill_sched_resval) will free_Value() it. But sched_pend_update_killer then calls free_ResValList_ptr on the request, which frees rv->val again (double-free) and leaves the worker zarray pointer dangling. The scheduling thread later reads it in build_host_eval_ctx -> use-after-free. The worker-construction path (schedobj.c:302) correctly uses MOVE_PTR(val, nv->val) to transfer ownership; sched_handle_resvals does not \u2014 inconsistency.",
|
||||
"fix": "FIXED: in sched_handle_resvals, after zarray_put(&w->resvals, r->idx, rv->val) and zarray_put(&sched->sharedInst, r->idx, rv->val), set rv->val = NULL to transfer ownership to the zarray (whose kill_sched_resval frees it). free_ResValList_ptr then skips the NULL val (free_Value_ptr is NULL-safe), eliminating the double-free/use-after-free. Verified: ASAN scheduler schedules a job to RUN->DONE with zero ASAN errors and stays alive.",
|
||||
"tags": [
|
||||
"scheduler",
|
||||
"use-after-free",
|
||||
"resvals",
|
||||
"ownership",
|
||||
"asan",
|
||||
"fixed"
|
||||
],
|
||||
"related_bugs": [
|
||||
"bug-1495"
|
||||
],
|
||||
"occurrences": 1,
|
||||
"last_seen": "2026-08-03"
|
||||
},
|
||||
{
|
||||
"id": "bug-1498",
|
||||
"timestamp": "2026-08-03",
|
||||
"error_message": "scheduler \u91cd\u590d\u8c03\u5ea6\u5df2\u5b8c\u6210\u7684\u4f5c\u4e1a: e2e-test (73930087014072320, sleep 10) \u5728 worker \u4e0a\u88ab\u8c03\u5ea6\u6267\u884c 3 \u6b21 (fcfs_elect_job x4), \u524d\u4e24\u6b21\u6210\u529f\u5b8c\u6210, \u7b2c\u4e09\u6b21\u88ab SIGKILL (code 143); \u6700\u7ec8 MCP \u72b6\u6001\u663e\u793a failed/EXIT, exec_hosts None; controller \u53cd\u590d\u65e5\u5fd7 rejecting backward START on terminal state",
|
||||
"file": "src/scheduler/src/scheduler.c / src/scheduler/src/decision.c (job \u5b8c\u6210\u72b6\u6001\u672a\u4ece runnable \u96c6\u5408\u79fb\u9664)",
|
||||
"root_cause": "1) sched_job_is_ready \u6052\u771f stub: pendJobs \u91cc\u4efb\u4f55\u4f5c\u4e1a\u90fd\u88ab elect; 2) \u6d3e\u53d1\u540e scheduler \u5185\u4f5c\u4e1a\u72b6\u6001\u4ecd\u4e3a PEND (controller \u4ece\u4e0d\u53d1 schedStartJob, record_job_start_fact \u7684 AFTER_EVENT \u901a\u77e5\u88ab\u63a8\u8fdf\u5230\u672a\u5b9e\u73b0\u7684 apply pump), fcfs_update_job \u5728\u6bcf\u6b21 job update \u65f6\u628a\u4ecd PEND \u7684\u4f5c\u4e1a\u91cd\u65b0\u585e\u56de pendJobs; 3) fcfs_elect_job \u6bcf\u79d2\u91cd\u626b\u91cd\u65b0 elect \u5df2\u6d3e\u53d1\u4f5c\u4e1a \u2192 \u91cd\u590d dispatch \u2192 worker \u88ab SIGTERM \u6740",
|
||||
"fix": "FIXED: 1) sched_job_is_ready() \u4ece\u6052\u771f stub \u6539\u4e3a\u68c0\u67e5 JOB_STAT_PEND \u4e14\u975e\u6302\u8d77; 2) sched_commit_decision dispatch \u5206\u652f\u628a\u4f5c\u4e1a\u6807\u8bb0\u4e3a JOB_STAT_RUN\uff08\u6d3e\u53d1\u5373\u79bb\u5f00 PEND \u96c6\u5408\uff09; 3) fcfs_update_job \u7528 ordq_peek \u53bb\u91cd\u9632\u91cd\u590d\u5165\u961f\u3002\u65b0\u589e test_redispatch.c \u56de\u5f52\u6d4b\u8bd5 (8 \u7528\u4f8b)\u3002\u5b9e\u673a\u9a8c\u8bc1: sleep 60 \u4f5c\u4e1a\u53ea elect 1 \u6b21, \u8dd1\u6ee1 60s, exit 0 completed successfully (\u5bf9\u6bd4\u4fee\u590d\u524d ~11s \u88ab\u6740 143)\u3002\u6ce8: \u4f5c\u4e1a\u4e0a\u62a5\u72b6\u6001\u4ecd\u53d7 controller apply-pump \u672a\u5b9e\u73b0\u5f71\u54cd, \u5c5e\u72ec\u7acb bug\u3002",
|
||||
"tags": [
|
||||
"scheduler",
|
||||
"re-dispatch",
|
||||
"job-lifecycle",
|
||||
"fcfs",
|
||||
"fixed"
|
||||
],
|
||||
"related_bugs": [
|
||||
"bug-1494"
|
||||
],
|
||||
"occurrences": 1,
|
||||
"last_seen": "2026-08-03"
|
||||
},
|
||||
{
|
||||
"id": "bug-1499",
|
||||
"timestamp": "2026-08-03",
|
||||
"error_message": "apiserver \u91cd\u542f\u540e\u6240\u6709 API key \u5931\u6548 (HTTP 401 Authentication failed / invalid or expired API key); .mcp.json \u4e2d\u7684 xce_ak_988620... key \u5728 09:07 apiserver \u91cd\u542f\u540e\u4e0d\u53ef\u7528",
|
||||
"file": "src/frontend/apiserver/store/apikey.go + cmd/main.go",
|
||||
"root_cause": "APIKeys \u53ea\u5728\u5185\u5b58 store, AddAPIKey \u4ec5\u5728 POST /xce/v1/apikeys \u751f\u6210\u63a5\u53e3\u88ab\u8c03\u7528; InitStores() \u542f\u52a8\u65f6\u4e0d seed, \u91cd\u542f\u5373\u5168\u90e8\u4e22\u5931",
|
||||
"fix": "\u4e34\u65f6: \u7528 admin \u767b\u5f55\u8c03 POST /xce/v1/apikeys \u91cd\u65b0\u751f\u6210 (scheduler-agent/mcp_operator); \u6839\u6cbb\u5f85\u5b9a (\u542f\u52a8\u65f6\u6301\u4e45\u5316/seed API keys)",
|
||||
"tags": [
|
||||
"apiserver",
|
||||
"apikey",
|
||||
"restart-loss"
|
||||
],
|
||||
"related_bugs": [],
|
||||
"occurrences": 1,
|
||||
"last_seen": "2026-08-03"
|
||||
}
|
||||
]
|
||||
|
|
@ -192,6 +192,15 @@ static int fcfs_update_job(xce_sched_plugin_t* plugin, xce_sched_job_t* j)
|
|||
|
||||
job->job = j;
|
||||
|
||||
/* bug-1498: never enqueue the same job twice. fcfs_commit/fcfs_del_job
|
||||
* removes a job on dispatch, but a job update can re-arrive before the
|
||||
* commit runs (or a dispatch-fail reset returns the job to PEND) — a
|
||||
* duplicate queue entry would be elected twice in one pass. */
|
||||
if (ordq_peek(&(q->pendJobs), (ordq_match_fn_t)job_match, j->jobid) != NULL) {
|
||||
free(job);
|
||||
return 0;
|
||||
}
|
||||
|
||||
ordq_put(&(q->pendJobs), job);
|
||||
|
||||
return 0;
|
||||
|
|
|
|||
|
|
@ -826,6 +826,12 @@ int sched_update(xce_scheduler_t* sched)
|
|||
continue;
|
||||
}
|
||||
zarray_put(&sched->sharedInst, r->idx, rv->val);
|
||||
/* Ownership of rv->val transfers to sharedInst (its killer,
|
||||
* kill_sched_resval, frees it). Clear the request's pointer so
|
||||
* sched_pend_update_killer's free_ResValList_ptr does NOT free
|
||||
* it again (bug-1497: double-free left the zarray entry
|
||||
* dangling -> heap-use-after-free in build_host_eval_ctx). */
|
||||
rv->val = NULL;
|
||||
}
|
||||
rc = 0;
|
||||
break;
|
||||
|
|
@ -846,6 +852,11 @@ int sched_update(xce_scheduler_t* sched)
|
|||
continue;
|
||||
}
|
||||
zarray_put(&w->resvals, r->idx, rv->val);
|
||||
/* Ownership of rv->val transfers to w->resvals (killer
|
||||
* kill_sched_resval frees it). Clear the request pointer so
|
||||
* sched_pend_update_killer does not double-free it
|
||||
* (bug-1497: use-after-free in build_host_eval_ctx). */
|
||||
rv->val = NULL;
|
||||
}
|
||||
rc = 0;
|
||||
break;
|
||||
|
|
@ -1263,8 +1274,27 @@ xce_sched_project_t* sched_get_project(xce_scheduler_t* sched, char* name)
|
|||
return make_sched_project(sched, name);
|
||||
}
|
||||
|
||||
/* FIXME this is just stub, we need to add more */
|
||||
int sched_job_is_ready(xce_sched_job_t* j) { return 1; }
|
||||
/*
|
||||
* sched_job_is_ready — a job is electable only while it is PENDING and not
|
||||
* suspended. Once dispatched (RUN), finished (EXIT/DONE), or suspended
|
||||
* (PSUSP/USUSP/SSUSP) it must never be re-elected. bug-1498: the previous
|
||||
* stub returned 1 unconditionally, so a running job that lingered in the fcfs
|
||||
* pendJobs queue (re-added on every job update because the scheduler was never
|
||||
* told the job had left PEND) was re-dispatched to the worker and killed.
|
||||
*/
|
||||
int sched_job_is_ready(xce_sched_job_t* j)
|
||||
{
|
||||
if (j == NULL) {
|
||||
return 0;
|
||||
}
|
||||
if ((j->state & JOB_STAT_PEND) == 0) {
|
||||
return 0; /* already dispatched/running or terminal */
|
||||
}
|
||||
if (j->state & (JOB_STAT_PSUSP | JOB_STAT_USUSP | JOB_STAT_SSUSP)) {
|
||||
return 0; /* suspended — not electable */
|
||||
}
|
||||
return 1;
|
||||
}
|
||||
|
||||
/* FIXME this is just stub, we need to add more */
|
||||
int sched_queue_is_ready(xce_sched_queue_t* q) { return 1; }
|
||||
|
|
@ -1284,6 +1314,16 @@ int sched_commit_decision(xce_scheduler_t* sched, xce_decision_t* decision)
|
|||
job->allocs = decision->u.alloc;
|
||||
job->accounts = make_job_account(job->allocs);
|
||||
|
||||
/* bug-1498: mark the job RUN the moment it is dispatched so it leaves
|
||||
* the PEND set — fcfs_update_job re-enqueues only PEND jobs and
|
||||
* sched_job_is_ready elects only PEND jobs. Without this the scheduler
|
||||
* is never told the job stopped pending (the controller's
|
||||
* record_job_start_fact defers the AFTER_EVENT schedStartJob notify to
|
||||
* the not-yet-implemented apply pump, controller/job.c) and re-dispatches
|
||||
* the running job. A later controller state update corrects it: PEND on
|
||||
* dispatch-fail (re-electable), EXIT/DONE on finish. */
|
||||
job->state = JOB_STAT_RUN;
|
||||
|
||||
return sched_commit_job_alloc(sched, job);
|
||||
}
|
||||
|
||||
|
|
|
|||
|
|
@ -56,12 +56,24 @@ sched_job_array_wire_e2e_test = executable('sched_job_array_wire_e2e_test',
|
|||
dependencies: [scheduler_test_deps],
|
||||
install: false)
|
||||
|
||||
# White-box regression test for bug-1498 (scheduler re-dispatches a job it
|
||||
# already dispatched): sched_job_is_ready PEND-gating + dispatch-commit marks
|
||||
# the job RUN. It #includes ../src/scheduler.c directly, so it is a standalone
|
||||
# TU with its own main() — built as a separate executable.
|
||||
sched_redispatch_test = executable('sched_redispatch_test',
|
||||
['test_redispatch.c'],
|
||||
include_directories:[incdir],
|
||||
dependencies: [scheduler_test_deps],
|
||||
install: false)
|
||||
|
||||
# Register as meson tests so `meson test --suite scheduler` runs them all.
|
||||
# detect_leaks=0 matches the suite convention (fixtures are not torn down).
|
||||
test('scheduler test', scheduler_test, suite: 'scheduler',
|
||||
env: ['ASAN_OPTIONS=detect_leaks=0'])
|
||||
test('scheduler job-update test', sched_job_update_test, suite: 'scheduler',
|
||||
env: ['ASAN_OPTIONS=detect_leaks=0'])
|
||||
test('scheduler redispatch test', sched_redispatch_test, suite: 'scheduler',
|
||||
env: ['ASAN_OPTIONS=detect_leaks=0'])
|
||||
test('scheduler handlers test', sched_handlers_test, suite: 'scheduler',
|
||||
env: ['ASAN_OPTIONS=detect_leaks=0'])
|
||||
test('scheduler job-array expand test', sched_job_array_test, suite: 'scheduler',
|
||||
|
|
|
|||
242
src/scheduler/testsuite/test_redispatch.c
Normal file
242
src/scheduler/testsuite/test_redispatch.c
Normal file
|
|
@ -0,0 +1,242 @@
|
|||
/*
|
||||
* test_redispatch.c - white-box regression tests for bug-1498: the scheduler
|
||||
* re-dispatched a job it had already dispatched (running job killed by a
|
||||
* duplicate dispatch).
|
||||
*
|
||||
* Root cause: sched_job_is_ready() was a stub returning 1 unconditionally, so
|
||||
* a job lingering in the fcfs pendJobs queue was always elected; and a
|
||||
* dispatched job was never marked non-PEND, so fcfs_update_job re-enqueued it
|
||||
* on every job update (the controller defers its schedStartJob notify).
|
||||
*
|
||||
* Strategy: pull the REAL scheduler.c into this TU (same white-box pattern as
|
||||
* test_job_update.c pulling schedobj.c), stub the scheduler-internal externs
|
||||
* defined in other .c files not linked here, and drive:
|
||||
* - sched_job_is_ready: PEND electable; RUN/EXIT/DONE/suspended/NULL not.
|
||||
* - sched_commit_decision(XCE_DECISION_DISPATCH): marks the job RUN so it
|
||||
* leaves the PEND set and is no longer electable.
|
||||
*/
|
||||
#define UNIT_TEST 1
|
||||
#include <errno.h>
|
||||
#include <stdio.h>
|
||||
#include <stdlib.h>
|
||||
#include <string.h>
|
||||
#include <stdatomic.h>
|
||||
|
||||
#include <unity/unity.h>
|
||||
|
||||
#include "kvmgr.h"
|
||||
#include "scheduler.h"
|
||||
|
||||
/* Pull the real implementation under test. */
|
||||
#include "../src/scheduler.c"
|
||||
|
||||
/* ── Stubs for scheduler.c externs defined in other .c files ─────────────── */
|
||||
|
||||
/* plugin.c — plugin dispatch table & lifecycle (not linked here). */
|
||||
int plugin_job_update(void* s, xce_sched_job_t* j) { (void)s; (void)j; return 0; }
|
||||
int plugin_queue_update(void* s, xce_sched_queue_t* q) { (void)s; (void)q; return 0; }
|
||||
int plugin_worker_update(void* s, xce_sched_worker_t* w) { (void)s; (void)w; return 0; }
|
||||
int plugin_job_state_change(void* s, xce_sched_job_t* j, uint32_t st)
|
||||
{
|
||||
(void)s; (void)j; (void)st; return 0;
|
||||
}
|
||||
int plugin_job_rusage_update(void* s, xce_sched_job_t* j, xce_job_rusages_t* r)
|
||||
{
|
||||
(void)s; (void)j; (void)r; return 0;
|
||||
}
|
||||
int plugin_commit_decision(void* s, xce_decision_t* d) { (void)s; (void)d; return 0; }
|
||||
int plugin_begin_session(void* s) { (void)s; return 0; }
|
||||
int plugin_end_session(void* s) { (void)s; return 0; }
|
||||
int plugin_config_update(void* s, xce_conf4sched_t* c) { (void)s; (void)c; return 0; }
|
||||
int plugin_init(void* s) { (void)s; return 0; }
|
||||
void plugin_unregister(void* s) { (void)s; }
|
||||
int plugin_job_election(void* s, xce_sched_job_t* j) { (void)s; (void)j; return 0; }
|
||||
|
||||
/* schedobj.c / resource.c / client helpers — stubbed for these tests. */
|
||||
void kill_sched_job(void* arg) { (void)arg; }
|
||||
void kill_sched_queue(void* arg) { (void)arg; }
|
||||
void kill_sched_worker(void* arg) { (void)arg; }
|
||||
void kill_sched_user(void* arg) { (void)arg; }
|
||||
void kill_sched_project(void* arg) { (void)arg; }
|
||||
int sched_commit_job_alloc(xce_scheduler_t* s, xce_sched_job_t* j)
|
||||
{
|
||||
(void)s; (void)j; return 0;
|
||||
}
|
||||
int sched_charge_account(xce_scheduler_t* s, xce_job_account_t* a)
|
||||
{
|
||||
(void)s; (void)a; return 0;
|
||||
}
|
||||
int sched_uncharge_account(xce_scheduler_t* s, xce_job_account_t* a)
|
||||
{
|
||||
(void)s; (void)a; return 0;
|
||||
}
|
||||
int sched_apply_job_rusage(xce_scheduler_t* s, xce_job_rusages_t* r)
|
||||
{
|
||||
(void)s; (void)r; return -ENOENT;
|
||||
}
|
||||
int sched_update_existing_job(xce_scheduler_t* s, xce_job_t* j)
|
||||
{
|
||||
(void)s; (void)j; return -ENOENT;
|
||||
}
|
||||
int sched_update_existing_queue(xce_scheduler_t* s, xce_queue_t* q)
|
||||
{
|
||||
(void)s; (void)q; return -ENOENT;
|
||||
}
|
||||
|
||||
/* schedobj.c / decision.c / plugins — additional externs scheduler.c
|
||||
* references (defined in .c files not linked here). */
|
||||
int sched_ctx_init(xce_sched_ctx_t* ctx, void* arg, xce_sched_obj_t* obj)
|
||||
{
|
||||
(void)ctx; (void)arg; (void)obj; return 0;
|
||||
}
|
||||
void sched_ctx_fini(xce_sched_ctx_t* ctx) { (void)ctx; }
|
||||
void sched_ctx_set_primary(xce_sched_ctx_t* ctx, xce_primary_resreq_t* p)
|
||||
{
|
||||
(void)ctx; (void)p;
|
||||
}
|
||||
xce_decision_t* make_pend_decision(xce_pendreason_t* r) { (void)r; return NULL; }
|
||||
xce_decision_t* make_dispatch_decision(xce_job_alloc_t* a) { (void)a; return NULL; }
|
||||
int register_fcfs(void* s) { (void)s; return 0; }
|
||||
int register_limit(void* s) { (void)s; return 0; }
|
||||
int register_seqjob_allocator(void* s) { (void)s; return 0; }
|
||||
int register_parjob_allocator(void* s) { (void)s; return 0; }
|
||||
void kill_sched_resval(xce_val_t* v) { (void)v; }
|
||||
xce_sched_job_t* make_sched_job(void* a, xce_job_t* j) { (void)a; (void)j; return NULL; }
|
||||
xce_sched_queue_t* make_sched_queue(void* a, xce_queue_t* q) { (void)a; (void)q; return NULL; }
|
||||
xce_sched_worker_t* make_sched_worker(void* a, xce_worker_t* w) { (void)a; (void)w; return NULL; }
|
||||
xce_sched_user_t* make_sched_user(void* a, char* n) { (void)a; (void)n; return NULL; }
|
||||
xce_sched_project_t* make_sched_project(void* a, char* n) { (void)a; (void)n; return NULL; }
|
||||
void sched_worker_release_host_ctx(xce_sched_worker_t* w) { (void)w; }
|
||||
|
||||
void setUp(void) { return; }
|
||||
void tearDown(void) { return; }
|
||||
|
||||
/* Note: sched_get_job / sched_add_job / sched_get_queue / ... are defined by
|
||||
* scheduler.c itself (real kvmgr-backed) and come in via the #include — no
|
||||
* stubs needed. They operate on sched->jobs etc., which fixture_init creates. */
|
||||
|
||||
/* ── Fixture ─────────────────────────────────────────────────────────────── */
|
||||
|
||||
static void fixture_init(xce_scheduler_t* sched)
|
||||
{
|
||||
kvmgr_params_t jobs_params = { .key_type = KVMGR_KEY_INT,
|
||||
.nslots = 59,
|
||||
.delta = 16,
|
||||
.datakiller = kill_sched_job };
|
||||
|
||||
memset(sched, 0, sizeof(*sched));
|
||||
resreq_init(1);
|
||||
xstring_table_init(1024 * 16);
|
||||
|
||||
sched->jobs = makeInstance(&xkvmgr_type, &jobs_params);
|
||||
}
|
||||
|
||||
static xce_sched_job_t* seed_job(xce_scheduler_t* sched, uint64_t jobid,
|
||||
uint32_t state)
|
||||
{
|
||||
xce_sched_job_t* j = (xce_sched_job_t*)calloc(1, sizeof(*j));
|
||||
TEST_ASSERT_NOT_NULL(j);
|
||||
j->jobid = jobid;
|
||||
j->state = state;
|
||||
sched_add_job(sched, j);
|
||||
return j;
|
||||
}
|
||||
|
||||
/* ── sched_job_is_ready ──────────────────────────────────────────────────── */
|
||||
|
||||
static void test_ready_null_not_ready(void)
|
||||
{
|
||||
TEST_ASSERT_EQUAL_INT(0, sched_job_is_ready(NULL));
|
||||
}
|
||||
|
||||
static void test_ready_pend_is_ready(void)
|
||||
{
|
||||
xce_sched_job_t j = { .state = JOB_STAT_PEND };
|
||||
TEST_ASSERT_EQUAL_INT(1, sched_job_is_ready(&j));
|
||||
}
|
||||
|
||||
static void test_ready_run_not_ready(void)
|
||||
{
|
||||
xce_sched_job_t j = { .state = JOB_STAT_RUN };
|
||||
TEST_ASSERT_EQUAL_INT(0, sched_job_is_ready(&j));
|
||||
}
|
||||
|
||||
static void test_ready_exit_not_ready(void)
|
||||
{
|
||||
xce_sched_job_t j = { .state = JOB_STAT_EXIT };
|
||||
TEST_ASSERT_EQUAL_INT(0, sched_job_is_ready(&j));
|
||||
}
|
||||
|
||||
static void test_ready_done_not_ready(void)
|
||||
{
|
||||
xce_sched_job_t j = { .state = JOB_STAT_DONE };
|
||||
TEST_ASSERT_EQUAL_INT(0, sched_job_is_ready(&j));
|
||||
}
|
||||
|
||||
static void test_ready_suspended_not_ready(void)
|
||||
{
|
||||
xce_sched_job_t j = { .state = JOB_STAT_PEND | JOB_STAT_USUSP };
|
||||
TEST_ASSERT_EQUAL_INT(0, sched_job_is_ready(&j));
|
||||
}
|
||||
|
||||
/* ── sched_commit_decision dispatch marks the job RUN ────────────────────── */
|
||||
|
||||
static void test_dispatch_commit_marks_job_run(void)
|
||||
{
|
||||
xce_scheduler_t sched;
|
||||
xce_sched_job_t* job;
|
||||
xce_job_alloc_t alloc;
|
||||
xce_decision_t decision;
|
||||
|
||||
fixture_init(&sched);
|
||||
|
||||
job = seed_job(&sched, 42, JOB_STAT_PEND);
|
||||
|
||||
memset(&alloc, 0, sizeof(alloc));
|
||||
alloc.jobid = 42;
|
||||
|
||||
memset(&decision, 0, sizeof(decision));
|
||||
decision.op = XCE_DECISION_DISPATCH;
|
||||
decision.u.alloc = &alloc;
|
||||
|
||||
TEST_ASSERT_EQUAL_INT(0, sched_commit_decision(&sched, &decision));
|
||||
|
||||
/* The dispatched job leaves PEND: state is RUN and it is not electable. */
|
||||
TEST_ASSERT_EQUAL_UINT(JOB_STAT_RUN, job->state);
|
||||
TEST_ASSERT_EQUAL_INT(0, sched_job_is_ready(job));
|
||||
}
|
||||
|
||||
static void test_dispatch_commit_null_alloc_unchanged(void)
|
||||
{
|
||||
xce_scheduler_t sched;
|
||||
xce_sched_job_t* job;
|
||||
xce_decision_t decision;
|
||||
|
||||
fixture_init(&sched);
|
||||
job = seed_job(&sched, 43, JOB_STAT_PEND);
|
||||
|
||||
memset(&decision, 0, sizeof(decision));
|
||||
decision.op = XCE_DECISION_PEND;
|
||||
decision.u.reason = NULL;
|
||||
|
||||
TEST_ASSERT_EQUAL_INT(0, sched_commit_decision(&sched, &decision));
|
||||
/* Non-dispatch decision must not touch the job's state. */
|
||||
TEST_ASSERT_EQUAL_UINT(JOB_STAT_PEND, job->state);
|
||||
}
|
||||
|
||||
/* ── Runner ──────────────────────────────────────────────────────────────── */
|
||||
|
||||
int main(int argc, char* argv[])
|
||||
{
|
||||
(void)argc; (void)argv;
|
||||
UNITY_BEGIN();
|
||||
RUN_TEST(test_ready_null_not_ready, 0);
|
||||
RUN_TEST(test_ready_pend_is_ready, 0);
|
||||
RUN_TEST(test_ready_run_not_ready, 0);
|
||||
RUN_TEST(test_ready_exit_not_ready, 0);
|
||||
RUN_TEST(test_ready_done_not_ready, 0);
|
||||
RUN_TEST(test_ready_suspended_not_ready, 0);
|
||||
RUN_TEST(test_dispatch_commit_marks_job_run, 0);
|
||||
RUN_TEST(test_dispatch_commit_null_alloc_unchanged, 0);
|
||||
return UNITY_END();
|
||||
}
|
||||
Loading…
Add table
Add a link
Reference in a new issue