lei.chen/myxce
1
0
Fork 1
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
myxce/src/controller/job.c
Rongsong Shen 5522d6f274 feat(ha-commit-barrier-rollout): mark_job_* idempotency/ordering guards (task 6.2) 
Guards at the top of mark_job_start/finish/update under the caller's
job lock, before BEFORE_EVENT: duplicate (FINISH on terminal) → INFO
no-op skipping the AFTER_EVENT hook (no WAL append, lsn frozen);
terminal→non-terminal backward (START/UPDATE) → WARN reject preserving
state. Shared job_state_is_backward predicate provably admits every
production forward merge (PDONE/PERR/suspend bit-OR) while rejecting
overwrites. mark_job_fail intentionally unguarded (its merges are
always terminal-forward; job_ctrl pre-gates terminal). 5/5 guard tests
green; full job-lifecycle suite green; census 0 FAIL.
2026-06-13 04:54:36 +00:00

1210 lines
33 KiB
C
Raw Blame History

#include <errno.h>
#include <signal.h>
#include <stdbool.h>
#include <string.h>
#include <time.h>
#include "cluster.h"
#include "controller.capnp.h"
#include "jobj.h"
#include "persist.h"
#include "preason.h"
#include "xce/cluster_def.h"
#include "xce/errnox.h"
#include "xce/types.h"
#include "xstring.h"
static int mark_job_start(cluster_t*, job_t*, job_pidinfo_t*);
static int mark_job_finish(cluster_t*, job_t*, xce_jobfinish_t*);
static int mark_job_fail(cluster_t*, job_t*, job_failinfo_t*);
static int mark_job_update(cluster_t*, job_t*, int);
/* A job is terminal once it carries a DONE or EXIT bit. Terminal jobs reject
* backward (terminal -> non-terminal) transitions and treat re-applied
* terminal transitions as duplicates; forward bit-OR merges (PDONE, PERR,
* suspend bits) on a terminal job remain legal. */
#define JOB_STATE_TERMINAL_BITS (JOB_STAT_DONE | JOB_STAT_EXIT)
static inline bool job_state_is_terminal(int state)
{
return (state & JOB_STATE_TERMINAL_BITS) != 0;
}
/* Shared backward predicate for START and UPDATE (Req 5.2): a transition is
* backward when the job is already terminal but the requested next state drops
* every terminal bit it currently holds (e.g. START overwriting DONE with a
* bare JOB_STAT_RUN, or an UPDATE clearing the terminal bits). A forward merge
* that preserves at least one terminal bit (postdone OR'ing PDONE) is NOT
* backward. */
static inline bool job_state_is_backward(int cur, int next)
{
return job_state_is_terminal(cur) && !job_state_is_terminal(next);
}
static job_t* create_job(cluster_t* c, xce_job_t* j)
{
job_t* job = NULL;
job = makeJob(c->jobmgr, j);
return job;
}
uint64_t job_submit(void* c, xce_job_submit_t* submit)
{
job_t* job = NULL;
uint64_t base_id = submit->jobid;
xce_job_t j = { .submit = submit->submit };
time_t now = time(NULL);
int i;
j.sub_time = now;
j.queue_time = now;
j.start_time = 0;
j.finish_time = 0;
j.pidinfo = NULL;
j.state = JOB_STAT_PEND;
j.allocs = NULL;
j.run_time = 0;
j.run_usage = NULL;
j.exit_info = NULL;
j.ckptinfo = NULL;
j.pending_ctrl = 0;
for (i = 0; i < submit->array_size; i++) {
j.jobid = base_id + i;
job = create_job(c, &j);
if (job == NULL) {
return -errno;
}
}
return base_id;
}
int load_jobs(void* c)
{
return 0;
}
/* Reconstruct a job from a WAL_JOB_SUBMIT Cap'n Proto payload.
* Uses the jobid embedded in the serialized xce_job_t (not the caller's arg).
* Returns -EEXIST if the job is already present (idempotent replay guard). */
int restore_job(cluster_t* c, uint64_t jobid_unused,
const void* capnp_payload, size_t len)
{
(void)jobid_unused;
if (!capnp_payload || len == 0)
return -EINVAL;
struct capn c_ctx;
capn_init_mem(&c_ctx, (const uint8_t*)capnp_payload, len, 0);
Job_ptr jp;
jp.p = capn_getp(capn_root(&c_ctx), 0, 1);
struct Job cj;
xce_job_t j;
memset(&j, 0, sizeof(j));
read_Job(&cj, jp);
decode_Job(&j, &cj);
capn_free(&c_ctx);
/* Safety guard: skip if already present (WAL replay may see duplicates
* when recovery restarts from a segment boundary). */
job_t* existing = NULL;
lock(c->jobmgr, RTTI_LOCK_READ);
int found = key_find(c->jobmgr, (void*)j.jobid, (void**)&existing);
unlock(c->jobmgr);
if (found > 0 && existing != NULL)
return -EEXIST;
job_t* job = create_job(c, &j);
if (!job)
return -errno;
return 0;
}
/* Apply a recorded job state transition during WAL recovery.
* Looks up the job (which must already exist from WAL_JOB_SUBMIT replay)
* and overwrites its state with the value stored in the WAL entry. */
int restore_job_state(cluster_t* c, uint64_t jobid, uint32_t state)
{
job_t* j = NULL;
lock(c->jobmgr, RTTI_LOCK_READ);
key_find(c->jobmgr, (void*)jobid, (void**)&j);
unlock(c->jobmgr);
if (!j)
return -ENOENT;
lock(j, RTTI_LOCK_WRITE);
j->job.state = (int)state;
unlock(j);
return 0;
}
static int get_nslots_in_alloc(xce_host_alloc_t* alloc)
{
int i;
for (i = 0; i < alloc->nallocs; i++) {
if (strcmp(alloc->allocs[i]->resname, "slots") == 0) {
return (int)alloc->allocs[i]->value;
}
}
return 1;
}
static void free_launchinfo(xce_launch_t* launch)
{
int i;
for (i = 0; i < launch->nhosts; i++) {
FREEUP(launch->hosts[i]);
}
FREEUP(launch->hosts);
}
static int mk_launchinfo(xce_launch_t* launch, xce_job_alloc_t* alloc)
{
int i;
int rc = 0;
memset(launch, 0x0, sizeof(*launch));
launch->hosts = (xce_host_launch_t**)calloc(alloc->nhosts,
sizeof(xce_host_launch_t*));
if (launch->hosts == NULL) {
return -ENOMEM;
}
launch->nhosts = alloc->nhosts;
for (i = 0; i < alloc->nhosts; i++) {
launch->hosts[i]
= (xce_host_launch_t*)calloc(1, sizeof(xce_host_launch_t));
if (launch->hosts[i] == NULL) {
rc = -ENOMEM;
break;
}
launch->hosts[i]->host = alloc->allocs[i]->host;
launch->hosts[i]->nranks = get_nslots_in_alloc(alloc->allocs[i]);
}
if (rc < 0) {
free_launchinfo(launch);
}
return rc;
}
static int dispatch_a_job_(cluster_t* c, endpoint_t* ep, xce_job_alloc_t* alloc)
{
int rc = 0;
job_t* j = NULL;
worker_t* w = NULL;
xce_host_alloc_t** allocs;
int nc;
xce_job_exec_t einfo;
xce_launch_t launchinfo;
TRACE("%s jobid %ld", __func__, alloc->jobid);
lock(c->jobmgr, RTTI_LOCK_READ);
rc = key_find(c->jobmgr, (void*)alloc->jobid, (void**)&j);
if (j != NULL) {
reference(j);
}
unlock(c->jobmgr);
if (rc < 0) {
return rc;
}
if (j == NULL) {
PERROR("jobmgr_lockjob");
return -errno;
}
nc = alloc->nhosts;
if (nc <= 0) {
dereference(j);
return -EINVAL;
}
/* FIXME: change case of nc > 1 just hard coded mpi as
* the real job type later
*/
mk_launchinfo(&launchinfo, alloc);
allocs = (xce_host_alloc_t**)alloc->allocs;
/* using head node of job */
lock(c->workermgr, RTTI_LOCK_READ);
rc = key_find(c->workermgr, (void*)allocs[0]->host, (void**)&w);
if (w != NULL) {
reference(w);
}
unlock(c->workermgr);
if (rc < 0) {
return rc;
}
if (w == NULL) {
free_launchinfo(&launchinfo);
return -errno;
}
lock(w, RTTI_LOCK_READ);
if ((w->ep == NULL) || (w->host.status != 0)) {
ERROR("worker %s is not in correct state, status %x ep %p",
w->host.name, w->host.status, w->ep);
free_launchinfo(&launchinfo);
SET_ERROR(E_XCE_BAD_WORKER);
unlock(w);
dereference(w);
return -errno;
}
/* FIXME: we may consider to optimize when a job has enter a queue? */
if (1) {
char* q_pre_exec;
char* q_post_exec;
rc = get_queue_exec(c, j->job.submit->queue, &q_pre_exec, &q_post_exec);
if (rc < 0) {
unlock(w);
dereference(w);
dereference(j);
free_launchinfo(&launchinfo);
return rc;
}
if (j->job.submit->start_info->q_pre_exec != NULL) { }
if (j->job.submit->start_info->q_post_exec != NULL) { }
j->job.submit->start_info->q_pre_exec = q_pre_exec;
j->job.submit->start_info->q_post_exec = q_post_exec;
}
einfo.jobid = alloc->jobid;
einfo.start_info = j->job.submit->start_info;
einfo.launchinfo = &launchinfo;
rc = xce_startjob_req(w->ep, &einfo);
unlock(w);
dereference(w);
free_launchinfo(&launchinfo);
if (j->job.allocs != NULL) {
free_JobAlloc_ptr(&(j->job.allocs));
}
j->job.allocs = (xce_job_alloc_t*)calloc(1, sizeof(xce_job_alloc_t));
j->job.allocs->jobid = alloc->jobid;
j->job.allocs->nhosts = nc;
MOVE_PTR(j->job.allocs->allocs, allocs);
alloc->allocs = NULL;
if (rc < 0) {
SET_ERROR(-rc);
PERROR("xce_startjob_req");
return rc;
}
return rc;
}
int job_ctrl(cluster_t* c, xce_jobctrl_t* ctrinfo)
{
uint64_t jobid = ctrinfo->jobid;
job_t* j = NULL;
int rc = 0;
TRACE("%s job_ctrl job %ld", __func__, jobid);
lock(c->jobmgr, RTTI_LOCK_READ);
rc = key_find(c->jobmgr, (void*)jobid, (void**)&j);
if (j != NULL) {
reference(j);
}
unlock(c->jobmgr);
if (rc < 0) {
return rc;
}
if (j == NULL) {
PERROR("jobmgr_lockjob");
return -ENOENT;
}
/* bug-447: key_find returns 1 on found (binary librtti, unnormalizable
* upstream). Normalize the found-rc to 0 so the not-started siginfo
* branch below (which appends via the mark_job_* hooks but never
* reassigns rc) returns 0 to the handler's commit-barrier pattern
* instead of leaking 1 as the reply status. Real errors are
* untouched: rc < 0 returned above, the j == NULL miss returned
* -ENOENT, and every other branch sets rc itself. */
rc = 0;
/* FIXME: eliminate held multiple locks */
lock(j, RTTI_LOCK_READ);
if (j->job.allocs != NULL) {
xce_host_alloc_t** allocs = j->job.allocs->allocs;
worker_t* w = NULL;
/* job control command will be sent to first node
* for parallel jobs
*/
lock(c->workermgr, RTTI_LOCK_READ);
rc = key_find(c->workermgr, (void*)allocs[0]->host, (void**)&w);
if (w != NULL) {
reference(w);
}
unlock(c->workermgr);
if (rc < 0) {
unlock(j);
dereference(j);
return rc;
}
if (w != NULL) {
lock(w, RTTI_LOCK_READ);
/* FIXME: better method to check host status */
if ((w->ep != NULL) && (w->host.status == 0)) {
rc = xce_jobctrl_req(w->ep, ctrinfo);
if (rc < 0) {
ERROR("job ctrl %ld on host %s returns %d", jobid,
w->host.name, rc);
}
} else {
ERROR("worker %s is not in correct state, status %x ep %p",
w->host.name, w->host.status, w->ep);
rc = -errno;
}
unlock(w);
dereference(w);
} else {
rc = -errno;
}
} else {
/* job has not been started yet */
job_failinfo_t failinfo = {
.jobid = jobid,
};
xce_use(&failinfo);
switch (ctrinfo->action) {
case JobControl_u_siginfo:
switch (ctrinfo->u.siginfo->signo) {
case SIGCONT:
if (j->job.state
& (JOB_STAT_PSUSP | JOB_STAT_USUSP | JOB_STAT_SSUSP)) {
int state = j->job.state;
/* resume suspend job? */
state &= ~(JOB_STAT_PSUSP | JOB_STAT_USUSP);
mark_job_update(c, j, state);
}
break;
case SIGSTOP:
case SIGTSTP:
if (!(j->job.state
& (JOB_STAT_PSUSP | JOB_STAT_USUSP | JOB_STAT_SSUSP))) {
int state = j->job.state;
state |= JOB_STAT_PSUSP;
mark_job_update(c, j, state);
}
break;
case SIGKILL:
case SIGTERM:
default:
if (j->job.state
& (JOB_STAT_DONE | JOB_STAT_EXIT | JOB_STAT_ERR)) {
break;
}
/* FIXME: */
failinfo.code = 128 + ctrinfo->u.siginfo->signo;
failinfo.detail = "Job killed by signal";
mark_job_fail(c, j, &failinfo);
break;
}
break;
case JobControl_u_ckptoption:
if (j->job.state & (JOB_STAT_DONE | JOB_STAT_EXIT | JOB_STAT_ERR)) {
ERROR("job <%ld> has been finished, no checkpoint can be done.",
jobid);
} else {
ERROR("job %ld has not been started, no checkpoint can be done",
jobid);
}
rc = -EINVAL;
break;
default:
rc = -EINVAL;
break;
}
}
unlock(j);
return rc;
}
static void notify_dispatch(cluster_t* c, endpoint_t* ep, uint64_t jobid,
int code)
{
/* clang-format off */
job_failinfo_t info = {
.jobid = jobid,
.code = code
};
xce_notify_data_t data = {
.event = NotifyData_data_jobDispatchFail,
.data = {
.dispatchfail = &info
}
};
/* clang-format on */
notify(c, ep, &data);
}
int handle_jobdispatch(cluster_t* c, endpoint_t* ep, xce_request_t* request)
{
int rc = 0;
int i;
xce_job_dispatch_t* dispatchmsg = request->body.dispatchmsg;
xce_reply_t reply;
/* reply job dispatch that we'll handle request */
init_reply_by_req(&reply, request);
reply.status = 0;
reply.data_which = RequestReply_data_nodata;
xce_reply(ep, c->myhost, &reply);
for (i = 0; i < dispatchmsg->njobs; i++) {
int rc1;
xce_job_alloc_t* alloc = NULL;
MOVE_PTR(alloc, dispatchmsg->allocs[i]);
rc1 = dispatch_a_job_(c, ep, alloc);
if (rc1 < 0) {
/* notify dispatch fail */
notify_dispatch(c, ep, alloc->jobid, rc1);
} else {
/* notify dispatch ok */
notify_dispatch(c, ep, alloc->jobid, 0);
}
free_JobAlloc_ptr(&(alloc));
}
return rc;
}
static int xlist_deref_job_item_(job_t* j, void* arg) { return 0; }
int handle_jobsubmit(cluster_t* c, endpoint_t* ep, xce_request_t* request)
{
uint64_t jobid;
xce_job_submit_t* submit;
xce_reply_t reply;
xlist_t jlist;
job_t* j = NULL;
int i;
int rc;
submit = request->body.jobsubmsg;
init_reply_by_req(&reply, request);
if (NULLSTR(submit->submit->user) || NULLSTR(submit->submit->queue)
|| (submit->submit->start_info == NULL)
|| NULLSTR(submit->submit->start_info->cmdline)) {
jobid = 0;
errno = EINVAL;
} else {
xce_run_hooks(&(c->hooksys), XCE_CONTROLLER_HOOK_JOB, HOOK_BEFORE_EVENT,
HOOK_DETAIL_JOB_NEW, c, submit);
jobid = job_submit(c, submit);
}
if (jobid == 0) {
reply.status = -errno;
reply.data_which = RequestReply_data_nodata;
xce_reply(ep, c->myhost, &reply);
return -errno;
}
/* Build job list for the AFTER_EVENT hook BEFORE replying to client.
* The AFTER_EVENT hook writes WAL and waits for majority replication —
* the client must not be acknowledged until the job is durable. */
xlist_init(&jlist, submit->array_size);
for (i = 0; i < submit->array_size; i++) {
lock(c->jobmgr, RTTI_LOCK_READ);
rc = key_find(c->jobmgr, (void*)(jobid + i), (void**)&j);
if (j != NULL) {
reference(j);
}
unlock(c->jobmgr);
if ((rc <= 0) || (j == NULL)) {
char idstring[128];
fmt_jobid(idstring, sizeof(idstring) - 1, jobid);
ERROR("%s fail to lock job %s (%lu)", __func__, idstring, jobid);
} else {
if (xlist_store(&jlist, j) < 0) {
PERROR("xlist_store");
}
}
}
int hook_rc = xce_run_hooks(&(c->hooksys), XCE_CONTROLLER_HOOK_JOB,
HOOK_AFTER_EVENT,
HOOK_DETAIL_JOB_NEW, c, &jlist);
xlist_iter(&jlist, (xlist_iter_fn_t)xlist_deref_job_item_, NULL);
xlist_fini(&jlist);
/* If persistence failed (replication timeout, I/O error), reject the
* submission so the client knows the job was not made durable. */
if (hook_rc != 0) {
WARN("handle_jobsubmit: persistence hook failed (rc=%d) — rejecting job",
hook_rc);
reply.status = hook_rc;
reply.data_which = RequestReply_data_nodata;
xce_reply(ep, c->myhost, &reply);
return hook_rc;
}
/* Reply only AFTER WAL write + majority replication succeeded. */
reply.status = 0;
reply.data_which = RequestReply_data_jobid;
reply.data.jobid = jobid;
xce_reply(ep, c->myhost, &reply);
return 0;
}
static int mark_job_start(cluster_t* c, job_t* job, job_pidinfo_t* info)
{
int cur = job->job.state;
/* Transition guard (Req 5.2): START sets the non-terminal JOB_STAT_RUN. A
* START on an already-terminal job (stale/duplicate worker report after
* the job finished) is a backward transition — reject it, preserve the
* terminal state, and fire NO hook (no WAL append). Return success-no-op
* so the caller (on_job_start) still reports success. */
if (job_state_is_backward(cur, JOB_STAT_RUN)) {
WARN("job %ld: rejecting backward START on terminal state 0x%x — "
"preserving terminal state",
job->job.jobid, cur);
return 0;
}
xce_run_hooks(&(c->hooksys), XCE_CONTROLLER_HOOK_JOB, HOOK_BEFORE_EVENT,
HOOK_DETAIL_JOB_START, c, info, job);
/* update job information */
job->job.state = JOB_STAT_RUN;
job->job.start_time = time(NULL);
if (job->job.pidinfo == NULL) {
job->job.pidinfo = (job_pidinfo_t*)calloc(1, sizeof(job_pidinfo_t));
}
job->job.pidinfo->npids = copy_int_list((int**)&(job->job.pidinfo->pids),
(int*)info->pids, info->npids);
job->job.pidinfo->npgids = copy_int_list((int**)&(job->job.pidinfo->pgids),
(int*)info->pgids, info->npgids);
if (info->exdata != NULL) {
job->job.pidinfo->exdata = makeString(info->exdata);
} else {
job->job.pidinfo->exdata = NULL;
}
xce_run_hooks(&(c->hooksys), XCE_CONTROLLER_HOOK_JOB, HOOK_AFTER_EVENT,
HOOK_DETAIL_JOB_START, c, info, job);
return 0;
}
int on_job_start(cluster_t* c, job_pidinfo_t* info)
{
job_t* job = NULL;
int rc;
TRACE("%s jobid %ld", __func__, info->jobid);
lock(c->jobmgr, RTTI_LOCK_READ);
rc = key_find(c->jobmgr, (void*)info->jobid, (void**)&job);
if (job != NULL) {
reference(job);
}
unlock(c->jobmgr);
if ((rc <= 0) || (job == NULL)) {
ERROR("can not find job %ld", info->jobid);
return -errno;
}
lock(job, RTTI_LOCK_WRITE);
mark_job_start(c, job, info);
unlock(job);
dereference(job);
return 0;
}
static int mark_job_finish(cluster_t* c, job_t* job, xce_jobfinish_t* finish)
{
int cur = job->job.state;
/* Transition guard (Req 5.1): FINISH drives the job to a terminal state
* (DONE on exit_code 0, else EXIT). If the job is already terminal the
* FINISH has already been applied (retransmit / WAL replay) — log it and
* return a success-no-op WITHOUT firing the AFTER_EVENT hook, so no second
* WAL entry is appended and current_lsn does not advance. */
if (job_state_is_terminal(cur)) {
INFO("job %ld: duplicate FINISH on terminal state 0x%x — no-op",
job->job.jobid, cur);
return 0;
}
xce_run_hooks(&(c->hooksys), XCE_CONTROLLER_HOOK_JOB, HOOK_BEFORE_EVENT,
HOOK_DETAIL_JOB_EXIT, c, finish, job);
/* update job information */
if (finish->exit_code == 0) {
job->job.state = JOB_STAT_DONE;
} else {
job->job.state = JOB_STAT_EXIT;
}
job->job.finish_time = time(NULL);
/* fill job run time/rusage information */
if (job->job.exit_info == NULL) {
job->job.exit_info = (job_exitinfo_t*)calloc(1, sizeof(job_exitinfo_t));
}
if (job->job.exit_info != NULL) {
job->job.exit_info->exitcode = finish->exit_code;
}
job->job.run_time = job->job.finish_time - job->job.start_time;
xce_run_hooks(&(c->hooksys), XCE_CONTROLLER_HOOK_JOB, HOOK_AFTER_EVENT,
HOOK_DETAIL_JOB_EXIT, c, finish, job);
return 0;
}
int on_job_finish(cluster_t* c, xce_jobfinish_t* finish)
{
job_t* job = NULL;
TRACE("%s job finish jobid %ld exit code %d", __func__, finish->jobid,
finish->exit_code);
lock(c->jobmgr, RTTI_LOCK_READ);
key_find(c->jobmgr, (void*)finish->jobid, (void**)&job);
if (job != NULL) {
reference(job);
}
unlock(c->jobmgr);
if (job == NULL) {
ERROR("can not find job %ld", finish->jobid);
return -errno;
}
lock(job, RTTI_LOCK_WRITE);
mark_job_finish(c, job, finish);
unlock(job);
dereference(job);
return 0;
}
static int mark_job_fail(cluster_t* c, job_t* job, job_failinfo_t* failinfo)
{
xce_run_hooks(&(c->hooksys), XCE_CONTROLLER_HOOK_JOB, HOOK_BEFORE_EVENT,
HOOK_DETAIL_JOB_FAIL, c, failinfo, job);
/* update job information */
switch (failinfo->stage) {
case JOB_EXEC_STAGE_Q_POST_EXEC:
case JOB_EXEC_STAGE_POST_EXEC:
if ((job->job.state & (JOB_STAT_EXIT | JOB_STAT_DONE)) == 0) {
WARN("job %ld got post exec fail notification but job's exit "
"status has not been set",
job->job.jobid);
job->job.state |= JOB_STAT_EXIT;
}
job->job.state |= JOB_STAT_PERR;
break;
default:
job->job.state = JOB_STAT_EXIT;
break;
}
job->job.finish_time = time(NULL);
xce_run_hooks(&(c->hooksys), XCE_CONTROLLER_HOOK_JOB, HOOK_AFTER_EVENT,
HOOK_DETAIL_JOB_FAIL, c, failinfo, job);
return 0;
}
static int mark_job_update(cluster_t* c, job_t* job, int state)
{
int cur = job->job.state;
/* Transition guard (Req 5.1/5.2), sharing the backward predicate with
* START: an UPDATE that clears every terminal bit a terminal job holds is
* backward — reject it, preserve the terminal state, fire no hook. A
* forward merge that keeps a terminal bit (postdone OR'ing PDONE) is not
* backward and proceeds. A no-op update (requested state already current)
* is logged and skipped so it appends no duplicate WAL entry. */
if (job_state_is_backward(cur, state)) {
WARN("job %ld: rejecting backward UPDATE 0x%x -> 0x%x — preserving "
"terminal state",
job->job.jobid, cur, state);
return 0;
}
if (state == cur) {
INFO("job %ld: duplicate UPDATE to state 0x%x — no-op", job->job.jobid,
cur);
return 0;
}
xce_run_hooks(&(c->hooksys), XCE_CONTROLLER_HOOK_JOB, HOOK_BEFORE_EVENT,
HOOK_DETAIL_JOB_UPDATE, c, job);
/* update job state */
job->job.state = state;
xce_run_hooks(&(c->hooksys), XCE_CONTROLLER_HOOK_JOB, HOOK_AFTER_EVENT,
HOOK_DETAIL_JOB_UPDATE, c, job);
return 0;
}
int on_job_fail(cluster_t* c, job_failinfo_t* failinfo)
{
job_t* job = NULL;
TRACE("%s job fail jobid %ld code %d", __func__, failinfo->jobid,
failinfo->code);
lock(c->jobmgr, RTTI_LOCK_READ);
key_find(c->jobmgr, (void*)failinfo->jobid, (void**)&job);
if (job != NULL) {
reference(job);
}
unlock(c->jobmgr);
if (job == NULL) {
ERROR("can not find job %ld", failinfo->jobid);
return -errno;
}
lock(job, RTTI_LOCK_WRITE);
mark_job_fail(c, job, failinfo);
unlock(job);
dereference(job);
return 0;
}
int on_job_stop(cluster_t* c, uint64_t jobid)
{
job_t* job = NULL;
int state;
TRACE("%s job stop jobid %ld", __func__, jobid);
lock(c->jobmgr, RTTI_LOCK_READ);
key_find(c->jobmgr, (void*)jobid, (void**)&job);
if (job != NULL) {
reference(job);
}
unlock(c->jobmgr);
if (job == NULL) {
ERROR("can not find job %ld", jobid);
return -errno;
}
lock(job, RTTI_LOCK_WRITE);
state = job->job.state;
xce_run_hooks(&(c->hooksys), XCE_CONTROLLER_HOOK_JOB, HOOK_BEFORE_EVENT,
HOOK_DETAIL_JOB_STOP, c, job);
state |= JOB_STAT_USUSP;
job->job.state = state;
xce_run_hooks(&(c->hooksys), XCE_CONTROLLER_HOOK_JOB, HOOK_AFTER_EVENT,
HOOK_DETAIL_JOB_STOP, c, job);
unlock(job);
dereference(job);
return 0;
}
int on_job_resume(cluster_t* c, uint64_t jobid)
{
job_t* job = NULL;
int state;
TRACE("%s job resume jobid %ld", __func__, jobid);
lock(c->jobmgr, RTTI_LOCK_READ);
key_find(c->jobmgr, (void*)jobid, (void**)&job);
if (job != NULL) {
reference(job);
}
unlock(c->jobmgr);
if (job == NULL) {
ERROR("can not find job %ld", jobid);
return -errno;
}
lock(job, RTTI_LOCK_WRITE);
state = job->job.state;
xce_run_hooks(&(c->hooksys), XCE_CONTROLLER_HOOK_JOB, HOOK_BEFORE_EVENT,
HOOK_DETAIL_JOB_RESUME, c, job);
state &= ~JOB_STAT_USUSP;
job->job.state = state;
xce_run_hooks(&(c->hooksys), XCE_CONTROLLER_HOOK_JOB, HOOK_AFTER_EVENT,
HOOK_DETAIL_JOB_RESUME, c, job);
unlock(job);
dereference(job);
return 0;
}
int on_job_postdone(cluster_t* c, endpoint_t* ep, uint64_t jobid)
{
job_t* job = NULL;
int state;
TRACE("%s job post done jobid %ld", __func__, jobid);
lock(c->jobmgr, RTTI_LOCK_READ);
key_find(c->jobmgr, (void*)jobid, (void**)&job);
if (job != NULL) {
reference(job);
}
unlock(c->jobmgr);
if (job == NULL) {
ERROR("can not find job %ld", jobid);
return -errno;
}
lock(job, RTTI_LOCK_WRITE);
state = job->job.state;
if ((state & (JOB_STAT_EXIT | JOB_STAT_DONE)) == 0) {
WARN("job %ld got post exec fail notification but job's exit status "
"has not been set",
job->job.jobid);
state |= JOB_STAT_EXIT;
/* ensure that job finish time has been set */
job->job.finish_time = time(NULL);
}
state |= JOB_STAT_PDONE;
mark_job_update(c, job, state);
unlock(job);
dereference(job);
return 0;
}
int on_job_ckpt(cluster_t* c, endpoint_t* ep, xce_ckptinfo_t* ckptinfo)
{
uint64_t jobid;
char* info = NULL;
job_t* j = NULL;
if (ckptinfo == NULL) {
ERROR("%s ckptinfo should not be NULL", __func__);
return -EINVAL;
}
jobid = ckptinfo->jobid;
info = ckptinfo->ckptinfo;
TRACE("%s job %ld ckptinfo %s", __func__, jobid, info);
lock(c->jobmgr, RTTI_LOCK_READ);
key_find(c->jobmgr, (void*)jobid, (void**)&j);
if (j != NULL) {
reference(j);
}
unlock(c->jobmgr);
if (j == NULL) {
ERROR("%s can not find job %ld", __func__, jobid);
return -errno;
}
lock(j, RTTI_LOCK_WRITE);
xce_run_hooks(&(c->hooksys), XCE_CONTROLLER_HOOK_JOB, HOOK_BEFORE_EVENT,
HOOK_DETAIL_JOB_CKPT, c, j);
if (j->job.ckptinfo != NULL) {
dereference(j->job.ckptinfo);
}
j->job.ckptinfo = makeString(info);
xce_run_hooks(&(c->hooksys), XCE_CONTROLLER_HOOK_JOB, HOOK_AFTER_EVENT,
HOOK_DETAIL_JOB_CKPT, c, j);
unlock(j);
dereference(j);
return 0;
}
int do_jobcontrol_op(cluster_t* c, endpoint_t* ep, xce_request_t* request)
{
int rc = 0;
xce_reply_t reply;
init_reply_by_req(&reply, request);
rc = job_ctrl(c, request->body.jobctrlmsg);
/* Commit barrier (ha-commit-barrier-rollout Req 1.1-1.4): the success
* reply is sent only after the operation's WAL entry is majority-
* committed; barrier failures (-ETIMEDOUT, ...) become the error
* reply. Errors from job_ctrl reply immediately — no barrier wait.
* job_ctrl released all entity locks before returning, so blocking
* here holds no lock. timeout 0 = configured sync_timeout_ms. */
if (rc == 0) {
rc = persist_commit_barrier(&c->persist, 0);
if (rc != 0)
WARN("%s commit barrier failed, rc %d", __func__, rc);
}
reply.status = rc;
reply.data_which = RequestReply_data_nodata;
xce_reply(ep, c->myhost, &reply);
return rc;
}
int update_job_rusages(cluster_t* c, endpoint_t* ep, xce_request_t* request)
{
xce_job_rusages_t* rusages = request->body.updatemsg->data.jobrusages;
job_t* j = NULL;
worker_t* w = NULL;
char* host = NULL;
TRACE("%s trying to update job(%ld) rusage", __func__, rusages->jobid);
xce_run_hooks(&(c->hooksys), XCE_CONTROLLER_HOOK_JOB, HOOK_BEFORE_EVENT,
HOOK_DETAIL_JOB_RUSAGE_UPDATE, c, rusages);
lock(c->jobmgr, RTTI_LOCK_READ);
key_find(c->jobmgr, (void*)rusages->jobid, (void**)&j);
if (j != NULL) {
reference(j);
}
unlock(c->jobmgr);
if (j == NULL) {
PERROR("jobmgr_lockjob");
return -errno;
}
w = get_ep_worker(c, ep);
if (w == NULL) {
dereference(j);
return errno;
}
host = makeString(w->host.name);
if (host == NULL) {
dereference(j);
return -ENOMEM;
}
TRACE("%s update job (%ld) rusage for host %s", __func__, rusages->jobid,
host);
lock(j, RTTI_LOCK_WRITE);
xce_run_hooks(&(c->hooksys), XCE_CONTROLLER_HOOK_JOB, HOOK_BEFORE_EVENT,
HOOK_DETAIL_JOB_UPDATE, c, j);
update_host_runusage(&(j->job.run_usage), host, rusages->count,
rusages->usages);
update_pids(&(j->job.pidinfo), rusages->npids, rusages->pids);
update_pgids(&(j->job.pidinfo), rusages->npgids, rusages->pgids);
/* FIXME
* update other fields of job rusage later
*/
xce_run_hooks(&(c->hooksys), XCE_CONTROLLER_HOOK_JOB, HOOK_AFTER_EVENT,
HOOK_DETAIL_JOB_UPDATE, c, j);
xce_run_hooks(&(c->hooksys), XCE_CONTROLLER_HOOK_JOB, HOOK_AFTER_EVENT,
HOOK_DETAIL_JOB_RUSAGE_UPDATE, c, rusages);
unlock(j);
dereference(j);
return 0;
}
static int set_preason(cluster_t* c, xce_pendreason_t* reasons)
{
job_t* j = NULL;
xce_job_t* job = NULL;
TRACE("%s jobid %ld", __func__, reasons->jobid);
lock(c->jobmgr, RTTI_LOCK_READ);
key_find(c->jobmgr, (void*)reasons->jobid, (void**)&j);
if (j != NULL) {
reference(j);
}
unlock(c->jobmgr);
if (j == NULL) {
PERROR("jobmgr_lockjob");
return -ENOENT;
}
lock(j, RTTI_LOCK_WRITE);
xce_run_hooks(&(c->hooksys), XCE_CONTROLLER_HOOK_JOB, HOOK_BEFORE_EVENT,
HOOK_DETAIL_SETPREASON, c, j);
job = &(j->job);
if (job->pend_reasons != NULL) {
erase_job_preason(job->pend_reasons);
FREEUP(job->pend_reasons);
}
MOVE_PTR(job->pend_reasons, reasons->reasons);
xce_run_hooks(&(c->hooksys), XCE_CONTROLLER_HOOK_JOB, HOOK_AFTER_EVENT,
HOOK_DETAIL_SETPREASON, c, j);
unlock(j);
dereference(j);
return 0;
}
int do_set_preason(cluster_t* c, endpoint_t* ep, xce_request_t* request)
{
int i;
xce_preason_set_t* reasons = request->body.preasonmsg;
xce_reply_t reply;
init_reply_by_req(&reply, request);
reply.status = 0;
reply.data_which = RequestReply_data_nodata;
xce_reply(ep, c->myhost, &reply);
for (i = 0; i < reasons->nreasons; i++) {
int rc = 0;
if (reasons->reasons[i] == NULL) {
continue;
}
rc = set_preason(c, reasons->reasons[i]);
if (rc < 0) {
PERROR("set_preason");
}
}
return 0;
}
int do_clr_preason(cluster_t* c, endpoint_t* ep, xce_request_t* request)
{
int i;
xce_reply_t reply;
xce_clear_reason_t* clreason = request->body.clrpreasonmsg;
init_reply_by_req(&reply, request);
reply.status = 0;
reply.data_which = RequestReply_data_nodata;
xce_reply(ep, c->myhost, &reply);
for (i = 0; i < clreason->njobs; i++) {
uint64_t jobid = clreason->jobs[i];
job_t* j;
xce_job_t* job;
lock(c->jobmgr, RTTI_LOCK_READ);
key_find(c->jobmgr, (void*)jobid, (void**)&j);
if (j != NULL) {
reference(j);
}
unlock(c->jobmgr);
if (j == NULL) {
PERROR("jobmgr_lockjob");
continue;
}
lock(j, RTTI_LOCK_WRITE);
xce_run_hooks(&(c->hooksys), XCE_CONTROLLER_HOOK_JOB, HOOK_BEFORE_EVENT,
HOOK_DETAIL_CLRPREASON, c, j);
job = &(j->job);
if (job->pend_reasons != NULL) {
erase_job_preason(job->pend_reasons);
FREEUP(job->pend_reasons);
}
xce_run_hooks(&(c->hooksys), XCE_CONTROLLER_HOOK_JOB, HOOK_AFTER_EVENT,
HOOK_DETAIL_CLRPREASON, c, j);
unlock(j);
dereference(j);
}
return 0;
}
/* job_is_terminal and job_should_retain live in persist.c —
* they only depend on xce_job_t fields and persist_config_t,
* and must be accessible from the unit test binary which links persist.c. */
Reference in a new issue View git blame Copy permalink