myxce/src/scheduler/include/plugin.h

#if !defined(_PLUGIN_H_)

#define _PLUGIN_H_ 1

#include <stdint.h>
#include <stdlib.h>

#include "decision.h"
#include "resreq.h"
#include "sched/types.h"

typedef void* plugin_data_t;

/* hooker of plugin, the first parameter should be xce_sched_plugin_t */
typedef int (*plugin_update_config_hook_t)(void*, xce_conf4sched_t*);
typedef int (*plugin_update_queue_hook_t)(void*, xce_sched_queue_t*);
typedef int (*plugin_update_job_hook_t)(void*, xce_sched_job_t*);
typedef int (*plugin_update_worker_hook_t)(void*, xce_sched_worker_t*);
typedef int (*plugin_job_state_change_hook_t)(void*, xce_sched_job_t*,
                                              uint32_t);
typedef int (*plugin_commit_decision_hook_t)(void*, xce_decision_t*);
typedef int (*plugin_job_election_hook_t)(void*, xce_sched_job_t*);
typedef int (*plugin_prepare_allocation_hook_t)(void*, xce_sched_ctx_t*);
typedef int (*plugin_job_rusage_hook_t)(void*, xce_sched_job_t*,
                                        xce_job_rusages_t*);

/* initialize function of plugin */
typedef int (*plugin_init_fn_t)(void*);

typedef void (*plugin_fini_fn_t)(void*);

/* plugin function to elect job to be scheduler */
typedef void* (*plugin_job_election_fn_t)(void*);

/* plugin callback when a job has been elected */

typedef int (*plugin_begin_session_fn_t)(void*);

typedef int (*plugin_end_session_fn_t)(void*);

/* allocation function of job */
typedef int (*plugin_job_allocate_fn_t)(void*, xce_sched_ctx_t*);

typedef struct {
    plugin_update_config_hook_t      config_hook;
    plugin_update_queue_hook_t       queue_hook;
    plugin_update_job_hook_t         job_hook;
    plugin_job_state_change_hook_t   jstate_hook;
    plugin_update_worker_hook_t      worker_hook;
    plugin_commit_decision_hook_t    commit_hook;
    plugin_job_election_hook_t       job_election_hook;
    plugin_prepare_allocation_hook_t prepare_allocation_hook;
    plugin_job_rusage_hook_t         rusage_hook;
} plugin_hooks_t;

/* Forward declaration -- xce_job_picker_iface_t is fully defined below
 * (Req 1 AC 2). Only needed here as a pointer field on xce_sched_plugin_t
 * (picker plugin registration category, scheduler-core task 1.2);
 * re-declared as the same typedef once the struct body is complete below
 * -- same idiom as cluster_t across myconf.h/persist.h/ha.h/cluster_def.h. */
typedef struct xce_job_picker_iface_s xce_job_picker_iface_t;

/* xce_sched_core_t is defined in core.h -- forward-declared here (re-declared
 * again, harmlessly, near plugin_register_core()'s own declaration below)
 * so plugin_begin_session()/plugin_end_session() can be declared against it
 * ahead of that later block. */
typedef struct xce_sched_core_s xce_sched_core_t;

typedef struct {
    char*                     name;
    void*                     sched;
    uint32_t                  plugin_id;
    plugin_init_fn_t          init_fn;
    plugin_fini_fn_t          fini_fn;
    plugin_begin_session_fn_t begin_session_fn;
    plugin_end_session_fn_t   end_session_fn;
    plugin_job_election_fn_t  job_elect_fn;
    plugin_job_allocate_fn_t  job_alloc_fn;
    plugin_hooks_t            hooks;
    plugin_data_t             data;
    /* Picker plugin registration category (task 1.2): non-NULL once this
     * plugin participates in the xce_job_picker_iface_t contract -- either
     * because it was authored against the new interface directly, or
     * because plugin_register() adapted it from the deprecated job_elect_fn
     * hook via the compatibility wrapper (Req 5 "Migration from old
     * job_elect_fn"). Stays NULL for plugin categories that are neither
     * (allocator/limit plugins never set job_elect_fn). */
    xce_job_picker_iface_t* picker_iface;
} xce_sched_plugin_t;

extern int  plugin_register(void*, void*);
extern void plugin_unregister(void*);
extern int  plugin_config_update(void*, xce_conf4sched_t*);
extern int  plugin_queue_update(void*, xce_sched_queue_t*);
extern int  plugin_job_update(void*, xce_sched_job_t*);
extern int  plugin_worker_update(void*, xce_sched_worker_t*);
extern int  plugin_job_state_change(void*, xce_sched_job_t*, uint32_t);
/* plugin_begin_session()/plugin_end_session() - relocated to xce_sched_core_t*
 * (bug-1681, mirroring sched_account_jobs()'s identical scheduler-sim-
 * decision-parity task 1.1 relocation): the per-plugin begin/end_session_fn
 * iteration only ever touches core->plugins, never anything else on
 * xce_scheduler_t* -- so, like plugin_register_core() below, these are
 * callable from a driver with no xce_scheduler_t* (the simulation driver).
 * See driver.c's xce_sched_driver_run_normal_mode_round() for the normal-
 * mode call site and sim_loop.c's sched_sim_driver_run() for the mirrored
 * simulation-mode one. */
extern int  plugin_begin_session(xce_sched_core_t*);
extern int  plugin_end_session(xce_sched_core_t*);
extern int  plugin_commit_decision(void*, xce_decision_t*);
extern int  plugin_prepare_allocation(void*, xce_sched_ctx_t*);
extern int  plugin_job_election(void*, xce_sched_job_t*);
extern int  plugin_job_rusage_update(void*, xce_sched_job_t*,
                                     xce_job_rusages_t*);
extern int  register_fcfs(void*);
extern int  register_builtin_fcfs(void*);
extern int  register_limit(void*);
extern int  register_seqjob_allocator(void*);
extern int  register_parjob_allocator(void*);

/* ---------------------------------------------------------------------
 * Job picker plugin interface (xce_job_picker_iface_t)
 *
 * scheduler-core spec, Req 1 AC 2 / AC 5, Req 2 AC 6.
 *
 * Supersedes plugin_job_election_hook_t / plugin_job_election_fn_t
 * (job_elect_fn above) as the job-selection contract: the core scheduling
 * loop calls picker->next_job(picker) to get the next schedulable job (or
 * NULL) and carries zero knowledge of project/queue/job iteration or
 * ordering — all of that lives behind this interface (Req 1 AC 1).
 * job_elect_fn-only plugins keep working during the transition via a
 * compatibility wrapper (registered in plugin.c, scheduler-core task 1.2);
 * new pickers implement xce_job_picker_iface_t directly.
 * --------------------------------------------------------------------- */

/* xce_sched_core_t is defined in core.h, added by the scheduler-core spec's
 * Phase 2 core/driver extraction. Forward-declared here (same idiom as
 * cluster_t in myconf.h/persist.h/ha.h) to avoid a circular include —
 * init() below only ever holds/passes a pointer to it. */
typedef struct xce_sched_core_s xce_sched_core_t;

/*
 * builtin_fcfs_new_plugin - factory half of register_builtin_fcfs()'s
 * template-build step (plugins/builtin_fcfs.c), extracted so a caller with
 * no xce_scheduler_t* (e.g. the simulation driver, via
 * plugin_register_core() below) can obtain a freshly calloc'd, fully
 * populated `xce_sched_plugin_t` for builtin_fcfs -- same picker_iface/
 * init_fn/fini_fn template register_builtin_fcfs() itself uses, just not
 * yet registered anywhere. Returns NULL on allocation failure. Caller owns
 * the returned plugin (frees it only on a subsequent registration failure
 * -- once registered, the plugin registry owns it, same lifetime rule
 * every other plugin category in this codebase already follows).
 */
extern xce_sched_plugin_t* builtin_fcfs_new_plugin(void);

/*
 * plugin_register_core - Req 5 AC 17 (scheduler-core spec, task 11.2): the
 * "core.h-scoped plugin registration path" sim.h's own doc comment on
 * sched_sim_driver_start() anticipated but did not build (task 11.1's
 * documented "Known scope boundary"). plugin_register() above requires a
 * genuine `xce_scheduler_t*` (it dereferences `sched->core.plugins` and
 * stores `plugin->sched = sched` for plugin_unregister()'s later use) --
 * unavailable to a driver like the simulation driver that deliberately has
 * no such type. This is the SAME registration mechanism minus that one
 * dependency: run the plugin's init_fn (same "driver thread, at plugin
 * register" timing plugin.h's own hook-category doc comment documents),
 * then key_add() it into `core->plugins` directly -- identical steps
 * plugin_register() itself performs, in the same order, just addressed at
 * xce_sched_core_t* instead of xce_scheduler_t*. `plugin->sched` is left
 * NULL (no xce_scheduler_t* exists to store) -- safe, since
 * plugin_unregister() is a no-op on a NULL `plugin->sched` and nothing
 * calls it for a plugin registered this way (no sim-driver teardown path
 * exists yet). Returns the assigned plugin_id (>= 0) on success, or a
 * negative errno: -EINVAL for a NULL core/plugin, whatever init_fn
 * returned if it failed, or key_add()'s own negative return.
 */
extern int plugin_register_core(xce_sched_core_t*, xce_sched_plugin_t*);

/*
 * Hook categories and the thread each category runs in (Req 1 AC 3):
 *
 * Lifecycle hooks (MUST) — driver thread, at plugin register/teardown:
 *   init   One-time setup; receives a core reference for state queries.
 *          Called exactly once, before any other hook.
 *   fini   Teardown; frees all picker-owned resources.
 *
 * State-change hooks (MUST) — driver thread; called synchronously, only
 * from inside core_push_events(), which itself is only invoked between
 * sessions (picker thread blocked on cbuf_get(&wbuf), allocator thread
 * blocked on cbuf_get(&jbuf)). No mid-session event injection:
 *   on_queue_update       Add/update a queue in the picker's internal
 *                         ordering.                  <- QUEUE_UPDATE event
 *   on_job_push           Add a newly pending job to the candidate set.
 *                                                       <- JOBS_PUSH event
 *   on_job_state_change   Drop the job from candidates if it left pending;
 *                         re-add if it returned to pending.
 *                                                <- JOB_STATE_CHANGE event
 *   on_job_update         Reorder the job in candidates if its priority or
 *                         queue changed.               <- JOB_UPDATE event
 *
 * Session hooks (MUST) — picker thread, at scheduling-round boundaries:
 *   begin_session   Reset the iteration cursor. Called at the start of
 *                   every scheduling round. Session-aware requirement: a
 *                   picker MUST reset all iteration state here — never
 *                   carry it over from the previous session.
 *   next_job        Return the next schedulable job per the picker's
 *                   ordering, or NULL once exhausted. Cancel-safe
 *                   requirement: next_job() runs in the dedicated picker
 *                   thread, which is torn down via pthread_cancel — the
 *                   iteration loop inside next_job() (and any blocking
 *                   point it reaches, e.g. cbuf_get(&wbuf) between
 *                   sessions) MUST have defined pthread_cancel
 *                   cancellation points (pthread_testcancel() or an
 *                   existing cancellation-point call).
 *   end_session     End-of-round notification; called before the core
 *                   sleeps between rounds.
 *
 * Post-allocation hooks (MUST) — allocator thread, after each allocation
 * attempt for a job next_job() returned:
 *   on_dispatch   Job was allocated; remove it from candidates
 *                 permanently.
 *   on_pend       Job was pended (or preempted back to pend); keep it for
 *                 the next round, may deprioritize.
 *
 * Optional hooks (MAY be NULL) — same thread as the triggering event
 * above (on_config: driver thread inside core_push_events(); on_job_rusage:
 * driver thread inside core_push_events()):
 *   on_config       Rebuild picker strategy from config. NULL if the
 *                   picker is config-agnostic.
 *   on_job_rusage   Track per-job resource usage. NULL if the picker is
 *                   not resource-aware.
 *
 * Contract (Req 1 AC 5, Req 2 AC 6):
 *   - Cancel-safe: next_job() has defined pthread_cancel cancellation
 *     points.
 *   - Session-aware: begin_session() resets all iteration state.
 *   - Hook implementations never block indefinitely — the picker thread
 *     holds no lock the allocator thread needs.
 *   - next_job() never returns the same job twice within one session.
 *
 * Preconditions / postconditions:
 *   - init() is called exactly once before any other hook.
 *   - begin_session() precedes every next_job() sequence.
 *   - next_job() returns NULL exactly when no ready job remains for the
 *     current session.
 */
typedef struct xce_job_picker_iface_s {
    int (*init)(void* picker, xce_sched_core_t* core);
    void (*fini)(void* picker);
    int (*begin_session)(void* picker);
    xce_sched_job_t* (*next_job)(void* picker);
    int (*end_session)(void* picker);
    int (*on_dispatch)(void* picker, uint64_t jobid);
    int (*on_pend)(void* picker, uint64_t jobid);
    int (*on_queue_update)(void* picker, xce_sched_queue_t* queue);
    int (*on_job_push)(void* picker, xce_sched_job_t* job);
    int (*on_job_state_change)(void* picker, xce_sched_job_t* job,
                               uint32_t state);
    int (*on_job_update)(void* picker, xce_sched_job_t* job);
    int (*on_config)(void* picker, xce_conf4sched_t* config); /* MAY be NULL */
    int (*on_job_rusage)(void* picker, xce_sched_job_t* job,
                         xce_job_rusages_t* rusages);         /* MAY be NULL */
} xce_job_picker_iface_t;

#endif