Rongsong Shen
959b0cdacb
Build the live 3-node chaotic-multi-kill config-upgrade soak scenario (run-ha-soak.sh --config-upgrade) required by Requirements 4.1, 4.3, 6.1, 6.4. This needed genuinely new client-side infrastructure: a hand-rolled capnp send path for OP_upgradeConfig (the auto-generated encoder is a no-op for its Data fields, worked around the same way xce_replconfigpush_req_raw already does), plus cmd_hostctrl/cmd_upgradeconfig CLI commands. Building and running this live surfaced two real production bugs, both fixed here: - bug-1468: an unrelated prior commit inverted OPCode_upgradeConfig's primary/standby dispatch guard in cluster.c, making config upgrades unreachable from any network client. - bug-1469: apply_committed_entry's WAL_CONFIG_MARKER case never called config_activate_committed(), so the node that originates a config upgrade never refreshed its own in-memory state as part of committing it. Killing that node before some later, unrelated event happened to refresh it left its checkpoint permanently stale -- the first live, empirical reproduction of bug-857's originally hypothesized failure mode. Fixed by activating before the marker-triggered checkpoint write, since checkpoint content is built from live runtime tables that only reflect the reload after activation runs. A separate, narrower checkpoint divergence (bug-1471, not config-related) remains open and still blocks a clean soak PASS -- task 8.6 stays in-progress until it's resolved.
50 lines
2.4 KiB
C
50 lines
2.4 KiB
C
#if !defined(_XCEAPI_H_)
|
|
|
|
#define _XCEAPI_H_ 1
|
|
|
|
#include "config.h"
|
|
|
|
#include "xce/types.h"
|
|
#include "xcectx.h"
|
|
|
|
extern int xce_hello(xce_ctx_t*, char*);
|
|
extern int xce_nop(xce_ctx_t*);
|
|
extern int xce_heartbeat(xce_ctx_t*, int);
|
|
extern int xce_shutdown(xce_ctx_t*);
|
|
extern int xce_reslist(xce_ctx_t*, xce_resource_t***);
|
|
extern int xce_join(xce_ctx_t*, int, hostattrs_t*);
|
|
extern int xce_workerlist(xce_ctx_t*, xce_worker_t***);
|
|
extern int xce_jobdispatch(xce_ctx_t*, xce_job_dispatch_t*);
|
|
extern int xce_jobsubmit(xce_ctx_t*, xce_job_submit_t*, uint64_t*);
|
|
extern int xce_joblist(xce_ctx_t*, xce_job_t***);
|
|
extern int xce_clusterconf(xce_ctx_t*, xce_clusterconf_t**);
|
|
extern int xce_ctrlstatus(xce_ctx_t*, xce_ctrlstatus_t**);
|
|
extern int xce_push(xce_ctx_t*, xce_check_fn_t, void*, int, int, int, void**);
|
|
extern int xce_update_rows(xce_ctx_t*, int, int, xlist_t*);
|
|
extern int xce_resval(xce_ctx_t*, char*, char*, xce_resval_t***);
|
|
|
|
extern int xce_notify(xce_ctx_t*, xce_notify_data_t*);
|
|
extern int xce_update_resvals(xce_ctx_t*, int, xce_resval_t**);
|
|
extern int xce_jobctrl(xce_ctx_t*, xce_jobctrl_t*);
|
|
extern int xce_queuectrl(xce_ctx_t*, xce_queuectrl_t*);
|
|
extern int xce_hostctrl(xce_ctx_t*, xce_hostctrl_t*);
|
|
/* xce_upgradeconfig: send OP_upgradeConfig (sha256 + serialised ClusterConfig
|
|
* blob) via xce_upgradeconfig_req_raw and wait for the reply. Returns the
|
|
* server's reply status (0 on success; a negative errno/E_XCE_* code on
|
|
* failure — the server logs the human-readable reason, see
|
|
* do_upgrade_config_with_bytes/send_upgrade_error, config_repl.c). Mirrors
|
|
* xce_hostctrl/xce_queuectrl's shape; the richer UpgradeConfigReply fields
|
|
* (version_tag/acked_count/error text) are not surfaced to the caller — no
|
|
* consumer of this API currently needs them beyond success/failure. */
|
|
extern int xce_upgradeconfig(xce_ctx_t*, const uint8_t *sha256,
|
|
size_t sha256_len, const uint8_t *bytes,
|
|
size_t bytes_len);
|
|
extern int xce_runtask(xce_ctx_t*, xce_taskrun_t*);
|
|
extern int xce_update_jusage(xce_ctx_t*, uint64_t, int, int*, int, int*, int,
|
|
xce_rusage_t**);
|
|
extern int xce_set_pend_reason(xce_ctx_t*, xce_preason_set_t*);
|
|
extern int xce_clear_reason(xce_ctx_t*, xce_clear_reason_t*);
|
|
extern int xce_jobinfo(xce_ctx_t*, uint64_t, xce_job_t**);
|
|
extern int xce_fetchfile(xce_ctx_t*, xce_fetchfile_t*, xce_fetchfile_reply_t**);
|
|
|
|
#endif
|