Rongsong Shen
8b7173bb09
The controller forwards a kill as soon as it has dispatched a job, but
the worker queues the start and only registers the job (and, for the
real worker, connects its IPC client) once it starts -- seconds later
for the first jobs after a worker starts. A signal arriving in between
was dropped ("Failed to find worker"), although the API reported it
accepted, and the job ran to completion.
New pending_signal table: the start handler records the job, a signal
for a queued or still-starting job is kept there, and it is delivered
when the job reaches RUNNING (virtual: killed_signal; real: IPC). A
failed start or a job that ends drops the entry.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
111 lines
2.8 KiB
Meson
111 lines
2.8 KiB
Meson
xcecd_worker_srcs = [
|
|
'src/xcecd_worker.c',
|
|
'src/inter_job_utils.c',
|
|
'src/xcecd_exdata.c',
|
|
'src/uv_ipc.c',
|
|
'src/uv_proc.c',
|
|
'src/static_array.c',
|
|
'src/xcecd_cgroups.c',
|
|
'src/xcecd_worker_utils.c',
|
|
'src/pending_signal.c',
|
|
'src/xcecd_resync.c',
|
|
'src/controller_connector.c',
|
|
'src/xcecd_dbus_manager.c',
|
|
'src/xcecd_db.c',
|
|
'src/xcecd.c',
|
|
'src/connection_handler.c',
|
|
'src/resource_sync.c',
|
|
'src/node_information.c',
|
|
'src/thread_pool.c',
|
|
'src/hardware_monitor.c',
|
|
'src/system_monitor.c',
|
|
'src/process_manager.c',
|
|
'src/process_worker_manager.c',
|
|
'src/xcecd_sig.c',
|
|
]
|
|
|
|
incdir = include_directories('.', 'include', '../include', '../lib')
|
|
|
|
libuv_dep = dependency('libuv')
|
|
elogind_dep = dependency('libelogind')
|
|
sqlite3_dep = dependency('sqlite3')
|
|
libcgroup_dep = dependency('libcgroup')
|
|
hwloc_dep = dependency('hwloc')
|
|
|
|
xcecd_worker_deps = [
|
|
libxce_dep,
|
|
libcgroup_dep,
|
|
hwloc_dep,
|
|
libuv_dep,
|
|
elogind_dep,
|
|
sqlite3_dep,
|
|
struct2json_dep,
|
|
yaml_deps,
|
|
tinylog_dep,
|
|
]
|
|
|
|
xcecd_worker = executable('xcecd_worker',
|
|
xcecd_worker_srcs,
|
|
c_args:['-DIPC_WORKER'],
|
|
include_directories: [incdir],
|
|
dependencies: [xcecd_worker_deps],
|
|
install: true)
|
|
|
|
xrun_srcs = [
|
|
'src/xrun.c'
|
|
]
|
|
|
|
xrun_deps = [
|
|
libxce_dep,
|
|
tinylog_dep,
|
|
]
|
|
|
|
xrun = executable('xrun',
|
|
xrun_srcs,
|
|
c_args: ['-DXRUN'],
|
|
include_directories: [incdir],
|
|
dependencies: [xrun_deps],
|
|
install: true)
|
|
|
|
xcecd_srcs = [
|
|
'src/static_array.c',
|
|
'src/inter_job_utils.c',
|
|
'src/xcecd_sig.c',
|
|
'src/uv_ipc.c',
|
|
'src/xcecd_db.c',
|
|
'src/xcecd_exdata.c',
|
|
'src/xcecd_cgroups.c',
|
|
'src/xcecd_dbus_manager.c',
|
|
# 'src/main.c',
|
|
'src/xcecd.c',
|
|
'src/thread_pool.c',
|
|
'src/system_monitor.c',
|
|
'src/process_manager.c',
|
|
'src/process_worker_manager.c',
|
|
'src/connection_handler.c',
|
|
'src/controller_connector.c',
|
|
'src/resource_sync.c',
|
|
'src/xcecd_worker_utils.c',
|
|
'src/xcecd_resync.c',
|
|
'src/hardware_monitor.c',
|
|
'src/node_information.c',
|
|
'src/job_information.c',
|
|
'src/pending_signal.c'
|
|
]
|
|
|
|
xcecd_deps = [xcecd_worker_deps]
|
|
xcecd = executable('xcecd',
|
|
[xcecd_srcs,'src/main.c'],
|
|
c_args: ['-DDBUS_MANAGER'],
|
|
include_directories: [incdir],
|
|
dependencies: [xcecd_deps],
|
|
install: true)
|
|
|
|
xcecd_virtual = executable('xcecd_virtual',
|
|
[xcecd_srcs,'src/main.c'],
|
|
c_args: ['-DVIRTUAL_CLUSTER', '-DDBUS_MANAGER'],
|
|
include_directories: [incdir],
|
|
dependencies:[xcecd_deps],
|
|
install:true)
|
|
|
|
subdir('testsuite')
|