Task 4.3: trace on all|job SEL... [level] [lines N] [file PATH], off and
status, parsed from the raw line; invalid arguments are named and leave
the settings unchanged; refcounted next/current settings; status shows
the settings in effect or pending, whole arrays as <base>[*], and stored
trace memory against its bound.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Task 4.2: a new trace replaces a job's earlier one; above 64 MiB the
oldest traces are evicted (never the newest) and marked discarded until
a newer capture; info trace renders a job's or an array's stored traces
in the current units mode, or reports discarded / no trace with the
job's state / unknown job.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Task 4.1: hierarchy, summary-level position summaries, truncation marker
with the fixed totals block, 50-host outcome cap with aggregates and
separate limit charges, no-decision and reconstructed records, amounts
in the REPL units mode, identical bytes to one or two sinks.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Task 3.4: the runner records no-plan reasons, the cluster-wide check,
plans (tried, discarded, not tried) and their ends, positions, claimed
skips and per-host candidate verdicts, rollbacks, commit or finalize
failure, and search end. A declined or generator-failed requirement now
counts once as 'no plan generated'. Runner results are unchanged.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Task 3.3: the pre-filter records selection mismatches and internal
errors as host verdicts, a scan stopped by an error marks the position
as a scan error, and unsatisfy_() hands every checked row to the current
record. Iterator and check results are unchanged.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Task 3.2: single requirements, top-level compounds, alternatives and
members push their path level and record one begin and one end; member
failures record the members not tried, merge failures and skipped
alternatives are separate entries, the chosen alternative or all-failed
is recorded, and each compound attempt's reasons are captured before the
job's stored reason is replaced. Scheduling results are unchanged.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Task 3.1: when the sim publishes trace settings, sched_allocator() counts
job positions, starts a record for wanted jobs with their selection and
cluster-wide limits, pushes no-decision kinds as trace-only decisions,
and attaches the captured outcome to built decisions; every handoff
clears core->trace_rec. Live (trace_ctl NULL) is unchanged.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Task 2.4: outcome capture moves to sched_trace_outcome.c and the
position/host/summary/rollback half of the model to sched_trace_scan.c;
shared helpers go behind sched_trace_internal.h (sti_ prefix). Code is
moved unchanged; every target that compiles the trace sources gets all
four, and the core isolation scan covers the new files.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Task 2.3: dispatch rows with limit charges listed separately and
resolved through the job's matched limits (raw-number fallback), pend
reason set deep-copied, 50 hosts in detail with the rest aggregated,
and RECONSTRUCTED records holding the dispatch outcome.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
test_tlog_format_shows_frozen_virtual_time_not_infotime asserted that
"1999" (info->time's year) appears nowhere in the formatted line, but
the line also carries getpid(), so the test failed whenever its PID
contained 1999. It now asserts the exact frozen timestamp field.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Task 2.2: each checked row carries name, flags, value type, total,
in-use, reserved, requested and met (same comparison as unsatisfy_());
limit rows resolve through the scope's matched limits and never count as
shortfalls; the cluster-wide check keeps every row, a host only unmet
rows, which set its shortfall/limit verdict.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Task 2.1: policy, queue and priority/queue-time ordering keys, each
matched cluster-wide limit as (name, scope), and per-code attempt
failure reasons with the hosts and resources they name, all copied into
the record arena.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Task 1.8: the core gains trace_ctl/trace_rec (NULL unless the sim REPL
sets them) and SCHED_TRACE evaluates its call only while a record is
being built.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Task 1.7: xce_decision_t gains a trace pointer (NULL from every existing
constructor) and XCE_DECISION_TRACE with make_trace_decision(); the live
driver skips trace-only decisions and frees any attached trace.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Task 1.6: the 27 tests that #include a hooked scheduler source now also
include sched_trace.c and sched_trace_capture.c.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
remove_workdir() now checks snprintf's result and skips a truncated path
instead of unlinking whatever it happens to name.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Task 1.5: per-requirement plan counts and search-end statements,
decision-wide counters exact past truncation, summary-level position
tallies (per verdict kind and per limit), merged rollback entries.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
xce_scheduler --sim started with no shared resource pool when the shared
values came only from the recording's SnapshotEntry (license value=(none)),
so jobs needing a shared resource pended instead of dispatching. Two
defects caused it:
- Load side (snapshot_load.c): a resval was treated as shared only when
rv->host == NULL. The capnp round trip (write_snapshot_entry ->
decode_SnapshotEntry) reads a NULL host back as "", so every shared
resval in a .replay file was skipped. A NULL or empty host now means
the shared pool; only a named host marks per-worker data.
- Save side (snapshot.c, snapshot_wire.c): core->sharedInst and each
worker's resvals were walked with i < .count. zarray_t.count is the
number of filled slots, not the highest idx + 1, and both arrays are
sparse by resource idx, so higher-index values were dropped from the
snapshot. Both loops are now bounded by .caps, as repl_info.c already is.
New test test_snapshot_sparse_resvals.c covers the in-memory save/load,
the empty-host load, and the real sched_record_start() -> .replay ->
sched_sim_driver_start() round trip.
Regenerated fixtures/repl_trace_baseline/set_output.replay: its mid-run
snapshot now carries license, limit=cluster_slots and each worker's
limit=host_slots, which the old writer dropped (all other fixtures
unchanged).
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Task 1.4: requirement path push/pop with balanced begin/end entries
carrying the full nesting path, one entry per traced event kind, and a
line budget that stops storing at the bound and counts omitted lines.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Task 1.3: trace types and constants, per-record arena, job selection
matching, no-decision record finishing; empty capture module; both
sources scanned by the core isolation test with a no-stdio check.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Task 1.2: translate_units_mode, repl_format_numeric_resource_value,
repl_format_consumable_value_and_used and repl_current_units_mode move
unchanged from repl_info.c and are declared in repl_internal.h so the
trace renderer can reuse them.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Task 1.1: scripted REPL session over a contention replay (license, cluster
and host limits, parallel and alternative jobs); transcript, recordings and
--sim-verify result committed as fixtures and compared byte for byte.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
- wal-layout-check.py: every WAL segment must hold one contiguous LSN run
starting at the LSN in its name (bug-1920 signature); the sequential,
chaotic and truncated-fence modes fail on a misfiled segment.
- --truncated-fence: breaks ctrl-1's WAL tail CRC so it boots
RECOVER_TRUNCATED, makes it win an election (promotion REFUSED), then
requires the fence to be healed and released after catch-up and the
node to lead with zero job loss (bug-1919 lifecycle, proven from logs).
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
The worker-rejoin-resync query sent when a worker with live jobs re-joins
had no handler in xce_test's worker context, so the controller resolved
every such round by its 15 s timeout, withholding dispatch meanwhile.
New fake_resync.{c,h} reassembles the paginated query and builds the
report like xcecd (queried jobs in order, running or unrecognized, then
unqueried running jobs); the handler sends it with a non-blocking request.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
A reconnect made from inside a task of the endpoint it re-establishes (a
request handler that failed over) waited out the full 2 s quiesce bound:
its own reference cannot drain, and the old connection's queued tasks are
serialised behind it -- and those then ran after the owner was re-armed,
reaching the new session.
Each VTASK_IO task now records the endpoint's reconnect_gen when queued and
vtask_entry drops a task whose generation is stale; the vtask manager
tracks the endpoint whose task the current thread runs
(vtask_current_io_ep), and xce_ctx_quiesce_ep skips the wait in that case.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Worker-context handlers (startjob, runtasks, jobcontrol) run as tasks of
the worker's own connection, so their synchronous notify RPCs waited for
a reply queued behind themselves, timed out (-110) and failed the client
over; the session never joined again, so the controller rejected every
later worker request ("is not a worker") and job usage stayed zero.
Handlers now queue the notification (new worker_notify.{c,h} FIFO) and a
one-shot delay-manager task sends it; housekeeping retries anything left.
A recorded worker join is repeated with the saved attributes once the
connection's reconnect_gen changes.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
The controller computed run usage (CPU time, memory, CPU peak and
efficiency, LSF bjobs -l definitions) but the capnp Job struct had no
field for it, so the job pushed to the apiserver never carried it, and
snapshots (the same struct) dropped it: a job restored from a checkpoint
lost its accumulated usage.
- controller.capnp: Job.runUsage @13 (JobRunusage); old entries decode
with no run usage.
- apiserver: map run_usage into JobInfo; max_mem, avg_mem, used_mem,
cpu_time, peak_cpu, peak_cpu_time, peak_cpu_duration, mem_efficiency,
avg_cpu_efficiency, peak_cpu_efficiency become queryable columns.
- xcecli: -o fields MAX_MEM, AVG_MEM, MEM_EFFICIENCY, CPU_PEAK,
CPU_PEAK_DURATION, CPU_EFFICIENCY, CPU_PEAK_EFFICIENCY (CPU_TIME now
renders too), and a MEMORY USAGE / CPU USAGE block in jobs list -l.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
The configAck byte-delivery barrier waited 500 ms, below scheduling
delay on an oversubscribed host, so a push to a healthy majority was
rejected with -110 while its already-appended marker still committed.
CONF_PUSH_TIMEOUT_MS is now 2000 ms, the wait holds a commit-wait
admission slot (new commit_blocking_admit/release; a full budget fails
fast with not-ready), and the timeout reply no longer claims the change
was not committed.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Work dispatched for the old connection (the io_worker's epoll batch,
queued VTASK_IO reply tasks) could still run while the reconnect tore
down and re-armed ctx->ep; a queued reply of the old connection then
reached the new session. The reconnect now unmonitors the old fd,
clears ep->owner (stale tasks are dropped) and waits for the endpoint's
references to drain, bounded at 2 s so a caller that is itself one of
those tasks cannot deadlock. vtask_entry reads ep->owner under ep->lock.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
