Adds Requirement 6 (Human-Readable Units for Byte-Valued Limit Amounts)
to the spec: requirements, design, research, and tasks 7-10.
Task 7 (Foundation): promotes the REPL's byte-unit scaling algorithm
and byte-valued-resource classifier into src/lib/utils.c/utils.h
(xce_format_bytes_human, xce_is_bytes_valued_resource), alongside a
new display-mode-aware composer (xce_format_units_value,
xce_units_mode_t) -- following the fmt_jobid()/fmt_jobid_ex()
precedent. repl_fmt.c's scheduler-only functions become one-line
delegating wrappers. repl_info.c's repl_format_numeric_resource_value()
(shared by info worker/info resource, not just the upcoming info
limit) is retyped to delegate to the new shared composer via a small
translate_units_mode() bridge, so every consumer benefits from one
implementation going forward.
No existing symbol's signature changed; only new symbols were added.
Confirmed behavior-preserving: full scheduler suite 85/85 unchanged,
including info worker/info resource's own regression tests. One
narrow, untested, out-of-requirement-scope corner case found and
documented (swp's RAW/BOTH mode rendering under the new single-value
composer interface) -- logged in tasks.md's Implementation Notes.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RLSNJhNoULvVcUhXEFafQC
The primary echoes its own last_known_elected_at_ms on every outgoing
heartbeat (threaded through xce_ha_heartbeat_req's existing scalar-arg
plumbing, alongside term/committed_lsn/committed_config_tag); a standby
processing a received heartbeat (ha_consume_heartbeat_committed, the sole
production call site) stores it unconditionally into its own
last_known_elected_at_ms, reconcile-free -- no other HA field moves.
ha_observe_heartbeat_committed itself is untouched; the new store sits
next to its call site, not inside it.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RLSNJhNoULvVcUhXEFafQC
A user-reported core dump showed xce_scheduler crashing with SIGSEGV in
its allocator thread: zarray_get_ex dereferencing a NULL array->data
inside match_job_host_limit_() (plugins/limit.c), reached via schedobj.c's
reset_sched_obj().
Root cause: zarray_fini() freed array->data and set it to NULL, but left
array->caps/count/pos at their stale pre-fini values instead of resetting
to the safe (0,0,0) state zarray_init() establishes. xlist_fini() had the
identical gap. Both structs' own bounds checks (`idx >= caps`) treat a
nonzero caps as a guarantee that data is a valid allocation -- a
guarantee broken for any caller that reuses the same struct after
_fini() without re-init.
schedobj.c's reset_sched_obj() does exactly that: it tears down a job's
own PERSISTENT schedobj (reused for the job's whole lifetime, not a
disposable scratch object) whenever the cluster's config version has
advanced, with no matching re-init. Once a host-limit match had grown
hlimits' capacity, and the config version bumped again while that job
sat PEND, the next allocation attempt for the same job dereferenced the
torn array -- exactly matching the reported backtrace. This same crash
class had already caused at least one earlier, never-successfully-root-
caused crash near the same call site (2026-08-17).
Fixed at the library-primitive level rather than reset_sched_obj()'s
call site: zarray_fini()/xlist_fini() now reset caps/count/pos to 0,
matching what _init() establishes. This makes every existing
_fini()-then-reuse caller correct by construction, with zero changes
needed at any call site. Audited every non-test zarray_fini()/
xlist_fini() call site first -- none relies on caps/count surviving
_fini(), so this is a pure safety improvement, not a behavior change.
RED confirmed by temporarily disabling both resets: new tests failed
cleanly ("Expected 0 Was 4" / "Expected 0 Was 2", the stale pre-fini
caps). GREEN confirmed restored: full lib suite 314/314, scheduler
suite 77/77, zero regressions.
bug-1817.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RLSNJhNoULvVcUhXEFafQC
pthread_cond_wait() reacquires its mutex before honoring a cancellation,
but mylock.c installed no cleanup handler to release it again -- a
thread cancelled mid-wait terminated holding the lock forever. vtaskmgr's
pthread_cancel()-based teardown could land there from three angles
(dispatcher cancelled while polling the shared queue, or a vcpu racing
back into it after its own shutdown signal), permanently deadlocking any
other thread that touched the same queue and hanging vtaskmgr_fini()'s
pthread_join() indefinitely.
Reproduced live as xce_test hanging on Ctrl-D exit once a connection
context was entered; gdb confirmed a vcpu thread blocked forever on a
mutex owned by an already-exited thread ID.
Fix: cbuf_put()/cbuf_get()/cbuf_timedget() now unlock via a
pthread_cleanup_push/pop handler around the wait, so a cancelled waiter
always releases the mutex. vcpu_idle()/vcpu_entry() also recognize the
teardown poison pill and exit immediately instead of needlessly
re-announcing into the already-dead shared queue.
New test_vtaskmgr_teardown.c reproduces the race deterministically
(self-pinned to one CPU, since true multi-core parallelism rarely hits
the window) and bounds vtaskmgr_fini() with a timed join so a
regression fails fast instead of hanging the suite. Logged as bug-1810.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RLSNJhNoULvVcUhXEFafQC
free_host_account() (src/lib/misc.c) freed acct->accounts[] and acct
itself but never acct->host, the strdup'd string make_host_account()
(xcealloc.c) allocates -- a real leak on every free_job_account() call,
including the live production dispatch path (scheduler.c, core_events.c),
not just test fixtures. Already root-caused and the exact fix specified
in bug-1621 (logged, never applied); applied here: FREEUP(acct->host)
before FREEUP(acct), mirroring free_res_account()'s existing
FREEUP(acct->resname) pattern.
Also closes bug-1723: test_xcealloc.c's two multi-host overflow
regression tests (added by bug-1722's fix) never freed their own
locally-built fixture trees. Added free_JobAlloc_ptr(&jalloc) to
test_make_job_account_multi_host_no_overflow() and
free_HostAlloc_list(2, hallocs) to
test_make_host_allocs_multi_host_no_overflow(), exactly as bug-1723's
own root-cause note specified.
Together these take xcelib_test from a deterministic 456-byte/29-
allocation LeakSanitizer SIGABRT (masking every other libxce test result
behind it) to 1/1 Ok. Full xce-build.sh all asan --incremental: 94/94 Ok,
zero regressions.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01GLfB5uWRdmx2WiZSFC7Fm7
While live-verifying gitea#46, found and fixed a cascade of 5 previously
undetected bugs that together made every usergroup-scoped limit in
limits.yaml silently non-functional:
- Named usergroups/hostgroups (users.yaml/hosts.yaml) were never
registered into the scheduler's group managers (groupmgr_add() had zero
production callers), so any limit referencing one by name could never
resolve real membership.
- An unconfigured limit scope (e.g. no "projects:") arrived as an
empty-but-present capnp group, not NULL, so build_consumer() built a
real empty group (matching no one) instead of falling back to "all".
- Three separate call sites conflated key_find()'s negative "not found"
return with a real error, short-circuiting before ever reaching the
"instantiate on first use" logic right below them -- the same defect
class already fixed once before in this codebase (bug-1495).
- Two call sites passed &(sched->core.resmgr) where a plain handle was
expected, one level of indirection too many, causing RTTI's key_find()
to reject it as an invalid handle.
All five are live-verified: fresh cluster deploys now correctly match and
instantiate usage tracking for all 7 limits in limits.yaml on every job
submission, reproduced across multiple independent from-scratch redeploys.
A 6th, architecturally distinct issue remains open (bug-1789, logged, not
fixed): sched_fill_limit_requests() computes a job's consumption of a
slots-scoped global limit by reading the wrong request vector, so the
numeric cap itself still never binds. This needs a design decision on
intended cross-scope semantics, not a mechanical fix, so it's left for a
follow-up.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Hb6Edtj4KbS8CrgEWYdA2E
Adds apply_job_task_count() to overwrite a standalone primary resreq's
minTasks/maxTasks with a job's real requested task count, no-op for
COMPOUND/ALTER nested primaries, with a defensive min>max clamp.
Closes the gap that lets scheduler-allocation's multi-host allocator
ever be reached (bug-1770). Wiring at live ingest call sites follows
in subsequent tasks.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01XYdtrEWWZfKRRGED7raEYg
Adds rusage_hash to xce_primary_resreq_t (computed once by
parse_resreq_primary() via a new hash_rusages() helper, hashing
rusage content rather than raw struct bytes since resname is a
non-interned strdup'd pointer), the xce_resreq_fingerprint_t value
type, and resreq_fp on xce_primary_schedobj_t, populated once at real
job-ingest time in core_build_primary_schedobj().
Task 1.2 (scheduler-allocation spec). Requirement 7.1.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01XYdtrEWWZfKRRGED7raEYg
An idle scheduler (nothing queued to publish) never noticed a dead
controller connection: sched_needs_rejoin was only ever set as a side
effect of an active client-library call, and an idle round makes none.
After any controller failover with nothing already in flight, jobs
submitted to the new primary stayed PEND indefinitely.
Adds xcecli_is_connection_broken() (libxce) -- a pure, socket-free read
of the transport's already-async-maintained dead/alive flag, set for
free by the existing RDHUP disconnect handler with zero application
calls. sched_check_pending_rejoin() now retries xcecli_join() on either
the existing reactive flag or this new passive signal, so a healthy
idle scheduler still makes zero extra network calls while a genuinely
dead connection self-heals within one ~1s round -- live-verified
against a 3-node HA cluster (rejoin fired ~300ms after new-primary
election with nothing submitted in between).
Also closes out bug-1735 (job memory/CPU usage reporting): confirmed
already fixed on this branch since 2026-08-30, just never marked in
the bug log.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01XYdtrEWWZfKRRGED7raEYg
Add xce_job_state_query_req()/xce_job_state_report_req() to request.c,
paginating job IDs / job-state entries across OPCode_jobStateQuery /
OPCode_jobStateReport messages via direct Request.body union arms
(mirroring xce_jobdispatch_req/xce_notify_req's direct-send shape, not
xce_push_data_req's XceData-table multiplexing -- these are dedicated
union arms, not multiplexed push/reply-get traffic). 8 round-trip tests
(normal/empty/multi-page for both query and report, covering all 4
JobStateStatus values and both queried states) all pass.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Y4M5MJM2zK6nU43da267Ku
vtask_enq() published a task onto the shared dispatch queue via
dataq_enq() before finishing its own initialization (task->owner) -- a
concurrent vcpu could dequeue, run, and free the task before the
producer's own write executed, an ASAN-confirmed UAF that crashed 2 of
3 controllers under a heavy burst-array-job HA workload. Moved
task->owner = vtaskmgr before the publish, mirroring the endpoint_ref-
before-publish discipline already established two lines above it
(bug-1298). Adds a stress-test regression guard (test_vtask_enq_race.c).
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_019QxaSzHRB7pmYFp4cVnwkA
Task 1.1: new deep-copy for xce_job_alloc_t composed from existing
make_alloc/make_host_alloc/make_job_alloc, explicitly preserving each
allocation's original from/duration rather than accepting make_alloc's
own time(NULL) stamp. TDD: 6 new unit tests (single-host, multi-host,
multi-resource-per-host, shared-resource-pool, independence-after-free,
from/duration fidelity), all passing under ASAN.
Also logs bug-1723 (pre-existing, unrelated leak in two bug-1722 test
fixtures, confirmed via git-stash A/B rebuild to be byte-for-byte
identical before and after this change) -- documentation only, not fixed
here.
Requirements: 1.1, 1.4
make_job_account() allocates account->accounts via calloc(1,
sizeof(xce_host_account_t*)) -- room for exactly 1 host pointer -- but
its own loop writes account->accounts[i] for i up to jalloc->nhosts-1,
overflowing the heap allocation for any job spanning more than one
host. Already reachable from live production dispatch (core_events.c,
schedobj.c, scheduler.c) for any multi-host job -- found while
verifying viability of a proposed scheduler snapshot-allocation-capture
fix, not from a user report.
Sibling function make_host_allocs() has the identical bug shape
(calloc(1, ...) vs a loop writing up to nhosts-1); every current call
site happens to pass nhosts=1 so it has never actually overflowed in
production, but it's the same live footgun in a public exported
helper. Fixed alongside since it's the identical bug class in the same
file.
New test_xcealloc.c drives a 2-host allocation through both functions,
reproducing the exact ASAN heap-buffer-overflow at xcealloc.c:188
pre-fix (RED), passing post-fix (GREEN). Both calloc(1, ...) sites
changed to size the allocation by the actual host count.
Full regression: libxce 303/303 (was 301, +2 new), scheduler 53/54 (1
pre-existing unrelated bug-1560 flake), controller 1211/1213 (2
pre-existing unrelated bug-1561 overlayfs flakes) -- zero new
failures.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01AgYRU3zDTqNGV5Jk8aiKLg
- src/schema/controller.capnp: JobSubmitData gains
fromHost @10: Text $C.mapname("from_host") -- auto-regenerates
controller.capnp.c/h via the existing meson capnpc-c custom_target.
- src/include/xce/types.h: job_submit_data_t gains char* from_host.
- src/lib/jobj.c: jobsub_init/jobsub_destroy (the hand-written,
ref-counted, content-deduped job-submit interning object -- not
auto-generated) thread from_host through the deep-copy, the dedup
identity comparison, and the destroy path.
Closes the wire-format half of the round-trip: from_host now survives
from the apiserver's submission all the way through the controller and
back on every subsequent job-state push, and rides along for free in
the existing WAL_JOB_SUBMIT persistence across a controller restart.
Did not need to touch job.c's build_job_submit_payloads() (bare
pointer borrow of the already-decoded submit struct) or any WAL
apply-path code (capnp_encode_job/decode_Job already generically
handle the whole xce_job_t including its full .submit sub-struct).
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01AgYRU3zDTqNGV5Jk8aiKLg
Adds xce_compose_version_ex() as a sibling of the existing, completely
untouched xce_compose_version(): when dirty_fingerprint is non-empty, it
strips a trailing -dirty from the commit field (anchored tail-slice
strcmp, not a substring search) and appends -<dirty_fingerprint> instead;
when empty/NULL, it delegates directly to the original function, so
output is structurally guaranteed byte-identical -- including the
Requirement 5.2 fallback case (dirty tree, fingerprint computation
failed) where commit_id's own pre-existing -dirty suffix already signals
"modified" with no new sentinel needed.
No main.c call sites touched -- consuming daemons (tasks 3.2/3.3) still
call the original xce_compose_version() and will switch to the new
function themselves.
Verified independently by review, full lib suite on both debug and ASAN
profiles: 301 tests, 0 failures, 0 ignored; suffix-anchoring, buffer
safety, and the empty-fingerprint delegation path all confirmed correct
by hand-tracing the implementation, not just trusting the test results.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Adds xce_version_field()/xce_compose_version() (utils.h/utils.c) to
compose a version string carrying commit id + build time, rendering
"unknown" for either field when its underlying meson-supplied define is
empty -- ready for controller/scheduler/worker to consume.
MK_VERSION/STR (the pre-existing, compile-time-only macro pair) can't
express this empty-to-"unknown" substitution at the preprocessor level,
so this is a runtime mechanism instead. Round 1 review REJECTED an
earlier version of this task for silently orphaning MK_VERSION/STR
(the task explicitly asked to "extend" them) and for leaving an
undocumented architectural trap: argp_program_version is a file-scope
const char* initialized at compile time, which cannot call a runtime
function -- consuming code must instead compute into a static buffer
inside main() and assign the pointer before argp_parse() runs. Round 2
adds an explicit SUPERSEDED doc comment on MK_VERSION/STR plus NOTE FOR
CALLERS guidance covering both points, and was APPROVED.
Also expands task 3.2's boundary to include controller/testsuite/test.c
(a third MK_VERSION/STR call site discovered during review) so no
caller of the superseded macro survives implementation.
5 new unit tests in test_utils.c (RED->GREEN, TDD).
Task 3.1/13 of build-time-versioning.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
makeGroup()'s existing-group update path (hit whenever a config-push
re-applies a group name that already has members, e.g. a retried config
push during controller failover) released xce_g_member_t.u.name via
FREEUP() (plain free()). u.name is allocated by makeString(), an
rtti-managed, refcounted pointer that is not a malloc()-base address --
freeing it directly corrupts the heap. group_killer() in the same file
already releases the identical field correctly via dereference().
Switch both FREEUP(m->u.name) call sites to dereference(m->u.name) to
match. Add a regression test that re-applies config for the same group
name twice, reproducing the exact ASAN bad-free at group.c:234 pre-fix.
This is the root cause of the reproducible xce_scheduler
"free(): invalid pointer" SIGABRT crashes seen during 3-attempt
controller-failover config-push retries (8 confirmed core dumps).
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
xcecli_jobsubmit() could return rc>=0 (success) while leaving its *jobid
output parameter at 0, reproducible under concurrent client load
immediately after a fresh single-node election (~1-3/9 clients per round
in the original repro).
Root cause: XCECLI_FAILOVER_CALL's idempotent-replay rule
(client_failover.c's xce_failover_classify) normalizes a retried resend
that hits the server's EEXIST/inflight-collision rejection into overall
success -- but that rejection reply carries no payload
(handle_jobsubmit's EEXIST branches reply with RequestReply_data_nodata,
job.c), so xce_jobsubmit() never populates *jobid on the winning
attempt, nor did it on the earlier failing attempt (raw status was
already negative).
Adds jobsubmit_finalize_jobid() (client_internal.h/client.c), called
from xcecli_jobsubmit() right after XCECLI_FAILOVER_CALL returns. Sets
*jobid = submit->jobid (the client-generated id already on the wire --
the controller commits/echoes this exact value on every genuine success
reply, bug-786/job.c:1439) whenever the overall call succeeded,
otherwise leaves it untouched. Placed at the jobsubmit-specific wrapper
layer, not the generic classify/decide layer, which stays fully generic.
3 new socket-free unit tests in test_libxce_retry.c (following this
codebase's direct-state-simulation style for I/O-adjacent logic).
Live-validated: full ASAN rebuild clean, libxce test suite 1/1 OK with
all 3 new tests passing, and a 5-round/45-client concurrent-submit
repro against a live single-node cluster showed 0 "no clean ack"
failures (vs. 1-3/9 per round pre-fix).
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
XCECLI_FF_CALL (backing xcecli_heartbeat) can silently rotate+reconnect
the transport entirely inside a single call and still return success, so
heartbeat.go's failure-to-success transition detector could never observe
a reconnect that completes within one heartbeat tick -- the common case,
since elections finish in single-digit seconds against a default 30s
interval. apiserver's application-level rejoin never fired on a real
idle-period failover, and job pushes silently stopped reaching it.
Adds a monotonic reconnect_gen counter to endpoint_t (netio.h), bumped by
xce_ctx_reconnect() (xcectx.c) on every successful reconnect regardless of
trigger path. heartbeat.go now compares this generation every tick instead
of tracking success/failure transitions. Re-validated live against task
5.2's exact scenario (apiserver alone, zero write traffic): rejoin fired
22s after a primary kill, 12s after election.
Reopens and closes out component-failover-adoption's own NO-GO -> GO
validation cycle from 2026-08-15.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
xce_cluster_config_to_client_config() converts a validated candidate
list into a fully-populated xce_client_config_t, copying candidates
in order with no special-casing for a single candidate. The
truncate-with-warning safety net stays in place as a defensive guard
now that N_MAX_MASTERS and MAX_HA_CANDIDATES match.
Also removes a WARN check in xce_cluster_config_validate() that
became unreachable dead code once task 1.1 reconciled the two
candidate-count constants (both checks tested the same field against
the same constant with no mutation between them).
Task 1.2 of component-failover-adoption (Requirement 1 AC1-AC7).
N_MAX_MASTERS (client.h) now derives from config.h's MAX_HA_CANDIDATES
instead of an independently-maintained literal (3 vs 4 previously).
Fixes worker's and scheduler's hardcoded `> 3` startup checks to
reference the constant symbolically, and updates the client-retry
test fixture so it doesn't exercise an uninitialized 4th slot.
Task 1.1 of component-failover-adoption (Requirement 1 AC7).
controller.capnp declared `struct Data $C.mapname("xce_data_t")` (an
OPCode_get query-result tagged union) at file scope, which shadows
Cap'n Proto's builtin Data blob type for every later `: Data` field in
the same file. This silently miscompiled 7 fields across 6 structs as
a struct-pointer type instead of a raw byte blob: UpgradeConfigRequest
.sha256/.bytes, ReplConfigReply.sha256/.bytes, ReplConfigPushRequest
.sha256/.bytes, ReplEnvelope.payload, SnapshotTransfer's chunk
payload, WalCatchupEntry.payload/.batchPayloads, and CtrlHelloRequest
.key. Production C code had already routed around it for years via
hand-rolled raw capn_ptr manipulation (see request.c's own comments);
nothing before now needed the generated codec/accessors to actually
work for these fields.
Renamed the local struct to XceData (capnp-level name only; the
$C.mapname("xce_data_t") C typedef is unchanged) and explicitly
repointed getdata/pushmsg at XceData by name, since those two fields
correctly want the local tagged union. Updated every derived
generated-identifier reference across 19 hand-written files spanning
controller, lib, scheduler, and the Go apiserver/xcecli CGo bindings.
Fixed 5 call sites in lib/request.c that had been typed against the
old workaround alias but now legitimately receive the correct
capn_data type (a pure type-name swap -- Data_ptr/XceData_ptr and
capn_data share the identical {capn_ptr p} layout).
Verified via full rebuild+test: lib (1/1), controller (3/3, incl. the
job-array push regression tests), scheduler (15/15), Go apiserver +
xcecli (all packages green), and a direct pycapnp round-trip proving
UpgradeConfigRequest.sha256/.bytes now encode/decode correctly.
Bug: bug-1461 (.wolf/buglog.json). Unblocks admin-config-tool task 3.3.
bug-1453: remove unused client-side CA-certificate plumbing. C-side:
drop ca_cert_path from xce_cluster_config_t, do_connect()'s ca_cert
param, --ca-cert flags on worker/scheduler, and controller's cert
population (TLS is server-side only, SSL_VERIFY_NONE everywhere on
the client side already, verified zero SSL_CTX_load_verify_locations
calls in the C tree). Go-side: delete xcecli's self-signed cert
TOFU-pinning flow (cmd/auth/cert/*), CACert field, SetRootCAs/
loadRootCAs, and every call site.
bug-1454: fix xcecli_ctx_t leak in scheduler.c sched_init() — the
unconditional initial ctx_init was never freed before the HA
candidate loop re-initialized it on the first iteration.
bug-1455: sched_init()'s memset(sched, 0, ...) was silently wiping
sched->cluster_cfg that main.c had populated from --peers just before
calling sched_init(), so --peers was always ignored and the scheduler
fell back to the hardcoded localhost:9990 single-host default.
Restructured sched_init() to take cluster_cfg as an explicit parameter
(assigned after the memset) instead of relying on caller-side
ordering with a separate sched_set_cluster_cfg() setter, which is now
removed.
bug-1456: revert an unsafe stack-local xce_client_config_t introduced
while fixing bug-1455 — xcecli_ctx_init() stores that pointer as
ctx->conf and client_failover.c dereferences it for the ctx's entire
life (runtime reconnect), so a per-loop-iteration stack copy would
dangle the moment sched_init() returned. Back to mutating the
caller-owned, process-lifetime config in place.
Verified: full ASAN build (all components), meson test suite 9/9 OK,
manual scheduler testsuite 15/15, Go build/vet/test all pass.
Raft-drive-async's reconnect-offload burst (Task 2.1/2.2) exposed a
latent race in io_worker's epoll dispatch loop: ha.c's
on_standby_connected() evicts a stale duplicate peer channel via
iomgr_unmonitor()+endpoint_unref(), but epoll_ctl(DEL) only stops
FUTURE epoll_wait() calls -- it does not invalidate an event for that
same endpoint already sitting in the CURRENT batch's events[] array.
A later event in the same batch then dereferences the freed
endpoint_t/SSL*, producing the ASAN SEGV observed deep inside
OpenSSL's ssl3_read_bytes during raft-drive-async's round-9 soak.
The original "concurrent SSL_do_handshake from two io_worker threads"
hypothesis was wrong and is retracted -- iomgr_start() creates exactly
one io_worker thread per iomgr_t.
Fix: extract io_worker_dispatch_batch(), which takes endpoint_ref() on
every endpoint in the batch before dispatching any of them and
endpoint_unref()s each only after the whole batch completes -- the
same lock-free ref/unref bracket already used for bug-1298 and
INVOKE_MSG_HANDLER, just never applied to io_worker's own loop. Pure
atomics, no locks, no blocking added to the hot path.
Adds test_netio_batch_dispatch_uaf.c, which drives the real dispatch
loop with a synthetic epoll_event[] batch (TDD RED confirmed via ASAN
heap-use-after-free before the fix, GREEN after). Verified further
with two independent clean 10-round live sequential HA soaks (33 and
36 jobs, zero loss) and full ASAN suite runs (xcelib_test 294/0,
controller_unit_test 972/0). raft-drive-async's kiro-validate-impl
re-run flips NO-GO to GO.
restore_job_array()'s bulk-insert pass could fail partway through
(key_add() on realloc growth exhaustion), leaving an already-inserted
prefix permanently visible in c->jobmgr but excluded from
out_new_jobs -- so those elements existed and were individually
addressable but never reached HOOK_DETAIL_JOB_NEW, never scheduled or
pushed, not on this attempt or any later successful retry. A literal
violation of Requirements 2.3 and 9.4, tracked as bug-1443.
Adds kvmgr_reserve()/xzarray_reserve(), new purely-additive primitives
in shared kvmgr.c/zarray.c (following the existing kvmgr_capture_keys()
template -- bare extern function, no RTTI vtable slot, caller-holds-
write-lock contract), that pre-grow c->jobmgr's backing store before
the bulk-insert pass begins, closing the dominant N-scaling failure
trigger structurally.
Found a genuine off-by-one in the existing, unmodified
xzarray_ensure_items(): its strict less-than sufficiency check means
reserving exactly array_size and then performing array_size real
stores still triggers one more growth cycle on the last store.
Reserving array_size + 1 is the exact minimal correct compensation,
independently re-derived and confirmed by review with concrete
arithmetic.
For the now-much-narrower residual case (kvtab_add()'s own small
per-entry allocation, or a content collision -- both non-N-scaling,
honestly documented as still theoretically possible): restore_job_array()
now populates out_new_jobs with whatever prefix was genuinely inserted
before a failure, and apply_committed_entry() fires HOOK_DETAIL_JOB_NEW
for that non-empty partial prefix even when the overall return is
negative, while still propagating the negative rc so the LSN correctly
halts and the Live Apply Resource Fence still engages for the
remainder. A genuinely-inserted element is never left un-pushed again.
Task 7.1 of job-array-single-wal-record (Requirements 2.3, 9.4, 9.6).
extract_data() (src/lib/request.c), the shared reassembly step every
inbound push passes through inside vtask_entry() before any receiver's
handler runs, had no case for Data_data_jobArray -- it hit
default: rc=-EINVAL. Because vtask_entry()'s callnext check treats any
nonzero return (including a negative errno) as "reassembly complete,
proceed," this never surfaced as an error: the real payload was freed
and the receiver silently handed an empty, zeroed dataset_t, with no
log anywhere in the chain. Tasks 5.1-5.3 were each individually
correct and tested in isolation, but the feature was dead on the real
wire end-to-end.
Adds case Data_data_jobArray: passing the single, unchunked
descriptor straight through (no pagination needed, unlike the
existing LIST-shaped cases) and nulls the source pointer after
transfer -- verified this is not cosmetic, since free_Request()'s
pushmsg case would otherwise double-free it via free_Data()'s live
Data_data_jobArray branch.
Proven with a real xce_encode()/xce_decode() round-trip through the
fixed extract_data() -> sched_handle_dataset() -> sched_on_job_array()
(task 5.3, unmodified) chain, not just a unit-level check on
extract_data() alone. Also confirms task 5.4's future API-server
receive path shares this exact fix, since both go through the same
xcecli_ctx_init() -> vtask_entry() -> extract_data() pipeline.
One self-flagged, non-blocking residual gap (pre-existing since task
5.3, out of this task's request.c-only boundary): dataset->rows for
the jobArray case is never deep-freed downstream, leaking one bounded
xce_job_submit_t per successfully-delivered array push commit.
Task 5.3b of job-array-single-wal-record (Requirements 6.1, 6.2, 6.4, 8.4).
Inserted mid-run after independent review confirmed the gap; user
confirmed sequencing (fix now, before task 5.4).
- job_init() now checks makeJobsub()/makeString(ckptinfo) return
values and propagates failure instead of storing NULL with a
success return (Req 10.1).
- Root-caused the previously observed makeJobsub() NULL-with-EINVAL
failure to a test-binary-only hazard: multiple controller test
files each called job_obj_init() from their own setUp() with no
cross-file coordination, re-running jobsub_table_init() against an
already-live lock/table. Fixed via atomic_flag-guarded idempotent
job_obj_init()/job_obj_fini(), plus a distinct -ENODEV return from
makeJobsub()/makeJobstartinfo() when the table isn't ready
(previously fell through to undefined behavior) (Req 10.2).
- Verified (test) MOVE_PTR fields are always NULL on a freshly-built
submission payload -- no code change needed (Req 10.3).
- Fixed job_destroy()'s accounts leak via the existing
free_job_account() helper, replacing the stale FIXME (Req 10.4).
- Verified (inspection + test) struct Job's capnp schema has no
ckptinfo field, so decode_Job/free_Job have nothing to leak there
-- no code change needed (Req 10.5).
Independently re-verified: reviewer reproduced a pre-existing,
unrelated rtti-library leak-on-init-failure against a stashed
pre-task copy of jobj.c to confirm it predates this change.
Task 1.3 of job-array-single-wal-record.
Replace the deliberate election-carrier leak with an atomic refcount:
a bias reference held by ha->elect_ctx plus one reference per captured
vote endpoint, released via a new endpoint_t.on_fini teardown-completion
hook (fired once, before ep->data is freed). Both real-election and
PreVote capture sites (raft_cb_send_vote_request,
raft_cb_send_pre_vote_request) increment on capture; both publish sites
(ha_start_election_async, ha_start_prevote_async) now atomic_exchange
the outgoing carrier and release it instead of leaking or freeing
outright, so a still-outstanding vote endpoint keeps the superseded
carrier alive until its own teardown completes.
Verified: 758+ controller tests green, isolated LeakSanitizer run shows
zero ha_elect_ctx_t leaks across many election/PreVote rounds, no
premature-free/UAF under supersession, and a live 10-round HA soak
(36 jobs, zero loss, all 3 nodes served as primary).
Found via extended chaotic /xce-test-ha soaking on top of the bug-1419 fix
(same session). Both bugs independently caused the 10-round chaotic soak to
fail; sequential and chaotic now pass cleanly and repeatably.
1. Term-desync liveness deadlock (new): a standby that loses a near-
simultaneous election race to a peer can legitimately end up at a HIGHER
term than the peer that actually won and became primary. The primary's
now-stale-term AppendEntries/heartbeats are correctly rejected by the raft
library, but every one of those rejected messages was ALSO resetting the
standby's own liveness deadline (ha_on_heartbeat_received), so its
liveness timeout never fired and it could never start a fresh,
higher-term election to let the cluster self-heal — a permanent stall.
Fix: ha_msg_term_is_stale() gates the liveness reset (and
ha_discover_primary step-down) on the incoming message's own term stamp,
skipping it for provably-stale messages, in cluster.c's wal_catchup_entry
and nop/heartbeat handlers.
2. bug-847 (root-caused 2026-06-30, never fixed): a per-sub-entry `payload`
Data blob in a multi-entry WAL catch-up batch loses its capnp pointer once
the message crosses a segment boundary — the receiver decodes
raw_payload_len=0 for entries at/after the boundary and silently persists
empty WAL entries (structurally intact: correct LSN/term/CRC chain, empty
content). Only surfaces when a node rejoins and catches up a real batch,
which is why it needed a live chaotic soak (not the 2-entry unit test) to
reproduce. Fix: carry every sub-entry's payload concatenated in ONE
top-level batchPayloads blob instead of one Data blob per entry — a
single top-level blob does not exhibit the cross-segment loss. Sliced
back apart on decode using each sub-entry's own wirePayloadLen, a plain
scalar that (like lsn/entryType/term) decodes via the generic generated
decode path and was never subject to the bug. Confirmed via targeted
diagnostic logging that the corrupted entry arrives already-empty over
the wire (not a receive-side race), and via a faithful reproduction at
live JOB_SUBMIT payload size (5×3560B) after the original 2-entry/
14×872B tests turned out not to cross a segment boundary in this
environment.
Incidental fixes found and fixed along the way:
- A real self-deadlock (persist_entry_term() re-acquiring p->lock from
inside a caller that already held it) introduced by an initial, ultimately
unnecessary WAL-read locking fix attempted before bug-847 was pinned down;
fixed via a new persist_entry_term_locked() lock-free counterpart. Left in
place as a genuine (if incidental) hardening of ha_stream_wal_to_standby's
read consistency.
- .claude/skills/xce-test-ha/SKILL.md's `context: fork` frontmatter caused
the skill's own forked sub-session teardown to SIGHUP the whole
xce_controller process group mid-soak, killing all 3 nodes silently with
no error logged, whenever the soak was launched via the Skill tool itself
(setsid/nohup inside run-ha-soak.sh only protects against a controlling
terminal's own SIGHUP, not a parent forked-session's teardown). Removed;
added explicit guidance to launch long soaks via direct Bash from the main
session instead.
Verified: full 78-group unit regression sweep clean (0 failures) after each
change; two consecutive clean 10-round chaotic soaks and one clean 10-round
sequential soak on the final binary (zero committed divergence, zero job
loss, all 3 nodes led in both modes).
Extend raft_sim.c's deterministic TLA+-conformance harness with two
fault-injectable checks: no reaction before commit, and idempotent
re-apply of an already-committed entry. Wired as dedicated tests only,
not into raft_sim_check_all's fixed four-invariant contract (owned by
a separate spec). RED/GREEN independently verified by adversarial
review; zero regression to existing scenario functions.
bug-847 (catch-up WAL batch drops payloads across capnp segment boundaries):
its purpose-built RED reproducer, test_wal_batch_roundtrip_large_payloads
(14 entries x 872-byte payloads, 12.2KB total, genuinely spans multiple
4096-byte capnp segments per capn-malloc.c's create()), was still
TEST_IGNORE_MESSAGE'd. Un-ignoring it and running under ASAN with leak
detection: clean pass, byte-exact payloads, zero leaks, 2/2 runs. Traced the
vendored c-capnproto far-pointer machinery (write_ptr/capn_setp in capn.c)
to confirm the cross-segment struct->Data reference path is correct by
construction — whatever regressed this already got fixed elsewhere (library
bump or an incidental request.c change); the ignore was just never removed.
No production code changed.
bug-1307 (task-5.7 election-jitter data-safety regression: 7 divergences +
4 job losses over 6 chaotic rounds): re-ran the exact reproducing scenario
(6-round chaotic soak, real ext4, ASAN binaries) — 21 jobs, 0 divergence,
0 job loss, clean PASS. Confirms the raft-ha-core-safety Phase 5 work
resolved it.
Both bugs were the last 2 of the 7 flagged in the prior staleness sweep;
all 7 are now closed (6 were already fixed and undetected, 1 needed the
test un-ignored).
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01SDWVNQLKxqTVHh42cH7rV3
bug-1401: xce_free_ctrlstatus(s) was defined as free_CtrlStatus(s), which
only frees the fields inside xce_ctrlstatus_t. The real client reply path
(decode_CtrlStatus_ptr) calloc's the struct itself, so every ctrlstatus call
leaked sizeof(xce_ctrlstatus_t) (120 bytes). Existing unit tests never caught
it because they built/freed the struct via the raw stack-decode + bare
free_CtrlStatus() helpers, never exercising the actual client macro. Fixed
by switching the macro to free_CtrlStatus_ptr(&(s)) and added a regression
test that exercises the real heap-decode path; RED confirmed the exact
120-byte/1-alloc LeakSanitizer signature before the fix.
bug-1400: the originally reported SEGV in cmd_jobsub on malformed positional
input is stale — NULLSTR guards added 2025-11-05 already reject it cleanly.
The real residual defect was submit.start_info leaking on all 4 early-return
validation paths; fixed by routing them through a shared `goto cleanup`
(matches the existing goto-clean idiom in queue_ctrl).
bug-1396 (job-count anomaly after cold-restart-all, not yet root-caused):
instrumented test-commit-durability.sh's assert_job_count() to dump the live
joblist and ACKED_FILE ledger on any count mismatch instead of only the
count, per the bug's own recorded next step.
Verified: controller ASAN build + full controller_unit_test green; lib
xcelib_test 285/285 green, 0 ASAN leaks.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01SDWVNQLKxqTVHh42cH7rV3
ha_send_snapshot_to_standby ignored the network send's return value in its
chunk loop, silently truncating a transfer on a mid-stream error while still
logging "complete" (bug-1386). Fixing the silent drop exposed a second,
independent bug in the same pipeline: ha_handle_snapshot_chunk appended
received chunks in arrival order instead of at their wire-carried
chunk_offset, so out-of-order delivery across the vtask pool corrupted the
reassembled file even though every chunk's bytes were individually correct
(bug-1389). Fixed by checking every fallible call in the send loop and
switching the receiver to pwrite-at-offset with a count-based completion
tracker.
Adds snapverify/snapdiff xce_test commands (offline checkpoint-file
structural validator and byte-level comparator) used to diagnose bug-1389 and
kept as standing diagnostic tools for future snapshot-transfer triage.
g_drive_async_configpush_offload flipped back ON after both fixes, validated
via 6-round chaotic + 3/3 force-snapshot soak (raft-drive-async task 3.3).
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01SDWVNQLKxqTVHh42cH7rV3
vtaskmgr gains vtask_class_t (LIVENESS/LIVE_BLOCK/REQ_BLOCK) + a pool-level
blocking reservation: REQ_BLOCK fast-rejects -XCE_ERR_NOT_READY past
n_vcpus-R; LIVENESS never gated (deadlock-freedom). commit_submit folds its
inflight_waits onto the pool via commit_set_pool; production wired in
cluster.c phase2 (vtaskmgr_set_liveness_reserved(R) + commit_set_pool).
Lock order p->lock->ce->lock->blk_lock. Dormant until 3.1. Commit suites
38/30/22/38 green; lib 282/0, controller 196/0, ASAN clean. Phase 1 done.
socket_connect sets O_NONBLOCK before connect and bounds the attempt with
poll(timeout); new connect_timeout_ms param (0=DEFAULT_CONNECT_TIMEOUT_MS);
all 5 callers updated (ha.c x3, client.c, xcectx.c). Revalidation Trigger:
shared netio helper signature changed. Broad build links all components;
xcelib_test 278/0, controller_unit_test 194/0. 1.4/1.5 unit tests satisfied
by the TDD output of 1.2/1.3 (test_slowlane.c, test_netio_bounded_connect.c).
- sim_tla_action_name: drop brittle per-case 'raft.tla:NNN' line-number comments
(some had drifted a few lines off; the return string IS the stable raft.tla
Next-disjunct name, and the function header already cites raft.tla:454).
- test_sim_5_1_partition_heal: the per-follower convergence loop was vacuous —
it bounded by commit_index, which stays 0 for followers under the leader-only
commit model, so the loop never ran. Bound by log_count instead (followers DO
advance the replicated log); Log Matching still guarantees the shared-prefix
terms agree. Now non-vacuous; still passes.
Test/comment-only; no behavior change. Lib suite Ok:1 Fail:0.
Adds raft_sim_scenario_figure8: a previous-term entry on a quorum under a
new-term leader is NOT committed until a current-term entry commits (library-
gated by raft_advance_commit; verified by a mutation test). Also restores the
raft_sim_scenario_drop_dup_reorder implementation that commit e445404 (task 5.3)
silently dropped from raft_sim.c (a stray git checkout reverted the uncommitted
impl), which had left the lib build broken with an undefined reference.
Build green: test_sim_5_3_drop_dup_reorder + test_sim_5_4_figure8 both PASS.
raft_on_vote_reply double-counted duplicated vote-responses (counter ignored
from_idx) and failed to drop stale-term replies, allowing two leaders at the
same term (bug-851 split-brain family). Mirror the existing pre-vote per-peer
dedup pattern (new vote_replies[] set) and add DropStaleResponse (term <
currentTerm). Surfaced by the raft-sim-conformance oracle (task 4.2).
47 raft / 264 overall lib tests pass.
