Three bugs found while diagnosing a live controller log, all in the worker resource-value path: 1. Every host relying on the documented hosts.yaml auto-detect default (no max_slot, meaning "use CPU count") got 0 scheduling slots, permanently blocking the scheduler from placing jobs on it. mxj is UInt32 on the wire and can't carry the schema's -1 sentinel; mapping.py worked around this by leaving it unset, which defaults to 0 -- and 0 is never < 0, so apply_join_state()'s auto-detect fallback never fired. Fixed by encoding the sentinel as 0xFFFFFFFF, which the controller's `int mxj` field reinterprets back to -1 via its existing implicit uint32_t->int conversion. No C-side or wire schema change needed for this part; the fallback itself was already correct but had zero test coverage for a negative mxj, now added. 2. update_resvals()/update_resval_list() logged the failure reason via PERROR, which reads process-global errno -- but update_resval()'s failure paths return raw negative codes directly and never touch errno, so the controller log filled with misleading "update_resval: Success" / "update_resval: Resource temporarily unavailable" lines instead of the real reason. Fixed to decode the actual rc via xce_strerror_r and name the failing resource. 3. maxmem is canonically stored/wired as raw bytes but had no unit metadata, so resval/workerlist printed it as a bare number that read as garbage (e.g. workerlist's fixed-width columns visually smeared a multi-GB byte count across the MaxCPU/MaxMem headers). Added an optional `unit` field to the Resource/ResourceVal capnp structs (and xce_resource_t/xce_resval_t/resources.yaml) so resval and workerlist can render a human-readable value (e.g. "30.90 GB") while the stored value stays raw bytes -- display-only, every other resource unaffected. Regenerated the xceadmin golden fixture (fixtures/full/expected.bin) twice: once for the mxj sentinel encoding change, once for the new Resource.unit field growing every resource's wire size by one pointer slot. Both diffs verified byte-for-byte isolated to exactly the expected change before regenerating. Verified: 1095/1095 controller_unit_test (stable across repeated runs), 229/229 xceadmin pytest, clean rebuild of lib/controller/xceadmin/xce_test. Two related findings logged to .wolf/buglog.json but deliberately not fixed here (out of scope per discussion): a pre-existing flaky segfault in the combined controller_unit_test binary, and maxswap/maxtmp being hardcoded stub values on the worker side. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
153 lines
3.3 KiB
C
153 lines
3.3 KiB
C
#include <errno.h>
|
|
#include <rtti.h>
|
|
#include <stdarg.h>
|
|
#include <stdatomic.h>
|
|
#include <stdlib.h>
|
|
#include <string.h>
|
|
|
|
#include "mylock.h"
|
|
#include "resobj.h"
|
|
#include "utils.h"
|
|
#include "xstring.h"
|
|
|
|
typedef struct {
|
|
atomic_ulong refcount;
|
|
} resobj_private_t;
|
|
|
|
static size_t resobj_datasize(va_list ap)
|
|
{
|
|
size_t sz = sizeof(xce_resource_t);
|
|
|
|
return sz;
|
|
}
|
|
|
|
static int resobj_init(meta_obj_t* obj, va_list ap)
|
|
{
|
|
xce_resource_t* dst = RTTI_OBJ_TO_DATA(xce_resource_t, obj);
|
|
resobj_private_t* priv = (resobj_private_t*)RTTI_OBJ_TO_PRIV(obj);
|
|
xce_resource_t* src = va_arg(ap, xce_resource_t*);
|
|
|
|
if (src == NULL) {
|
|
return -EINVAL;
|
|
}
|
|
|
|
memcpy(dst, src, sizeof(*dst));
|
|
|
|
dst->name = makeString(src->name);
|
|
dst->desc = makeString(src->desc);
|
|
dst->unit = makeString(src->unit);
|
|
|
|
#if 0
|
|
if (src->distributions != NULL) {
|
|
MOVE_PTR(dst->distributions, src->distributions);
|
|
}
|
|
#else
|
|
/* FIXME: */
|
|
dst->distributions = NULL;
|
|
#endif
|
|
|
|
#if 0
|
|
MOVE_PTR(dst->hbased_defined, src->hbased_defined);
|
|
#else
|
|
/* FIXME: */
|
|
dst->hbased_defined = NULL;
|
|
#endif
|
|
|
|
priv->refcount = 1;
|
|
|
|
return 1;
|
|
}
|
|
|
|
static void resobj_destroy(meta_obj_t* obj)
|
|
{
|
|
xce_resource_t* r = RTTI_OBJ_TO_DATA(xce_resource_t, obj);
|
|
resobj_private_t* priv = (resobj_private_t*)RTTI_OBJ_TO_PRIV(obj);
|
|
|
|
dereference(r->name);
|
|
dereference(r->desc);
|
|
dereference(r->unit);
|
|
|
|
memset(priv, 0x0, sizeof(*priv));
|
|
|
|
return;
|
|
}
|
|
|
|
static int resobj_reference(meta_obj_t* obj)
|
|
{
|
|
resobj_private_t* priv = (resobj_private_t*)RTTI_OBJ_TO_PRIV(obj);
|
|
|
|
atomic_fetch_add(&(priv->refcount), 1);
|
|
|
|
return 1;
|
|
}
|
|
|
|
static void resobj_dereference(meta_obj_t* obj)
|
|
{
|
|
resobj_private_t* priv = (resobj_private_t*)RTTI_OBJ_TO_PRIV(obj);
|
|
xce_resource_t* w = RTTI_OBJ_TO_DATA(xce_resource_t, obj);
|
|
uint64_t count = 0;
|
|
|
|
count = atomic_fetch_sub(&(priv->refcount), 1);
|
|
|
|
if (count == 1) {
|
|
destroy_(w, (obj_destroy_fn_t)resobj_destroy);
|
|
}
|
|
|
|
return;
|
|
}
|
|
|
|
static typeinfo_t resobj_type
|
|
= { .name = "xce resobj",
|
|
.privateSize = sizeof(resobj_private_t),
|
|
.dataSize = (datasize_fn_t)resobj_datasize,
|
|
.init = (obj_init_fn_t)resobj_init,
|
|
.destroy = NULL,
|
|
.interfaces
|
|
= { .reference = &(intf_reference_t) {
|
|
.reference = (reference_fn_t)resobj_reference,
|
|
.dereference = (dereference_fn_t)resobj_dereference } } };
|
|
|
|
static xce_resource_t* makeResource_(var resmgr, xce_resource_t* r)
|
|
{
|
|
xce_resource_t* resobj = NULL;
|
|
int rc;
|
|
|
|
rc = key_find(resmgr, (void*)r->name, (void**)&resobj);
|
|
|
|
if ((rc < 0) && (rc != -ENOENT)) {
|
|
errno = -rc;
|
|
|
|
return NULL;
|
|
}
|
|
|
|
if (rc > 0) {
|
|
errno = EEXIST;
|
|
return NULL;
|
|
}
|
|
|
|
resobj = makeInstance(&resobj_type, r);
|
|
if (resobj != NULL) {
|
|
rc = key_add(resmgr, (void*)resobj->name, (void*)resobj);
|
|
|
|
if (rc < 0) {
|
|
destroy(resobj);
|
|
|
|
errno = -rc;
|
|
return NULL;
|
|
}
|
|
|
|
resobj->idx = rc;
|
|
}
|
|
return resobj;
|
|
}
|
|
|
|
xce_resource_t* makeResource(var resmgr, xce_resource_t* r)
|
|
{
|
|
xce_resource_t* r1 = NULL;
|
|
|
|
lock(resmgr, RTTI_LOCK_WRITE);
|
|
r1 = makeResource_(resmgr, r);
|
|
unlock(resmgr);
|
|
|
|
return r1;
|
|
}
|