lei.chen/myxce
1
0
Fork 1
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

fix(frontend): count host job-state columns and EXEC_HOST by real slots

Browse source 
NJOBS/RUN/SSUSP/USUSP (xcecli hosts list -l) and EXEC_HOST (xcecli jobs
list) always showed a hardcoded 1 slot per host regardless of a job's
actual per-host allocation -- rawJobToModel()'s ExecHosts JSONB builder
never read the real per-host "slots" resource from the C job allocation,
so the already-correct downstream slot-counting logic (computeHostSlotUsage,
bug-1743) and EXEC_HOST's "N*host" formatter never had real data to work
with. convert.go now extracts each host's real slots allocation via a new
CGO indexing helper, mirroring the scheduler's own get_nslots_in_alloc()
convention.

Also wires hosts list -l's "CURRENT LOAD USED FOR SCHEDULING" table (tmp/
swap/mem/slots and friends) to the host's real live resource values --
previously entirely hardcoded placeholder strings, never connected to any
backend data.
This commit is contained in:
Rongsong Shen 2026-09-07 07:32:00 +00:00
parent f55b49f1a7
commit e395eaa3ad
No known key found for this signature in database
GPG key ID: 5BCDAAE0123E9FE2
5 changed files with 223 additions and 28 deletions
Download patch file Download diff file Expand all files Collapse all files

23
src/frontend/apiserver/backend/convert.go
View file

@ -9,6 +9,10 @@ package backend
// Helper to index into xce_host_alloc_t** (CGO cannot dereference C pointer-to-pointer arrays).
static xce_host_alloc_t *job_alloc_host(xce_job_alloc_t *a, int i) { return a->allocs[i]; }
// Helper to index into xce_alloc_t** (same CGO limitation as above) -- one
// host's per-resource allocation list, scanned for the "slots" entry.
static xce_alloc_t *host_alloc_res(xce_host_alloc_t *h, int i) { return h->allocs[i]; }
*/
import "C"
@ -114,9 +118,24 @@ func cJobToModel(job *C.xce_job_t) *models.JobInfo {
n := int(job.allocs.nhosts)
for i := 0; i < n; i++ {
h := C.job_alloc_host(job.allocs, C.int(i))
if h != nil && h.host != nil {
r.execHosts = append(r.execHosts, C.GoString(h.host))
if h == nil || h.host == nil {
continue
}
// bug-1743-followup: this host's own "slots" resource
// allocation (xce_host_alloc_t.allocs[]), mirroring the C
// scheduler's own get_nslots_in_alloc()/repl_worker_alloc_
// nslots() resname scan -- defaults to 1 when absent, same as
// those.
nslots := 1
nallocs := int(h.nallocs)
for j := 0; j < nallocs; j++ {
res := C.host_alloc_res(h, C.int(j))
if res != nil && res.resname != nil && C.GoString(res.resname) == "slots" {
nslots = int(res.value)
break
}
}
r.execHosts = append(r.execHosts, rawHostSlot{host: C.GoString(h.host), slots: nslots})
}
}
return rawJobToModel(r)