Files
ww/test/wcc/989_pkgcache_concurrent_run.c
Hojun-Cho a9778ec000 wcc,ww,os: atomic pkgcache store via temp+rename, both stages (#104)
The out/.pkgcache content-keyed store copied each artifact IN-PLACE
(cp -f / copyfile) to the fixed paths P.wwi/P.o/P.key. Key-last gave
crash-consistency but NOT concurrent-read safety: two same-stage builds
of a shared lib pkg (rt/time/os) target one out/.pkgcache/<pkg>/P.{wwi,o};
once an early finisher writes P.key, a later build's cache_lookup copies
P.wwi/P.o while a mid-finisher is still mid-write -> torn read -> corrupt
link / cs!=ww. The key is content-only, so it is purely the non-atomic
write.

Fix (Go-build-cache pattern, both stages in lock-step, rule 10): write
each artifact to a per-pid same-dir temp (P.wwi.tmp.<pid> etc.) then
rename() into place. Same dir => rename is atomic (cross-fs is not);
per-pid temp => concurrent writers don't clobber each other mid-copy;
content-keyed => last-writer-wins is byte-identical. Key renamed LAST so
a reader that sees the new key always finds complete artifacts. On any
mid-store error the per-pid temps are unlinked so a failed store leaves
no litter (cstage goto cleanup; wwstage cachermtmp helper).

  cstage cmd/ww/main.c cache_store: libc rename(2) + getpid().
  wwstage selfhost/cmd/ww/main.ww cachestore: new os.rename + cachetmp.
  lib/os/os.ww: add rename(2) (RENAME=82), ref/hare/os/os.ha:17 -- returns
    raw i32 errno like sibling remove/mkdir/rmdir (ww's os is the flat
    syscall floor, no fs:: layer); a second pathbuf2 slot holds newpath
    since kpath's single pathbuf can't carry both paths.

cache_lookup is unchanged: it reads cache->private scratch, and an atomic
source is never torn.

The torn-read race is closed BY CONSTRUCTION; a deterministic behavioral
regression-guard isn't feasible through the product build path (content-
keying => concurrent COLD builds all MISS+STORE, never HIT-read a mid-store
entry; a warm cache is never re-stored). The deferred white-box guard is
TASK #105. A WHY-comment at both fix sites records this.

Tests: 989_sepbuild_run KEEPS its private per-pid WW_PKGCACHE -- the
comment is corrected: the pin is NOT a torn-read mask (closed by
construction) but cold-compile isolation for the test's INTERMEDIATE
(.s/.unit.ww) byte-id compare, which a cache HIT legitimately skips
producing. The former 989_pkgcache_atomic_run is renamed to
989_pkgcache_concurrent_run and HONESTLY relabeled: it is a concurrent
shared-cache build-correctness smoke (N concurrent --sep builds sharing
one cache -> every binary byte-identical to an isolated reference + correct
run, both stages), NOT a torn-read/atomicity proof (a review revert-
experiment proved the original claim vacuous). Shrunk to 4 concurrent
builds x 1 batch x both stages. COLD/dev-only, off every byte-id/bootstrap
gate.

selfhost/cmd/ww/main.combined.ww remains stale (its writer was deleted at
the M4 E3-C1 flip; #90 deletes the file) -- not regenerated.

make test: all 445 passed; make sizelint clean; 990-997 byte-id hold.
2026-06-18 20:45:12 +09:00

228 lines
7.0 KiB
C

/*
* 989_pkgcache_concurrent_run — concurrent shared-cache build-correctness
* smoke (#104). N distinct root programs that all `import shared` are built
* CONCURRENTLY into ONE shared WW_PKGCACHE; every resulting binary must be
* byte-IDENTICAL to a reference built in ISOLATION (private cache) and run to
* its expected exit. This guards that concurrent `ww build --sep` sharing one
* out/.pkgcache produces correct, deterministic binaries — a regression guard
* for the cache subsystem under contention (store crash, lock bug, wrong-key
* copy, etc.).
*
* It does NOT prove the temp+rename store is atomic against torn reads: with
* content-keying every concurrent cold build MISSES at lookup and STORES (it
* never HIT-reads a mid-store entry), so the torn-read window is not forced
* here. That race is closed by construction at the cache_store fix site; the
* deferred white-box guard is TASK #105.
*
* Both driver stages (rule 10): the cs and ww references are byte-identical.
* Light wwstage-driver test (CLAUDE.md rule 14): all outputs + caches live
* under a private /tmp tree, so it is parallel-safe and off every byte-id /
* bootstrap gate. Models 989_pkgcache_run conventions.
*/
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <unistd.h>
#include <sys/wait.h>
#include <sys/stat.h>
#define NPROG 4
#define BASE_EXIT 7 /* shared.v() == 7; rootI returns 7 + I */
static int
runwait(const char *cmd)
{
int rc = system(cmd);
if (rc == -1) return -1;
if (WIFEXITED(rc)) return WEXITSTATUS(rc);
return 1;
}
static const char *
absbin(void)
{
const char *b = getenv("BIN");
if (!b) b = "out/bin";
if (b[0] == '/') return b;
static char buf[2048];
char cwd[1024];
if (getcwd(cwd, sizeof cwd) == NULL) return NULL;
snprintf(buf, sizeof buf, "%s/%s", cwd, b);
return buf;
}
static int
write_file(const char *path, const char *body)
{
FILE *f = fopen(path, "wb");
if (!f) return -1;
fputs(body, f);
fclose(f);
return 0;
}
static int
slurp(const char *path, char **outbuf, size_t *outlen)
{
FILE *f = fopen(path, "rb");
if (!f) return -1;
fseek(f, 0, SEEK_END);
long n = ftell(f);
fseek(f, 0, SEEK_SET);
if (n < 0) { fclose(f); return -1; }
char *b = malloc((size_t)n + 1);
if (!b) { fclose(f); return -1; }
if (fread(b, 1, (size_t)n, f) != (size_t)n) { free(b); fclose(f); return -1; }
b[n] = '\0';
fclose(f);
*outbuf = b;
*outlen = (size_t)n;
return 0;
}
static int
files_eq(const char *a, const char *b)
{
char *ba = NULL, *bb = NULL;
size_t na = 0, nb = 0;
if (slurp(a, &ba, &na) < 0 || slurp(b, &bb, &nb) < 0) {
free(ba); free(bb);
return -1;
}
int eq = (na == nb && memcmp(ba, bb, na) == 0);
free(ba); free(bb);
return eq ? 0 : 1;
}
static const char *shared_src =
"package shared;\n"
"export fn v() i32 = { return 7; };\n";
int
main(void)
{
const char *bin = absbin();
if (!bin) return 1;
int fail = 0;
char td[64], cmd[8192], batch[32768];
char sharedww[1024];
snprintf(td, sizeof td, "/tmp/wwconc_%d", getpid());
snprintf(cmd, sizeof cmd, "rm -rf %s", td);
runwait(cmd);
snprintf(cmd, sizeof cmd, "mkdir -p %s/shared", td);
runwait(cmd);
snprintf(sharedww, sizeof sharedww, "%s/shared/shared.ww", td);
if (write_file(sharedww, shared_src)) { fail++; goto out; }
/* N distinct roots, each importing the one shared pkg. Distinct return
* (7 + I) so each program — and so each clean binary — is distinguishable,
* while the contended cache entry (shared) is common to all. */
for (int i = 0; i < NPROG; i++) {
char rootww[1024], src[256];
snprintf(rootww, sizeof rootww, "%s/root%d.ww", td, i);
snprintf(src, sizeof src,
"package main;\nimport shared;\n"
"fn main() i32 = { return shared.v() + %d; };\n", i);
if (write_file(rootww, src)) { fail++; goto out; }
}
struct { const char *drv, *tag; } stg[] = {
{ "ww", "cs" },
{ "ww_ww", "ww" },
};
for (int s = 0; s < 2; s++) {
const char *drv = stg[s].drv, *tag = stg[s].tag;
char shcache[1024];
snprintf(shcache, sizeof shcache, "%s/cache.%s", td, tag);
/* References: each rootI built ISOLATED (private cache, no contention)
* = the clean baseline bytes a concurrent build must reproduce. */
for (int i = 0; i < NPROG; i++) {
char refcache[1024], refprog[1024], refscr[1024], rootww[1024];
snprintf(refcache, sizeof refcache, "%s/refc.%s.%d", td, tag, i);
snprintf(refprog, sizeof refprog, "%s/ref.%s.%d", td, tag, i);
snprintf(refscr, sizeof refscr, "%s/ref.%s.%d.sepwork", td, tag, i);
snprintf(rootww, sizeof rootww, "%s/root%d.ww", td, i);
snprintf(cmd, sizeof cmd,
"rm -rf %s %s; WW_PKGCACHE='%s' timeout 240 %s/%s build --sep "
"-o %s %s >/dev/null 2>&1",
refscr, refcache, refcache, bin, drv, refprog, rootww);
if (runwait(cmd) != 0) {
fprintf(stderr, "concur FAIL[%s]: reference build %d failed\n",
drv, i);
fail++;
}
if (runwait(refprog) != BASE_EXIT + i) {
fprintf(stderr, "concur FAIL[%s]: reference %d wrong exit\n",
drv, i);
fail++;
}
}
/* Fresh shared cache so every build in the batch MISS-stores `shared`
* concurrently → write contention on shared/P.{wwi,o,key}. Distinct
* per-prog output so every binary can be verified, not just one. */
snprintf(cmd, sizeof cmd, "rm -rf %s", shcache);
runwait(cmd);
size_t off = 0;
off += (size_t)snprintf(batch + off, sizeof batch - off,
"export WW_PKGCACHE='%s'; ", shcache);
for (int i = 0; i < NPROG; i++) {
off += (size_t)snprintf(batch + off, sizeof batch - off,
"( rm -rf %s/c.%s.%d.sepwork; timeout 240 %s/%s build "
"--sep -o %s/c.%s.%d %s/root%d.ww >/dev/null 2>&1 ) & ",
td, tag, i, bin, drv,
td, tag, i, td, i);
}
off += (size_t)snprintf(batch + off, sizeof batch - off, "wait");
if (off >= sizeof batch) {
fprintf(stderr, "concur FAIL: batch cmd truncated\n");
fail++; goto out;
}
runwait(batch);
for (int i = 0; i < NPROG; i++) {
char prog[1024], refprog[1024];
snprintf(prog, sizeof prog, "%s/c.%s.%d", td, tag, i);
snprintf(refprog, sizeof refprog, "%s/ref.%s.%d", td, tag, i);
if (runwait(prog) != BASE_EXIT + i) {
fprintf(stderr, "concur FAIL[%s]: concurrent prog i=%d "
"wrong/failed exit\n", drv, i);
fail++;
}
if (files_eq(prog, refprog) != 0) {
fprintf(stderr, "concur FAIL[%s]: concurrent binary i=%d "
"!= isolated reference\n", drv, i);
fail++;
}
}
}
/* rule 10: the cs and ww isolated references are byte-identical. */
for (int i = 0; i < NPROG; i++) {
char a[1024], b[1024];
snprintf(a, sizeof a, "%s/ref.cs.%d", td, i);
snprintf(b, sizeof b, "%s/ref.ww.%d", td, i);
if (files_eq(a, b) != 0) {
fprintf(stderr, "concur FAIL: cs != ww reference %d (rule 10)\n", i);
fail++;
}
}
out:
snprintf(cmd, sizeof cmd, "rm -rf %s", td);
runwait(cmd);
if (fail) {
fprintf(stderr, "concur: %d check(s) failed\n", fail);
return 1;
}
printf("concur: %d concurrent --sep builds sharing one cache, both stages "
"— every binary byte-identical to its isolated reference + correct run; "
"cs==ww references (rule 10)\n", NPROG);
return 0;
}