wdgzyjx/myxce
1
0
Fork 0
forked from lei.chen/myxce
Code Pull requests Activity

fix(raft-ha-core-safety): close 5.10a — WAL segment rotation + endpoint UAF blocking real snapshot catch-up

Browse source 
Chain of fixes needed to get --force-snapshot soak to a real live PASS
(raft-ha-core-safety task 5.10a / ha-entity-snapshots task 7.1):

1. WAL segment rotation was gated on a hardcoded 64MB compile-time
   constant; trim_wal_segments() never deletes the active (currently-open)
   segment. At soak job counts a segment never rotated, so nothing was
   ever physically trimmable and ha_evaluate_repl_action always chose
   STREAM_WAL over SEND_SNAPSHOT for an empty-rejoining node. Fixed by
   threading a wal_segment_bytes override through persist_config_t
   (mirrors the --max-wal-records pattern: config.h default, persist.h
   setter, persist.c 3 usage sites + minimum-floor enforcement, 6-point
   CLI wiring through main.c/myconf.h/myapp.c/cluster.c) plus a new
   --wal-segment-bytes CLI flag. run-ha-soak.sh's --force-snapshot mode
   now sets WAL_SEGMENT_BYTES=4096 to force real rotation at soak scale.

2. This unmasked a genuine heap-use-after-free in INVOKE_MSG_HANDLER
   (include/netio.h): the macro calls ep->msg_handler(ep) synchronously
   (not via the vtask dispatcher, so the bug-1298 vtask ref/unref pairing
   doesn't cover it) then writes ep->fsm_in.pkt = NULL. A stale vote-reply
   handler chain (raft_on_vote_reply -> raft_cb_become_follower ->
   endpoint_unref) could drop the endpoint's last ref and free it inside
   the handler call, so the trailing write hit freed memory. This is the
   first-ever live exercise of a node receiving a snapshot transfer while
   mid-election. Fixed by holding a ref across the synchronous call, same
   pattern task 5.8 established for the async path.

With both fixes: --force-snapshot soak now PASSES live (committed
divergence=0, job_loss=0, confirmed real "HA: snapshot" install on the
restarted node) — first genuine live proof of this scenario. 3-round
--chaotic regression clean. Full 217-test controller suite green
before/after every fix in the chain.

Builds on the delaymgr starvation fix (b9ad018) and walcompare
checkpoint-floor fix (f3c86a6) from earlier in this investigation.
This commit is contained in:
Rongsong Shen 2026-07-02 04:11:20 +00:00
parent b9ad01878c
commit 1439e2655e
11 changed files with 115 additions and 40 deletions
Download patch file Download diff file Expand all files Collapse all files

8
src/controller/cluster.c
View file

@ -1330,6 +1330,14 @@ int cluster_init_phase2(cluster_t* c)
* deterministic record count instead of the 10000-record default. */
persist_config_set_max_wal_records(&pcfg, c->myconf->max_wal_records);
/* --wal-segment-bytes physical-segment-size override (0 = keep the
* persist default). raft-ha-core-safety task 5.10a / ha-entity-
* snapshots task 7.1: a segment is only trimmable once it rotates
* out, so forcing a real snapshot-triggered catch-up in the soak
* needs a small deterministic segment size instead of the 64 MB
* production default. */
persist_config_set_wal_segment_bytes(&pcfg, c->myconf->wal_segment_bytes);
persist_set_workdir(&c->persist, workdir, name);
rc = persist_init(&c->persist, &pcfg, c);
if (rc != 0) {

15
src/controller/main.c
View file

@ -32,6 +32,7 @@ const char* argp_program_bug_address = BUG_EMAIL;
#define OPT_SYNC_TIMEOUT 261
#define OPT_WAL_SYNC 262
#define OPT_MAX_WAL_RECORDS 263
#define OPT_WAL_SEGMENT_BYTES 264
struct arguments {
char* myname;
@ -46,6 +47,7 @@ struct arguments {
uint32_t sync_timeout_ms;
uint32_t wal_sync_ms;
uint32_t max_wal_records;
uint32_t wal_segment_bytes;
};
static struct argp_option options[] = {
@ -71,6 +73,10 @@ static struct argp_option options[] = {
{ "max-wal-records", OPT_MAX_WAL_RECORDS, "N", 0,
"WAL records since last checkpoint before an async checkpoint is "
"scheduled (0 = default; persist enforces a minimum of 100)" },
{ "wal-segment-bytes", OPT_WAL_SEGMENT_BYTES, "N", 0,
"Physical WAL segment file size in bytes; a segment is only eligible "
"for trim/delete after it rotates out (0 = default 64 MB; persist "
"enforces a minimum of 4096)" },
{ 0 }
};
@ -134,6 +140,13 @@ static error_t parse_opt(int key, char* arg, struct argp_state* state)
arguments->max_wal_records = (uint32_t)v;
break;
}
case OPT_WAL_SEGMENT_BYTES: {
long v = atol(arg);
if (v < 0)
argp_error(state, "--wal-segment-bytes must be >= 0 (got: %s)", arg);
arguments->wal_segment_bytes = (uint32_t)v;
break;
}
default:
return ARGP_ERR_UNKNOWN;
}
@ -188,6 +201,7 @@ int main(int argc, char* argv[])
arguments.sync_timeout_ms = 0; /* 0 = not set; use persist config default */
arguments.wal_sync_ms = 0; /* 0 = not set; use persist config default */
arguments.max_wal_records = 0; /* 0 = not set; use persist config default */
arguments.wal_segment_bytes = 0; /* 0 = not set; use persist config default */
argp_parse(&argp, argc, argv, 0, 0, &arguments);
@ -239,6 +253,7 @@ int main(int argc, char* argv[])
myconf.sync_timeout_ms = arguments.sync_timeout_ms;
myconf.wal_sync_ms = arguments.wal_sync_ms;
myconf.max_wal_records = arguments.max_wal_records;
myconf.wal_segment_bytes = arguments.wal_segment_bytes;
memset(&myconf.peers_cfg, 0, sizeof(myconf.peers_cfg));
if (arguments.peers_str) {

8
src/controller/myapp.c
View file

@ -177,6 +177,14 @@ int myapp_run(myconf_t *myconf)
* deterministic record count instead of the 10000-record default. */
persist_config_set_max_wal_records(&pcfg, myconf->max_wal_records);
/* --wal-segment-bytes physical-segment-size override (0 = keep the
* persist default). raft-ha-core-safety task 5.10a / ha-entity-
* snapshots task 7.1: a segment is only trimmable once it rotates
* out, so forcing a real snapshot-triggered catch-up in the soak
* needs a small deterministic segment size instead of the 64 MB
* production default. */
persist_config_set_wal_segment_bytes(&pcfg, myconf->wal_segment_bytes);
persist_set_workdir(&c.persist, workdir, name);
rc = persist_init(&c.persist, &pcfg, &c);
if (rc != 0) {

16
src/controller/persist.c
View file

@ -94,7 +94,6 @@ static int capnp_encode_worker(const xce_worker_t* w, uint8_t** out, size_t* out
/* Constants */
/* ------------------------------------------------------------------ */
#define WAL_SEGMENT_SIZE_BYTES (64UL * 1024 * 1024) /* 64 MB per segment */
#define WAL_SEG_FMT "%s/seg-%016" PRIx64 ".wal"
/* NFS_SUPER_MAGIC — reject WAL on NFS mounts (unreliable fsync) */
@ -148,7 +147,7 @@ static int open_new_segment(persist_t* p)
/* Pre-allocate segment space to avoid fragmentation and metadata updates
* on every write. posix_fallocate is best-effort — ignore errors. */
posix_fallocate(fd, 0, (off_t)WAL_SEGMENT_SIZE_BYTES);
posix_fallocate(fd, 0, (off_t)p->config.wal_segment_bytes);
p->wal_fd = fd;
p->seg_offset = 0;
@ -571,6 +570,15 @@ int persist_init(persist_t* p, persist_config_t* cfg, cluster_t* c)
p->config.max_wal_records = 100;
}
/* Enforce minimum value for wal_segment_bytes to prevent a rotation storm
* (must comfortably fit at least one max-payload entry: header + up to
* MAX_WAL_PAYLOAD_BYTES). */
if (p->config.wal_segment_bytes < 4096) {
ERROR("persist: wal_segment_bytes=%u too low (minimum 4096) — setting to 4096",
p->config.wal_segment_bytes);
p->config.wal_segment_bytes = 4096;
}
/* Initialise atomic checkpoint-trigger counters */
atomic_store(&p->wal_record_count, 0);
atomic_store(&p->checkpoint_in_progress, 0);
@ -790,7 +798,7 @@ int persist_wal_async(persist_t* p, uint32_t type,
repl_broadcast(&p->repl, &hdr, payload, len, prev_log_term);
/* Rotate segment when full */
if (p->seg_offset >= WAL_SEGMENT_SIZE_BYTES) {
if (p->seg_offset >= p->config.wal_segment_bytes) {
if (rotate_segment(p) != 0) {
pthread_mutex_unlock(&p->lock);
return -EIO;
@ -1204,7 +1212,7 @@ int persist_wal_write_replicated(persist_t* p, uint64_t lsn, uint32_t type,
}
/* Rotate segment when full (same threshold as the primary append). */
if (p->seg_offset >= WAL_SEGMENT_SIZE_BYTES) {
if (p->seg_offset >= p->config.wal_segment_bytes) {
if (rotate_segment(p) != 0) {
pthread_mutex_unlock(&p->lock);
return -EIO;