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

fix(raft-drive-async): resolve snapshot chunk-drop (bug-1386) and chunk misordering (bug-1389)

Browse source 
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
This commit is contained in:
Rongsong Shen 2026-07-03 02:40:12 +00:00
parent 02e46f6ba1
commit 5cb36794d2
14 changed files with 1553 additions and 43 deletions
Download patch file Download diff file Expand all files Collapse all files

132
src/controller/testsuite/test_snapdiff.c Normal file
View file

@ -0,0 +1,132 @@
#define _GNU_SOURCE
#include <errno.h>
#include <stdint.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <unistd.h>
#include <unity/unity.h>
#include "snapdiff.h"
static char g_dir[256];
static void fresh_dir(void)
{
strcpy(g_dir, "/tmp/xce_snapdiff_XXXXXX");
TEST_ASSERT_NOT_NULL(mkdtemp(g_dir));
}
static void cleanup_dir(void)
{
char cmd[512];
snprintf(cmd, sizeof(cmd), "rm -rf %s", g_dir);
system(cmd);
}
static void write_file(const char* path, size_t size, uint8_t fill,
size_t flip_at, uint8_t flip_to)
{
uint8_t* buf = malloc(size);
memset(buf, fill, size);
if (flip_at < size)
buf[flip_at] = flip_to;
FILE* fp = fopen(path, "wb");
TEST_ASSERT_NOT_NULL(fp);
fwrite(buf, 1, size, fp);
fclose(fp);
free(buf);
}
static void test_identical_files(void)
{
fresh_dir();
char p1[512], p2[512];
snprintf(p1, sizeof(p1), "%s/a.bin", g_dir);
snprintf(p2, sizeof(p2), "%s/b.bin", g_dir);
write_file(p1, 1000, 0x42, 2000 /* no flip */, 0);
write_file(p2, 1000, 0x42, 2000, 0);
snapdiff_report_t rep;
int rc = snapdiff_paths(p1, p2, stdout, &rep);
TEST_ASSERT_EQUAL_INT(0, rc);
TEST_ASSERT_EQUAL_INT(1, rep.identical);
TEST_ASSERT_EQUAL_INT(-1, (int)rep.diff_offset);
cleanup_dir();
}
static void test_size_mismatch(void)
{
fresh_dir();
char p1[512], p2[512];
snprintf(p1, sizeof(p1), "%s/a.bin", g_dir);
snprintf(p2, sizeof(p2), "%s/b.bin", g_dir);
write_file(p1, 1000, 0x42, 2000, 0);
write_file(p2, 999, 0x42, 2000, 0);
snapdiff_report_t rep;
int rc = snapdiff_paths(p1, p2, stdout, &rep);
TEST_ASSERT_EQUAL_INT(1, rc);
TEST_ASSERT_EQUAL_INT(1, rep.size_mismatch);
TEST_ASSERT_EQUAL_INT(0, rep.identical);
cleanup_dir();
}
/* bug-1389 regression shape: two SNAPDIFF_CHUNK_SIZE-sized chunks, content
* diverges starting at the exact first byte of chunk index 1 — the OPCode_
* snapshotTransfer chunk-boundary corruption signature. */
static void test_diff_at_chunk_boundary_is_flagged(void)
{
fresh_dir();
char p1[512], p2[512];
snprintf(p1, sizeof(p1), "%s/a.bin", g_dir);
snprintf(p2, sizeof(p2), "%s/b.bin", g_dir);
size_t size = SNAPDIFF_CHUNK_SIZE * 2;
write_file(p1, size, 0x11, size, 0);
write_file(p2, size, 0x11, SNAPDIFF_CHUNK_SIZE /* flip first byte of chunk 1 */,
0x22);
snapdiff_report_t rep;
int rc = snapdiff_paths(p1, p2, stdout, &rep);
TEST_ASSERT_EQUAL_INT(1, rc);
TEST_ASSERT_EQUAL_INT(0, rep.identical);
TEST_ASSERT_EQUAL_INT(SNAPDIFF_CHUNK_SIZE, (int)rep.diff_offset);
TEST_ASSERT_EQUAL_INT(1, rep.at_chunk_boundary);
TEST_ASSERT_EQUAL_INT(1, (int)rep.chunk_index);
cleanup_dir();
}
static void test_diff_mid_chunk_is_not_flagged_as_boundary(void)
{
fresh_dir();
char p1[512], p2[512];
snprintf(p1, sizeof(p1), "%s/a.bin", g_dir);
snprintf(p2, sizeof(p2), "%s/b.bin", g_dir);
write_file(p1, 1000, 0x11, 2000, 0);
write_file(p2, 1000, 0x11, 500 /* mid-file, not a chunk boundary */, 0x22);
snapdiff_report_t rep;
int rc = snapdiff_paths(p1, p2, stdout, &rep);
TEST_ASSERT_EQUAL_INT(1, rc);
TEST_ASSERT_EQUAL_INT(500, (int)rep.diff_offset);
TEST_ASSERT_EQUAL_INT(0, rep.at_chunk_boundary);
cleanup_dir();
}
static void test_missing_path_errors(void)
{
snapdiff_report_t rep;
int rc = snapdiff_paths("/tmp/xce_snapdiff_missing_a_zzz",
"/tmp/xce_snapdiff_missing_b_zzz", stdout, &rep);
TEST_ASSERT_LESS_THAN_INT(0, rc);
}
void test_snapdiff(void)
{
RUN_TEST(test_identical_files);
RUN_TEST(test_size_mismatch);
RUN_TEST(test_diff_at_chunk_boundary_is_flagged);
RUN_TEST(test_diff_mid_chunk_is_not_flagged_as_boundary);
RUN_TEST(test_missing_path_errors);
}