fix: spurious errors/warnings from a pc13v HA deploy (bug-1872..1877)

- bug-1872 (worker): "Failed to find any disk statistics in
  /proc/diskstats" ERROR every 15 s on an NVMe-only host. The whole-disk
  filter guessed from the name and skipped anything ending in a digit or
  containing 'p' -- every nvmeXnY, mmcblkN, even sdp -- so io was never
  reported. diskstats.h now counts a device only when
  /sys/block/<name>/device exists (real disks; not partitions, loop, dm,
  md, zram), and a host with no disk warns once.
- bug-1873 (worker): "Failed to get worker pid" WARN on job start. MainPID
  reads 0 until systemd has forked the new transient unit; xcecd.c already
  retries, so the miss is DEBUG and the final failure names the unit.
- bug-1874 (scheduler): deprecation WARN for the legacy xce_sched_fcfs on
  every start, though builtin_fcfs is the picker. Registration still wraps
  a job_elect_fn plugin but no longer warns; selecting one warns once.
- bug-1875 (apiserver): "Not running as root -- PAM authentication will not
  work" with the default provider config_file; now only for provider pam.
- bug-1876 (controller): standbys logged "cluster_init_phase2 ... failed
  (rc=-22)" WARN every 3 s while waiting for the primary's config push,
  a state the function itself calls normal. It returns -EAGAIN for that
  wait; callers log it at INFO, other failures still WARN.
- bug-1877 (controller): "WAL/snapshot stored unencrypted" warned without
  looking. persist_path_encrypted() checks fscrypt (statx) and dm-crypt
  (sysfs dm/uuid CRYPT-, through LVM slaves); the warning stays when the
  storage is not shown to be encrypted (e.g. a plain /tmp).

Tests: worker diskstats_test (2 of 4 RED on the old filter with pc13v's
/proc/diskstats), controller test_phase2_cold_boot and
test_persist_encryption, scheduler picker tests, apiserver
TestRootWarning. Full ASAN build: all 113 suites pass (controller 319/0,
harness 141/0).

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
This commit is contained in:
Rongsong Shen 2026-09-28 04:35:19 +00:00
parent 8cadeeb2d0
commit 44173f74ae
Signed by untrusted user: rshen
GPG key ID: 80533536B0EB651C
23 changed files with 619 additions and 63 deletions

View file

@ -0,0 +1,115 @@
/*
* test_persist_encryption.c -- bug-1877: persist_init() warned "WAL/snapshot
* stored unencrypted" on every start without looking, so the warning also
* fired on encrypted storage. persist_dev_is_dmcrypt() now checks the WAL's
* block device in sysfs for a dm-crypt (LUKS) layer, directly or under LVM
* (via `slaves`); the warning stays for storage it cannot show is encrypted.
*/
#include <errno.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sys/stat.h>
#include <unistd.h>
#include <unity/unity.h>
#include "persist.h"
static char g_sysfs[256];
static void mkdirs(const char* rel)
{
char path[512];
char cmd[640];
snprintf(path, sizeof(path), "%s/%s", g_sysfs, rel);
snprintf(cmd, sizeof(cmd), "mkdir -p '%s'", path);
TEST_ASSERT_EQUAL_INT(0, system(cmd));
}
static void put(const char* rel, const char* text)
{
char path[512];
FILE* fp;
snprintf(path, sizeof(path), "%s/%s", g_sysfs, rel);
fp = fopen(path, "w");
TEST_ASSERT_NOT_NULL(fp);
fputs(text, fp);
fclose(fp);
}
static void fake_sysfs(void)
{
char cmd[300];
snprintf(g_sysfs, sizeof(g_sysfs), "/tmp/test_persist_enc.%d", (int)getpid());
snprintf(cmd, sizeof(cmd), "rm -rf %s", g_sysfs);
TEST_ASSERT_EQUAL_INT(0, system(cmd));
/* 259:2 nvme0n1p2, a plain partition */
mkdirs("dev/block/259:2");
mkdirs("class/block/nvme0n1p2");
put("class/block/nvme0n1p2/dev", "259:2\n");
/* 253:0 dm-0 = LUKS on nvme0n1p2 */
mkdirs("dev/block/253:0/dm");
mkdirs("dev/block/253:0/slaves/nvme0n1p2");
put("dev/block/253:0/dm/uuid", "CRYPT-LUKS2-0123abcd-luks-0123\n");
mkdirs("class/block/dm-0");
put("class/block/dm-0/dev", "253:0\n");
/* 253:1 dm-1 = LVM volume on dm-0 */
mkdirs("dev/block/253:1/dm");
mkdirs("dev/block/253:1/slaves/dm-0");
put("dev/block/253:1/dm/uuid", "LVM-abcdefabcdef\n");
/* 253:2 dm-2 = LVM volume straight on the plain partition */
mkdirs("dev/block/253:2/dm");
mkdirs("dev/block/253:2/slaves/nvme0n1p2");
put("dev/block/253:2/dm/uuid", "LVM-fedcbafedcba\n");
}
static void drop_sysfs(void)
{
char cmd[300];
snprintf(cmd, sizeof(cmd), "rm -rf %s", g_sysfs);
TEST_ASSERT_EQUAL_INT(0, system(cmd));
}
static void test_luks_device_is_encrypted(void)
{
fake_sysfs();
TEST_ASSERT_EQUAL_INT(1, persist_dev_is_dmcrypt(g_sysfs, 253, 0));
drop_sysfs();
}
static void test_lvm_on_luks_is_encrypted(void)
{
fake_sysfs();
TEST_ASSERT_EQUAL_INT(1, persist_dev_is_dmcrypt(g_sysfs, 253, 1));
drop_sysfs();
}
static void test_plain_partition_and_plain_lvm_are_not(void)
{
fake_sysfs();
TEST_ASSERT_EQUAL_INT(0, persist_dev_is_dmcrypt(g_sysfs, 259, 2));
TEST_ASSERT_EQUAL_INT(0, persist_dev_is_dmcrypt(g_sysfs, 253, 2));
drop_sysfs();
}
static void test_unknown_device_is_not_claimed_encrypted(void)
{
fake_sysfs();
TEST_ASSERT_EQUAL_INT(0, persist_dev_is_dmcrypt(g_sysfs, 8, 99));
drop_sysfs();
}
void test_persist_encryption(void)
{
UnitySetTestFile(__FILE__);
RUN_TEST(test_luks_device_is_encrypted);
RUN_TEST(test_lvm_on_luks_is_encrypted);
RUN_TEST(test_plain_partition_and_plain_lvm_are_not);
RUN_TEST(test_unknown_device_is_not_claimed_encrypted);
}