Hi Guys,
When I run stress-ng via the following steps on one ARM64 dual
socket system(Cavium Thunder), the kernel oops[1] can often be
triggered after running the stress test for several hours(sometimes
it may take longer):
- git clone git://kernel.ubuntu.com/cking/stress-ng.git
- apply the attachment patch which just makes the posix file
lock stress test more aggressive
- run the test via '~/git/stress-ng$./stress-ng --lockf 128 --aggressive'
>From the oops log, looks one garbage file_lock node is got
from the linked list of 'ctx->flc_posix' when the issue happens.
BTW, the issue isn't observed on single socket Cavium Thunder yet,
and the same issue can be seen on Ubuntu Xenial(v4.4 based kernel)
too.
Thanks,
Ming
[1] kernel oops log
ubuntu@ubuntu:~/git/stress-ng$ ./stress-ng --lockf 128 --aggressive
stress-ng: info: [63828] defaulting to a 86400 second run per stressor
stress-ng: info: [63828] dispatching hogs: 128 lockf
stress-ng: info: [63828] cache allocate: default cache size: 16384K
[80659.799092] Unable to handle kernel NULL pointer dereference at
virtual address 00000030
[80659.807219] pgd = ffff81001f365800
[80659.810683] [00000030] *pgd=000001001a290003,
*pud=000001001a290003, *pmd=0000010fa07f0003, *pte=0000000000000000
[80659.821029] Internal error: Oops: 96000007 [#1] SMP
[80659.825901] Modules linked in:
[80659.828962] CPU: 15 PID: 63848 Comm: stress-ng-lockf Tainted: G
W 4.8.0 #167
[80659.837132] Hardware name: Cavium ThunderX CRB/To be filled by
O.E.M., BIOS 5.11 12/12/2012
[80659.845479] task: ffff81001ee78580 task.stack: ffff81001f798000
[80659.851402] PC is at posix_locks_conflict+0x94/0xc0
[80659.856282] LR is at posix_lock_inode+0x90/0x6b0
[80659.860896] pc : [<ffff00000828c694>] lr : [<ffff00000828cd90>]
pstate: a0000145
[80659.868285] sp : ffff81001f79bca0
[80659.871596] x29: ffff81001f79bca0 x28: ffff81001f798000
[80659.876915] x27: ffff800fdffbc160 x26: 0000000000000000
[80659.882234] x25: ffff800fd2da2b30 x24: ffff800fce927430
[80659.887551] x23: ffff800fce92d8f0 x22: ffff81001f79bd30
[80659.892869] x21: ffff800fd2da2b18 x20: fffffffffffffff8
[80659.898187] x19: ffff800fdffbc160 x18: 0000000000001140
[80659.903504] x17: 0000ffff8870a578 x16: ffff000008245768
[80659.908821] x15: 0000ffff888bc000 x14: 0000000000000000
[80659.914139] x13: 00000003e8000000 x12: 0000000000000018
[80659.919457] x11: 00000000000e6a17 x10: 00000000ffffffd0
[80659.924776] x9 : 0000000000000000 x8 : ffff800fce927500
[80659.930094] x7 : 0000000000000000 x6 : 000000000000007f
[80659.935413] x5 : 0000000000000080 x4 : ffff800fce927438
[80659.940729] x3 : ffff800fce927458 x2 : 00000000000026b9
[80659.946047] x1 : ffff81001f37f300 x0 : 0000000000000000
[80659.951363]
[80659.952851] Process stress-ng-lockf (pid: 63848, stack limit =
0xffff81001f798020)
[80659.960415] Stack: (0xffff81001f79bca0 to 0xffff81001f79c000)
[80659.966158] bca0: ffff81001f79bcc0 ffff00000828cd90
fffffffffffffff8 ffff800fa3a66568
[80659.973986] bcc0: ffff81001f79bd40 ffff00000828d5f0
ffff800f8185c700 ffff800fdffbc160
[80659.981812] bce0: 0000000000000006 0000000000000000
ffff81001f79bdd0 0000000000000006
[80659.989638] bd00: 0000000000000120 0000000000000019
ffff0000088b1000 ffff81001f798000
[80659.997465] bd20: ffff81001f79bd40 ffff000008403fec
ffff81001f79bd30 ffff81001f79bd30
[80660.005292] bd40: ffff81001f79bd70 ffff00000828d8bc
ffff800f8185c700 ffff800fdffbc160
[80660.013118] bd60: ffff800fdffbc1b8 ffff800f8185c700
ffff81001f79bde0 ffff00000828ef10
[80660.020944] bd80: ffff800f8185c700 0000000000000000
ffff800fdffbc160 ffff800fa3a66568
[80660.028770] bda0: 0000000000000006 0000000000000004
ffff81001f79bde0 ffff00000828ee14
[80660.036596] bdc0: ffff800f8185c700 00000000fffffff2
ffff800fdffbc160 ffff810ff99aae80
[80660.044423] bde0: ffff81001f79be70 ffff000008245b84
ffff800f8185c700 ffff800f8185c700
[80660.052249] be00: 0000000000000000 0000000000000006
0000ffffdad5d4b0 0000000000000004
[80660.060087] be20: 0000000000000120 000000000000003e
0000000000010001 0000000000000000
[80660.067916] be40: 0000000000000008 0000000000000000
0000000000010001 0000000000000000
[80660.075742] be60: 0000000000000008 0000000000000000
0000000000000000 ffff0000080836f0
[80660.083568] be80: 0000000000000000 00000000005c5000
ffffffffffffffff 0000ffff8870a3b8
[80660.091394] bea0: 0000000080000000 0000000000000015
0000000080000000 00000000005c5000
[80660.099220] bec0: 0000000000000004 0000000000000006
0000ffffdad5d4b0 00000000ffffff80
[80660.107046] bee0: 0000ffffdad5d490 0000000026c26373
000000000000176f 0000000000004650
[80660.114873] bf00: 0000000000000019 0000000000006536
00000000ffffffd0 00000000000e6a17
[80660.122698] bf20: 0000000000000018 00000003e8000000
0000000000000000 0000ffff888bc000
[80660.130524] bf40: 000000000048a170 0000ffff8870a578
0000000000001140 000000000000055f
[80660.138351] bf60: 00000000005c5000 0000000000000004
0000ffff879f9008 0000000000000000
[80660.146177] bf80: 0000000000000002 000000000048b530
2001000800400201 0000ffffdad60758
[80660.154004] bfa0: 000000000048b008 0000ffffdad5d390
0000ffff8870a518 0000ffffdad5d390
[80660.161830] bfc0: 0000ffff8870a3b8 0000000080000000
0000000000000004 0000000000000019
[80660.169656] bfe0: 0000000000000000 0000000000000000
0000000000000000 0000000000000000
[80660.177481] Call trace:
[80660.179928] Exception stack(0xffff81001f79bad0 to 0xffff81001f79bc00)
[80660.186365] bac0:
ffff800fdffbc160 0001000000000000
[80660.194192] bae0: ffff81001f79bca0 ffff00000828c694
ffff800fc0002c00 ffff81001ee78600
[80660.202017] bb00: ffff81001f79bb70 ffff00000820b57c
ffff800fcb2a6d88 ffff800fc0002c00
[80660.209843] bb20: 0000000000000001 ffff810008ddbf00
ffff81001f79bc30 ffff81001f79bc30
[80660.217670] bb40: 0000000000000000 ffff810fa0712be8
ffff800f81dfd680 ffff810fa0712be8
[80660.225496] bb60: 0000000000000001 ffff810008ddbf00
0000000000000000 ffff81001f37f300
[80660.233322] bb80: 00000000000026b9 ffff800fce927458
ffff800fce927438 0000000000000080
[80660.241148] bba0: 000000000000007f 0000000000000000
ffff800fce927500 0000000000000000
[80660.248974] bbc0: 00000000ffffffd0 00000000000e6a17
0000000000000018 00000003e8000000
[80660.256800] bbe0: 0000000000000000 0000ffff888bc000
ffff000008245768 0000ffff8870a578
[80660.264636] [<ffff00000828c694>] posix_locks_conflict+0x94/0xc0
[80660.270559] [<ffff00000828cd90>] posix_lock_inode+0x90/0x6b0
[80660.276220] [<ffff00000828d5f0>] vfs_lock_file+0x68/0x78
[80660.281537] [<ffff00000828d8bc>] do_lock_file_wait+0x54/0xe0
[80660.287199] [<ffff00000828ef10>] fcntl_setlk+0x1c0/0x308
[80660.292513] [<ffff000008245b84>] SyS_fcntl+0x41c/0x5b8
[80660.297653] [<ffff0000080836f0>] el0_svc_naked+0x24/0x28
[80660.302961] Code: a8c27bfd d65f03c0 d503201f f9401e61 (f9401e80)
[80660.309188] ---[ end trace aa50050684d3a3fe ]---
diff --git a/stress-lockf.c b/stress-lockf.c
index fb2f7b5f085e..232c269d0ec8 100644
--- a/stress-lockf.c
+++ b/stress-lockf.c
@@ -43,7 +43,7 @@
#define LOCK_FILE_SIZE (64 * 1024)
#define LOCK_SIZE (8)
-#define LOCK_MAX (1024)
+#define LOCK_MAX (8192)
typedef struct lockf_info {
off_t offset;
diff --git a/stress-ng.c b/stress-ng.c
index 7ab2ab1c42a6..de48d2a34738 100644
--- a/stress-ng.c
+++ b/stress-ng.c
@@ -1642,12 +1642,22 @@ static void kill_procs(const int sig)
int j;
for (j = 0; j < procs[i].started_procs; j++) {
- if (procs[i].pids[j])
- (void)kill(procs[i].pids[j], signum);
+ if (procs[i].pids[j].pid)
+ (void)kill(procs[i].pids[j].pid, signum);
}
}
}
+static int on_one_sock(unsigned cpu1, unsigned cpu2, unsigned cpus)
+{
+ unsigned mid = cpus / 2;
+ if (cpu1 < mid && cpu2 < mid)
+ return 1;
+ if (cpu1 >= mid && cpu2 >= mid)
+ return 1;
+ return 0;
+}
+
/*
* wait_procs()
* wait for procs
@@ -1670,7 +1680,8 @@ static void MLOCKED wait_procs(bool *success, bool *resource_success)
cpu_set_t proc_mask;
unsigned long int cpu = 0;
const uint32_t ticks_per_sec = stress_get_ticks_per_second() * 5;
- const useconds_t usec_sleep = ticks_per_sec ? 1000000 / ticks_per_sec : 1000000 / 250;
+ //const useconds_t usec_sleep = ticks_per_sec ? 1000000 / ticks_per_sec : 1000000 / 250;
+ const useconds_t usec_sleep = 50000;
while (opt_do_wait) {
const int32_t cpus = stress_get_processors_configured();
@@ -1685,7 +1696,9 @@ static void MLOCKED wait_procs(bool *success, bool *resource_success)
int j;
for (j = 0; j < procs[i].started_procs; j++) {
- const pid_t pid = procs[i].pids[j];
+ const pid_t pid = procs[i].pids[j].pid;
+ unsigned last_cpu =
+ procs[i].pids[j].last_cpu;
if (pid) {
cpu_set_t mask;
int32_t cpu_num;
@@ -1694,10 +1707,16 @@ static void MLOCKED wait_procs(bool *success, bool *resource_success)
cpu_num = mwc32() % cpus;
} while (!(CPU_ISSET(cpu_num, &proc_mask)));
+ if (on_one_sock(last_cpu,
+ cpu_num,
+ cpus))
+ cpu_num = cpus - cpu_num -1;
+
CPU_ZERO(&mask);
CPU_SET(cpu_num, &mask);
if (sched_setaffinity(pid, sizeof(mask), &mask) < 0)
goto do_wait;
+ procs[i].pids[j].last_cpu = cpu_num;
}
}
}
@@ -1713,7 +1732,7 @@ do_wait:
for (j = 0; j < procs[i].started_procs; j++) {
pid_t pid;
redo:
- pid = procs[i].pids[j];
+ pid = procs[i].pids[j].pid;
if (pid) {
int status, ret;
@@ -1752,7 +1771,7 @@ redo:
*success = false;
break;
}
- proc_finished(&procs[i].pids[j]);
+ proc_finished(&procs[i].pids[j].pid);
pr_dbg(stderr, "process [%d] terminated\n", ret);
} else if (ret == -1) {
/* Somebody interrupted the wait */
@@ -1760,7 +1779,7 @@ redo:
goto redo;
/* This child did not exist, mark it done anyhow */
if (errno == ECHILD)
- proc_finished(&procs[i].pids[j]);
+ proc_finished(&procs[i].pids[j].pid);
}
}
}
@@ -1901,7 +1920,7 @@ again:
default:
if (pid > -1) {
(void)setpgid(pid, pgrp);
- procs[i].pids[j] = pid;
+ procs[i].pids[j].pid = pid;
procs[i].started_procs++;
}
@@ -2952,7 +2971,7 @@ next_opt:
/* Sequential mode has no bogo ops threshold */
for (i = 0; i < STRESS_MAX; i++) {
procs[i].bogo_ops = 0;
- procs[i].pids = calloc(opt_sequential, sizeof(pid_t));
+ procs[i].pids = calloc(opt_sequential, sizeof(my_pid_t));
if (!procs[i].pids) {
pr_err(stderr, "cannot allocate pid list\n");
free_procs();
@@ -2980,7 +2999,7 @@ next_opt:
if (max_procs < procs[i].num_procs)
max_procs = procs[i].num_procs;
if (procs[i].num_procs) {
- procs[i].pids = calloc(procs[i].num_procs, sizeof(pid_t));
+ procs[i].pids = calloc(procs[i].num_procs, sizeof(my_pid_t));
if (!procs[i].pids) {
pr_err(stderr, "cannot allocate pid list\n");
free_procs();
@@ -3008,7 +3027,7 @@ next_opt:
if (max_procs < procs[i].num_procs)
max_procs = procs[i].num_procs;
if (procs[i].num_procs) {
- procs[i].pids = calloc(procs[i].num_procs, sizeof(pid_t));
+ procs[i].pids = calloc(procs[i].num_procs, sizeof(my_pid_t));
if (!procs[i].pids) {
pr_err(stderr, "cannot allocate pid list\n");
free_procs();
diff --git a/stress-ng.h b/stress-ng.h
index c5104a322e45..4f4098fc0d11 100644
--- a/stress-ng.h
+++ b/stress-ng.h
@@ -1713,7 +1713,12 @@ typedef struct {
} stress_t;
typedef struct {
- pid_t *pids; /* process id */
+ pid_t pid;
+ unsigned last_cpu;
+} my_pid_t;
+
+typedef struct {
+ my_pid_t *pids; /* process id */
int32_t started_procs; /* count of started processes */
int32_t num_procs; /* number of process per stressor */
uint64_t bogo_ops; /* number of bogo ops */
