mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-17 23:36:49 +07:00
cf4182f3d0
Add examples to show how to use nvme fault injection. Signed-off-by: Thomas Tai <thomas.tai@oracle.com> Reviewed-by: Eric Saint-Etienne <eric.saint.etienne@oracle.com> Signed-off-by: Karl Volz <karl.volz@oracle.com> Reviewed-by: Keith Busch <keith.busch@intel.com> Signed-off-by: Sagi Grimberg <sagi@grimberg.me> Signed-off-by: Jens Axboe <axboe@kernel.dk>
117 lines
4.0 KiB
Plaintext
117 lines
4.0 KiB
Plaintext
NVMe Fault Injection
|
||
====================
|
||
Linux's fault injection framework provides a systematic way to support
|
||
error injection via debugfs in the /sys/kernel/debug directory. When
|
||
enabled, the default NVME_SC_INVALID_OPCODE with no retry will be
|
||
injected into the nvme_end_request. Users can change the default status
|
||
code and no retry flag via the debugfs. The list of Generic Command
|
||
Status can be found in include/linux/nvme.h
|
||
|
||
Following examples show how to inject an error into the nvme.
|
||
|
||
First, enable CONFIG_FAULT_INJECTION_DEBUG_FS kernel config,
|
||
recompile the kernel. After booting up the kernel, do the
|
||
following.
|
||
|
||
Example 1: Inject default status code with no retry
|
||
---------------------------------------------------
|
||
|
||
mount /dev/nvme0n1 /mnt
|
||
echo 1 > /sys/kernel/debug/nvme0n1/fault_inject/times
|
||
echo 100 > /sys/kernel/debug/nvme0n1/fault_inject/probability
|
||
cp a.file /mnt
|
||
|
||
Expected Result:
|
||
|
||
cp: cannot stat ‘/mnt/a.file’: Input/output error
|
||
|
||
Message from dmesg:
|
||
|
||
FAULT_INJECTION: forcing a failure.
|
||
name fault_inject, interval 1, probability 100, space 0, times 1
|
||
CPU: 0 PID: 0 Comm: swapper/0 Not tainted 4.15.0-rc8+ #2
|
||
Hardware name: innotek GmbH VirtualBox/VirtualBox,
|
||
BIOS VirtualBox 12/01/2006
|
||
Call Trace:
|
||
<IRQ>
|
||
dump_stack+0x5c/0x7d
|
||
should_fail+0x148/0x170
|
||
nvme_should_fail+0x2f/0x50 [nvme_core]
|
||
nvme_process_cq+0xe7/0x1d0 [nvme]
|
||
nvme_irq+0x1e/0x40 [nvme]
|
||
__handle_irq_event_percpu+0x3a/0x190
|
||
handle_irq_event_percpu+0x30/0x70
|
||
handle_irq_event+0x36/0x60
|
||
handle_fasteoi_irq+0x78/0x120
|
||
handle_irq+0xa7/0x130
|
||
? tick_irq_enter+0xa8/0xc0
|
||
do_IRQ+0x43/0xc0
|
||
common_interrupt+0xa2/0xa2
|
||
</IRQ>
|
||
RIP: 0010:native_safe_halt+0x2/0x10
|
||
RSP: 0018:ffffffff82003e90 EFLAGS: 00000246 ORIG_RAX: ffffffffffffffdd
|
||
RAX: ffffffff817a10c0 RBX: ffffffff82012480 RCX: 0000000000000000
|
||
RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000
|
||
RBP: 0000000000000000 R08: 000000008e38ce64 R09: 0000000000000000
|
||
R10: 0000000000000000 R11: 0000000000000000 R12: ffffffff82012480
|
||
R13: ffffffff82012480 R14: 0000000000000000 R15: 0000000000000000
|
||
? __sched_text_end+0x4/0x4
|
||
default_idle+0x18/0xf0
|
||
do_idle+0x150/0x1d0
|
||
cpu_startup_entry+0x6f/0x80
|
||
start_kernel+0x4c4/0x4e4
|
||
? set_init_arg+0x55/0x55
|
||
secondary_startup_64+0xa5/0xb0
|
||
print_req_error: I/O error, dev nvme0n1, sector 9240
|
||
EXT4-fs error (device nvme0n1): ext4_find_entry:1436:
|
||
inode #2: comm cp: reading directory lblock 0
|
||
|
||
Example 2: Inject default status code with retry
|
||
------------------------------------------------
|
||
|
||
mount /dev/nvme0n1 /mnt
|
||
echo 1 > /sys/kernel/debug/nvme0n1/fault_inject/times
|
||
echo 100 > /sys/kernel/debug/nvme0n1/fault_inject/probability
|
||
echo 1 > /sys/kernel/debug/nvme0n1/fault_inject/status
|
||
echo 0 > /sys/kernel/debug/nvme0n1/fault_inject/dont_retry
|
||
|
||
cp a.file /mnt
|
||
|
||
Expected Result:
|
||
|
||
command success without error
|
||
|
||
Message from dmesg:
|
||
|
||
FAULT_INJECTION: forcing a failure.
|
||
name fault_inject, interval 1, probability 100, space 0, times 1
|
||
CPU: 1 PID: 0 Comm: swapper/1 Not tainted 4.15.0-rc8+ #4
|
||
Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006
|
||
Call Trace:
|
||
<IRQ>
|
||
dump_stack+0x5c/0x7d
|
||
should_fail+0x148/0x170
|
||
nvme_should_fail+0x30/0x60 [nvme_core]
|
||
nvme_loop_queue_response+0x84/0x110 [nvme_loop]
|
||
nvmet_req_complete+0x11/0x40 [nvmet]
|
||
nvmet_bio_done+0x28/0x40 [nvmet]
|
||
blk_update_request+0xb0/0x310
|
||
blk_mq_end_request+0x18/0x60
|
||
flush_smp_call_function_queue+0x3d/0xf0
|
||
smp_call_function_single_interrupt+0x2c/0xc0
|
||
call_function_single_interrupt+0xa2/0xb0
|
||
</IRQ>
|
||
RIP: 0010:native_safe_halt+0x2/0x10
|
||
RSP: 0018:ffffc9000068bec0 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff04
|
||
RAX: ffffffff817a10c0 RBX: ffff88011a3c9680 RCX: 0000000000000000
|
||
RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000
|
||
RBP: 0000000000000001 R08: 000000008e38c131 R09: 0000000000000000
|
||
R10: 0000000000000000 R11: 0000000000000000 R12: ffff88011a3c9680
|
||
R13: ffff88011a3c9680 R14: 0000000000000000 R15: 0000000000000000
|
||
? __sched_text_end+0x4/0x4
|
||
default_idle+0x18/0xf0
|
||
do_idle+0x150/0x1d0
|
||
cpu_startup_entry+0x6f/0x80
|
||
start_secondary+0x187/0x1e0
|
||
secondary_startup_64+0xa5/0xb0
|