Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

plugin/cuda: disable CUDA plugin if /dev/nvidiactl isn't present #2479

Merged
merged 1 commit into from
Sep 15, 2024
+11 −2
Merged

plugin/cuda: disable CUDA plugin if /dev/nvidiactl isn't present #2479

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions criu/include/fault-injection.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,6 +22,7 @@ enum faults {
FI_DONT_USE_PAGEMAP_SCAN = 135,
FI_DUMP_CRASH = 136,
FI_DISABLE_FREEZE_CGROUP = 137,
FI_PLUGIN_CUDA_FORCE_ENABLE = 138,
FI_MAX,
};

Expand Down
10 changes: 9 additions & 1 deletion plugins/cuda/cuda_plugin.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,6 +5,7 @@
#include "pid.h"
#include "proc_parse.h"
#include "seize.h"
#include "fault-injection.h"

#include <common/list.h>
#include <compel/infect.h>
Expand Down Expand Up @@ -460,8 +461,15 @@ CR_PLUGIN_REGISTER_HOOK(CR_PLUGIN_HOOK__RESUME_DEVICES_LATE, cuda_plugin_resume_

int cuda_plugin_init(int stage)
{
int ret = cuda_checkpoint_supports_flag("--action");
int ret;

if (!fault_injected(FI_PLUGIN_CUDA_FORCE_ENABLE) && access("/dev/nvidiactl", F_OK)) {
rst0git marked this conversation as resolved.
Show resolved Hide resolved
pr_info("/dev/nvidiactl doesn't exist. The CUDA plugin is disabled.\n");
plugin_disabled = true;
return 0;
}

ret = cuda_checkpoint_supports_flag("--action");
if (ret == -1) {
pr_warn("check that %s is present in $PATH\n", CUDA_CHECKPOINT);
plugin_disabled = true;
Expand Down
2 changes: 1 addition & 1 deletion scripts/ci/run-ci-tests.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -363,4 +363,4 @@ make -C plugins/amdgpu/ test_topology_remap
./test/zdtm.py run -t zdtm/static/maps00 -t zdtm/static/maps02 --criu-plugin amdgpu
./test/zdtm.py run -t zdtm/static/maps00 -t zdtm/static/maps02 --criu-plugin amdgpu cuda

./test/zdtm.py run -t zdtm/static/sigpending -t zdtm/static/pthread00 --mocked-cuda-checkpoint
./test/zdtm.py run -t zdtm/static/sigpending -t zdtm/static/pthread00 --mocked-cuda-checkpoint --fault 138
Loading