proc: add /proc/<pid>/arch_status
Subsystems (4)
PATCH v19 1/3 proc: add /proc/<pid>/arch_status
The architecture specific information of the running processes could be useful to the userland. Add /proc/<pid>/arch_status interface support to examine process architecture specific information externally.
v3:
Add a /proc/<pid>/arch_state interface to expose per-task cpu specific state values.
v5:
Change the interface to /proc/pid/status since no other architectures need a separated CPU specific interface.
v18:
Change the interface to /proc/pid/arch_status. The interface /proc/<pid>/status should not be different on different architectures. It would be better to separate the arch staff into its own file /proc/<pid>/arch_status and make sure that everything in it is namespaced.
--- fs/proc/Kconfig | 4 ++++ fs/proc/base.c | 6 ++++++ include/linux/proc_fs.h | 9 +++++++++ 3 files changed, 19 insertions(+)
fs/proc/Kconfig +4 -0
@@ -97,3 +97,7 @@ config PROC_CHILDREN Say Y if you are running any user-space software which takes benefit from this interface. For example, rkt is such a piece of software. + +config PROC_PID_ARCH_STATUS + def_bool n + depends on PROC_FS
fs/proc/base.c +6 -0
@@ -3066,6 +3066,9 @@ static const struct pid_entry tgid_base_stuff[] = {#ifdef CONFIG_STACKLEAK_METRICS ONE("stack_depth", S_IRUGO, proc_stack_depth),#endif +#ifdef CONFIG_PROC_PID_ARCH_STATUS + ONE("arch_status", S_IRUGO, proc_pid_arch_status), +#endif };static int proc_tgid_base_readdir (struct file *file,struct dir_context *ctx)
@@ -3454,6 +3457,9 @@ static const struct pid_entry tid_base_stuff[] = {#ifdef CONFIG_LIVEPATCH ONE("patch_state", S_IRUSR, proc_pid_patch_state),#endif +#ifdef CONFIG_PROC_PID_ARCH_STATUS + ONE("arch_status", S_IRUGO, proc_pid_arch_status), +#endif };static int proc_tid_base_readdir (struct file *file,struct dir_context *ctx)
include/linux/proc_fs.h +9 -0
@@ -75,6 +75,15 @@ struct proc_dir_entry *proc_create_net_single_write(const char *name, umode_t mo void *data);extern struct pid *tgid_pidfd_to_pid (const struct file *file); +#ifdef CONFIG_PROC_PID_ARCH_STATUS +/* +* The architecture which selects CONFIG_PROC_PID_ARCH_STATUS must +* provide proc_pid_arch_status() definition. +*/ +int proc_pid_arch_status (struct seq_file *m,struct pid_namespace *ns, +struct pid *pid,struct task_struct *task); +#endif /* CONFIG_PROC_PID_ARCH_STATUS */ +#else /* CONFIG_PROC_FS */ static inline void proc_root_init (void )
Signature · 1 line
2.17.1
PATCH v19 2/3 x86,/proc/pid/arch_status: Add AVX-512 usage elapsed time
AVX-512 components use could cause core turbo frequency drop. So it's useful to expose AVX-512 usage elapsed time as a heuristic hint for the user space job scheduler to cluster the AVX-512 using tasks together.
Tensorflow example:
$ while [ 1 ]; do cat /proc/tid/arch_status | grep AVX512; sleep 1; done AVX512_elapsed_ms: 4 AVX512_elapsed_ms: 8 AVX512_elapsed_ms: 4
This means that 4 milliseconds have elapsed since the AVX512 usage of tensorflow task was detected when the task was scheduled out.
Or:
$ cat /proc/tid/arch_status | grep AVX512 AVX512_elapsed_ms: -1
The number '-1' indicates that no AVX512 usage recorded before thus the task unlikely has frequency drop issue.
User space tools may want to further check by:
$ perf stat --pid <pid> -e core_power.lvl2_turbo_license -- sleep 1
Performance counter stats for process id '3558':
3,251,565,961 core_power.lvl2_turbo_license
1.004031387 seconds time elapsedNon-zero counter value confirms that the task causes frequency drop.
--- arch/x86/Kconfig | 1 + arch/x86/kernel/fpu/xstate.c | 47 ++++++++++++++++++++++++++++++++++++ 2 files changed, 48 insertions(+)
arch/x86/Kconfig +1 -0
@@ -208,6 +208,7 @@ config X86 select USER_STACKTRACE_SUPPORT select VIRT_TO_BUS select X86_FEATURE_NAMES if PROC_FS + select PROC_PID_ARCH_STATUS if PROC_FS config INSTRUCTION_DECODER def_bool y
arch/x86/kernel/fpu/xstate.c +47 -0
56 lines not on this page · raw message
Signature · 1 line
2.17.1
tip-bot for Aubrey Li
merge bot[tip:x86/core] x86/process: Add AVX-512 usage elapsed time to /proc/pid/arch_status
x86/process: Add AVX-512 usage elapsed time to /proc/pid/arch_status
Commit-ID: 0c608dad2a771c0a11b6d12148d1a8b975e015d4 Gitweb: https://git.kernel.org/tip/0c608dad2a771c0a11b6d12148d1a8b975e015d4 Author: Aubrey Li <[email protected]> AuthorDate: Thu, 6 Jun 2019 09:22:35 +0800 Committer: Thomas Gleixner <[email protected]> CommitDate: Wed, 12 Jun 2019 11:42:13 +0200
x86/process: Add AVX-512 usage elapsed time to /proc/pid/arch_status
AVX-512 components usage can result in turbo frequency drop. So it's useful to expose AVX-512 usage elapsed time as a heuristic hint for user space job schedulers to cluster the AVX-512 using tasks together.
Examples:
$ while [ 1 ]; do cat /proc/tid/arch_status | grep AVX512; sleep 1; done AVX512_elapsed_ms: 4 AVX512_elapsed_ms: 8 AVX512_elapsed_ms: 4
This means that 4 milliseconds have elapsed since the tsks AVX512 usage was detected when the task was scheduled out.
$ cat /proc/tid/arch_status | grep AVX512 AVX512_elapsed_ms: -1
'-1' indicates that no AVX512 usage was recorded for this task.
The time exposed is not necessarily accurate when the arch_status file is read as the AVX512 usage is only evaluated when a task is scheduled out. Accurate usage information can be obtained with performance counters.
[ tglx: Massaged changelog ]
--- arch/x86/Kconfig | 1 + arch/x86/kernel/fpu/xstate.c | 47 ++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 48 insertions(+)
arch/x86/Kconfig +1 -0
@@ -217,6 +217,7 @@ config X86 select USER_STACKTRACE_SUPPORT select VIRT_TO_BUS select X86_FEATURE_NAMES if PROC_FS + select PROC_PID_ARCH_STATUS if PROC_FS config INSTRUCTION_DECODER def_bool y
arch/x86/kernel/fpu/xstate.c +47 -0
56 lines not on this page · raw message
PATCH v19 3/3 Documentation/filesystems/proc.txt: add arch_status file
In reply to Aubrey LiAdded /proc/<pid>/arch_status file, and added AVX512_elapsed_ms in /proc/<pid>/arch_status. Report it in Documentation/filesystems/proc.txt
--- Documentation/filesystems/proc.txt | 39 ++++++++++++++++++++++++++++++ 1 file changed, 39 insertions(+)
Documentation/filesystems/proc.txt +39 -0
@@ -45,6 +45,7 @@ Table of Contents 3.9 /proc/<pid>/map_files - Information about memory mapped files 3.10 /proc/<pid>/timerslack_ns - Task timerslack value 3.11 /proc/<pid>/patch_state - Livepatch patch operation state + 3.12 /proc/<pid>/arch_status - Task architecture specific information 4 Configuring procfs 4.1 Mount options
@@ -1948,6 +1949,44 @@ patched. If the patch is being enabled, then the task has already been patched. If the patch is being disabled, then the task hasn't been unpatched yet. +3.12 /proc/<pid>/arch_status - task architecture specific status +------------------------------------------------------------------- +When CONFIG_PROC_PID_ARCH_STATUS is enabled, this file displays the +architecture specific status of the task. + +Example +------- + $ cat /proc/6753/arch_status + AVX512_elapsed_ms: 8 + +Description +----------- + +x86 specific entries: +--------------------- + AVX512_elapsed_ms: + ------------------ + If AVX512 is supported on the machine, this entry shows the milliseconds + elapsed since the last time AVX512 usage was recorded. The recording + happens on a best effort basis when a task is scheduled out. This means + that the value depends on two factors: + + 1) The time which the task spent on the CPU without being scheduled + out. With CPU isolation and a single runnable task this can take + several seconds. + + 2) The time since the task was scheduled out last. Depending on the + reason for being scheduled out (time slice exhausted, syscall ...) + this can be arbitrary long time. + + As a consequence the value cannot be considered precise and authoritative + information. The application which uses this information has to be aware + of the overall scenario on the system in order to determine whether a + task is a real AVX512 user or not. + + A special value of '-1' indicates that no AVX512 usage was recorded, thus + the task is unlikely an AVX512 user, but depends on the workload and the + scheduling scenario, it also could be a false negative mentioned above. ------------------------------------------------------------------------------ Configuring procfs
Signature · 1 line
2.17.1
tip-bot for Aubrey Li
merge bot[tip:x86/core] Documentation/filesystems/proc.txt: Add arch_status file
Documentation/filesystems/proc.txt: Add arch_status file
Commit-ID: 711486fd18596315d42cebaac3dba8c408f60a3d Gitweb: https://git.kernel.org/tip/711486fd18596315d42cebaac3dba8c408f60a3d Author: Aubrey Li <[email protected]> AuthorDate: Thu, 6 Jun 2019 09:22:36 +0800 Committer: Thomas Gleixner <[email protected]> CommitDate: Wed, 12 Jun 2019 11:42:13 +0200
Documentation/filesystems/proc.txt: Add arch_status file
Add documentation for /proc/<pid>/arch_status file and the x86 specific AVX512_elapsed_ms entry in it.
[ tglx: Massage changelog ]
--- Documentation/filesystems/proc.txt | 40 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 40 insertions(+)
Documentation/filesystems/proc.txt +40 -0
@@ -45,6 +45,7 @@ Table of Contents 3.9 /proc/<pid>/map_files - Information about memory mapped files 3.10 /proc/<pid>/timerslack_ns - Task timerslack value 3.11 /proc/<pid>/patch_state - Livepatch patch operation state + 3.12 /proc/<pid>/arch_status - Task architecture specific information 4 Configuring procfs 4.1 Mount options
@@ -1948,6 +1949,45 @@ patched. If the patch is being enabled, then the task has already been patched. If the patch is being disabled, then the task hasn't been unpatched yet. +3.12 /proc/<pid>/arch_status - task architecture specific status +------------------------------------------------------------------- +When CONFIG_PROC_PID_ARCH_STATUS is enabled, this file displays the +architecture specific status of the task. + +Example +------- + $ cat /proc/6753/arch_status + AVX512_elapsed_ms: 8 + +Description +----------- + +x86 specific entries: +--------------------- + AVX512_elapsed_ms: + ------------------ + If AVX512 is supported on the machine, this entry shows the milliseconds + elapsed since the last time AVX512 usage was recorded. The recording + happens on a best effort basis when a task is scheduled out. This means + that the value depends on two factors: + + 1) The time which the task spent on the CPU without being scheduled + out. With CPU isolation and a single runnable task this can take + several seconds. + + 2) The time since the task was scheduled out last. Depending on the + reason for being scheduled out (time slice exhausted, syscall ...) + this can be arbitrary long time. + + As a consequence the value cannot be considered precise and authoritative + information. The application which uses this information has to be aware + of the overall scenario on the system in order to determine whether a + task is a real AVX512 user or not. Precise information can be obtained + with performance counters. + + A special value of '-1' indicates that no AVX512 usage was recorded, thus + the task is unlikely an AVX512 user, but depends on the workload and the + scheduling scenario, it also could be a false negative mentioned above. ------------------------------------------------------------------------------ Configuring procfs
Quoted 4 lines · On Thu, 6 Jun 2019 09:22:34 +0800 Aubrey Li <[email protected]> wrote:
The architecture specific information of the running processes could be useful to the userland. Add /proc/<pid>/arch_status interface support to examine process architecture specific information externally.
I'll grab these for some testing. I can merge them up if the x86 maintainers are OK with it all. However I think it's best that these be merged via an x86 tree, please.
tip-bot for Aubrey Li
merge bot[tip:x86/core] proc: Add /proc/<pid>/arch_status
In reply to Aubrey Liproc: Add /proc/<pid>/arch_status
Commit-ID: 68bc30bb9f33fc8d11e3d110d29e06490896a999 Gitweb: https://git.kernel.org/tip/68bc30bb9f33fc8d11e3d110d29e06490896a999 Author: Aubrey Li <[email protected]> AuthorDate: Thu, 6 Jun 2019 09:22:34 +0800 Committer: Thomas Gleixner <[email protected]> CommitDate: Wed, 12 Jun 2019 11:42:13 +0200
proc: Add /proc/<pid>/arch_status
Exposing architecture specific per process information is useful for various reasons. An example is the AVX512 usage on x86 which is important for task placement for power/performance optimizations.
Adding this information to the existing /prcc/pid/status file would be the obvious choise, but it has been agreed on that a explicit arch_status file is better in separating the generic and architecture specific information.
[ tglx: Massage changelog ]
--- fs/proc/Kconfig | 4 ++++ fs/proc/base.c | 6 ++++++ include/linux/proc_fs.h | 9 +++++++++ 3 files changed, 19 insertions(+)
fs/proc/Kconfig +4 -0
@@ -98,3 +98,7 @@ config PROC_CHILDREN Say Y if you are running any user-space software which takes benefit from this interface. For example, rkt is such a piece of software. + +config PROC_PID_ARCH_STATUS + def_bool n + depends on PROC_FS
fs/proc/base.c +6 -0
@@ -3061,6 +3061,9 @@ static const struct pid_entry tgid_base_stuff[] = {#ifdef CONFIG_STACKLEAK_METRICS ONE("stack_depth", S_IRUGO, proc_stack_depth),#endif +#ifdef CONFIG_PROC_PID_ARCH_STATUS + ONE("arch_status", S_IRUGO, proc_pid_arch_status), +#endif };static int proc_tgid_base_readdir (struct file *file,struct dir_context *ctx)
@@ -3449,6 +3452,9 @@ static const struct pid_entry tid_base_stuff[] = {#ifdef CONFIG_LIVEPATCH ONE("patch_state", S_IRUSR, proc_pid_patch_state),#endif +#ifdef CONFIG_PROC_PID_ARCH_STATUS + ONE("arch_status", S_IRUGO, proc_pid_arch_status), +#endif };static int proc_tid_base_readdir (struct file *file,struct dir_context *ctx)
include/linux/proc_fs.h +9 -0
@@ -75,6 +75,15 @@ struct proc_dir_entry *proc_create_net_single_write(const char *name, umode_t mo void *data);extern struct pid *tgid_pidfd_to_pid (const struct file *file); +#ifdef CONFIG_PROC_PID_ARCH_STATUS +/* +* The architecture which selects CONFIG_PROC_PID_ARCH_STATUS must +* provide proc_pid_arch_status() definition. +*/ +int proc_pid_arch_status (struct seq_file *m,struct pid_namespace *ns, +struct pid *pid,struct task_struct *task); +#endif /* CONFIG_PROC_PID_ARCH_STATUS */ +#else /* CONFIG_PROC_FS */ static inline void proc_root_init (void )