Some new features for the preempt/irqsoff tracers
Subsystems (3)
v6 cover Some new features for the preempt/irqsoff tracers
Hello all,
Changes in v5:
- [PATCH 1/4]:
* Using the irq_work mechanism instead of the games with linked lists, percpu variables and modifications to the scheduling and idle code.
- [PATCH 2/4]:
* Updated the copyright message, adding my own name and what I did.
- [PATCH 3/4]:
* Added my own name as author to the copyright message.
- [PACTH 4/4]:
* Improved the build on sh architecture with gcc 7.4.0 by including linux/types.h. The build on sh architecture still fails for me later in the build process with an ICE error from the compiler but the same failure also happens without any of my patches.
This series is meant to address two issues with the latency tracing.
The first three patches provide a method to trace latencies that always occurs very close to each other and to differentiate between them, in spite of the fact that the latency tracers work in overwrite mode.
[PATCH 1/4] This implement fs notification for tracing_max_latency. It makes it possible for userspace to detect when a new latency has been detected.
[PATCH 2/4] This extends the preemptirq_delay_test module so that it can be used to generate a burst of closely occurring latencies.
[PATCH 3/4] This adds a user space program to the tools directory that utilizes the fs notification feature and a randomized algorithm to print out any of the latencies in a burst with approximately equal probability.
The last patch is not directly connected but earlier it didn't apply cleanly on its own. However, now it does, so in principle it could be applied separately from the others.
[PATCH 4/4] This adds the option console-latency to the trace options. This makes it possible to enable tracing of console latencies.
best regards,
Viktor
Viktor Rosendahl (4):
ftrace: Implement fs notification for tracing_max_latency
preemptirq_delay_test: Add the burst feature and a sysfs trigger Add the latency-collector to tools
ftrace: Add an option for tracing console latencies
include/linux/irqflags.h | 22 + kernel/printk/printk.c | 6 +- kernel/trace/Kconfig | 6 +- kernel/trace/preemptirq_delay_test.c | 147 +++- kernel/trace/trace.c | 75 +- kernel/trace/trace.h | 19 + kernel/trace/trace_hwlat.c | 4 +- kernel/trace/trace_irqsoff.c | 12 + tools/Makefile | 14 +- tools/trace/Makefile | 20 + tools/trace/latency-collector.c | 1212 ++++++++++++++++++++++++++ 11 files changed, 1504 insertions(+), 33 deletions(-) create mode 100644 tools/trace/Makefile create mode 100644 tools/trace/latency-collector.c
Signature · 1 line
2.17.1
PATCH v6 1/4 ftrace: Implement fs notification for tracing_max_latency
This patch implements the feature that the tracing_max_latency file, e.g. /sys/kernel/debug/tracing/tracing_max_latency will receive notifications through the fsnotify framework when a new latency is available.
One particularly interesting use of this facility is when enabling threshold tracing, through /sys/kernel/debug/tracing/tracing_thresh, together with the preempt/irqsoff tracers. This makes it possible to implement a user space program that can, with equal probability, obtain traces of latencies that occur immediately after each other in spite of the fact that the preempt/irqsoff tracers operate in overwrite mode.
This facility works with the hwlat, preempt/irqsoff, and wakeup tracers.
The tracers may call the latency_fsnotify() from places such as __schedule() or do_idle(); this makes it impossible to call queue_work() directly without risking a deadlock. The same would happen with a softirq, kernel thread or tasklet. For this reason we use the irq_work mechanism to call queue_work().
--- kernel/trace/trace.c | 75 +++++++++++++++++++++++++++++++++++++- kernel/trace/trace.h | 18 +++++++++ kernel/trace/trace_hwlat.c | 4 +- 3 files changed, 94 insertions(+), 3 deletions(-)
kernel/trace/trace.c +73 -2
@@ -44,6 +44,9 @@#include <linux/trace.h> #include <linux/sched/clock.h> #include <linux/sched/rt.h> +#include <linux/fsnotify.h> +#include <linux/irq_work.h> +#include <linux/workqueue.h> #include "trace.h" #include "trace_output.h"
@@ -1480,6 +1483,74 @@ static ssize_t trace_seq_to_buffer(struct trace_seq *s, void *buf, size_t cnt)unsigned long __read_mostly tracing_thresh; +#if (defined(CONFIG_TRACER_MAX_TRACE ) || defined(CONFIG_HWLAT_TRACER )) && \ + defined(CONFIG_FSNOTIFY ) + +static const struct file_operations tracing_max_lat_fops; +static struct workqueue_struct *fsnotify_wq; + +static void latency_fsnotify_workfn (struct work_struct *work) +{ + struct trace_array *tr = container_of(work, struct trace_array, + fsnotify_work); +fsnotify (tr->d_max_latency->d_inode,FS_MODIFY , + tr->d_max_latency->d_inode,FSNOTIFY_EVENT_INODE ,NULL ,0 ); +} + +static void latency_fsnotify_workfn_irq (struct irq_work *iwork) +{ + struct trace_array *tr = container_of(iwork, struct trace_array, + fsnotify_irqwork); +queue_work (fsnotify_wq, &tr->fsnotify_work); +} + +static void trace_create_maxlat_file (struct trace_array *tr, +struct dentry *d_tracer) +{ +INIT_WORK (&tr->fsnotify_work, latency_fsnotify_workfn); +init_irq_work (&tr->fsnotify_irqwork, latency_fsnotify_workfn_irq); + tr->d_max_latency =trace_create_file ("tracing_max_latency" ,0644 , + d_tracer, &tr->max_latency, + &tracing_max_lat_fops); +} + +__init static int latency_fsnotify_init (void ) +{ + fsnotify_wq =alloc_workqueue ("tr_max_lat_wq" , +WQ_UNBOUND |WQ_HIGHPRI ,0 ); +if (!fsnotify_wq) { +pr_err ("Unable to allocate tr_max_lat_wq\n" ); +return -ENOMEM ; + } +return 0 ; +} + +late_initcall_sync (latency_fsnotify_init); + +void latency_fsnotify (struct trace_array *tr) +{ +if (!fsnotify_wq) +return ; +/* +* We cannot call queue_work(&tr->fsnotify_work) from here because it's +* possible that we are called from __schedule() or do_idle(), which +* could cause a deadlock. +*/ +irq_work_queue (&tr->fsnotify_irqwork); +} + +/* +* (defined(CONFIG_TRACER_MAX_TRACE) || defined(CONFIG_HWLAT_TRACER)) && \ +* defined(CONFIG_FSNOTIFY) +*/ +#else + +#define trace_create_maxlat_file (tr, d_tracer) \ + trace_create_file("tracing_max_latency", 0644, d_tracer, \ + &tr->max_latency, &tracing_max_lat_fops) + +#endif +#ifdef CONFIG_TRACER_MAX_TRACE /* * Copy the new maximum trace into the separate maximum-trace
@@ -1518,6 +1589,7 @@ __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)/* record this tasks comm */ tracing_record_cmdline (tsk); +latency_fsnotify (tr); }/**
@@ -8550,8 +8622,7 @@ init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer)create_trace_options_dir (tr);#if defined(CONFIG_TRACER_MAX_TRACE ) || defined(CONFIG_HWLAT_TRACER ) -trace_create_file ("tracing_max_latency" ,0644 , d_tracer, - &tr->max_latency, &tracing_max_lat_fops); +trace_create_maxlat_file (tr, d_tracer);#endif if (ftrace_create_function_files (tr, d_tracer))
kernel/trace/trace.h +18 -0
@@ -16,6 +16,8 @@#include <linux/trace_events.h> #include <linux/compiler.h> #include <linux/glob.h> +#include <linux/irq_work.h> +#include <linux/workqueue.h> #ifdef CONFIG_FTRACE_SYSCALLS #include <asm/unistd.h> /* For NR_SYSCALLS */
@@ -264,6 +266,11 @@ struct trace_array {#endif #if defined(CONFIG_TRACER_MAX_TRACE ) || defined(CONFIG_HWLAT_TRACER )unsigned long max_latency; +#ifdef CONFIG_FSNOTIFY +struct dentry *d_max_latency; +struct work_struct fsnotify_work; +struct irq_work fsnotify_irqwork; +#endif #endif struct trace_pid_list __rcu *filtered_pids;/*
@@ -785,6 +792,17 @@ void update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu);#endif /* CONFIG_TRACER_MAX_TRACE */ +#if (defined(CONFIG_TRACER_MAX_TRACE ) || defined(CONFIG_HWLAT_TRACER )) && \ + defined(CONFIG_FSNOTIFY ) + +void latency_fsnotify (struct trace_array *tr); + +#else + +#define latency_fsnotify (tr) do { } while (0) + +#endif +#ifdef CONFIG_STACKTRACE void __trace_stack (struct trace_array *tr,unsigned long flags,int skip,int pc);
kernel/trace/trace_hwlat.c +3 -1
@@ -254,8 +254,10 @@ static int get_sample(void)trace_hwlat_sample (&s);/* Keep a running maximum ever recorded hardware latency */ -if (sample > tr->max_latency) +if (sample > tr->max_latency) { tr->max_latency = sample; +latency_fsnotify (tr); + } } out:
Signature · 1 line
2.17.1
Re: [PATCH v6 1/4] ftrace: Implement fs notification for tracing_max_latency
Quoted 16 lines · Viktor Rosendahl
This patch implements the feature that the
tracing_max_latencyfile, e.g./sys/kernel/debug/tracing/tracing_max_latencywill receive notifications through the fsnotify framework when a new latency is available.One particularly interesting use of this facility is when enabling threshold tracing, through
/sys/kernel/debug/tracing/tracing_thresh, together with the preempt/irqsoff tracers. This makes it possible to implement a user space program that can, with equal probability, obtain traces of latencies that occur immediately after each other in spite of the fact that the preempt/irqsoff tracers operate in overwrite mode.This facility works with the hwlat, preempt/irqsoff, and wakeup tracers.
Quoted 6 lines
The tracers may call the
latency_fsnotify()from places such as__schedule()ordo_idle(); this makes it impossible to callqueue_work()directly without risking a deadlock. The same would happen with a softirq, kernel thread or tasklet. For this reason we use theirq_workmechanism to callqueue_work().Signed-off-by Viktor Rosendahl <[email protected]>
Looks better now, one comment below:
Quoted 53 lines
--- kernel/trace/trace.c | 75 +++++++++++++++++++++++++++++++++++++- kernel/trace/trace.h | 18 +++++++++ kernel/trace/trace_hwlat.c | 4 +- 3 files changed, 94 insertions(+), 3 deletions(-)kernel/trace/trace.c +32
-0@@ -44,6 +44,9 @@#include <linux/trace.h> #include <linux/sched/clock.h> #include <linux/sched/rt.h> +#include <linux/fsnotify.h> +#include <linux/irq_work.h> +#include <linux/workqueue.h> #include "trace.h" #include "trace_output.h" @@ -1480,6 +1483,74 @@ static ssize_t trace_seq_to_buffer(struct trace_seq *s, void *buf, size_t cnt)unsigned long __read_mostly tracing_thresh; +#if (defined(CONFIG_TRACER_MAX_TRACE ) || defined(CONFIG_HWLAT_TRACER )) && \ + defined(CONFIG_FSNOTIFY ) + +static const struct file_operations tracing_max_lat_fops; +static struct workqueue_struct *fsnotify_wq; + +static void latency_fsnotify_workfn (struct work_struct *work) +{ + struct trace_array *tr = container_of(work, struct trace_array, + fsnotify_work); +fsnotify (tr->d_max_latency->d_inode,FS_MODIFY , + tr->d_max_latency->d_inode,FSNOTIFY_EVENT_INODE ,NULL ,0 ); +} + +static void latency_fsnotify_workfn_irq (struct irq_work *iwork) +{ + struct trace_array *tr = container_of(iwork, struct trace_array, + fsnotify_irqwork); +queue_work (fsnotify_wq, &tr->fsnotify_work); +} + +static void trace_create_maxlat_file (struct trace_array *tr, +struct dentry *d_tracer) +{ +INIT_WORK (&tr->fsnotify_work, latency_fsnotify_workfn); +init_irq_work (&tr->fsnotify_irqwork, latency_fsnotify_workfn_irq); + tr->d_max_latency =trace_create_file ("tracing_max_latency" ,0644 , + d_tracer, &tr->max_latency, + &tracing_max_lat_fops);
kernel/trace/trace.c static ssize_t trace_seq_to_buffer(struct trace_seq *s, void *buf, size_t cnt) · line 1524
Quoted 10 lines
kernel/trace/trace.c +10
-0+} + +__init static int latency_fsnotify_init (void ) +{ + fsnotify_wq =alloc_workqueue ("tr_max_lat_wq" , +WQ_UNBOUND |WQ_HIGHPRI ,0 ); +if (!fsnotify_wq) { +pr_err ("Unable to allocate tr_max_lat_wq\n" ); +return -ENOMEM ; + }
Why not just use the system workqueue instead of adding another workqueue?
thanks,
- Joel
Re: [PATCH v6 1/4] ftrace: Implement fs notification for tracing_max_latency
Quoted 1 line · Joel Fernandes
On Thu, Sep 05, 2019 at 03:25:45PM +0200, Viktor Rosendahl wrote:
<clip>
Quoted 12 lines
kernel/trace/trace.c static ssize_t trace_seq_to_buffer(struct trace_seq *s, void *buf, size_t cnt) · line 1524
Quoted 9 lines
kernel/trace/trace.c +9
-0+ +__init static int latency_fsnotify_init (void ) +{ + fsnotify_wq =alloc_workqueue ("tr_max_lat_wq" , +WQ_UNBOUND |WQ_HIGHPRI ,0 ); +if (!fsnotify_wq) { +pr_err ("Unable to allocate tr_max_lat_wq\n" ); +return -ENOMEM ; + }Why not just use the system workqueue instead of adding another workqueue?
For the the latency-collector to work properly in the worst case, when a new latency occurs immediately, the fsnotify must be received in less time than what the threshold is set to. If we always are slower we will always lose certain latencies.
My intention was to minimize latency in some important cases, so that user space receives the notification sooner rather than later.
There doesn't seem to be any system workqueue with WQ_UNBOUND and WQ_HIGHPRI. My thinking was that WQ_UNBOUND might help with the latency in some important cases.
If we use:
queue_work(system_highpri_wq, &tr->fsnotify_work);
then the work will (almost) always execute on the same CPU but if we are unlucky that CPU could be too busy while there could be another CPU in the system that would be able to process the work soon enough.
queue_work_on() could be used to queue the work on another CPU but it seems difficult to select the right CPU.
best regards,
Viktor
Re: [PATCH v6 1/4] ftrace: Implement fs notification for tracing_max_latency
Quoted 30 lines · Viktor Rosendahl
Quoted 1 line · Joel Fernandes
On Thu, Sep 05, 2019 at 03:25:45PM +0200, Viktor Rosendahl wrote:
<clip>
Quoted 12 lines
kernel/trace/trace.c static ssize_t trace_seq_to_buffer(struct trace_seq *s, void *buf, size_t cnt) · line 1524
Quoted 9 lines
kernel/trace/trace.c +9
-0+ +__init static int latency_fsnotify_init (void ) +{ + fsnotify_wq =alloc_workqueue ("tr_max_lat_wq" , +WQ_UNBOUND |WQ_HIGHPRI ,0 ); +if (!fsnotify_wq) { +pr_err ("Unable to allocate tr_max_lat_wq\n" ); +return -ENOMEM ; + }Why not just use the system workqueue instead of adding another workqueue?
For the the latency-collector to work properly in the worst case, when a new latency occurs immediately, the fsnotify must be received in less time than what the threshold is set to. If we always are slower we will always lose certain latencies.
My intention was to minimize latency in some important cases, so that user space receives the notification sooner rather than later.
There doesn't seem to be any system workqueue with
WQ_UNBOUNDandWQ_HIGHPRI. My thinking was thatWQ_UNBOUNDmight help with the latency in some important cases.If we use:
Quoted 8 lines
queue_work(system_highpri_wq, &tr->fsnotify_work);then the work will (almost) always execute on the same CPU but if we are unlucky that CPU could be too busy while there could be another CPU in the system that would be able to process the work soon enough.
queue_work_on()could be used to queue the work on another CPU but it seems difficult to select the right CPU.
Ok, a separate WQ is fine with me as such since the preempt/irq events are on a debug kernel anyway.
I'll keep reviewing your patches next few days, I am at the LPC conference so might be a bit slow. Overall I think the series look like its maturing and getting close.
thanks,
- Joel
Re: [PATCH v6 1/4] ftrace: Implement fs notification for tracing_max_latency
Quoted 36 lines · Viktor Rosendahl
Quoted 36 lines · Joel Fernandes
Quoted 1 line · Viktor Rosendahl
<clip>
Quoted 12 lines
kernel/trace/trace.c static ssize_t trace_seq_to_buffer(struct trace_seq *s, void *buf, size_t cnt) · line 1524
Quoted 9 lines
kernel/trace/trace.c +9
-0+ +__init static int latency_fsnotify_init (void ) +{ + fsnotify_wq =alloc_workqueue ("tr_max_lat_wq" , +WQ_UNBOUND |WQ_HIGHPRI ,0 ); +if (!fsnotify_wq) { +pr_err ("Unable to allocate tr_max_lat_wq\n" ); +return -ENOMEM ; + }Why not just use the system workqueue instead of adding another workqueue?
For the the latency-collector to work properly in the worst case, when a new latency occurs immediately, the fsnotify must be received in less time than what the threshold is set to. If we always are slower we will always lose certain latencies.
My intention was to minimize latency in some important cases, so that user space receives the notification sooner rather than later.
There doesn't seem to be any system workqueue with
WQ_UNBOUNDandWQ_HIGHPRI. My thinking was thatWQ_UNBOUNDmight help with the latency in some important cases.If we use:
queue_work(system_highpri_wq, &tr->fsnotify_work);then the work will (almost) always execute on the same CPU but if we are unlucky that CPU could be too busy while there could be another CPU in the system that would be able to process the work soon enough.
Quoted 5 lines
Quoted 2 lines
queue_work_on()could be used to queue the work on another CPU but it seems difficult to select the right CPU.Ok, a separate WQ is fine with me as such since the preempt/irq events are on a debug kernel anyway.
Keep in mind that this feature is also enabled by the wakeup tracers and by hwlat. These are often enabled by production kernels.
I guess it would be possible to add some ifdefs so that we create a new workqueue only if preempt/irqsoff tracing is enabled in the kernel config and use system_highpri_wq if we only have the wakeup and hwlat tracers in the config.
However, I don't really like adding yet some more ifdefs to the code.
Since a new workqueue will not necessariy create a new worker thread nowadays, I thought that it would be OK with a new unbound workqueue, which should not add much to the tendency to create more worker threads.
Quoted 5 lines
I'll keep reviewing your patches next few days, I am at the LPC conference so might be a bit slow. Overall I think the series look like its maturing and getting close.
Ok, thanks. Could you let me know when you have looked through it all so that I know when it makes sense to make another reroll of the series?
best regards,
Viktor
PATCH v6 2/4 preemptirq_delay_test: Add the burst feature and a sysfs trigger
In reply to Viktor RosendahlThis burst feature enables the user to generate a burst of preempt/irqsoff latencies. This makes it possible to test whether we are able to detect latencies that systematically occur very close to each other.
The maximum burst size is 10. We also create 10 identical test functions, so that we get 10 different backtraces; this is useful when we want to test whether we can detect all the latencies in a burst. Otherwise, there would be no easy way of differentiating between which latency in a burst was captured by the tracer.
In addition, there is a sysfs trigger, so that it's not necessary to reload the module to repeat the test. The trigger will appear as /sys/kernel/preemptirq_delay_test/trigger in sysfs.
--- kernel/trace/Kconfig | 6 +- kernel/trace/preemptirq_delay_test.c | 147 +++++++++++++++++++++++---- 2 files changed, 131 insertions(+), 22 deletions(-)
kernel/trace/Kconfig +3 -3
@@ -751,9 +751,9 @@ config PREEMPTIRQ_DELAY_TEST configurable delay. The module busy waits for the duration of the critical section. - For example, the following invocation forces a one-time irq-disabled - critical section for 500us: - modprobe preemptirq_delay_test test_mode=irq delay=500000 + For example, the following invocation generates a burst of three + irq-disabled critical sections for 500us: + modprobe preemptirq_delay_test test_mode=irq delay=500 burst_size=3 If unsure, say N
kernel/trace/preemptirq_delay_test.c +128 -19
189 lines not on this page · raw message
Signature · 1 line
2.17.1
PATCH v6 3/4 Add the latency-collector to tools
In reply to Viktor RosendahlThis is a tool that is intended to work around the fact that the preemptoff, irqsoff, and preemptirqsoff tracers only work in overwrite mode. The idea is to act randomly in such a way that we do not systematically lose any latencies, so that if enough testing is done, all latencies will be captured. If the same burst of latencies is repeated, then sooner or later we will have captured all the latencies.
It also works with the wakeup_dl, wakeup_rt, wakeup, and hwlat tracers. However, in that case it is probably not useful to use the random sleep functionality.
The reason why it may be desirable to catch all latencies with a long test campaign is that for some organizations, it's necessary to test the kernel in the field and not practical for developers to work iteratively with field testers. Because of cost and project schedules it is not possible to start a new test campaign every time a latency problem has been fixed.
It uses inotify to detect changes to /sys/kernel/debug/tracing/trace. When a latency is detected, it will either sleep or print immediately, depending on a function that act as an unfair coin toss.
If immediate print is chosen, it means that we open /sys/kernel/debug/tracing/trace and thereby cause a blackout period that will hide any subsequent latencies.
If sleep is chosen, it means that we wait before opening /sys/kernel/debug/tracing/trace, by default for 1000 ms, to see if there is another latency during this period. If there is, then we will lose the previous latency. The coin will be tossed again with a different probability, and we will either print the new latency, or possibly a subsequent one.
The probability for the unfair coin toss is chosen so that there is equal probability to obtain any of the latencies in a burst. However, this assumes that we make an assumption of how many latencies there can be. By default the program assumes that there are no more than 2 latencies in a burst, the probability of immediate printout will be:
1/2 and 1
Thus, the probability of getting each of the two latencies will be 1/2.
If we ever find that there is more than one latency in a series, meaning that we reach the probability of 1, then the table will be expanded to:
1/3, 1/2, and 1
Thus, we assume that there are no more than three latencies and each with a probability of 1/3 of being captured. If the probability of 1 is reached in the new table, that is we see more than two closely occurring latencies, then the table will again be extended, and so on.
On my systems, it seems like this scheme works fairly well, as long as the latencies we trace are long enough, 300 us seems to be enough. This userspace program receive the inotify event at the end of a latency, and it has time until the end of the next latency to react, that is to open /sys/kernel/debug/tracing/trace. Thus, if we trace latencies that are >300 us, then we have at least 300 us to react.
The minimum latency will of course not be 300 us on all systems, it will depend on the hardware, kernel version, workload and configuration.
Example output:
root@myhost:~# echo 100 > /sys/kernel/debug/tracing/tracing_thresh root@myhost:~# echo preemptirqsoff > /sys/kernel/debug/tracing/current_tracer root@myhost:~# latency-collector -rvv -a 11 & [1] 4915 root@myhost:~# Running with policy rr and priority 99. Using 3 print threads. /sys/kernel/debug/tracing/trace will be printed with random delay Start size of the probability table: 11 Print a message when prob. table table changes size: true Print a warning when an event has been lost: true Sleep time is: 1000 ms Initializing probability table to 11 Thread 4916 runs with policy rr and priority 99 Thread 4917 runs with policy rr and priority 99 Thread 4918 runs with policy rr and priority 99 Thread 4919 runs with policy rr and priority 99
root@myhost:~# modprobe preemptirq_delay_test delay=105 test_mode=alternate burst_size=10 2850.638308 Latency 1 printout skipped due to random delay 2850.638383 Latency 2 printout skipped due to random delay 2850.638497 Latency 3 immediate print
Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
BEGIN <<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
alternat-4922 6d... 0us!: execute_preemptirqtest <-preemptirqtest_2 alternat-4922 6d... 106us : execute_preemptirqtest <-preemptirqtest_2 alternat-4922 6d... 106us : tracer_hardirqs_on <-preemptirqtest_2 alternat-4922 6d... 108us : <stack trace>
=> preemptirqtest_2
=> preemptirq_delay_run
=> kthread
=> ret_from_fork
Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
END <<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
In the example above, we randomly, happened to get the third latency in a burst burst of 10. If the experiment is repeated enough times, we will get all 10.
Sometimes, there will be lost latencies, so that we get:
3054.078294 Latency 44 printout skipped due to inotify loop ..or:
3211.957685 Latency 112 printout skipped due to print loop
In my experience, these are not frequent enough to be a problem.
Also, we do not really lose any latency in these cases, it's more like we get another latency than what was intended by the design.
--- tools/Makefile | 14 +- tools/trace/Makefile | 20 + tools/trace/latency-collector.c | 1212 +++++++++++++++++++++++++++++++ 3 files changed, 1240 insertions(+), 6 deletions(-) create mode 100644 tools/trace/Makefile create mode 100644 tools/trace/latency-collector.c
tools/Makefile +8 -6
@@ -30,6 +30,7 @@ help: @echo ' spi - spi tools' @echo ' objtool - an ELF object analysis tool' @echo ' tmon - thermal monitoring and tuning tool' + @echo ' trace - misc tracing tools' @echo ' turbostat - Intel CPU idle stats and freq reporting tool' @echo ' usb - USB testing tools' @echo ' virtio - vhost test module'
@@ -63,7 +64,7 @@ acpi: FORCE cpupower: FORCE $(call descend,power/$@) -cgroup firewire hv guest spi usb virtio vm bpf iio gpio objtool leds wmi pci firmware debugging: FORCE +cgroup firewire hv guest spi usb virtio vm bpf iio gpio objtool leds wmi pci firmware debugging trace: FORCE $(call descend,$@) liblockdep: FORCE
@@ -99,7 +100,7 @@ all: acpi cgroup cpupower gpio hv firewire liblockdep \ perf selftests spi turbostat usb \ virtio vm bpf x86_energy_perf_policy \ tmon freefall iio objtool kvm_stat wmi \ - pci debugging + pci debugging trace acpi_install: $(call descend,power/$(@:_install=),install)
@@ -107,7 +108,7 @@ acpi_install: cpupower_install: $(call descend,power/$(@:_install=),install) -cgroup_install firewire_install gpio_install hv_install iio_install perf_install spi_install usb_install virtio_install vm_install bpf_install objtool_install wmi_install pci_install debugging_install: +cgroup_install firewire_install gpio_install hv_install iio_install perf_install spi_install usb_install virtio_install vm_install bpf_install objtool_install wmi_install pci_install debugging_install trace_install: $(call descend,$(@:_install=),install) liblockdep_install:
@@ -133,7 +134,8 @@ install: acpi_install cgroup_install cpupower_install gpio_install \ perf_install selftests_install turbostat_install usb_install \ virtio_install vm_install bpf_install x86_energy_perf_policy_install \ tmon_install freefall_install objtool_install kvm_stat_install \ - wmi_install pci_install debugging_install intel-speed-select_install + wmi_install pci_install debugging_install intel-speed-select_install \ + trace_install acpi_clean: $(call descend,power/acpi,clean)
@@ -141,7 +143,7 @@ acpi_clean: cpupower_clean: $(call descend,power/cpupower,clean) -cgroup_clean hv_clean firewire_clean spi_clean usb_clean virtio_clean vm_clean wmi_clean bpf_clean iio_clean gpio_clean objtool_clean leds_clean pci_clean firmware_clean debugging_clean: +cgroup_clean hv_clean firewire_clean spi_clean usb_clean virtio_clean vm_clean wmi_clean bpf_clean iio_clean gpio_clean objtool_clean leds_clean pci_clean firmware_clean debugging_clean trace_clean: $(call descend,$(@:_clean=),clean) liblockdep_clean:
@@ -180,6 +182,6 @@ clean: acpi_clean cgroup_clean cpupower_clean hv_clean firewire_clean \ vm_clean bpf_clean iio_clean x86_energy_perf_policy_clean tmon_clean \ freefall_clean build_clean libbpf_clean libsubcmd_clean liblockdep_clean \ gpio_clean objtool_clean leds_clean wmi_clean pci_clean firmware_clean debugging_clean \ - intel-speed-select_clean + intel-speed-select_clean trace_clean .PHONY: FORCE
tools/trace/Makefile new file +20 -0
@@ -0,0 +1,20 @@ +# SPDX-License-Identifier: GPL-2.0 +# Makefile for vm tools +# +TARGETS = latency-collector +CFLAGS = -Wall -Wextra -g -O2 +LDFLAGS = -lpthread + +all: $(TARGETS) + +%: %.c + $(CC) $(CFLAGS) -o $@ $< $(LDFLAGS) + +clean: + $(RM) latency-collector + +sbindir ?= /usr/sbin + +install: all + install -d $(DESTDIR)$(sbindir) + install -m 755 -p $(TARGETS) $(DESTDIR)$(sbindir)
tools/trace/latency-collector.c new file +1212 -0
1,212 lines not on this page · raw message
Signature · 1 line
2.17.1
PATCH v6 4/4 ftrace: Add an option for tracing console latencies
In reply to Viktor RosendahlThis new trace option "console-latency" will enable the latency tracers to trace the console latencies. Previously this has always been implicitely disabled. I guess this is because they are considered to be well known and unavoidable.
However, for some organizations it may nevertheless be desirable to trace them. Basically, we want to be able to tell that there are latencies in the system under test because someone has incorrectly enabled the serial console.
--- include/linux/irqflags.h | 22 ++++++++++++++++++++++ kernel/printk/printk.c | 6 ++++-- kernel/trace/trace.h | 1 + kernel/trace/trace_irqsoff.c | 12 ++++++++++++ 4 files changed, 39 insertions(+), 2 deletions(-)
include/linux/irqflags.h +22 -0
@@ -13,6 +13,7 @@#define _LINUX_TRACE_IRQFLAGS_H#include <linux/typecheck.h> +#include <linux/types.h> #include <asm/irqflags.h> /* Currently trace_softirqs_on/off is used only by lockdep */
@@ -68,9 +69,30 @@ do { \defined (CONFIG_PREEMPT_TRACER) extern void stop_critical_timings(void);extern void start_critical_timings (void ); +extern bool console_tracing_disabled (void ); + +# define console_stop_critical_timings (flag) \ + do { \ + typecheck(bool, flag); \ + flag = console_tracing_disabled(); \ + if (flag) \ + stop_critical_timings(); \ + } while (0) + +# define console_start_critical_timings (flag) \ + do { \ + typecheck(bool, flag); \ + if (flag) \ + start_critical_timings(); \ + } while (0) +#else # define stop_critical_timings () do { } while (0)# define start_critical_timings () do { } while (0) +# define console_stop_critical_timings (flag) \ + do { typecheck(bool, flag); } while (0) +# define console_start_critical_timings (flag) \ + do { typecheck(bool, flag); } while (0)#endif /*
kernel/printk/printk.c +4 -2
@@ -2359,6 +2359,7 @@ void console_unlock(void)static char ext_text[CONSOLE_EXT_LOG_MAX ];static char text[LOG_LINE_MAX +PREFIX_MAX ];unsigned long flags; +bool cflag;bool do_cond_resched, retry;if (console_suspended) {
@@ -2459,9 +2460,10 @@ void console_unlock(void)*/ console_lock_spinning_enable (); -stop_critical_timings ();/* don't trace print latency */ +/* don't trace print latency if it's disabled */ +console_stop_critical_timings (cflag);call_console_drivers (ext_text, ext_len, text, len); -start_critical_timings (); +console_start_critical_timings (cflag);if (console_lock_spinning_disable_and_check ()) {printk_safe_exit_irqrestore (flags);
kernel/trace/trace.h +1 -0
@@ -1262,6 +1262,7 @@ extern int trace_get_user(struct trace_parser *parser, const char __user *ubuf,C (PRINTK_MSGONLY ,"printk-msg-only" ), \C (CONTEXT_INFO ,"context-info" ),/* Print pid/cpu/time */ \C (LATENCY_FMT ,"latency-format" ), \ +C (CONSOLE_LATENCY ,"console-latency" ), \C (RECORD_CMD ,"record-cmd" ), \C (RECORD_TGID ,"record-tgid" ), \ C(OVERWRITE, "overwrite"), \
kernel/trace/trace_irqsoff.c +12 -0
@@ -456,6 +456,18 @@ void stop_critical_timings(void)EXPORT_SYMBOL_GPL (stop_critical_timings);NOKPROBE_SYMBOL (stop_critical_timings); +bool console_tracing_disabled (void ) +{ +struct trace_array *tr = irqsoff_trace; +int pc =preempt_count (); + +if (!preempt_trace (pc) && !irq_trace ()) +return false; + +return !(tr->trace_flags &TRACE_ITER_CONSOLE_LATENCY ); +} +EXPORT_SYMBOL_GPL (console_tracing_disabled); +#ifdef CONFIG_FUNCTION_TRACER static bool function_enabled;
Signature · 1 line
2.17.1