diff options
| -rw-r--r-- | README.markdown | 87 | ||||
| -rw-r--r-- | src/cyclictest/cyclictest.c | 30 |
2 files changed, 114 insertions, 3 deletions
diff --git a/README.markdown b/README.markdown new file mode 100644 index 0000000..3ab6ddf --- /dev/null +++ b/README.markdown @@ -0,0 +1,87 @@ +# RT-Tests + +This repository contains some programs that test various rt-linux features. + +## Usage + +### Compile + + sudo apt-get install build-essential libnuma-dev + make + +### Run tests + +To run one test thread per CPU or per CPU core, each thread on a separate +processor, type + + sudo ./cyclictest -a -t -n -p99 + +On a non-realtime system, you may see something like + + T: 0 ( 3431) P:99 I:1000 C: 100000 Min: 5 Act: 10 Avg: 14 Max: 39242 + T: 1 ( 3432) P:98 I:1500 C: 66934 Min: 4 Act: 10 Avg: 17 Max: 39661 + +The rightmost column contains the most important result, i.e. the worst-case +latency of 39.242 milliseconds. On a realtime-enabled system, the result may +look like + + T: 0 ( 3407) P:99 I:1000 C: 100000 Min: 7 Act: 10 Avg: 10 Max: 18 + T: 1 ( 3408) P:98 I:1500 C: 67043 Min: 7 Act: 8 Avg: 10 Max: 22 + +and, thus, indicate an apparent short-term worst-case latency of 18 +microseconds. + +Running cyclictest only over a short period of time and without creating +appropriate real-time stress conditions is rather meaningless, since the +execution of an asynchronous event from idle state is normally always quite +fast, and every - even non-RT system - can do that. The challenge is to minimize + the latency when reacting to an asynchronuous event, irrespective of what code +path is executed at the time when the external event arrives. +Therefore, specific stress conditions must be present while cyclictest is +running to reliably determine the worst-case latency of a given system. + +### Latency fighting + +If - as in the above example - a low worst-case latency is measured, and this is +the case even under a system load that is equivalent to the load expected under +production conditions, everything is alright. +Of course, the measurement must last suffciently long, preferably 24 hours or +more to run several hundred million test threads. If possible, the `-i` command +line option (thread interval) should be used to increase the number of test +threads over time. +As a role of thumb, the thread interval should be set to a value twice as long +as the expected worst-case latency. If at the end of such a test period the +worst-cae latency still did not exceed the value that is assumed critical for a +given system, the particular kernel in combination with the hardware in use can +then probably be regarded as real-time capable. + +What, however, if the latency is higher than acceptable? Then, the famous +"*latency fighting*" begins. For this purpose, the cyclictest tool provides the +`-b` option that causes a function tracing to be written to +`/sys/kernel/debug/tracing/trace`, if a specified latency threshold was +exceeded, for example: + + ./cyclictest -a -t -n -p99 -f -b100 + +This causes the program to abort execution, if the latency value exceeds 100 +microseconds; the culprit can then be found in the trace output at +`/sys/kernel/debug/tracing/trace`. +The kernel function that was executed just before a latency of more than 100 +microseconds was detected is marked with an exclamation mark such as + + qemu-30047 2D.h3 742805us : __activate_task+0x42/0x68 <cyclicte-426> (199 1) + qemu-30047 2D.h3 742806us : __trace_start_sched_wakeup+0x40/0x161 <cyclicte-426> (0 -1) + qemu-30047 2DNh3 742806us!: try_to_wake_up+0x422/0x460 <cyclicte-426> (199 -5) + qemu-30047 2DN.1 742939us : __sched_text_start+0xf3/0xdcd (c064e442 0) + +The first column indicates the calling process responsible for triggering the +latency. + +If the trace output is not obvious, it can be submitted to the OSADL Latency +Fight Support Service at +[latency-fighters@osadl.org](mailto:latency-fighters@osadl.org). +In addition to the output of `cat /sys/kernel/debug/tracing/trace`, the output +of `lspci` and the `.config` file that was used to build the kernel in question +must be submitted. We are sure you understand that OSADL members will be served +first, but we promise to do our best to help everybody to successfully fight +against kernel and driver latencies. diff --git a/src/cyclictest/cyclictest.c b/src/cyclictest/cyclictest.c index 731b4bd..6a61a9c 100644 --- a/src/cyclictest/cyclictest.c +++ b/src/cyclictest/cyclictest.c @@ -33,6 +33,7 @@ #include <sys/time.h> #include <sys/utsname.h> #include <sys/mman.h> +#include <sys/resource.h> #include "rt_numa.h" #include "rt-utils.h" @@ -170,6 +171,7 @@ static int duration = 0; static int use_nsecs = 0; static int refresh_on_max; static int force_sched_other; +static int priospread = 0; static pthread_cond_t refresh_on_max_cond = PTHREAD_COND_INITIALIZER; static pthread_mutex_t refresh_on_max_lock = PTHREAD_MUTEX_INITIALIZER; @@ -641,7 +643,10 @@ void *timerthread(void *param) memset(&schedp, 0, sizeof(schedp)); schedp.sched_priority = par->prio; - sched_setscheduler(0, par->policy, &schedp); + if(sched_setscheduler(0, par->policy, &schedp) == -1){ + fprintf(stderr,"sched_setscheduler prio %d failed\n",par->prio); + par->prio=0; + } /* Get current time */ clock_gettime(par->clock, &now); @@ -845,6 +850,7 @@ static void display_help(int error) "-p PRIO --prio=PRIO priority of highest prio thread\n" "-P --preemptoff Preempt off tracing (used with -b)\n" "-q --quiet print only a summary on exit\n" + "-Q --priospread spread priority levels starting at specified value\n" "-r --relative use relative timer instead of absolute\n" "-s --system use sys_nanosleep and sys_setitimer\n" "-t --threads one thread per available processor\n" @@ -943,6 +949,7 @@ static void process_options (int argc, char *argv[]) { int error = 0; int max_cpus = sysconf(_SC_NPROCESSORS_CONF); + struct rlimit rlim; for (;;) { int option_index = 0; @@ -984,9 +991,10 @@ static void process_options (int argc, char *argv[]) {"smp", no_argument, NULL, 'S'}, {"numa", no_argument, NULL, 'U'}, {"latency", required_argument, NULL, 'e'}, + {"priospread", no_argument, NULL, 'Q'}, {NULL, 0, NULL, 0} }; - int c = getopt_long(argc, argv, "a::b:Bc:Cd:Efh:H:i:Il:MnNo:O:p:PmqrsSt::uUvD:wWT:y:e:", + int c = getopt_long(argc, argv, "a::b:Bc:Cd:Efh:H:i:Il:MnNo:O:p:PmqQrsSt::uUvD:wWT:y:e:", long_options, &option_index); if (c == -1) break; @@ -1045,6 +1053,7 @@ static void process_options (int argc, char *argv[]) } break; case 'q': quiet = 1; break; + case 'Q': priospread = 1; break; case 'r': timermode = TIMER_RELTIME; break; case 's': use_system = MODE_SYS_OFFSET; break; case 't': @@ -1140,11 +1149,26 @@ static void process_options (int argc, char *argv[]) if (priority < 0 || priority > 99) error = 1; + if (priospread && priority == 0) { + fprintf(stderr, "defaulting realtime priority to %d\n", + num_threads+1); + priority = num_threads+1; + } + if (priority && (policy != SCHED_FIFO && policy != SCHED_RR)) { fprintf(stderr, "policy and priority don't match: setting policy to SCHED_FIFO\n"); policy = SCHED_FIFO; } + /* check against rlimit see /etc/security/limits.conf */ + getrlimit(RLIMIT_RTPRIO, &rlim); + if ( priority > rlim.rlim_max){ + fprintf(stderr, "defaulting realtime priority to %d\n", + (int) rlim.rlim_max); + priority = rlim.rlim_max; + } + + if ((policy == SCHED_FIFO || policy == SCHED_RR) && priority == 0) { fprintf(stderr, "defaulting realtime priority to %d\n", num_threads+1); @@ -1456,7 +1480,7 @@ int main(int argc, char **argv) par->policy = SCHED_OTHER; force_sched_other = 1; } - if (priority && !histogram && !smp && !numa) + if (priospread) priority--; par->clock = clocksources[clocksel]; par->mode = mode; |