HTML rendering created 2025-09-06 byMichael Kerrisk, author ofThe Linux Programming Interface. For details of in-depthLinux/UNIX system programming training courses that I teach, lookhere. Hosting byjambit GmbH. |  |
NAME |SYNOPSIS |DESCRIPTION |RETURN VALUE |EXAMPLE |FILES |SEE ALSO |AUTHOR |REPORTING BUGS |LICENSE |RESOURCES |COPYING |NOTES |COLOPHON | |
LIBTRACEFS(3) libtracefs ManualLIBTRACEFS(3)tracefs_cpu_read_buf, tracefs_cpu_buffered_read_buf, tracefs_cpu_flush_buf - Reading trace_pipe_raw data returning a kbuffer
#include <tracefs.h> struct kbuffer *tracefs_cpu_read_buf(struct tracefs_cpu *tcpu, boolnonblock); struct kbuffer *tracefs_cpu_buffered_read_buf(struct tracefs_cpu *tcpu, boolnonblock); struct kbuffer *tracefs_cpu_flush_buf(struct tracefs_cpu *tcpu);
This set of APIs can be used to read the raw data from the trace_pipe_raw files in the tracefs file system and return a kbuffer structure to read it with. Thetracefs_cpu_read_buf()reads the trace_pipe_raw files associated totcpu and returns a kbuffer structure that can be used to iterate the events. Ifnonblock is set, and there’s no data available, it will return immediately. Otherwise depending on howtcpu was opened, it will block. Iftcpu was opened with nonblock set, then thisnonblock will make no difference. Thetracefs_cpu_buffered_read_buf()is basically the same astracefs_cpu_read_buf()except that it uses a pipe through splice to buffer reads. This will batch reads keeping the reading from the ring buffer less intrusive to the system, as just reading all the time can cause quite a disturbance. Note, one difference between this andtracefs_cpu_read()is that it will read only in sub buffer pages. If the ring buffer has not filled a page, then it will not return anything, even withnonblock set. Calls totracefs_cpu_flush_buf()ortracefs_cpu_flush()should be done to read the rest of the file at the end of the trace. Thetracefs_cpu_flush_buf()reads the trace_pipe_raw file associated by thetcpu and puts it intobuffer, which must be the size of the sub buffer which is retrieved. This should be called at the end of tracing to get the rest of the data. This call will convert the file descriptor of trace_pipe_raw into non-blocking mode.
The functionstracefs_cpu_read_buf(), tracefs_cpu_buffered_read_buf()* andtracefs_cpu_flush()returns a kbuffer descriptor that can be iterated over to find the events. Note, this descriptor is part of the tracefs_cpu structure and should not be freed. It will be freed. It returns NULL on error or if nonblock is set and there are no events available. In the case of no events, errno will be set with EAGAIN.
#include <stdlib.h> #include <ctype.h> #include <tracefs.h> static void read_page(struct tep_handle *tep, struct kbuffer *kbuf) { static struct trace_seq seq; struct tep_record record; if (seq.buffer) trace_seq_reset(&seq); else trace_seq_init(&seq); while ((record.data = kbuffer_read_event(kbuf, &record.ts))) { record.size = kbuffer_event_size(kbuf); kbuffer_next_event(kbuf, NULL); tep_print_event(tep, &seq, &record, "%s-%d %9d\t%s: %s\n", TEP_PRINT_COMM, TEP_PRINT_PID, TEP_PRINT_TIME, TEP_PRINT_NAME, TEP_PRINT_INFO); trace_seq_do_printf(&seq); trace_seq_reset(&seq); } } int main (int argc, char **argv) { struct tracefs_cpu *tcpu; struct tep_handle *tep; struct kbuffer *kbuf; int cpu; if (argc < 2 || !isdigit(argv[1][0])) { printf("usage: %s cpu\n\n", argv[0]); exit(-1); } cpu = atoi(argv[1]); tep = tracefs_local_events(NULL); if (!tep) { perror("Reading trace event formats"); exit(-1); } tcpu = tracefs_cpu_open(NULL, cpu, 0); if (!tcpu) { perror("Open CPU 0 file"); exit(-1); } while ((kbuf = tracefs_cpu_buffered_read_buf(tcpu, true))) { read_page(tep, kbuf); } kbuf = tracefs_cpu_flush_buf(tcpu); if (kbuf) read_page(tep, kbuf); tracefs_cpu_close(tcpu); tep_free(tep); return 0; }tracefs.h Header file to include in order to have access to the library APIs.-ltracefs Linker switch to add when building a program that uses the library.
tracefs_cpu_open(3)tracefs_cpu_close(3)tracefs_cpu_read(3)tracefs_cpu_buffered_read(3)tracefs_cpu_flush(3)libtracefs(3),libtraceevent(3),trace-cmd(1)
Steven Rostedt<rostedt@goodmis.org[1]>
Report bugs to <linux-trace-devel@vger.kernel.org[2]>
libtracefs is Free Software licensed under the GNU LGPL 2.1
https://git.kernel.org/pub/scm/libs/libtrace/libtracefs.git/
Copyright (C) 2022 Google, Inc. Free use of this software is granted under the terms of the GNU Public License (GPL).
1. rostedt@goodmis.org mailto:rostedt@goodmis.org 2. linux-trace-devel@vger.kernel.org mailto:linux-trace-devel@vger.kernel.org
This page is part of thelibtracefs (Linux kernel trace file system library) project. Information about the project can be found at ⟨https://www.trace-cmd.org/⟩. If you have a bug report for this manual page, see ⟨https://www.trace-cmd.org/⟩. This page was obtained from the project's upstream Git repository ⟨https://git.kernel.org/pub/scm/libs/libtrace/libtracefs.git⟩ on 2025-08-11. (At that time, the date of the most recent commit that was found in the repository was 2025-06-02.) If you discover any rendering problems in this HTML version of the page, or you believe there is a better or more up-to-date source for the page, or you have corrections or improvements to the information in this COLOPHON (which isnot part of the original manual page), send a mail to man-pages@man7.orglibtracefs 1.8.1 01/02/2025LIBTRACEFS(3)Pages that refer to this page:tracefs_cpu_open_mapped(3), tracefs_cpu_read_size(3)
HTML rendering created 2025-09-06 byMichael Kerrisk, author ofThe Linux Programming Interface. For details of in-depthLinux/UNIX system programming training courses that I teach, lookhere. Hosting byjambit GmbH. | |