Yocto Project Profiling and Tracing Manual

As a simple test case, we'll profile the 'wget' of a fairly large file, which is a minimally interesting case because it has both file and network I/O aspects, and at least in the case of standard Yocto images, it's implemented as part of busybox, so the methods we use to analyze it can be used in a very similar way to the whole host of supported busybox applets in Yocto.

     root@crownbay:~# rm linux-2.6.19.2.tar.bz2; \
     wget http://downloads.yoctoproject.org/mirror/sources/linux-2.6.19.2.tar.bz2
                

The quickest and easiest way to get some basic overall data about what's going on for a particular workload is to profile it using 'perf stat'. 'perf stat' basically profiles using a few default counters and displays the summed counts at the end of the run:

     root@crownbay:~# perf stat wget http://downloads.yoctoproject.org/mirror/sources/linux-2.6.19.2.tar.bz2
     Connecting to downloads.yoctoproject.org (140.211.169.59:80)
     linux-2.6.19.2.tar.b 100% |***************************************************| 41727k  0:00:00 ETA

     Performance counter stats for 'wget http://downloads.yoctoproject.org/mirror/sources/linux-2.6.19.2.tar.bz2':

           4597.223902 task-clock                #    0.077 CPUs utilized
                 23568 context-switches          #    0.005 M/sec
                    68 CPU-migrations            #    0.015 K/sec
                   241 page-faults               #    0.052 K/sec
            3045817293 cycles                    #    0.663 GHz
       <not supported> stalled-cycles-frontend
       <not supported> stalled-cycles-backend
             858909167 instructions              #    0.28  insns per cycle
             165441165 branches                  #   35.987 M/sec
              19550329 branch-misses             #   11.82% of all branches

          59.836627620 seconds time elapsed
                

Many times such a simple-minded test doesn't yield much of interest, but sometimes it does (see Real-world Yocto bug (slow loop-mounted write speed)).

Also, note that 'perf stat' isn't restricted to a fixed set of counters - basically any event listed in the output of 'perf list' can be tallied by 'perf stat'. For example, suppose we wanted to see a summary of all the events related to kernel memory allocation/freeing along with cache hits and misses:

     root@crownbay:~# perf stat -e kmem:* -e cache-references -e cache-misses wget http://downloads.yoctoproject.org/mirror/sources/linux-2.6.19.2.tar.bz2
     Connecting to downloads.yoctoproject.org (140.211.169.59:80)
     linux-2.6.19.2.tar.b 100% |***************************************************| 41727k  0:00:00 ETA

     Performance counter stats for 'wget http://downloads.yoctoproject.org/mirror/sources/linux-2.6.19.2.tar.bz2':

                  5566 kmem:kmalloc
                125517 kmem:kmem_cache_alloc
                     0 kmem:kmalloc_node
                     0 kmem:kmem_cache_alloc_node
                 34401 kmem:kfree
                 69920 kmem:kmem_cache_free
                   133 kmem:mm_page_free
                    41 kmem:mm_page_free_batched
                 11502 kmem:mm_page_alloc
                 11375 kmem:mm_page_alloc_zone_locked
                     0 kmem:mm_page_pcpu_drain
                     0 kmem:mm_page_alloc_extfrag
              66848602 cache-references
               2917740 cache-misses              #    4.365 % of all cache refs

          44.831023415 seconds time elapsed
                

So 'perf stat' gives us a nice easy way to get a quick overview of what might be happening for a set of events, but normally we'd need a little more detail in order to understand what's going on in a way that we can act on in a useful way.

To dive down into a next level of detail, we can use 'perf record'/'perf report' which will collect profiling data and present it to use using an interactive text-based UI (or simply as text if we specify --stdio to 'perf report').

As our first attempt at profiling this workload, we'll simply run 'perf record', handing it the workload we want to profile (everything after 'perf record' and any perf options we hand it - here none - will be executed in a new shell). perf collects samples until the process exits and records them in a file named 'perf.data' in the current working directory.

     root@crownbay:~# perf record wget http://downloads.yoctoproject.org/mirror/sources/linux-2.6.19.2.tar.bz2

     Connecting to downloads.yoctoproject.org (140.211.169.59:80)
     linux-2.6.19.2.tar.b 100% |************************************************| 41727k  0:00:00 ETA
     [ perf record: Woken up 1 times to write data ]
     [ perf record: Captured and wrote 0.176 MB perf.data (~7700 samples) ]
            

To see the results in a 'text-based UI' (tui), simply run 'perf report', which will read the perf.data file in the current working directory and display the results in an interactive UI:

     root@crownbay:~# perf report
                

The above screenshot displays a 'flat' profile, one entry for each 'bucket' corresponding to the functions that were profiled during the profiling run, ordered from the most popular to the least (perf has options to sort in various orders and keys as well as display entries only above a certain threshold and so on - see the perf documentation for details). Note that this includes both userspace functions (entries containing a [.]) and kernel functions accounted to the process (entries containing a [k]). (perf has command-line modifiers that can be used to restrict the profiling to kernel or userspace, among others).

Notice also that the above report shows an entry for 'busybox', which is the executable that implements 'wget' in Yocto, but that instead of a useful function name in that entry, it displays a not-so-friendly hex value instead. The steps below will show how to fix that problem.

Before we do that, however, let's try running a different profile, one which shows something a little more interesting. The only difference between the new profile and the previous one is that we'll add the -g option, which will record not just the address of a sampled function, but the entire callchain to the sampled function as well:

     root@crownbay:~# perf record -g wget http://downloads.yoctoproject.org/mirror/sources/linux-2.6.19.2.tar.bz2
     Connecting to downloads.yoctoproject.org (140.211.169.59:80)
     linux-2.6.19.2.tar.b 100% |************************************************| 41727k  0:00:00 ETA
     [ perf record: Woken up 3 times to write data ]
     [ perf record: Captured and wrote 0.652 MB perf.data (~28476 samples) ]


     root@crownbay:~# perf report
                

Using the callgraph view, we can actually see not only which functions took the most time, but we can also see a summary of how those functions were called and learn something about how the program interacts with the kernel in the process.

Notice that each entry in the above screenshot now contains a '+' on the left-hand side. This means that we can expand the entry and drill down into the callchains that feed into that entry. Pressing 'enter' on any one of them will expand the callchain (you can also press 'E' to expand them all at the same time or 'C' to collapse them all).

In the screenshot above, we've toggled the __copy_to_user_ll() entry and several subnodes all the way down. This lets us see which callchains contributed to the profiled __copy_to_user_ll() function which contributed 1.77% to the total profile.

As a bit of background explanation for these callchains, think about what happens at a high level when you run wget to get a file out on the network. Basically what happens is that the data comes into the kernel via the network connection (socket) and is passed to the userspace program 'wget' (which is actually a part of busybox, but that's not important for now), which takes the buffers the kernel passes to it and writes it to a disk file to save it.

The part of this process that we're looking at in the above call stacks is the part where the kernel passes the data it's read from the socket down to wget i.e. a copy-to-user.

Notice also that here there's also a case where the hex value is displayed in the callstack, here in the expanded sys_clock_gettime() function. Later we'll see it resolve to a userspace function call in busybox.

The above screenshot shows the other half of the journey for the data - from the wget program's userspace buffers to disk. To get the buffers to disk, the wget program issues a write(2), which does a copy-from-user to the kernel, which then takes care via some circuitous path (probably also present somewhere in the profile data), to get it safely to disk.

Now that we've seen the basic layout of the profile data and the basics of how to extract useful information out of it, let's get back to the task at hand and see if we can get some basic idea about where the time is spent in the program we're profiling, wget. Remember that wget is actually implemented as an applet in busybox, so while the process name is 'wget', the executable we're actually interested in is busybox. So let's expand the first entry containing busybox:

Again, before we expanded we saw that the function was labeled with a hex value instead of a symbol as with most of the kernel entries. Expanding the busybox entry doesn't make it any better.

The problem is that perf can't find the symbol information for the busybox binary, which is actually stripped out by the Yocto build system.

One way around that is to put the following in your local.conf file when you build the image:

     INHIBIT_PACKAGE_STRIP = "1"
                

However, we already have an image with the binaries stripped, so what can we do to get perf to resolve the symbols? Basically we need to install the debuginfo for the busybox package.

To generate the debug info for the packages in the image, we can add dbg-pkgs to EXTRA_IMAGE_FEATURES in local.conf. For example:

     EXTRA_IMAGE_FEATURES = "debug-tweaks tools-profile dbg-pkgs"
                

Additionally, in order to generate the type of debuginfo that perf understands, we also need to set PACKAGE_DEBUG_SPLIT_STYLE in the local.conf file:

     PACKAGE_DEBUG_SPLIT_STYLE = 'debug-file-directory'
                

Once we've done that, we can install the debuginfo for busybox. The debug packages once built can be found in build/tmp/deploy/rpm/* on the host system. Find the busybox-dbg-...rpm file and copy it to the target. For example:

     [trz@empanada core2]$ scp /home/trz/yocto/crownbay-tracing-dbg/build/tmp/deploy/rpm/core2_32/busybox-dbg-1.20.2-r2.core2_32.rpm root@192.168.1.31:
     root@192.168.1.31's password:
     busybox-dbg-1.20.2-r2.core2_32.rpm                     100% 1826KB   1.8MB/s   00:01
                

Now install the debug rpm on the target:

     root@crownbay:~# rpm -i busybox-dbg-1.20.2-r2.core2_32.rpm
                

Now that the debuginfo is installed, we see that the busybox entries now display their functions symbolically:

If we expand one of the entries and press 'enter' on a leaf node, we're presented with a menu of actions we can take to get more information related to that entry:

One of these actions allows us to show a view that displays a busybox-centric view of the profiled functions (in this case we've also expanded all the nodes using the 'E' key):

Finally, we can see that now that the busybox debuginfo is installed, the previously unresolved symbol in the sys_clock_gettime() entry mentioned previously is now resolved, and shows that the sys_clock_gettime system call that was the source of 6.75% of the copy-to-user overhead was initiated by the handle_input() busybox function:

At the lowest level of detail, we can dive down to the assembly level and see which instructions caused the most overhead in a function. Pressing 'enter' on the 'udhcpc_main' function, we're again presented with a menu:

Selecting 'Annotate udhcpc_main', we get a detailed listing of percentages by instruction for the udhcpc_main function. From the display, we can see that over 50% of the time spent in this function is taken up by a couple tests and the move of a constant (1) to a register:

As a segue into tracing, let's try another profile using a different counter, something other than the default 'cycles'.

The tracing and profiling infrastructure in Linux has become unified in a way that allows us to use the same tool with a completely different set of counters, not just the standard hardware counters that traditional tools have had to restrict themselves to (of course the traditional tools can also make use of the expanded possibilities now available to them, and in some cases have, as mentioned previously).

We can get a list of the available events that can be used to profile a workload via 'perf list':

     root@crownbay:~# perf list

     List of pre-defined events (to be used in -e):
      cpu-cycles OR cycles                               [Hardware event]
      stalled-cycles-frontend OR idle-cycles-frontend    [Hardware event]
      stalled-cycles-backend OR idle-cycles-backend      [Hardware event]
      instructions                                       [Hardware event]
      cache-references                                   [Hardware event]
      cache-misses                                       [Hardware event]
      branch-instructions OR branches                    [Hardware event]
      branch-misses                                      [Hardware event]
      bus-cycles                                         [Hardware event]
      ref-cycles                                         [Hardware event]

      cpu-clock                                          [Software event]
      task-clock                                         [Software event]
      page-faults OR faults                              [Software event]
      minor-faults                                       [Software event]
      major-faults                                       [Software event]
      context-switches OR cs                             [Software event]
      cpu-migrations OR migrations                       [Software event]
      alignment-faults                                   [Software event]
      emulation-faults                                   [Software event]

      L1-dcache-loads                                    [Hardware cache event]
      L1-dcache-load-misses                              [Hardware cache event]
      L1-dcache-prefetch-misses                          [Hardware cache event]
      L1-icache-loads                                    [Hardware cache event]
      L1-icache-load-misses                              [Hardware cache event]
      .
      .
      .
      rNNN                                               [Raw hardware event descriptor]
      cpu/t1=v1[,t2=v2,t3 ...]/modifier                  [Raw hardware event descriptor]
       (see 'perf list --help' on how to encode it)

      mem:<addr>[:access]                                [Hardware breakpoint]

      sunrpc:rpc_call_status                             [Tracepoint event]
      sunrpc:rpc_bind_status                             [Tracepoint event]
      sunrpc:rpc_connect_status                          [Tracepoint event]
      sunrpc:rpc_task_begin                              [Tracepoint event]
      skb:kfree_skb                                      [Tracepoint event]
      skb:consume_skb                                    [Tracepoint event]
      skb:skb_copy_datagram_iovec                        [Tracepoint event]
      net:net_dev_xmit                                   [Tracepoint event]
      net:net_dev_queue                                  [Tracepoint event]
      net:netif_receive_skb                              [Tracepoint event]
      net:netif_rx                                       [Tracepoint event]
      napi:napi_poll                                     [Tracepoint event]
      sock:sock_rcvqueue_full                            [Tracepoint event]
      sock:sock_exceed_buf_limit                         [Tracepoint event]
      udp:udp_fail_queue_rcv_skb                         [Tracepoint event]
      hda:hda_send_cmd                                   [Tracepoint event]
      hda:hda_get_response                               [Tracepoint event]
      hda:hda_bus_reset                                  [Tracepoint event]
      scsi:scsi_dispatch_cmd_start                       [Tracepoint event]
      scsi:scsi_dispatch_cmd_error                       [Tracepoint event]
      scsi:scsi_eh_wakeup                                [Tracepoint event]
      drm:drm_vblank_event                               [Tracepoint event]
      drm:drm_vblank_event_queued                        [Tracepoint event]
      drm:drm_vblank_event_delivered                     [Tracepoint event]
      random:mix_pool_bytes                              [Tracepoint event]
      random:mix_pool_bytes_nolock                       [Tracepoint event]
      random:credit_entropy_bits                         [Tracepoint event]
      gpio:gpio_direction                                [Tracepoint event]
      gpio:gpio_value                                    [Tracepoint event]
      block:block_rq_abort                               [Tracepoint event]
      block:block_rq_requeue                             [Tracepoint event]
      block:block_rq_issue                               [Tracepoint event]
      block:block_bio_bounce                             [Tracepoint event]
      block:block_bio_complete                           [Tracepoint event]
      block:block_bio_backmerge                          [Tracepoint event]
      .
      .
      writeback:writeback_wake_thread                    [Tracepoint event]
      writeback:writeback_wake_forker_thread             [Tracepoint event]
      writeback:writeback_bdi_register                   [Tracepoint event]
      .
      .
      writeback:writeback_single_inode_requeue           [Tracepoint event]
      writeback:writeback_single_inode                   [Tracepoint event]
      kmem:kmalloc                                       [Tracepoint event]
      kmem:kmem_cache_alloc                              [Tracepoint event]
      kmem:mm_page_alloc                                 [Tracepoint event]
      kmem:mm_page_alloc_zone_locked                     [Tracepoint event]
      kmem:mm_page_pcpu_drain                            [Tracepoint event]
      kmem:mm_page_alloc_extfrag                         [Tracepoint event]
      vmscan:mm_vmscan_kswapd_sleep                      [Tracepoint event]
      vmscan:mm_vmscan_kswapd_wake                       [Tracepoint event]
      vmscan:mm_vmscan_wakeup_kswapd                     [Tracepoint event]
      vmscan:mm_vmscan_direct_reclaim_begin              [Tracepoint event]
      .
      .
      module:module_get                                  [Tracepoint event]
      module:module_put                                  [Tracepoint event]
      module:module_request                              [Tracepoint event]
      sched:sched_kthread_stop                           [Tracepoint event]
      sched:sched_wakeup                                 [Tracepoint event]
      sched:sched_wakeup_new                             [Tracepoint event]
      sched:sched_process_fork                           [Tracepoint event]
      sched:sched_process_exec                           [Tracepoint event]
      sched:sched_stat_runtime                           [Tracepoint event]
      rcu:rcu_utilization                                [Tracepoint event]
      workqueue:workqueue_queue_work                     [Tracepoint event]
      workqueue:workqueue_execute_end                    [Tracepoint event]
      signal:signal_generate                             [Tracepoint event]
      signal:signal_deliver                              [Tracepoint event]
      timer:timer_init                                   [Tracepoint event]
      timer:timer_start                                  [Tracepoint event]
      timer:hrtimer_cancel                               [Tracepoint event]
      timer:itimer_state                                 [Tracepoint event]
      timer:itimer_expire                                [Tracepoint event]
      irq:irq_handler_entry                              [Tracepoint event]
      irq:irq_handler_exit                               [Tracepoint event]
      irq:softirq_entry                                  [Tracepoint event]
      irq:softirq_exit                                   [Tracepoint event]
      irq:softirq_raise                                  [Tracepoint event]
      printk:console                                     [Tracepoint event]
      task:task_newtask                                  [Tracepoint event]
      task:task_rename                                   [Tracepoint event]
      syscalls:sys_enter_socketcall                      [Tracepoint event]
      syscalls:sys_exit_socketcall                       [Tracepoint event]
      .
      .
      .
      syscalls:sys_enter_unshare                         [Tracepoint event]
      syscalls:sys_exit_unshare                          [Tracepoint event]
      raw_syscalls:sys_enter                             [Tracepoint event]
      raw_syscalls:sys_exit                              [Tracepoint event]
                

Only a subset of these would be of interest to us when looking at this workload, so let's choose the most likely subsystems (identified by the string before the colon in the Tracepoint events) and do a 'perf stat' run using only those wildcarded subsystems:

     root@crownbay:~# perf stat -e skb:* -e net:* -e napi:* -e sched:* -e workqueue:* -e irq:* -e syscalls:* wget http://downloads.yoctoproject.org/mirror/sources/linux-2.6.19.2.tar.bz2
     Performance counter stats for 'wget http://downloads.yoctoproject.org/mirror/sources/linux-2.6.19.2.tar.bz2':

                 23323 skb:kfree_skb
                     0 skb:consume_skb
                 49897 skb:skb_copy_datagram_iovec
                  6217 net:net_dev_xmit
                  6217 net:net_dev_queue
                  7962 net:netif_receive_skb
                     2 net:netif_rx
                  8340 napi:napi_poll
                     0 sched:sched_kthread_stop
                     0 sched:sched_kthread_stop_ret
                  3749 sched:sched_wakeup
                     0 sched:sched_wakeup_new
                     0 sched:sched_switch
                    29 sched:sched_migrate_task
                     0 sched:sched_process_free
                     1 sched:sched_process_exit
                     0 sched:sched_wait_task
                     0 sched:sched_process_wait
                     0 sched:sched_process_fork
                     1 sched:sched_process_exec
                     0 sched:sched_stat_wait
         2106519415641 sched:sched_stat_sleep
                     0 sched:sched_stat_iowait
             147453613 sched:sched_stat_blocked
           12903026955 sched:sched_stat_runtime
                     0 sched:sched_pi_setprio
                  3574 workqueue:workqueue_queue_work
                  3574 workqueue:workqueue_activate_work
                     0 workqueue:workqueue_execute_start
                     0 workqueue:workqueue_execute_end
                 16631 irq:irq_handler_entry
                 16631 irq:irq_handler_exit
                 28521 irq:softirq_entry
                 28521 irq:softirq_exit
                 28728 irq:softirq_raise
                     1 syscalls:sys_enter_sendmmsg
                     1 syscalls:sys_exit_sendmmsg
                     0 syscalls:sys_enter_recvmmsg
                     0 syscalls:sys_exit_recvmmsg
                    14 syscalls:sys_enter_socketcall
                    14 syscalls:sys_exit_socketcall
                       .
                       .
                       .
                 16965 syscalls:sys_enter_read
                 16965 syscalls:sys_exit_read
                 12854 syscalls:sys_enter_write
                 12854 syscalls:sys_exit_write
                       .
                       .
                       .

          58.029710972 seconds time elapsed
                

Let's pick one of these tracepoints and tell perf to do a profile using it as the sampling event:

     root@crownbay:~# perf record -g -e sched:sched_wakeup wget http://downloads.yoctoproject.org/mirror/sources/linux-2.6.19.2.tar.bz2
                

The screenshot above shows the results of running a profile using sched:sched_switch tracepoint, which shows the relative costs of various paths to sched_wakeup (note that sched_wakeup is the name of the tracepoint - it's actually defined just inside ttwu_do_wakeup(), which accounts for the function name actually displayed in the profile:

     /*
      * Mark the task runnable and perform wakeup-preemption.
      */
     static void
     ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags)
     {
          trace_sched_wakeup(p, true);
          .
          .
          .
     }
                

A couple of the more interesting callchains are expanded and displayed above, basically some network receive paths that presumably end up waking up wget (busybox) when network data is ready.

Note that because tracepoints are normally used for tracing, the default sampling period for tracepoints is 1 i.e. for tracepoints perf will sample on every event occurrence (this can be changed using the -c option). This is in contrast to hardware counters such as for example the default 'cycles' hardware counter used for normal profiling, where sampling periods are much higher (in the thousands) because profiling should have as low an overhead as possible and sampling on every cycle would be prohibitively expensive.

Profiling is a great tool for solving many problems or for getting a high-level view of what's going on with a workload or across the system. It is however by definition an approximation, as suggested by the most prominent word associated with it, 'sampling'. On the one hand, it allows a representative picture of what's going on in the system to be cheaply taken, but on the other hand, that cheapness limits its utility when that data suggests a need to 'dive down' more deeply to discover what's really going on. In such cases, the only way to see what's really going on is to be able to look at (or summarize more intelligently) the individual steps that go into the higher-level behavior exposed by the coarse-grained profiling data.

As a concrete example, we can trace all the events we think might be applicable to our workload:

     root@crownbay:~# perf record -g -e skb:* -e net:* -e napi:* -e sched:sched_switch -e sched:sched_wakeup -e irq:*
      -e syscalls:sys_enter_read -e syscalls:sys_exit_read -e syscalls:sys_enter_write -e syscalls:sys_exit_write
      wget http://downloads.yoctoproject.org/mirror/sources/linux-2.6.19.2.tar.bz2
                

We can look at the raw trace output using 'perf script' with no arguments:

     root@crownbay:~# perf script

           perf  1262 [000] 11624.857082: sys_exit_read: 0x0
           perf  1262 [000] 11624.857193: sched_wakeup: comm=migration/0 pid=6 prio=0 success=1 target_cpu=000
           wget  1262 [001] 11624.858021: softirq_raise: vec=1 [action=TIMER]
           wget  1262 [001] 11624.858074: softirq_entry: vec=1 [action=TIMER]
           wget  1262 [001] 11624.858081: softirq_exit: vec=1 [action=TIMER]
           wget  1262 [001] 11624.858166: sys_enter_read: fd: 0x0003, buf: 0xbf82c940, count: 0x0200
           wget  1262 [001] 11624.858177: sys_exit_read: 0x200
           wget  1262 [001] 11624.858878: kfree_skb: skbaddr=0xeb248d80 protocol=0 location=0xc15a5308
           wget  1262 [001] 11624.858945: kfree_skb: skbaddr=0xeb248000 protocol=0 location=0xc15a5308
           wget  1262 [001] 11624.859020: softirq_raise: vec=1 [action=TIMER]
           wget  1262 [001] 11624.859076: softirq_entry: vec=1 [action=TIMER]
           wget  1262 [001] 11624.859083: softirq_exit: vec=1 [action=TIMER]
           wget  1262 [001] 11624.859167: sys_enter_read: fd: 0x0003, buf: 0xb7720000, count: 0x0400
           wget  1262 [001] 11624.859192: sys_exit_read: 0x1d7
           wget  1262 [001] 11624.859228: sys_enter_read: fd: 0x0003, buf: 0xb7720000, count: 0x0400
           wget  1262 [001] 11624.859233: sys_exit_read: 0x0
           wget  1262 [001] 11624.859573: sys_enter_read: fd: 0x0003, buf: 0xbf82c580, count: 0x0200
           wget  1262 [001] 11624.859584: sys_exit_read: 0x200
           wget  1262 [001] 11624.859864: sys_enter_read: fd: 0x0003, buf: 0xb7720000, count: 0x0400
           wget  1262 [001] 11624.859888: sys_exit_read: 0x400
           wget  1262 [001] 11624.859935: sys_enter_read: fd: 0x0003, buf: 0xb7720000, count: 0x0400
           wget  1262 [001] 11624.859944: sys_exit_read: 0x400
                

This gives us a detailed timestamped sequence of events that occurred within the workload with respect to those events.

In many ways, profiling can be viewed as a subset of tracing - theoretically, if you have a set of trace events that's sufficient to capture all the important aspects of a workload, you can derive any of the results or views that a profiling run can.

Another aspect of traditional profiling is that while powerful in many ways, it's limited by the granularity of the underlying data. Profiling tools offer various ways of sorting and presenting the sample data, which make it much more useful and amenable to user experimentation, but in the end it can't be used in an open-ended way to extract data that just isn't present as a consequence of the fact that conceptually, most of it has been thrown away.

Full-blown detailed tracing data does however offer the opportunity to manipulate and present the information collected during a tracing run in an infinite variety of ways.

Another way to look at it is that there are only so many ways that the 'primitive' counters can be used on their own to generate interesting output; to get anything more complicated than simple counts requires some amount of additional logic, which is typically very specific to the problem at hand. For example, if we wanted to make use of a 'counter' that maps to the value of the time difference between when a process was scheduled to run on a processor and the time it actually ran, we wouldn't expect such a counter to exist on its own, but we could derive one called say 'wakeup_latency' and use it to extract a useful view of that metric from trace data. Likewise, we really can't figure out from standard profiling tools how much data every process on the system reads and writes, along with how many of those reads and writes fail completely. If we have sufficient trace data, however, we could with the right tools easily extract and present that information, but we'd need something other than pre-canned profiling tools to do that.

Luckily, there is a general-purpose way to handle such needs, called 'programming languages'. Making programming languages easily available to apply to such problems given the specific format of data is called a 'programming language binding' for that data and language. Perf supports two programming language bindings, one for Python and one for Perl.

Now that we have the trace data in perf.data, we can use 'perf script -g' to generate a skeleton script with handlers for the read/write entry/exit events we recorded:

     root@crownbay:~# perf script -g python
     generated Python script: perf-script.py
                

The skeleton script simply creates a python function for each event type in the perf.data file. The body of each function simply prints the event name along with its parameters. For example:

     def net__netif_rx(event_name, context, common_cpu,
            common_secs, common_nsecs, common_pid, common_comm,
            skbaddr, len, name):
                    print_header(event_name, common_cpu, common_secs, common_nsecs,
                            common_pid, common_comm)

		     print "skbaddr=%u, len=%u, name=%s\n" % (skbaddr, len, name),
                

We can run that script directly to print all of the events contained in the perf.data file:

     root@crownbay:~# perf script -s perf-script.py

     in trace_begin
     syscalls__sys_exit_read     0 11624.857082795     1262 perf                  nr=3, ret=0
     sched__sched_wakeup      0 11624.857193498     1262 perf                  comm=migration/0, pid=6, prio=0,      success=1, target_cpu=0
     irq__softirq_raise       1 11624.858021635     1262 wget                  vec=TIMER
     irq__softirq_entry       1 11624.858074075     1262 wget                  vec=TIMER
     irq__softirq_exit        1 11624.858081389     1262 wget                  vec=TIMER
     syscalls__sys_enter_read     1 11624.858166434     1262 wget                  nr=3, fd=3, buf=3213019456,      count=512
     syscalls__sys_exit_read     1 11624.858177924     1262 wget                  nr=3, ret=512
     skb__kfree_skb           1 11624.858878188     1262 wget                  skbaddr=3945041280,           location=3243922184, protocol=0
     skb__kfree_skb           1 11624.858945608     1262 wget                  skbaddr=3945037824,      location=3243922184, protocol=0
     irq__softirq_raise       1 11624.859020942     1262 wget                  vec=TIMER
     irq__softirq_entry       1 11624.859076935     1262 wget                  vec=TIMER
     irq__softirq_exit        1 11624.859083469     1262 wget                  vec=TIMER
     syscalls__sys_enter_read     1 11624.859167565     1262 wget                  nr=3, fd=3, buf=3077701632,      count=1024
     syscalls__sys_exit_read     1 11624.859192533     1262 wget                  nr=3, ret=471
     syscalls__sys_enter_read     1 11624.859228072     1262 wget                  nr=3, fd=3, buf=3077701632,      count=1024
     syscalls__sys_exit_read     1 11624.859233707     1262 wget                  nr=3, ret=0
     syscalls__sys_enter_read     1 11624.859573008     1262 wget                  nr=3, fd=3, buf=3213018496,      count=512
     syscalls__sys_exit_read     1 11624.859584818     1262 wget                  nr=3, ret=512
     syscalls__sys_enter_read     1 11624.859864562     1262 wget                  nr=3, fd=3, buf=3077701632,      count=1024
     syscalls__sys_exit_read     1 11624.859888770     1262 wget                  nr=3, ret=1024
     syscalls__sys_enter_read     1 11624.859935140     1262 wget                  nr=3, fd=3, buf=3077701632,      count=1024
     syscalls__sys_exit_read     1 11624.859944032     1262 wget                  nr=3, ret=1024
                

That in itself isn't very useful; after all, we can accomplish pretty much the same thing by simply running 'perf script' without arguments in the same directory as the perf.data file.

We can however replace the print statements in the generated function bodies with whatever we want, and thereby make it infinitely more useful.

As a simple example, let's just replace the print statements in the function bodies with a simple function that does nothing but increment a per-event count. When the program is run against a perf.data file, each time a particular event is encountered, a tally is incremented for that event. For example:

     def net__netif_rx(event_name, context, common_cpu,
            common_secs, common_nsecs, common_pid, common_comm,
            skbaddr, len, name):
		          inc_counts(event_name)
                

Each event handler function in the generated code is modified to do this. For convenience, we define a common function called inc_counts() that each handler calls; inc_counts() simply tallies a count for each event using the 'counts' hash, which is a specialized hash function that does Perl-like autovivification, a capability that's extremely useful for kinds of multi-level aggregation commonly used in processing traces (see perf's documentation on the Python language binding for details):

     counts = autodict()

     def inc_counts(event_name):
            try:
                    counts[event_name] += 1
            except TypeError:
                    counts[event_name] = 1
                

Finally, at the end of the trace processing run, we want to print the result of all the per-event tallies. For that, we use the special 'trace_end()' function:

     def trace_end():
            for event_name, count in counts.iteritems():
                    print "%-40s %10s\n" % (event_name, count)
                

The end result is a summary of all the events recorded in the trace:

     skb__skb_copy_datagram_iovec                  13148
     irq__softirq_entry                             4796
     irq__irq_handler_exit                          3805
     irq__softirq_exit                              4795
     syscalls__sys_enter_write                      8990
     net__net_dev_xmit                               652
     skb__kfree_skb                                 4047
     sched__sched_wakeup                            1155
     irq__irq_handler_entry                         3804
     irq__softirq_raise                             4799
     net__net_dev_queue                              652
     syscalls__sys_enter_read                      17599
     net__netif_receive_skb                         1743
     syscalls__sys_exit_read                       17598
     net__netif_rx                                     2
     napi__napi_poll                                1877
     syscalls__sys_exit_write                       8990
                

Note that this is pretty much exactly the same information we get from 'perf stat', which goes a little way to support the idea mentioned previously that given the right kind of trace data, higher-level profiling-type summaries can be derived from it.

Documentation on using the 'perf script' python binding.

The examples so far have focused on tracing a particular program or workload - in other words, every profiling run has specified the program to profile in the command-line e.g. 'perf record wget ...'.

It's also possible, and more interesting in many cases, to run a system-wide profile or trace while running the workload in a separate shell.

To do system-wide profiling or tracing, you typically use the -a flag to 'perf record'.

To demonstrate this, open up one window and start the profile using the -a flag (press Ctrl-C to stop tracing):

     root@crownbay:~# perf record -g -a
     ^C[ perf record: Woken up 6 times to write data ]
     [ perf record: Captured and wrote 1.400 MB perf.data (~61172 samples) ]
                

In another window, run the wget test:

     root@crownbay:~# wget http://downloads.yoctoproject.org/mirror/sources/linux-2.6.19.2.tar.bz2
     Connecting to downloads.yoctoproject.org (140.211.169.59:80)
     linux-2.6.19.2.tar.b 100% |*******************************| 41727k  0:00:00 ETA
                

Here we see entries not only for our wget load, but for other processes running on the system as well:

In the snapshot above, we can see callchains that originate in libc, and a callchain from Xorg that demonstrates that we're using a proprietary X driver in userspace (notice the presence of 'PVR' and some other unresolvable symbols in the expanded Xorg callchain).

Note also that we have both kernel and userspace entries in the above snapshot. We can also tell perf to focus on userspace but providing a modifier, in this case 'u', to the 'cycles' hardware counter when we record a profile:

     root@crownbay:~# perf record -g -a -e cycles:u
     ^C[ perf record: Woken up 2 times to write data ]
     [ perf record: Captured and wrote 0.376 MB perf.data (~16443 samples) ]
                

Notice in the screenshot above, we see only userspace entries ([.])

Finally, we can press 'enter' on a leaf node and select the 'Zoom into DSO' menu item to show only entries associated with a specific DSO. In the screenshot below, we've zoomed into the 'libc' DSO which shows all the entries associated with the libc-xxx.so DSO.

We can also use the system-wide -a switch to do system-wide tracing. Here we'll trace a couple of scheduler events:

     root@crownbay:~# perf record -a -e sched:sched_switch -e sched:sched_wakeup
     ^C[ perf record: Woken up 38 times to write data ]
     [ perf record: Captured and wrote 9.780 MB perf.data (~427299 samples) ]
                

We can look at the raw output using 'perf script' with no arguments:

     root@crownbay:~# perf script

                perf  1383 [001]  6171.460045: sched_wakeup: comm=kworker/1:1 pid=21 prio=120 success=1 target_cpu=001
                perf  1383 [001]  6171.460066: sched_switch: prev_comm=perf prev_pid=1383 prev_prio=120 prev_state=R+ ==> next_comm=kworker/1:1 next_pid=21 next_prio=120
         kworker/1:1    21 [001]  6171.460093: sched_switch: prev_comm=kworker/1:1 prev_pid=21 prev_prio=120 prev_state=S ==> next_comm=perf next_pid=1383 next_prio=120
             swapper     0 [000]  6171.468063: sched_wakeup: comm=kworker/0:3 pid=1209 prio=120 success=1 target_cpu=000
             swapper     0 [000]  6171.468107: sched_switch: prev_comm=swapper/0 prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=kworker/0:3 next_pid=1209 next_prio=120
         kworker/0:3  1209 [000]  6171.468143: sched_switch: prev_comm=kworker/0:3 prev_pid=1209 prev_prio=120 prev_state=S ==> next_comm=swapper/0 next_pid=0 next_prio=120
                perf  1383 [001]  6171.470039: sched_wakeup: comm=kworker/1:1 pid=21 prio=120 success=1 target_cpu=001
                perf  1383 [001]  6171.470058: sched_switch: prev_comm=perf prev_pid=1383 prev_prio=120 prev_state=R+ ==> next_comm=kworker/1:1 next_pid=21 next_prio=120
         kworker/1:1    21 [001]  6171.470082: sched_switch: prev_comm=kworker/1:1 prev_pid=21 prev_prio=120 prev_state=S ==> next_comm=perf next_pid=1383 next_prio=120
                perf  1383 [001]  6171.480035: sched_wakeup: comm=kworker/1:1 pid=21 prio=120 success=1 target_cpu=001
                

     root@crownbay:~# perf record -a -e sched:sched_switch --filter 'next_comm != perf && prev_comm != perf' -e sched:sched_wakeup --filter 'comm != perf'
     ^C[ perf record: Woken up 38 times to write data ]
     [ perf record: Captured and wrote 9.688 MB perf.data (~423279 samples) ]


     root@crownbay:~# perf script

             swapper     0 [000]  7932.162180: sched_switch: prev_comm=swapper/0 prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=kworker/0:3 next_pid=1209 next_prio=120
         kworker/0:3  1209 [000]  7932.162236: sched_switch: prev_comm=kworker/0:3 prev_pid=1209 prev_prio=120 prev_state=S ==> next_comm=swapper/0 next_pid=0 next_prio=120
                perf  1407 [001]  7932.170048: sched_wakeup: comm=kworker/1:1 pid=21 prio=120 success=1 target_cpu=001
                perf  1407 [001]  7932.180044: sched_wakeup: comm=kworker/1:1 pid=21 prio=120 success=1 target_cpu=001
                perf  1407 [001]  7932.190038: sched_wakeup: comm=kworker/1:1 pid=21 prio=120 success=1 target_cpu=001
                perf  1407 [001]  7932.200044: sched_wakeup: comm=kworker/1:1 pid=21 prio=120 success=1 target_cpu=001
                perf  1407 [001]  7932.210044: sched_wakeup: comm=kworker/1:1 pid=21 prio=120 success=1 target_cpu=001
                perf  1407 [001]  7932.220044: sched_wakeup: comm=kworker/1:1 pid=21 prio=120 success=1 target_cpu=001
             swapper     0 [001]  7932.230111: sched_wakeup: comm=kworker/1:1 pid=21 prio=120 success=1 target_cpu=001
             swapper     0 [001]  7932.230146: sched_switch: prev_comm=swapper/1 prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=kworker/1:1 next_pid=21 next_prio=120
         kworker/1:1    21 [001]  7932.230205: sched_switch: prev_comm=kworker/1:1 prev_pid=21 prev_prio=120 prev_state=S ==> next_comm=swapper/1 next_pid=0 next_prio=120
             swapper     0 [000]  7932.326109: sched_wakeup: comm=kworker/0:3 pid=1209 prio=120 success=1 target_cpu=000
             swapper     0 [000]  7932.326171: sched_switch: prev_comm=swapper/0 prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=kworker/0:3 next_pid=1209 next_prio=120
         kworker/0:3  1209 [000]  7932.326214: sched_switch: prev_comm=kworker/0:3 prev_pid=1209 prev_prio=120 prev_state=S ==> next_comm=swapper/0 next_pid=0 next_prio=120
                    

perf isn't restricted to the fixed set of static tracepoints listed by 'perf list'. Users can also add their own 'dynamic' tracepoints anywhere in the kernel. For instance, suppose we want to define our own tracepoint on do_fork(). We can do that using the 'perf probe' perf subcommand:

     root@crownbay:~# perf probe do_fork
     Added new event:
       probe:do_fork        (on do_fork)

     You can now use it in all perf tools, such as:

	     perf record -e probe:do_fork -aR sleep 1
                

Adding a new tracepoint via 'perf probe' results in an event with all the expected files and format in /sys/kernel/debug/tracing/events, just the same as for static tracepoints (as discussed in more detail in the trace events subsystem section:

     root@crownbay:/sys/kernel/debug/tracing/events/probe/do_fork# ls -al
     drwxr-xr-x    2 root     root             0 Oct 28 11:42 .
     drwxr-xr-x    3 root     root             0 Oct 28 11:42 ..
     -rw-r--r--    1 root     root             0 Oct 28 11:42 enable
     -rw-r--r--    1 root     root             0 Oct 28 11:42 filter
     -r--r--r--    1 root     root             0 Oct 28 11:42 format
     -r--r--r--    1 root     root             0 Oct 28 11:42 id

     root@crownbay:/sys/kernel/debug/tracing/events/probe/do_fork# cat format
     name: do_fork
     ID: 944
     format:
	     field:unsigned short common_type;	offset:0;	size:2;	signed:0;
	     field:unsigned char common_flags;	offset:2;	size:1;	signed:0;
	     field:unsigned char common_preempt_count;	offset:3;	size:1;	signed:0;
	     field:int common_pid;	offset:4;	size:4;	signed:1;
	     field:int common_padding;	offset:8;	size:4;	signed:1;

	     field:unsigned long __probe_ip;	offset:12;	size:4;	signed:0;

     print fmt: "(%lx)", REC->__probe_ip
                

We can list all dynamic tracepoints currently in existence:

     root@crownbay:~# perf probe -l
      probe:do_fork        (on do_fork)
      probe:schedule       (on schedule)
                

Let's record system-wide ('sleep 30' is a trick for recording system-wide but basically do nothing and then wake up after 30 seconds):

     root@crownbay:~# perf record -g -a -e probe:do_fork sleep 30
     [ perf record: Woken up 1 times to write data ]
     [ perf record: Captured and wrote 0.087 MB perf.data (~3812 samples) ]
                

Using 'perf script' we can see each do_fork event that fired:

     root@crownbay:~# perf script

     # ========
     # captured on: Sun Oct 28 11:55:18 2012
     # hostname : crownbay
     # os release : 3.4.11-yocto-standard
     # perf version : 3.4.11
     # arch : i686
     # nrcpus online : 2
     # nrcpus avail : 2
     # cpudesc : Intel(R) Atom(TM) CPU E660 @ 1.30GHz
     # cpuid : GenuineIntel,6,38,1
     # total memory : 1017184 kB
     # cmdline : /usr/bin/perf record -g -a -e probe:do_fork sleep 30
     # event : name = probe:do_fork, type = 2, config = 0x3b0, config1 = 0x0, config2 = 0x0, excl_usr = 0, excl_kern
      = 0, id = { 5, 6 }
     # HEADER_CPU_TOPOLOGY info available, use -I to display
     # ========
     #
      matchbox-deskto  1197 [001] 34211.378318: do_fork: (c1028460)
      matchbox-deskto  1295 [001] 34211.380388: do_fork: (c1028460)
              pcmanfm  1296 [000] 34211.632350: do_fork: (c1028460)
              pcmanfm  1296 [000] 34211.639917: do_fork: (c1028460)
      matchbox-deskto  1197 [001] 34217.541603: do_fork: (c1028460)
      matchbox-deskto  1299 [001] 34217.543584: do_fork: (c1028460)
               gthumb  1300 [001] 34217.697451: do_fork: (c1028460)
               gthumb  1300 [001] 34219.085734: do_fork: (c1028460)
               gthumb  1300 [000] 34219.121351: do_fork: (c1028460)
               gthumb  1300 [001] 34219.264551: do_fork: (c1028460)
              pcmanfm  1296 [000] 34219.590380: do_fork: (c1028460)
      matchbox-deskto  1197 [001] 34224.955965: do_fork: (c1028460)
      matchbox-deskto  1306 [001] 34224.957972: do_fork: (c1028460)
      matchbox-termin  1307 [000] 34225.038214: do_fork: (c1028460)
      matchbox-termin  1307 [001] 34225.044218: do_fork: (c1028460)
      matchbox-termin  1307 [000] 34225.046442: do_fork: (c1028460)
      matchbox-deskto  1197 [001] 34237.112138: do_fork: (c1028460)
      matchbox-deskto  1311 [001] 34237.114106: do_fork: (c1028460)
                 gaku  1312 [000] 34237.202388: do_fork: (c1028460)
                

And using 'perf report' on the same file, we can see the callgraphs from starting a few programs during those 30 seconds:

First, from the host, ssh to the target:

     $ ssh -l root 192.168.1.47
     The authenticity of host '192.168.1.47 (192.168.1.47)' can't be established.
     RSA key fingerprint is 23:bd:c8:b1:a8:71:52:00:ee:00:4f:64:9e:10:b9:7e.
     Are you sure you want to continue connecting (yes/no)? yes
     Warning: Permanently added '192.168.1.47' (RSA) to the list of known hosts.
     root@192.168.1.47's password:
                

Once on the target, use these steps to create a trace:

     root@crownbay:~# lttng create
     Spawning a session daemon
     Session auto-20121015-232120 created.
     Traces will be written in /home/root/lttng-traces/auto-20121015-232120
                

Enable the events you want to trace (in this case all kernel events):

     root@crownbay:~# lttng enable-event --kernel --all
     All kernel events are enabled in channel channel0
                

Start the trace:

     root@crownbay:~# lttng start
     Tracing started for session auto-20121015-232120
                

And then stop the trace after awhile or after running a particular workload that you want to trace:

     root@crownbay:~# lttng stop
     Tracing stopped for session auto-20121015-232120
                

You can now view the trace in text form on the target:

     root@crownbay:~# lttng view
     [23:21:56.989270399] (+?.?????????) sys_geteuid: { 1 }, { }
     [23:21:56.989278081] (+0.000007682) exit_syscall: { 1 }, { ret = 0 }
     [23:21:56.989286043] (+0.000007962) sys_pipe: { 1 }, { fildes = 0xB77B9E8C }
     [23:21:56.989321802] (+0.000035759) exit_syscall: { 1 }, { ret = 0 }
     [23:21:56.989329345] (+0.000007543) sys_mmap_pgoff: { 1 }, { addr = 0x0, len = 10485760, prot = 3, flags = 131362, fd = 4294967295, pgoff = 0 }
     [23:21:56.989351694] (+0.000022349) exit_syscall: { 1 }, { ret = -1247805440 }
     [23:21:56.989432989] (+0.000081295) sys_clone: { 1 }, { clone_flags = 0x411, newsp = 0xB5EFFFE4, parent_tid = 0xFFFFFFFF, child_tid = 0x0 }
     [23:21:56.989477129] (+0.000044140) sched_stat_runtime: { 1 }, { comm = "lttng-consumerd", tid = 1193, runtime = 681660, vruntime = 43367983388 }
     [23:21:56.989486697] (+0.000009568) sched_migrate_task: { 1 }, { comm = "lttng-consumerd", tid = 1193, prio = 20, orig_cpu = 1, dest_cpu = 1 }
     [23:21:56.989508418] (+0.000021721) hrtimer_init: { 1 }, { hrtimer = 3970832076, clockid = 1, mode = 1 }
     [23:21:56.989770462] (+0.000262044) hrtimer_cancel: { 1 }, { hrtimer = 3993865440 }
     [23:21:56.989771580] (+0.000001118) hrtimer_cancel: { 0 }, { hrtimer = 3993812192 }
     [23:21:56.989776957] (+0.000005377) hrtimer_expire_entry: { 1 }, { hrtimer = 3993865440, now = 79815980007057, function = 3238465232 }
     [23:21:56.989778145] (+0.000001188) hrtimer_expire_entry: { 0 }, { hrtimer = 3993812192, now = 79815980008174, function = 3238465232 }
     [23:21:56.989791695] (+0.000013550) softirq_raise: { 1 }, { vec = 1 }
     [23:21:56.989795396] (+0.000003701) softirq_raise: { 0 }, { vec = 1 }
     [23:21:56.989800635] (+0.000005239) softirq_raise: { 0 }, { vec = 9 }
     [23:21:56.989807130] (+0.000006495) sched_stat_runtime: { 1 }, { comm = "lttng-consumerd", tid = 1193, runtime = 330710, vruntime = 43368314098 }
     [23:21:56.989809993] (+0.000002863) sched_stat_runtime: { 0 }, { comm = "lttng-sessiond", tid = 1181, runtime = 1015313, vruntime = 36976733240 }
     [23:21:56.989818514] (+0.000008521) hrtimer_expire_exit: { 0 }, { hrtimer = 3993812192 }
     [23:21:56.989819631] (+0.000001117) hrtimer_expire_exit: { 1 }, { hrtimer = 3993865440 }
     [23:21:56.989821866] (+0.000002235) hrtimer_start: { 0 }, { hrtimer = 3993812192, function = 3238465232, expires = 79815981000000, softexpires = 79815981000000 }
     [23:21:56.989822984] (+0.000001118) hrtimer_start: { 1 }, { hrtimer = 3993865440, function = 3238465232, expires = 79815981000000, softexpires = 79815981000000 }
     [23:21:56.989832762] (+0.000009778) softirq_entry: { 1 }, { vec = 1 }
     [23:21:56.989833879] (+0.000001117) softirq_entry: { 0 }, { vec = 1 }
     [23:21:56.989838069] (+0.000004190) timer_cancel: { 1 }, { timer = 3993871956 }
     [23:21:56.989839187] (+0.000001118) timer_cancel: { 0 }, { timer = 3993818708 }
     [23:21:56.989841492] (+0.000002305) timer_expire_entry: { 1 }, { timer = 3993871956, now = 79515980, function = 3238277552 }
     [23:21:56.989842819] (+0.000001327) timer_expire_entry: { 0 }, { timer = 3993818708, now = 79515980, function = 3238277552 }
     [23:21:56.989854831] (+0.000012012) sched_stat_runtime: { 1 }, { comm = "lttng-consumerd", tid = 1193, runtime = 49237, vruntime = 43368363335 }
     [23:21:56.989855949] (+0.000001118) sched_stat_runtime: { 0 }, { comm = "lttng-sessiond", tid = 1181, runtime = 45121, vruntime = 36976778361 }
     [23:21:56.989861257] (+0.000005308) sched_stat_sleep: { 1 }, { comm = "kworker/1:1", tid = 21, delay = 9451318 }
     [23:21:56.989862374] (+0.000001117) sched_stat_sleep: { 0 }, { comm = "kworker/0:0", tid = 4, delay = 9958820 }
     [23:21:56.989868241] (+0.000005867) sched_wakeup: { 0 }, { comm = "kworker/0:0", tid = 4, prio = 120, success = 1, target_cpu = 0 }
     [23:21:56.989869358] (+0.000001117) sched_wakeup: { 1 }, { comm = "kworker/1:1", tid = 21, prio = 120, success = 1, target_cpu = 1 }
     [23:21:56.989877460] (+0.000008102) timer_expire_exit: { 1 }, { timer = 3993871956 }
     [23:21:56.989878577] (+0.000001117) timer_expire_exit: { 0 }, { timer = 3993818708 }
     .
     .
     .
                

You can now safely destroy the trace session (note that this doesn't delete the trace - it's still there in ~/lttng-traces):

     root@crownbay:~# lttng destroy
     Session auto-20121015-232120 destroyed at /home/root
                

Note that the trace is saved in a directory of the same name as returned by 'lttng create', under the ~/lttng-traces directory (note that you can change this by supplying your own name to 'lttng create'):

     root@crownbay:~# ls -al ~/lttng-traces
     drwxrwx---    3 root     root          1024 Oct 15 23:21 .
     drwxr-xr-x    5 root     root          1024 Oct 15 23:57 ..
     drwxrwx---    3 root     root          1024 Oct 15 23:21 auto-20121015-232120
                

For LTTng userspace tracing, you need to have a properly instrumented userspace program. For this example, we'll use the 'hello' test program generated by the lttng-ust build.

The 'hello' test program isn't installed on the rootfs by the lttng-ust build, so we need to copy it over manually. First cd into the build directory that contains the hello executable:

     $ cd build/tmp/work/core2_32-poky-linux/lttng-ust/2.0.5-r0/git/tests/hello/.libs
                

Copy that over to the target machine:

     $ scp hello root@192.168.1.20:
                

You now have the instrumented lttng 'hello world' test program on the target, ready to test.

First, from the host, ssh to the target:

     $ ssh -l root 192.168.1.47
     The authenticity of host '192.168.1.47 (192.168.1.47)' can't be established.
     RSA key fingerprint is 23:bd:c8:b1:a8:71:52:00:ee:00:4f:64:9e:10:b9:7e.
     Are you sure you want to continue connecting (yes/no)? yes
     Warning: Permanently added '192.168.1.47' (RSA) to the list of known hosts.
     root@192.168.1.47's password:
                

Once on the target, use these steps to create a trace:

     root@crownbay:~# lttng create
     Session auto-20190303-021943 created.
     Traces will be written in /home/root/lttng-traces/auto-20190303-021943
                

Enable the events you want to trace (in this case all userspace events):

     root@crownbay:~# lttng enable-event --userspace --all
     All UST events are enabled in channel channel0
                

Start the trace:

     root@crownbay:~# lttng start
     Tracing started for session auto-20190303-021943
                

Run the instrumented hello world program:

     root@crownbay:~# ./hello
     Hello, World!
     Tracing...  done.
                

And then stop the trace after awhile or after running a particular workload that you want to trace:

     root@crownbay:~# lttng stop
     Tracing stopped for session auto-20190303-021943
                

You can now view the trace in text form on the target:

     root@crownbay:~# lttng view
     [02:31:14.906146544] (+?.?????????) hello:1424 ust_tests_hello:tptest: { cpu_id = 1 }, { intfield = 0, intfield2 = 0x0, longfield = 0, netintfield = 0, netintfieldhex = 0x0, arrfield1 = [ [0] = 1, [1] = 2, [2] = 3 ], arrfield2 = "test", _seqfield1_length = 4, seqfield1 = [ [0] = 116, [1] = 101, [2] = 115, [3] = 116 ], _seqfield2_length = 4,  seqfield2 = "test", stringfield = "test", floatfield = 2222, doublefield = 2, boolfield = 1 }
     [02:31:14.906170360] (+0.000023816) hello:1424 ust_tests_hello:tptest: { cpu_id = 1 }, { intfield = 1, intfield2 = 0x1, longfield = 1, netintfield = 1, netintfieldhex = 0x1, arrfield1 = [ [0] = 1, [1] = 2, [2] = 3 ], arrfield2 = "test", _seqfield1_length = 4, seqfield1 = [ [0] = 116, [1] = 101, [2] = 115, [3] = 116 ], _seqfield2_length = 4, seqfield2 = "test", stringfield = "test", floatfield = 2222, doublefield = 2, boolfield = 1 }
     [02:31:14.906183140] (+0.000012780) hello:1424 ust_tests_hello:tptest: { cpu_id = 1 }, { intfield = 2, intfield2 = 0x2, longfield = 2, netintfield = 2, netintfieldhex = 0x2, arrfield1 = [ [0] = 1, [1] = 2, [2] = 3 ], arrfield2 = "test", _seqfield1_length = 4, seqfield1 = [ [0] = 116, [1] = 101, [2] = 115, [3] = 116 ], _seqfield2_length = 4, seqfield2 = "test", stringfield = "test", floatfield = 2222, doublefield = 2, boolfield = 1 }
     [02:31:14.906194385] (+0.000011245) hello:1424 ust_tests_hello:tptest: { cpu_id = 1 }, { intfield = 3, intfield2 = 0x3, longfield = 3, netintfield = 3, netintfieldhex = 0x3, arrfield1 = [ [0] = 1, [1] = 2, [2] = 3 ], arrfield2 = "test", _seqfield1_length = 4, seqfield1 = [ [0] = 116, [1] = 101, [2] = 115, [3] = 116 ], _seqfield2_length = 4, seqfield2 = "test", stringfield = "test", floatfield = 2222, doublefield = 2, boolfield = 1 }
     .
     .
     .
                

You can now safely destroy the trace session (note that this doesn't delete the trace - it's still there in ~/lttng-traces):

     root@crownbay:~# lttng destroy
     Session auto-20190303-021943 destroyed at /home/root
                

blktrace and blkparse are designed from the ground up to be able to operate together in a 'pipe mode' where the stdout of blktrace can be fed directly into the stdin of blkparse:

     root@crownbay:~# blktrace /dev/sdc -o - | blkparse -i -
                

This enables long-lived tracing sessions to run without writing anything to disk, and allows the user to look for certain conditions in the trace data in 'real-time' by viewing the trace output as it scrolls by on the screen or by passing it along to yet another program in the pipeline such as grep which can be used to identify and capture conditions of interest.

There's actually another blktrace command that implements the above pipeline as a single command, so the user doesn't have to bother typing in the above command sequence:

     root@crownbay:~# btrace /dev/sdc
                

Because blktrace traces block I/O and at the same time normally writes its trace data to a block device, and in general because it's not really a great idea to make the device being traced the same as the device the tracer writes to, blktrace provides a way to trace without perturbing the traced device at all by providing native support for sending all trace data over the network.

To have blktrace operate in this mode, start blktrace on the target system being traced with the -l option, along with the device to trace:

     root@crownbay:~# blktrace -l /dev/sdc
     server: waiting for connections...
                

On the host system, use the -h option to connect to the target system, also passing it the device to trace:

     $ blktrace -d /dev/sdc -h 192.168.1.43
     blktrace: connecting to 192.168.1.43
     blktrace: connected!
                

On the target system, you should see this:

     server: connection from 192.168.1.43
                

In another shell, execute a workload you want to trace.

     root@crownbay:/media/sdc# rm linux-2.6.19.2.tar.bz2; wget http://downloads.yoctoproject.org/mirror/sources/linux-2.6.19.2.tar.bz2; sync
     Connecting to downloads.yoctoproject.org (140.211.169.59:80)
     linux-2.6.19.2.tar.b 100% |*******************************| 41727k  0:00:00 ETA
                

When it's done, do a Ctrl-C on the host system to stop the trace:

     ^C=== sdc ===
      CPU  0:                 7691 events,      361 KiB data
      CPU  1:                 4109 events,      193 KiB data
      Total:                 11800 events (dropped 0),      554 KiB data
                

On the target system, you should also see a trace summary for the trace just ended:

     server: end of run for 192.168.1.43:sdc
     === sdc ===
      CPU  0:                 7691 events,      361 KiB data
      CPU  1:                 4109 events,      193 KiB data
      Total:                 11800 events (dropped 0),      554 KiB data
                

The blktrace instance on the host will save the target output inside a hostname-timestamp directory:

     $ ls -al
     drwxr-xr-x   10 root     root          1024 Oct 28 02:40 .
     drwxr-sr-x    4 root     root          1024 Oct 26 18:24 ..
     drwxr-xr-x    2 root     root          1024 Oct 28 02:40 192.168.1.43-2012-10-28-02:40:56
                

cd into that directory to see the output files:

     $ ls -l
     -rw-r--r--    1 root     root        369193 Oct 28 02:44 sdc.blktrace.0
     -rw-r--r--    1 root     root        197278 Oct 28 02:44 sdc.blktrace.1
                

And run blkparse on the host system using the device name:

     $ blkparse sdc

      8,32   1        1     0.000000000  1263  Q  RM 6016 + 8 [ls]
      8,32   1        0     0.000036038     0  m   N cfq1263 alloced
      8,32   1        2     0.000039390  1263  G  RM 6016 + 8 [ls]
      8,32   1        3     0.000049168  1263  I  RM 6016 + 8 [ls]
      8,32   1        0     0.000056152     0  m   N cfq1263 insert_request
      8,32   1        0     0.000061600     0  m   N cfq1263 add_to_rr
      8,32   1        0     0.000075498     0  m   N cfq workload slice:300
      .
      .
      .
      8,32   0        0   177.266385696     0  m   N cfq1267 arm_idle: 8 group_idle: 0
      8,32   0        0   177.266388140     0  m   N cfq schedule dispatch
      8,32   1        0   177.266679239     0  m   N cfq1267 slice expired t=0
      8,32   1        0   177.266689297     0  m   N cfq1267 sl_used=9 disp=6 charge=9 iops=0 sect=56
      8,32   1        0   177.266692649     0  m   N cfq1267 del_from_rr
      8,32   1        0   177.266696560     0  m   N cfq1267 put_queue

     CPU0 (sdc):
      Reads Queued:           0,        0KiB	 Writes Queued:         270,   21,708KiB
      Read Dispatches:       59,    2,628KiB	 Write Dispatches:      495,   39,964KiB
      Reads Requeued:         0		 Writes Requeued:         0
      Reads Completed:       90,    2,752KiB	 Writes Completed:      543,   41,596KiB
      Read Merges:            0,        0KiB	 Write Merges:            9,      344KiB
      Read depth:             2        	 Write depth:             2
      IO unplugs:            20        	 Timer unplugs:           1
     CPU1 (sdc):
      Reads Queued:         688,    2,752KiB	 Writes Queued:         381,   20,652KiB
      Read Dispatches:       31,      124KiB	 Write Dispatches:       59,    2,396KiB
      Reads Requeued:         0		 Writes Requeued:         0
      Reads Completed:        0,        0KiB	 Writes Completed:       11,      764KiB
      Read Merges:          598,    2,392KiB	 Write Merges:           88,      448KiB
      Read depth:             2        	 Write depth:             2
      IO unplugs:            52        	 Timer unplugs:           0

     Total (sdc):
      Reads Queued:         688,    2,752KiB	 Writes Queued:         651,   42,360KiB
      Read Dispatches:       90,    2,752KiB	 Write Dispatches:      554,   42,360KiB
      Reads Requeued:         0		 Writes Requeued:         0
      Reads Completed:       90,    2,752KiB	 Writes Completed:      554,   42,360KiB
      Read Merges:          598,    2,392KiB	 Write Merges:           97,      792KiB
      IO unplugs:            72        	 Timer unplugs:           1

     Throughput (R/W): 15KiB/s / 238KiB/s
     Events (sdc): 9,301 entries
     Skips: 0 forward (0 -   0.0%)
                

You should see the trace events and summary just as you would have if you'd run the same command on the target.

It's also possible to trace block I/O using only trace events subsystem, which can be useful for casual tracing if you don't want to bother dealing with the userspace tools.

To enable tracing for a given device, use /sys/block/xxx/trace/enable, where xxx is the device name. This for example enables tracing for /dev/sdc:

     root@crownbay:/sys/kernel/debug/tracing# echo 1 > /sys/block/sdc/trace/enable
                

Once you've selected the device(s) you want to trace, selecting the 'blk' tracer will turn the blk tracer on:

     root@crownbay:/sys/kernel/debug/tracing# cat available_tracers
     blk function_graph function nop

     root@crownbay:/sys/kernel/debug/tracing# echo blk > current_tracer
                

Execute the workload you're interested in:

     root@crownbay:/sys/kernel/debug/tracing# cat /media/sdc/testfile.txt
                

And look at the output (note here that we're using 'trace_pipe' instead of trace to capture this trace - this allows us to wait around on the pipe for data to appear):

     root@crownbay:/sys/kernel/debug/tracing# cat trace_pipe
                 cat-3587  [001] d..1  3023.276361:   8,32   Q   R 1699848 + 8 [cat]
                 cat-3587  [001] d..1  3023.276410:   8,32   m   N cfq3587 alloced
                 cat-3587  [001] d..1  3023.276415:   8,32   G   R 1699848 + 8 [cat]
                 cat-3587  [001] d..1  3023.276424:   8,32   P   N [cat]
                 cat-3587  [001] d..2  3023.276432:   8,32   I   R 1699848 + 8 [cat]
                 cat-3587  [001] d..1  3023.276439:   8,32   m   N cfq3587 insert_request
                 cat-3587  [001] d..1  3023.276445:   8,32   m   N cfq3587 add_to_rr
                 cat-3587  [001] d..2  3023.276454:   8,32   U   N [cat] 1
                 cat-3587  [001] d..1  3023.276464:   8,32   m   N cfq workload slice:150
                 cat-3587  [001] d..1  3023.276471:   8,32   m   N cfq3587 set_active wl_prio:0 wl_type:2
                 cat-3587  [001] d..1  3023.276478:   8,32   m   N cfq3587 fifo=  (null)
                 cat-3587  [001] d..1  3023.276483:   8,32   m   N cfq3587 dispatch_insert
                 cat-3587  [001] d..1  3023.276490:   8,32   m   N cfq3587 dispatched a request
                 cat-3587  [001] d..1  3023.276497:   8,32   m   N cfq3587 activate rq, drv=1
                 cat-3587  [001] d..2  3023.276500:   8,32   D   R 1699848 + 8 [cat]
                

And this turns off tracing for the specified device:

     root@crownbay:/sys/kernel/debug/tracing# echo 0 > /sys/block/sdc/trace/enable