perf tools: Handle partial AUX records and print a warning

This patch decodes the 'partial' flag in AUX records and prints
a warning to the user, so that they don't have to guess why their
PT traces contain gaps (or missing altogether):

  Warning:
  AUX data had gaps in it 8 times out of 8!

  Are you running a KVM guest in the background?

Trying to be even more helpful, we will detect if the user's kvm driver sets up
exclusive VMX root mode for the entire lifespan of the kvm process:

  Reloading kvm_intel module with vmm_exclusive=0
  will reduce the gaps to only guest's timeslices.

Note however, that you'll still have gaps in cpu-wide traces even with
vmm_exclusive=0, but the number of gaps will be below 100% (as opposed to the
above example).

Currently this is the only reason for partial records.

Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Stephane Eranian <eranian@google.com>
Cc: Vince Weaver <vince@deater.net>
Link: http://lkml.kernel.org/r/8760j941ig.fsf@ashishki-desk.ger.corp.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 33fc2e9c0b0cc7e48241332a07d2cc854363c878..76b9c6bc8369617a9a1dde0f7da0254102a897c0 100644 (file)
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -1288,11 +1288,12 @@ int perf_event__process_exit(struct perf_tool *tool __maybe_unused,
 
 size_t perf_event__fprintf_aux(union perf_event *event, FILE *fp)
 {
-       return fprintf(fp, " offset: %#"PRIx64" size: %#"PRIx64" flags: %#"PRIx64" [%s%s]\n",
+       return fprintf(fp, " offset: %#"PRIx64" size: %#"PRIx64" flags: %#"PRIx64" [%s%s%s]\n",
                       event->aux.aux_offset, event->aux.aux_size,
                       event->aux.flags,
                       event->aux.flags & PERF_AUX_FLAG_TRUNCATED ? "T" : "",
-                      event->aux.flags & PERF_AUX_FLAG_OVERWRITE ? "O" : "");
+                      event->aux.flags & PERF_AUX_FLAG_OVERWRITE ? "O" : "",
+                      event->aux.flags & PERF_AUX_FLAG_PARTIAL   ? "P" : "");
 }
 
 size_t perf_event__fprintf_itrace_start(union perf_event *event, FILE *fp)

diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index e1d8166ebbd58f5184f40c64014c854b45514d0b..eb7a7b200737713a929883bc250093bd687e48ad 100644 (file)
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -276,6 +276,7 @@ struct events_stats {
        u64 total_lost;
        u64 total_lost_samples;
        u64 total_aux_lost;
+       u64 total_aux_partial;
        u64 total_invalid_chains;
        u32 nr_events[PERF_RECORD_HEADER_MAX];
        u32 nr_non_filtered_samples;

diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index ae42e742d46181963cbeaebbb90b72928929b5a3..24259bc2c598faa4187f8eb3a4538560cc913552 100644 (file)
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1,5 +1,6 @@
 #include <linux/kernel.h>
 #include <traceevent/event-parse.h>
+#include <api/fs/fs.h>
 
 #include <byteswap.h>
 #include <unistd.h>
@@ -1260,9 +1261,12 @@ static int machines__deliver_event(struct machines *machines,
        case PERF_RECORD_UNTHROTTLE:
                return tool->unthrottle(tool, event, sample, machine);
        case PERF_RECORD_AUX:
-               if (tool->aux == perf_event__process_aux &&
-                   (event->aux.flags & PERF_AUX_FLAG_TRUNCATED))
-                       evlist->stats.total_aux_lost += 1;
+               if (tool->aux == perf_event__process_aux) {
+                       if (event->aux.flags & PERF_AUX_FLAG_TRUNCATED)
+                               evlist->stats.total_aux_lost += 1;
+                       if (event->aux.flags & PERF_AUX_FLAG_PARTIAL)
+                               evlist->stats.total_aux_partial += 1;
+               }
                return tool->aux(tool, event, sample, machine);
        case PERF_RECORD_ITRACE_START:
                return tool->itrace_start(tool, event, sample, machine);
@@ -1555,6 +1559,23 @@ static void perf_session__warn_about_errors(const struct perf_session *session)
                            stats->nr_events[PERF_RECORD_AUX]);
        }
 
+       if (session->tool->aux == perf_event__process_aux &&
+           stats->total_aux_partial != 0) {
+               bool vmm_exclusive = false;
+
+               (void)sysfs__read_bool("module/kvm_intel/parameters/vmm_exclusive",
+                                      &vmm_exclusive);
+
+               ui__warning("AUX data had gaps in it %" PRIu64 " times out of %u!\n\n"
+                           "Are you running a KVM guest in the background?%s\n\n",
+                           stats->total_aux_partial,
+                           stats->nr_events[PERF_RECORD_AUX],
+                           vmm_exclusive ?
+                           "\nReloading kvm_intel module with vmm_exclusive=0\n"
+                           "will reduce the gaps to only guest's timeslices." :
+                           "");
+       }
+
        if (stats->nr_unknown_events != 0) {
                ui__warning("Found %u unknown events!\n\n"
                            "Is this an older tool processing a perf.data "