From a84fb5c63b3fc5376a271423b6bf2887c414282b Mon Sep 17 00:00:00 2001
From: Thomas Applencourt
 <applenco@aurora-uan-0012.hostmgmt.cm.aurora.alcf.anl.gov>
Date: Mon, 30 Sep 2024 22:04:33 +0000
Subject: [PATCH 1/2] better error message when bin doesn't exist

---
 xprof/xprof.rb.in | 49 +++++++++++++++++++++++++++++++----------------
 1 file changed, 32 insertions(+), 17 deletions(-)

diff --git a/xprof/xprof.rb.in b/xprof/xprof.rb.in
index 9b115c23..404987f3 100755
--- a/xprof/xprof.rb.in
+++ b/xprof/xprof.rb.in
@@ -307,12 +307,12 @@ class Sync_daemon
   # we always call clean-up the daemon
   def self.open
     yield f = new
-  rescue StandardError
-    raise
   ensure
-    return unless f
-    f.global_barrier
-    f.finalize
+    # https://www.rubydoc.info/gems/rubocop/RuboCop/Cop/Lint/EnsureReturn
+    if f
+      f.global_barrier
+      f.finalize
+    end
   end
 end
 
@@ -346,8 +346,7 @@ def env_tracers
    %w[ze ze libze_loader libTracerZE],
    %w[cuda cuda libcuda libTracerCUDA],
    %w[hip hip libamdhip64 libTracerHIP],
-   %w[mpi mpi libmpi libTracerMPI],
-  ].each do |name, bt_name, lib, libtracer|
+   %w[mpi mpi libmpi libTracerMPI]].each do |name, bt_name, lib, libtracer|
     # Backend requested, skip omp. It will be handled in a custom case bellow
     next unless OPTIONS[:'backend-names'].include?(bt_name)
 
@@ -430,6 +429,9 @@ def launch_usr_bin(env, cmd)
     LOGGER.warn { 'Application Exited' }
   rescue Interrupt
     LOGGER.warn { 'Application Received Interrupt Signal' }
+  rescue Errno::ENOENT
+    warn("#{__FILE__}: Can't find executable #{cmd.first}")
+    raise Errno::ENOENT
   end
 end
 
@@ -570,11 +572,13 @@ end
 
 def lm_lttng_teardown_session
   raise unless mpi_local_master?
+
   exec("lttng destroy #{lttng_session_uuid}")
 end
 
 def lm_lttng_kill_sessiond
   raise unless mpi_local_master?
+
   # Need to kill the sessiond Daemon. It's safe because each job has their own
   #
   # In theory, opening the lttng-sessiond.pid file is racy.
@@ -650,7 +654,19 @@ end
 
 # Start, Stop lttng, amd do the on-node analsysis
 def trace_and_on_node_processing(usr_argv)
-  # Global barrier at exit
+  def teardown_lttng(syncd)
+    # We need to be sure that all the local ranks are finished
+    # before the local master stops the lttng session
+    syncd.local_barrier('waiting_for_application_ending')
+    return unless mpi_local_master?
+
+    # Stop Lttng session
+    lm_lttng_teardown_session
+    # Lttng session is finished,
+    # we can kill the session daemon
+    lm_lttng_kill_sessiond
+  end
+
   Sync_daemon.open do |syncd|
     # Load Tracers and APILoaders Lib
     backends, h = env_tracers
@@ -661,19 +677,18 @@ def trace_and_on_node_processing(usr_argv)
     # Only local master spawn LTTNG daemon and start session
     lm_setup_lttng(backends) if mpi_local_master?
     syncd.local_barrier('waiting_for_lttng_setup')
+
     # Launch User Command
-    launch_usr_bin(h, usr_argv)
+    begin
+      launch_usr_bin(h, usr_argv)
+    rescue Errno::ENOENT
+      teardown_lttng(syncd)
+      exit(1)
+    end
 
-    # We need to be sure that all the local ranks are finished
-    # before the local master stops the lttng session
-    syncd.local_barrier('waiting_for_application_ending')
+    teardown_lttng(syncd)
     return unless mpi_local_master?
 
-    # Stop Lttng session
-    lm_lttng_teardown_session
-    # Lttng session is finished,
-    # we can kill the session daemon
-    lm_lttng_kill_sessiond
     # Preprocess trace
     lm_babeltrace(backends)
     lm_move_to_shared

From 19c3b4ddb7f39777df402d91b34f975f54b04ada Mon Sep 17 00:00:00 2001
From: Thomas Applencourt
 <applenco@aurora-uan-0012.hostmgmt.cm.aurora.alcf.anl.gov>
Date: Mon, 30 Sep 2024 22:54:19 +0000
Subject: [PATCH 2/2] fix daemon not run

---
 xprof/xprof.rb.in | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/xprof/xprof.rb.in b/xprof/xprof.rb.in
index 404987f3..0a2ed09a 100755
--- a/xprof/xprof.rb.in
+++ b/xprof/xprof.rb.in
@@ -307,6 +307,8 @@ class Sync_daemon
   # we always call clean-up the daemon
   def self.open
     yield f = new
+  rescue Errno::ENOENT
+    exit(1)
   ensure
     # https://www.rubydoc.info/gems/rubocop/RuboCop/Cop/Lint/EnsureReturn
     if f
@@ -683,7 +685,7 @@ def trace_and_on_node_processing(usr_argv)
       launch_usr_bin(h, usr_argv)
     rescue Errno::ENOENT
       teardown_lttng(syncd)
-      exit(1)
+      raise
     end
 
     teardown_lttng(syncd)