[PATCH yocto-autobuilder-helper] summarize_top_output.py: add script, use it and publish summary


sakib.sajal@...
 

summarize_top_output.py is used to summarize the top
output that is captured during autobuilder intermittent
failures.

Use the script to summarize the host top output and
publish the summary that is created instead of
the raw logfile.

Signed-off-by: Sakib Sajal <sakib.sajal@windriver.com>
---
scripts/collect-results | 2 +-
scripts/generate-testresult-index.py | 2 +-
scripts/run-config | 1 +
scripts/summarize_top_output.py | 132 +++++++++++++++++++++++++++
4 files changed, 135 insertions(+), 2 deletions(-)
create mode 100755 scripts/summarize_top_output.py

diff --git a/scripts/collect-results b/scripts/collect-results
index 7474e36..7178380 100755
--- a/scripts/collect-results
+++ b/scripts/collect-results
@@ -19,7 +19,7 @@ if [ -e $WORKDIR/buildhistory ]; then
fi

HSFILE=$WORKDIR/tmp/buildstats/*/host_stats
-d=`date +%Y-%m-%d--%H-%M`
+d="intermittent_failure_host_data"

mkdir -p $DEST/$target/$d

diff --git a/scripts/generate-testresult-index.py b/scripts/generate-testresult-index.py
index 7fdc17c..d85d606 100755
--- a/scripts/generate-testresult-index.py
+++ b/scripts/generate-testresult-index.py
@@ -154,7 +154,7 @@ for build in sorted(os.listdir(path), key=keygen, reverse=True):
hd = []
counter = 0
# do we really need the loop?
- for p in glob.glob(buildpath + "/*/*/host_stats*top.txt"):
+ for p in glob.glob(buildpath + "/*/*/host_stats*top_summary.txt"):
n_split = p.split(build)
res = reldir[0:-1] + n_split[1]
hd.append((res, str(counter)))
diff --git a/scripts/run-config b/scripts/run-config
index 8ed88cf..82de91f 100755
--- a/scripts/run-config
+++ b/scripts/run-config
@@ -327,6 +327,7 @@ elif args.phase == "finish" and args.stepname == "collect-results":
if args.results_dir:
hp.printheader("Running results collection")
runcmd([scriptsdir + "/collect-results", args.builddir, args.results_dir, args.target])
+ runcmd([scriptsdir + "/summarize_top_output.py", args.results_dir, args.target])
sys.exit(0)

if jcfg:
diff --git a/scripts/summarize_top_output.py b/scripts/summarize_top_output.py
new file mode 100755
index 0000000..0606a34
--- /dev/null
+++ b/scripts/summarize_top_output.py
@@ -0,0 +1,132 @@
+#!/usr/bin/env python3
+
+import os, sys, glob
+
+# constants
+top_header = 7
+top_summary = 5
+max_cols = 11
+
+# string substitution to make things easier to read
+subs = {
+ "/home/pokybuild/yocto-worker/" : "~/",
+ "/build/build/tmp/work/core2-32-poky-linux/" : "/.../POKY_32/.../",
+ "/build/build/tmp/work/core2-64-poky-linux/" : "/.../POKY_64/.../",
+ "/recipe-sysroot-native/usr/bin/x86_64-poky-linux/../../libexec/x86_64-poky-linux/gcc/x86_64-poky-linux/" : "/...GCC.../"
+}
+
+def usage():
+ print("Usage: " + sys.argv[0] + " <dest> <target>")
+
+def list_top_outputs(logfile):
+ # top delimiter
+ top_start = "start: top output"
+ top_end = "end: top output"
+
+ # list of top outputs
+ top_outputs = []
+
+ # flag
+ collect = False
+ with open(logfile) as log:
+ top_output = []
+ for line in log:
+ lstrip = line.strip()
+ if collect:
+ if lstrip.startswith(top_end):
+ collect = False
+ top_outputs.append(top_output)
+ top_output = []
+ else:
+ top_output.append(lstrip)
+ if lstrip.startswith(top_start):
+ collect = True
+
+ return top_outputs
+
+def summarize_top(top_outs):
+ summaries = []
+ kernel_summaries = []
+ short_summaries = []
+ for top_out in top_outs:
+ summary = {}
+ kernel_summary = {}
+ short_summary = top_out[:top_summary]
+ for line in top_out[top_header:]:
+ cmd = line.split(maxsplit=max_cols)[-1]
+ # kernel processes
+ if cmd[0] == "[" and cmd[-1] == "]":
+ kproc = cmd[1:-1].split("/")[0]
+ if kproc not in kernel_summary:
+ kernel_summary[kproc] = 1
+ else:
+ kernel_summary[kproc] += 1
+ continue
+ cmd_split = cmd.split()
+ prog = cmd_split[0]
+ if prog not in summary:
+ summary[prog] = 1
+ else:
+ summary[prog] += 1
+ summary = dict(sorted(summary.items(), key=lambda item: item[1], reverse=True))
+ kernel_summary = dict(sorted(kernel_summary.items(), key=lambda item: item[1], reverse=True))
+
+ summaries.append(summary)
+ kernel_summaries.append(kernel_summary)
+ short_summaries.append(short_summary)
+
+ return (short_summaries, summaries, kernel_summaries)
+
+def summarize_path(path):
+ p = path
+ for k, v in subs.items():
+ p = p.replace(k, v)
+ return p
+
+def write_summary(short_summary, summary, kernel_summary, logfile):
+ dirname = os.path.dirname(logfile)
+ fname = os.path.basename(logfile)
+ report_name = fname.split(".")[0] + "_summary.txt"
+ outfile = os.path.join(dirname, report_name)
+ out = "NOTE: program names have been shortened for better readability.\nSubstitutions are as follows:\n"
+ for k, v in subs.items():
+ out += (v + " = " + k + "\n")
+ out += "\n"
+
+ out += "top was invoked " + str(len(short_summary)) + " times.\n\n"
+
+ for i in range(len(short_summary)):
+ for l in short_summary[i]:
+ out += (l + "\n")
+
+ out += ("\nSummary: " + "\n")
+ for k, v in summary[i].items():
+ if v > 1:
+ r = summarize_path(k)
+ out += (str(v) + " " + r + "\n")
+
+ out += ("\nKernel Summary: " + "\n")
+ for k, v in kernel_summary[i].items():
+ if v > 1:
+ r = summarize_path(k)
+ out += (str(v) + " " + r + "\n")
+ out += ("\n")
+
+ with open(outfile, "w") as of:
+ of.write(out)
+
+def main():
+ if len(sys.argv) != 3:
+ usage()
+ sys.exit()
+
+ dest = sys.argv[1]
+ target = sys.argv[2]
+ host_data_dir = "intermittent_failure_host_data"
+ directory = os.path.join(dest, target, host_data_dir)
+ for f in glob.glob(directory + "/*_top.txt"):
+ outputs = list_top_outputs(f)
+ short_summary, summary, kernel_summary = summarize_top(outputs)
+ write_summary(short_summary, summary, kernel_summary, f)
+
+main()
--
2.25.1


Randy MacLeod
 

On 2021-06-16 4:43 a.m., sakib.sajal@windriver.com wrote:
summarize_top_output.py is used to summarize the top
output that is captured during autobuilder intermittent
failures.
Use the script to summarize the host top output and
publish the summary that is created instead of
the raw logfile.

Looks good Sakib,

Can you show people what the typical output looks like?
Is the raw top output still published?

../Randy


Signed-off-by: Sakib Sajal <sakib.sajal@windriver.com>
---
scripts/collect-results | 2 +-
scripts/generate-testresult-index.py | 2 +-
scripts/run-config | 1 +
scripts/summarize_top_output.py | 132 +++++++++++++++++++++++++++
4 files changed, 135 insertions(+), 2 deletions(-)
create mode 100755 scripts/summarize_top_output.py
diff --git a/scripts/collect-results b/scripts/collect-results
index 7474e36..7178380 100755
--- a/scripts/collect-results
+++ b/scripts/collect-results
@@ -19,7 +19,7 @@ if [ -e $WORKDIR/buildhistory ]; then
fi
HSFILE=$WORKDIR/tmp/buildstats/*/host_stats
-d=`date +%Y-%m-%d--%H-%M`
+d="intermittent_failure_host_data"
mkdir -p $DEST/$target/$d
diff --git a/scripts/generate-testresult-index.py b/scripts/generate-testresult-index.py
index 7fdc17c..d85d606 100755
--- a/scripts/generate-testresult-index.py
+++ b/scripts/generate-testresult-index.py
@@ -154,7 +154,7 @@ for build in sorted(os.listdir(path), key=keygen, reverse=True):
hd = []
counter = 0
# do we really need the loop?
- for p in glob.glob(buildpath + "/*/*/host_stats*top.txt"):
+ for p in glob.glob(buildpath + "/*/*/host_stats*top_summary.txt"):
n_split = p.split(build)
res = reldir[0:-1] + n_split[1]
hd.append((res, str(counter)))
diff --git a/scripts/run-config b/scripts/run-config
index 8ed88cf..82de91f 100755
--- a/scripts/run-config
+++ b/scripts/run-config
@@ -327,6 +327,7 @@ elif args.phase == "finish" and args.stepname == "collect-results":
if args.results_dir:
hp.printheader("Running results collection")
runcmd([scriptsdir + "/collect-results", args.builddir, args.results_dir, args.target])
+ runcmd([scriptsdir + "/summarize_top_output.py", args.results_dir, args.target])
sys.exit(0)
if jcfg:
diff --git a/scripts/summarize_top_output.py b/scripts/summarize_top_output.py
new file mode 100755
index 0000000..0606a34
--- /dev/null
+++ b/scripts/summarize_top_output.py
@@ -0,0 +1,132 @@
+#!/usr/bin/env python3
+
+import os, sys, glob
+
+# constants
+top_header = 7
+top_summary = 5
+max_cols = 11
+
+# string substitution to make things easier to read
+subs = {
+ "/home/pokybuild/yocto-worker/" : "~/",
+ "/build/build/tmp/work/core2-32-poky-linux/" : "/.../POKY_32/.../",
+ "/build/build/tmp/work/core2-64-poky-linux/" : "/.../POKY_64/.../",
+ "/recipe-sysroot-native/usr/bin/x86_64-poky-linux/../../libexec/x86_64-poky-linux/gcc/x86_64-poky-linux/" : "/...GCC.../"
+}
+
+def usage():
+ print("Usage: " + sys.argv[0] + " <dest> <target>")
+
+def list_top_outputs(logfile):
+ # top delimiter
+ top_start = "start: top output"
+ top_end = "end: top output"
+
+ # list of top outputs
+ top_outputs = []
+
+ # flag
+ collect = False
+ with open(logfile) as log:
+ top_output = []
+ for line in log:
+ lstrip = line.strip()
+ if collect:
+ if lstrip.startswith(top_end):
+ collect = False
+ top_outputs.append(top_output)
+ top_output = []
+ else:
+ top_output.append(lstrip)
+ if lstrip.startswith(top_start):
+ collect = True
+
+ return top_outputs
+
+def summarize_top(top_outs):
+ summaries = []
+ kernel_summaries = []
+ short_summaries = []
+ for top_out in top_outs:
+ summary = {}
+ kernel_summary = {}
+ short_summary = top_out[:top_summary]
+ for line in top_out[top_header:]:
+ cmd = line.split(maxsplit=max_cols)[-1]
+ # kernel processes
+ if cmd[0] == "[" and cmd[-1] == "]":
+ kproc = cmd[1:-1].split("/")[0]
+ if kproc not in kernel_summary:
+ kernel_summary[kproc] = 1
+ else:
+ kernel_summary[kproc] += 1
+ continue
+ cmd_split = cmd.split()
+ prog = cmd_split[0]
+ if prog not in summary:
+ summary[prog] = 1
+ else:
+ summary[prog] += 1
+ summary = dict(sorted(summary.items(), key=lambda item: item[1], reverse=True))
+ kernel_summary = dict(sorted(kernel_summary.items(), key=lambda item: item[1], reverse=True))
+
+ summaries.append(summary)
+ kernel_summaries.append(kernel_summary)
+ short_summaries.append(short_summary)
+
+ return (short_summaries, summaries, kernel_summaries)
+
+def summarize_path(path):
+ p = path
+ for k, v in subs.items():
+ p = p.replace(k, v)
+ return p
+
+def write_summary(short_summary, summary, kernel_summary, logfile):
+ dirname = os.path.dirname(logfile)
+ fname = os.path.basename(logfile)
+ report_name = fname.split(".")[0] + "_summary.txt"
+ outfile = os.path.join(dirname, report_name)
+ out = "NOTE: program names have been shortened for better readability.\nSubstitutions are as follows:\n"
+ for k, v in subs.items():
+ out += (v + " = " + k + "\n")
+ out += "\n"
+
+ out += "top was invoked " + str(len(short_summary)) + " times.\n\n"
+
+ for i in range(len(short_summary)):
+ for l in short_summary[i]:
+ out += (l + "\n")
+
+ out += ("\nSummary: " + "\n")
+ for k, v in summary[i].items():
+ if v > 1:
+ r = summarize_path(k)
+ out += (str(v) + " " + r + "\n")
+
+ out += ("\nKernel Summary: " + "\n")
+ for k, v in kernel_summary[i].items():
+ if v > 1:
+ r = summarize_path(k)
+ out += (str(v) + " " + r + "\n")
+ out += ("\n")
+
+ with open(outfile, "w") as of:
+ of.write(out)
+
+def main():
+ if len(sys.argv) != 3:
+ usage()
+ sys.exit()
+
+ dest = sys.argv[1]
+ target = sys.argv[2]
+ host_data_dir = "intermittent_failure_host_data"
+ directory = os.path.join(dest, target, host_data_dir)
+ for f in glob.glob(directory + "/*_top.txt"):
+ outputs = list_top_outputs(f)
+ short_summary, summary, kernel_summary = summarize_top(outputs)
+ write_summary(short_summary, summary, kernel_summary, f)
+
+main()

--
# Randy MacLeod
# Wind River Linux


Richard Purdie
 

On Wed, 2021-06-16 at 04:43 -0400, sakib.sajal@windriver.com wrote:
summarize_top_output.py is used to summarize the top
output that is captured during autobuilder intermittent
failures.

Use the script to summarize the host top output and
publish the summary that is created instead of
the raw logfile.


[...]
 if jcfg:
diff --git a/scripts/summarize_top_output.py b/scripts/summarize_top_output.py
new file mode 100755
index 0000000..0606a34
--- /dev/null
+++ b/scripts/summarize_top_output.py
@@ -0,0 +1,132 @@
+#!/usr/bin/env python3
+
+import os, sys, glob
+
+# constants
+top_header = 7
+top_summary = 5
+max_cols = 11
+
+# string substitution to make things easier to read
+subs = {
+ "/home/pokybuild/yocto-worker/" : "~/",
+ "/build/build/tmp/work/core2-32-poky-linux/" : "/.../POKY_32/.../",
+ "/build/build/tmp/work/core2-64-poky-linux/" : "/.../POKY_64/.../",
+ "/recipe-sysroot-native/usr/bin/x86_64-poky-linux/../../libexec/x86_64-poky-linux/gcc/x86_64-poky-linux/" : "/...GCC.../"
+}
One quick question - the above assumes an x86 target machine using those two tunes. 
Should that be wildcarded?

Cheers,

Richard


sakib.sajal@...
 

On 2021-06-16 11:41 a.m., Randy MacLeod wrote:
On 2021-06-16 4:43 a.m., sakib.sajal@windriver.com wrote:
summarize_top_output.py is used to summarize the top
output that is captured during autobuilder intermittent
failures.

Use the script to summarize the host top output and
publish the summary that is created instead of
the raw logfile.

Looks good Sakib,

Can you show people what the typical output looks like?
Is the raw top output still published?

../Randy
The script goes over the raw logfile (for example, foo.txt) which consists of multiple top outputs and summarizes each top output and writes them to foo_summary.txt

Some improvements that can be made:

1) create a separate file for each top summary, ie, if foo.txt has n top outputs, create foo_summary_[1...n].txt

2) since python3 is used to run many different kinds of jobs, it is difficult to generalize python3 threads. the script can be modified to log all the different jobs run under python3, right now it only counts the processes that are running python3.

Any feedback is welcome!

Sample output:

NOTE: program names have been shortened for better readability.
Substitutions are as follows:
~/ = /home/pokybuild/yocto-worker/
/.../POKY_32/.../ = /build/build/tmp/work/core2-32-poky-linux/
/.../POKY_64/.../ = /build/build/tmp/work/core2-64-poky-linux/
/...GCC.../ = /recipe-sysroot-native/usr/bin/x86_64-poky-linux/../../libexec/x86_64-poky-linux/gcc/x86_64-poky-linux/

top was invoked 12 times.

top - 16:51:30 up 4 days, 19:26,  1 user,  load average: 93.84, 57.26, 48.58
Tasks: 1084 total,  80 running, 664 sleeping,   0 stopped,   0 zombie
%Cpu(s):  2.1 us,  2.0 sy,  9.8 ni, 83.1 id,  2.9 wa,  0.0 hi, 0.0 si,  0.0 st
KiB Mem : 13192559+total,  5571436 free, 14307780 used, 11204637+buff/cache
KiB Swap:  8388604 total,  8239384 free,   149220 used. 11455193+avail Mem

Summary:
85  /bin/sh
41  python3
39  /bin/bash
30  x86_64-poky-linux-g++
29  make
16 ~/meta-oe/.../POKY_64/.../cpprest/2.10.18-r0/...GCC.../11.1.0/cc1plus
16 ~/meta-oe/.../POKY_64/.../libvpx/1.8.2-r0/...GCC.../11.1.0/cc1plus
16  ~/meta-oe/.../POKY_64/.../libvpx/1.8.2-r0/...GCC.../11.1.0/as
16 ~/meta-oe/.../POKY_64/.../cpprest/2.10.18-r0/recipe-sysroot-native/usr/bin/x86_64-poky-linux/x86_64-poky-linux-g++
16 ~/meta-oe/.../POKY_64/.../cpprest/2.10.18-r0/...GCC.../11.1.0/as
14 ~/meta-oe/.../POKY_64/.../rtorrent/0.9.8-r0/...GCC.../11.1.0/cc1plus
14 ~/meta-oe/.../POKY_64/.../rtorrent/0.9.8-r0/...GCC.../11.1.0/as
13 ~/meta-oe/.../POKY_64/.../vulkan-cts/1.2.6.0-r0/...GCC.../11.1.0/cc1plus
13 ~/meta-oe/.../POKY_64/.../vulkan-cts/1.2.6.0-r0/...GCC.../11.1.0/as
13 ~/meta-oe/.../POKY_64/.../vulkan-cts/1.2.6.0-r0/recipe-sysroot-native/usr/bin/x86_64-poky-linux/x86_64-poky-linux-g++
11  x86_64-poky-linux-gcc
10 ~/meta-oe/.../POKY_64/.../dovecot/2.3.14-r0/...GCC.../11.1.0/cc1
10 ~/meta-oe/.../POKY_64/.../fluentbit/1.3.5-r0/recipe-sysroot-native/usr/bin/x86_64-poky-linux/x86_64-poky-linux-gcc
10 ~/meta-oe/.../POKY_64/.../dovecot/2.3.14-r0/...GCC.../11.1.0/as
7 ~/meta-oe/.../POKY_64/.../fluentbit/1.3.5-r0/...GCC.../11.1.0/cc1
7 ~/meta-oe/.../POKY_64/.../fluentbit/1.3.5-r0/...GCC.../11.1.0/as
4  /usr/bin/python3
3  cmake
2 ~/meta-oe/.../POKY_64/.../vulkan-cts/1.2.6.0-r0/...GCC.../11.1.0/ar
2  sh
2  /lib/systemd/systemd
2  (sd-pam)
2  ninja
2  bitbake-server
2 ~/meta-oe/.../POKY_64/.../vulkan-cts/1.2.6.0-r0/recipe-sysroot-native/usr/bin/x86_64-poky-linux/x86_64-poky-linux-gcc-ar

Kernel Summary:
293  kworker
56  ksoftirqd
56  migration
56  watchdog
56  cpuhp
3  jbd2
3  ext4-rsv-conver
2  kdmflush
2  bioset
....

Sakib



Signed-off-by: Sakib Sajal <sakib.sajal@windriver.com>
---
  scripts/collect-results              |   2 +-
  scripts/generate-testresult-index.py |   2 +-
  scripts/run-config                   |   1 +
  scripts/summarize_top_output.py      | 132 +++++++++++++++++++++++++++
  4 files changed, 135 insertions(+), 2 deletions(-)
  create mode 100755 scripts/summarize_top_output.py

diff --git a/scripts/collect-results b/scripts/collect-results
index 7474e36..7178380 100755
--- a/scripts/collect-results
+++ b/scripts/collect-results
@@ -19,7 +19,7 @@ if [ -e $WORKDIR/buildhistory ]; then
  fi
    HSFILE=$WORKDIR/tmp/buildstats/*/host_stats
-d=`date +%Y-%m-%d--%H-%M`
+d="intermittent_failure_host_data"
    mkdir -p $DEST/$target/$d
  diff --git a/scripts/generate-testresult-index.py b/scripts/generate-testresult-index.py
index 7fdc17c..d85d606 100755
--- a/scripts/generate-testresult-index.py
+++ b/scripts/generate-testresult-index.py
@@ -154,7 +154,7 @@ for build in sorted(os.listdir(path), key=keygen, reverse=True):
      hd = []
      counter = 0
      # do we really need the loop?
-    for p in glob.glob(buildpath + "/*/*/host_stats*top.txt"):
+    for p in glob.glob(buildpath + "/*/*/host_stats*top_summary.txt"):
          n_split = p.split(build)
          res = reldir[0:-1] + n_split[1]
          hd.append((res, str(counter)))
diff --git a/scripts/run-config b/scripts/run-config
index 8ed88cf..82de91f 100755
--- a/scripts/run-config
+++ b/scripts/run-config
@@ -327,6 +327,7 @@ elif args.phase == "finish" and args.stepname == "collect-results":
      if args.results_dir:
          hp.printheader("Running results collection")
          runcmd([scriptsdir + "/collect-results", args.builddir, args.results_dir, args.target])
+        runcmd([scriptsdir + "/summarize_top_output.py", args.results_dir, args.target])
      sys.exit(0)
    if jcfg:
diff --git a/scripts/summarize_top_output.py b/scripts/summarize_top_output.py
new file mode 100755
index 0000000..0606a34
--- /dev/null
+++ b/scripts/summarize_top_output.py
@@ -0,0 +1,132 @@
+#!/usr/bin/env python3
+
+import os, sys, glob
+
+# constants
+top_header = 7
+top_summary = 5
+max_cols = 11
+
+# string substitution to make things easier to read
+subs = {
+    "/home/pokybuild/yocto-worker/" : "~/",
+    "/build/build/tmp/work/core2-32-poky-linux/" : "/.../POKY_32/.../",
+    "/build/build/tmp/work/core2-64-poky-linux/" : "/.../POKY_64/.../",
+ "/recipe-sysroot-native/usr/bin/x86_64-poky-linux/../../libexec/x86_64-poky-linux/gcc/x86_64-poky-linux/" : "/...GCC.../"
+}
+
+def usage():
+    print("Usage: " + sys.argv[0] + " <dest> <target>")
+
+def list_top_outputs(logfile):
+    # top delimiter
+    top_start = "start: top output"
+    top_end = "end: top output"
+
+    # list of top outputs
+    top_outputs = []
+
+    # flag
+    collect = False
+    with open(logfile) as log:
+        top_output = []
+        for line in log:
+            lstrip = line.strip()
+            if collect:
+                if lstrip.startswith(top_end):
+                    collect = False
+                    top_outputs.append(top_output)
+                    top_output = []
+                else:
+                    top_output.append(lstrip)
+            if lstrip.startswith(top_start):
+                collect = True
+
+    return top_outputs
+
+def summarize_top(top_outs):
+    summaries = []
+    kernel_summaries = []
+    short_summaries = []
+    for top_out in top_outs:
+        summary = {}
+        kernel_summary = {}
+        short_summary = top_out[:top_summary]
+        for line in top_out[top_header:]:
+            cmd = line.split(maxsplit=max_cols)[-1]
+            # kernel processes
+            if cmd[0] == "[" and cmd[-1] == "]":
+                kproc = cmd[1:-1].split("/")[0]
+                if kproc not in kernel_summary:
+                    kernel_summary[kproc] = 1
+                else:
+                    kernel_summary[kproc] += 1
+                continue
+            cmd_split = cmd.split()
+            prog = cmd_split[0]
+            if prog not in summary:
+                summary[prog] = 1
+            else:
+                summary[prog] += 1
+        summary = dict(sorted(summary.items(), key=lambda item: item[1], reverse=True))
+        kernel_summary = dict(sorted(kernel_summary.items(), key=lambda item: item[1], reverse=True))
+
+        summaries.append(summary)
+        kernel_summaries.append(kernel_summary)
+        short_summaries.append(short_summary)
+
+    return (short_summaries, summaries, kernel_summaries)
+
+def summarize_path(path):
+    p = path
+    for k, v in subs.items():
+        p = p.replace(k, v)
+    return p
+
+def write_summary(short_summary, summary, kernel_summary, logfile):
+    dirname = os.path.dirname(logfile)
+    fname = os.path.basename(logfile)
+    report_name = fname.split(".")[0] + "_summary.txt"
+    outfile = os.path.join(dirname, report_name)
+    out = "NOTE: program names have been shortened for better readability.\nSubstitutions are as follows:\n"
+    for k, v in subs.items():
+        out += (v + " = " + k + "\n")
+    out += "\n"
+
+    out += "top was invoked " + str(len(short_summary)) + " times.\n\n"
+
+    for i in range(len(short_summary)):
+        for l in short_summary[i]:
+            out += (l + "\n")
+
+        out += ("\nSummary: " + "\n")
+        for k, v in summary[i].items():
+            if v > 1:
+                r = summarize_path(k)
+                out += (str(v) + "  " + r + "\n")
+
+        out += ("\nKernel Summary: " + "\n")
+        for k, v in kernel_summary[i].items():
+            if v > 1:
+                r = summarize_path(k)
+                out += (str(v) + "  " + r + "\n")
+        out += ("\n")
+
+    with open(outfile, "w") as of:
+        of.write(out)
+
+def main():
+    if len(sys.argv) != 3:
+        usage()
+        sys.exit()
+
+    dest = sys.argv[1]
+    target = sys.argv[2]
+    host_data_dir = "intermittent_failure_host_data"
+    directory = os.path.join(dest, target, host_data_dir)
+    for f in glob.glob(directory + "/*_top.txt"):
+        outputs = list_top_outputs(f)
+        short_summary, summary, kernel_summary = summarize_top(outputs)
+        write_summary(short_summary, summary, kernel_summary, f)
+
+main()




sakib.sajal@...
 

On 2021-06-16 1:33 p.m., Richard Purdie wrote:
[Please note: This e-mail is from an EXTERNAL e-mail address]

On Wed, 2021-06-16 at 04:43 -0400, sakib.sajal@windriver.com wrote:
summarize_top_output.py is used to summarize the top
output that is captured during autobuilder intermittent
failures.

Use the script to summarize the host top output and
publish the summary that is created instead of
the raw logfile.


[...]
if jcfg:
diff --git a/scripts/summarize_top_output.py b/scripts/summarize_top_output.py
new file mode 100755
index 0000000..0606a34
--- /dev/null
+++ b/scripts/summarize_top_output.py
@@ -0,0 +1,132 @@
+#!/usr/bin/env python3
+
+import os, sys, glob
+
+# constants
+top_header = 7
+top_summary = 5
+max_cols = 11
+
+# string substitution to make things easier to read
+subs = {
+ "/home/pokybuild/yocto-worker/" : "~/",
+ "/build/build/tmp/work/core2-32-poky-linux/" : "/.../POKY_32/.../",
+ "/build/build/tmp/work/core2-64-poky-linux/" : "/.../POKY_64/.../",
+ "/recipe-sysroot-native/usr/bin/x86_64-poky-linux/../../libexec/x86_64-poky-linux/gcc/x86_64-poky-linux/" : "/...GCC.../"
+}
One quick question - the above assumes an x86 target machine using those two tunes.
Should that be wildcarded?

Cheers,

Richard
Yes it should be. We've looked at a number of logs and I will send a V2 with wild-carding for the cross-compiler paths.

After the V2, I plan on submitting patches for the following in roughly the presented order:

1) any process that is listed once (singleton) is not reported in the summary, but we are planning to make exceptions for "special" commands such as "rm" and "tar"

2) i noticed some zombie processes and it might be worthwhile to report them. Right now they are not indicated in the summary. Should we report all zombies or ignore the singletons?

For example I'd collapse [Parser-31], [Parser-32] into [Parser-N]


3) It would be nice to specify other builds going on and the top level directory

4) currently top does not show PPID, should we include the information in the output? This is useful for more context in the raw logfile.

5) show top 5 or 10 virtual memory users


From the yp-ab index page, there are no logs for arm host. I will run a build and make sure the script work well there as well.

Any ideas on why the arm host builds are not being shown on the index page?

Sakib