diff mbox series

[1/2] check: detect and preserve all coredumps made by a test

Message ID 166553911331.422356.4424521847397525024.stgit@magnolia (mailing list archive)
State New, archived
Headers show
Series fstests: improve coredump capture and storage | expand

Commit Message

Darrick J. Wong Oct. 12, 2022, 1:45 a.m. UTC 
From: Darrick J. Wong <djwong@kernel.org>

If someone sets kernel.core_uses_pid (or kernel.core_pattern), any
coredumps generated by fstests might have names that are longer than
just "core".  Since the pid isn't all that useful by itself, let's
record the coredumps by hash when we save them, so that we don't waste
space storing identical crash dumps.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 check     |   26 ++++++++++++++++++++++----
 common/rc |   16 ++++++++++++++++
 2 files changed, 38 insertions(+), 4 deletions(-)

Comments

Zorro Lang Oct. 12, 2022, 3:47 p.m. UTC | #1 
On Tue, Oct 11, 2022 at 06:45:13PM -0700, Darrick J. Wong wrote:
> From: Darrick J. Wong <djwong@kernel.org>
> 
> If someone sets kernel.core_uses_pid (or kernel.core_pattern), any
> coredumps generated by fstests might have names that are longer than
> just "core".  Since the pid isn't all that useful by itself, let's
> record the coredumps by hash when we save them, so that we don't waste
> space storing identical crash dumps.
> 
> Signed-off-by: Darrick J. Wong <djwong@kernel.org>
> ---
>  check     |   26 ++++++++++++++++++++++----
>  common/rc |   16 ++++++++++++++++
>  2 files changed, 38 insertions(+), 4 deletions(-)
> 
> 
> diff --git a/check b/check
> index af23572ccc..654d986b27 100755
> --- a/check
> +++ b/check
> @@ -913,11 +913,19 @@ function run_section()
>  			sts=$?
>  		fi
>  
> -		if [ -f core ]; then
> -			_dump_err_cont "[dumped core]"
> -			mv core $RESULT_BASE/$seqnum.core
> +		# If someone sets kernel.core_pattern or kernel.core_uses_pid,
> +		# coredumps generated by fstests might have a longer name than
> +		# just "core".  Use globbing to find the most common patterns,
> +		# assuming there are no other coredump capture packages set up.
> +		local cores=0
> +		for i in core core.*; do
> +			test -f "$i" || continue
> +			if ((cores++ == 0)); then
> +				_dump_err_cont "[dumped core]"
> +			fi
> +			_save_coredump "$i"
>  			tc_status="fail"
> -		fi
> +		done
>  
>  		if [ -f $seqres.notrun ]; then
>  			$timestamp && _timestamp
> @@ -950,6 +958,16 @@ function run_section()
>  			# of the check script itself.
>  			(_adjust_oom_score 250; _check_filesystems) || tc_status="fail"
>  			_check_dmesg || tc_status="fail"
> +
> +			# Save any coredumps from the post-test fs checks
> +			for i in core core.*; do
> +				test -f "$i" || continue
> +				if ((cores++ == 0)); then
> +					_dump_err_cont "[dumped core]"
> +				fi
> +				_save_coredump "$i"
> +				tc_status="fail"
> +			done
>  		fi
>  
>  		# Reload the module after each test to check for leaks or
> diff --git a/common/rc b/common/rc
> index d877ac77a0..152b8bb414 100644
> --- a/common/rc
> +++ b/common/rc
> @@ -4949,6 +4949,22 @@ _create_file_sized()
>  	return $ret
>  }
>  
> +_save_coredump()
> +{
> +	local path="$1"
> +
> +	local core_hash="$(_md5_checksum "$path")"
> +	local out_file="$RESULT_BASE/$seqnum.core.$core_hash"

I doubt this can work with fstests section, if we use section, the out_file
should be "$RESULT_BASE/$section/....", so I think if we can write this line
as:

  local out_file="$seqres.core.$core_hash"

Or use $REPORT_DIR?

Thanks,
Zorro

> +
> +	if [ -s "$out_file" ]; then
> +		rm -f "$path"
> +		return
> +	fi
> +	rm -f "$out_file"
> +
> +	mv "$path" "$out_file"
> +}
> +
>  init_rc
>  
>  ################################################################################
>
Darrick J. Wong Oct. 12, 2022, 3:51 p.m. UTC | #2 
On Wed, Oct 12, 2022 at 11:47:21PM +0800, Zorro Lang wrote:
> On Tue, Oct 11, 2022 at 06:45:13PM -0700, Darrick J. Wong wrote:
> > From: Darrick J. Wong <djwong@kernel.org>
> > 
> > If someone sets kernel.core_uses_pid (or kernel.core_pattern), any
> > coredumps generated by fstests might have names that are longer than
> > just "core".  Since the pid isn't all that useful by itself, let's
> > record the coredumps by hash when we save them, so that we don't waste
> > space storing identical crash dumps.
> > 
> > Signed-off-by: Darrick J. Wong <djwong@kernel.org>
> > ---
> >  check     |   26 ++++++++++++++++++++++----
> >  common/rc |   16 ++++++++++++++++
> >  2 files changed, 38 insertions(+), 4 deletions(-)
> > 
> > 
> > diff --git a/check b/check
> > index af23572ccc..654d986b27 100755
> > --- a/check
> > +++ b/check
> > @@ -913,11 +913,19 @@ function run_section()
> >  			sts=$?
> >  		fi
> >  
> > -		if [ -f core ]; then
> > -			_dump_err_cont "[dumped core]"
> > -			mv core $RESULT_BASE/$seqnum.core
> > +		# If someone sets kernel.core_pattern or kernel.core_uses_pid,
> > +		# coredumps generated by fstests might have a longer name than
> > +		# just "core".  Use globbing to find the most common patterns,
> > +		# assuming there are no other coredump capture packages set up.
> > +		local cores=0
> > +		for i in core core.*; do
> > +			test -f "$i" || continue
> > +			if ((cores++ == 0)); then
> > +				_dump_err_cont "[dumped core]"
> > +			fi
> > +			_save_coredump "$i"
> >  			tc_status="fail"
> > -		fi
> > +		done
> >  
> >  		if [ -f $seqres.notrun ]; then
> >  			$timestamp && _timestamp
> > @@ -950,6 +958,16 @@ function run_section()
> >  			# of the check script itself.
> >  			(_adjust_oom_score 250; _check_filesystems) || tc_status="fail"
> >  			_check_dmesg || tc_status="fail"
> > +
> > +			# Save any coredumps from the post-test fs checks
> > +			for i in core core.*; do
> > +				test -f "$i" || continue
> > +				if ((cores++ == 0)); then
> > +					_dump_err_cont "[dumped core]"
> > +				fi
> > +				_save_coredump "$i"
> > +				tc_status="fail"
> > +			done
> >  		fi
> >  
> >  		# Reload the module after each test to check for leaks or
> > diff --git a/common/rc b/common/rc
> > index d877ac77a0..152b8bb414 100644
> > --- a/common/rc
> > +++ b/common/rc
> > @@ -4949,6 +4949,22 @@ _create_file_sized()
> >  	return $ret
> >  }
> >  
> > +_save_coredump()
> > +{
> > +	local path="$1"
> > +
> > +	local core_hash="$(_md5_checksum "$path")"
> > +	local out_file="$RESULT_BASE/$seqnum.core.$core_hash"
> 
> I doubt this can work with fstests section, if we use section, the out_file
> should be "$RESULT_BASE/$section/....", so I think if we can write this line
> as:
> 
>   local out_file="$seqres.core.$core_hash"
> 
> Or use $REPORT_DIR?

I'll change it to REPORT_DIR.

--D

> Thanks,
> Zorro
> 
> > +
> > +	if [ -s "$out_file" ]; then
> > +		rm -f "$path"
> > +		return
> > +	fi
> > +	rm -f "$out_file"
> > +
> > +	mv "$path" "$out_file"
> > +}
> > +
> >  init_rc
> >  
> >  ################################################################################
> > 
>
diff mbox series

Patch

diff --git a/check b/check
index af23572ccc..654d986b27 100755
--- a/check
+++ b/check
@@ -913,11 +913,19 @@  function run_section()
 			sts=$?
 		fi
 
-		if [ -f core ]; then
-			_dump_err_cont "[dumped core]"
-			mv core $RESULT_BASE/$seqnum.core
+		# If someone sets kernel.core_pattern or kernel.core_uses_pid,
+		# coredumps generated by fstests might have a longer name than
+		# just "core".  Use globbing to find the most common patterns,
+		# assuming there are no other coredump capture packages set up.
+		local cores=0
+		for i in core core.*; do
+			test -f "$i" || continue
+			if ((cores++ == 0)); then
+				_dump_err_cont "[dumped core]"
+			fi
+			_save_coredump "$i"
 			tc_status="fail"
-		fi
+		done
 
 		if [ -f $seqres.notrun ]; then
 			$timestamp && _timestamp
@@ -950,6 +958,16 @@  function run_section()
 			# of the check script itself.
 			(_adjust_oom_score 250; _check_filesystems) || tc_status="fail"
 			_check_dmesg || tc_status="fail"
+
+			# Save any coredumps from the post-test fs checks
+			for i in core core.*; do
+				test -f "$i" || continue
+				if ((cores++ == 0)); then
+					_dump_err_cont "[dumped core]"
+				fi
+				_save_coredump "$i"
+				tc_status="fail"
+			done
 		fi
 
 		# Reload the module after each test to check for leaks or
diff --git a/common/rc b/common/rc
index d877ac77a0..152b8bb414 100644
--- a/common/rc
+++ b/common/rc
@@ -4949,6 +4949,22 @@  _create_file_sized()
 	return $ret
 }
 
+_save_coredump()
+{
+	local path="$1"
+
+	local core_hash="$(_md5_checksum "$path")"
+	local out_file="$RESULT_BASE/$seqnum.core.$core_hash"
+
+	if [ -s "$out_file" ]; then
+		rm -f "$path"
+		return
+	fi
+	rm -f "$out_file"
+
+	mv "$path" "$out_file"
+}
+
 init_rc
 
 ################################################################################