[Buildroot] [PATCHv2 2/4] pkg-generic: add step_pkg_size global instrumentation hook

["Jérôme Pouiller" <jezz@sysmic.org>]

Hello Thomas,

On Monday 01 December 2014 22:41:38 Thomas Petazzoni wrote:
> This patch adds a global instrumentation hook that collects the list
> of files installed in $(TARGET_DIR) by each package, and stores this
> list into a file called $(BUILD_DIR)/packages-file-list.txt. It can
> later be used to determine the size contribution of each package to
> the target root filesystem.
> 
> Note that in order to detect if a file installed by one package is
> later overriden by another package, we calculate the md5 of installed
> files and compare them at each installation of a new package.
> 
> This commit also adds a Config.in option to enable the collection of
> this data, as calculating the md5 of all installed files at the
> beginning and end of the installation of each package can be
> considered a time-consuming process which maybe some users will not be
> willing to suffer from.
> 
> Signed-off-by: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
> ---
>  Config.in              |  9 +++++++++
>  package/pkg-generic.mk | 36 ++++++++++++++++++++++++++++++++++++
>  2 files changed, 45 insertions(+)
> 
> diff --git a/Config.in b/Config.in
> index 1aa1080..328654c 100644
> --- a/Config.in
> +++ b/Config.in
> @@ -569,6 +569,15 @@ config BR2_GLOBAL_PATCH_DIR
>  	  Otherwise, if the directory <global-patch-dir>/<packagename> exists,
>  	  then all *.patch files in the directory will be applied.
>  
> +config BR2_COLLECT_FILE_SIZE_STATS
> +	bool "collect statistics about installed file size"
> +	help
> +	  Enable this option to let Buildroot collect data about the
> +	  installed files. When this option is enabled, you will be
> +	  able to use the 'size-stats' make target, which will
> +	  generate a graph and CSV files giving statistics about the
> +	  installed size of each file and each package.
> +
>  endmenu
>  
>  source "toolchain/Config.in"
> diff --git a/package/pkg-generic.mk b/package/pkg-generic.mk
> index 9643a30..82f8ff8 100644
> --- a/package/pkg-generic.mk
> +++ b/package/pkg-generic.mk
> @@ -55,6 +55,42 @@ define step_time
>  endef
>  GLOBAL_INSTRUMENTATION_HOOKS += step_time
>  
> +# Hooks to collect statistics about installed files
> +ifeq ($(BR2_COLLECT_FILE_SIZE_STATS),y)
> +
> +# This hook will be called before the target installation of a
> +# package. We store in a file named $(1).filelist_before the list of
> +# files currently installed in the target. Note that the MD5 is also
> +# stored, in order to identify if the files are overwritten.
> +define step_pkg_size_start
> +	(cd $(TARGET_DIR) ; find . -type f | xargs md5sum) | sort > \
> +		$(BUILD_DIR)/$(1).filelist_before
> +endef
I think this does not work if filename contains spaces.


> +# This hook will be called after the target installation of a
> +# package. We store in a file named $(1).filelist_after the list
> +# of files (and their MD5) currently installed in the target. We then
> +# do a diff with the $(1).filelist_before to compute the list of
> +# files installed by this package.
> +define step_pkg_size_end
> +	(cd $(TARGET_DIR); find . -type f | xargs md5sum) | sort > \
> +		$(BUILD_DIR)/$(1).filelist_after
> +	comm -13 $(BUILD_DIR)/$(1).filelist_before $(BUILD_DIR)/$(1).filelist_after | \
> +		while read hash file ; do \
> +			echo "$(1),$${file}" >> $(BUILD_DIR)/packages-file-list.txt ; \
> +		done
Does it would make sense if we also record removed lines? We may wrote 
another script that detect if a file was in conflict between two packages.

> +	$(RM) -f $(BUILD_DIR)/$(1).filelist_before \
> +		$(BUILD_DIR)/$(1).filelist_after
> +endef
> +
> +define step_pkg_size
> +	$(if $(filter install-target,$(2)),\
> +		$(if $(filter start,$(1)),$(call step_pkg_size_start,$(3))) \
> +		$(if $(filter end,$(1)),$(call step_pkg_size_end,$(3))))
> +endef
> +GLOBAL_INSTRUMENTATION_HOOKS += step_pkg_size
> +endif
> +
>  # User-supplied script
>  ifneq ($(BR2_INSTRUMENTATION_SCRIPTS),)
>  define step_user
> 

-- 
J?r?me Pouiller, Sysmic
Embedded Linux specialist
http://www.sysmic.fr