buildhistory: improve performance of image info collection

Reduce the number of calls to the packaging tool, especially in the case
of rpm, using helper utilities to gather the required information more
efficiently where possible.

Signed-off-by: Paul Eggleton <paul.eggleton@linux.intel.com>

5 files changed, 162 insertions, 101 deletions

diff --git a/meta/classes/buildhistory.bbclass b/meta/classes/buildhistory.bbclass
index f0bf849860..ddb76e8771 100644
--- a/meta/classes/buildhistory.bbclass
+++ b/meta/classes/buildhistory.bbclass
@@ -285,48 +285,43 @@ buildhistory_get_image_installed() {
 	mkdir -p ${BUILDHISTORY_DIR_IMAGE}
 
 	# Get list of installed packages
-	list_installed_packages | sort > ${BUILDHISTORY_DIR_IMAGE}/installed-package-names.txt
-	INSTALLED_PKGS=`cat ${BUILDHISTORY_DIR_IMAGE}/installed-package-names.txt`
+	pkgcache="${BUILDHISTORY_DIR_IMAGE}/installed-packages.tmp"
+	list_installed_packages file | sort > $pkgcache
+
+	cat $pkgcache | awk '{ print $1 }' > ${BUILDHISTORY_DIR_IMAGE}/installed-package-names.txt
+	cat $pkgcache | awk '{ print $2 }' | xargs -n1 basename > ${BUILDHISTORY_DIR_IMAGE}/installed-packages.txt
+
+	# Produce dependency graph
+	# First, filter out characters that cause issues for dot
+	rootfs_list_installed_depends | sed -e 's:-:_:g' -e 's:\.:_:g' -e 's:+::g' > ${BUILDHISTORY_DIR_IMAGE}/depends.tmp
+	# Change delimiter from pipe to -> and set style for recommend lines
+	sed -i -e 's:|: -> :' -e 's:\[REC\]:[style=dotted]:' -e 's:$:;:' ${BUILDHISTORY_DIR_IMAGE}/depends.tmp
+	# Add header, sorted and de-duped contents and footer and then delete the temp file
+	echo -e "digraph depends {\n    node [shape=plaintext]" > ${BUILDHISTORY_DIR_IMAGE}/depends.dot
+	cat ${BUILDHISTORY_DIR_IMAGE}/depends.tmp | sort | uniq >> ${BUILDHISTORY_DIR_IMAGE}/depends.dot
+	echo "}" >>  ${BUILDHISTORY_DIR_IMAGE}/depends.dot
+	rm ${BUILDHISTORY_DIR_IMAGE}/depends.tmp
 
-	# Produce installed package file and size lists and dependency graph
-	echo -n > ${BUILDHISTORY_DIR_IMAGE}/installed-packages.txt
+	# Produce installed package sizes list
 	echo -n > ${BUILDHISTORY_DIR_IMAGE}/installed-package-sizes.tmp
-	echo -e "digraph depends {\n    node [shape=plaintext]" > ${BUILDHISTORY_DIR_IMAGE}/depends.dot
-	for pkg in $INSTALLED_PKGS; do
-		pkgfile=`get_package_filename $pkg`
-		echo `basename $pkgfile` >> ${BUILDHISTORY_DIR_IMAGE}/installed-packages.txt
+	cat $pkgcache | while read pkg pkgfile
+	do
 		if [ -f $pkgfile ] ; then
 			pkgsize=`du -k $pkgfile | head -n1 | awk '{ print $1 }'`
 			echo $pkgsize $pkg >> ${BUILDHISTORY_DIR_IMAGE}/installed-package-sizes.tmp
 		fi
-
-		deps=`list_package_depends $pkg`
-		for dep in $deps ; do
-			echo "$pkg OPP $dep;" | sed -e 's:-:_:g' -e 's:\.:_:g' -e 's:+::g' | sed 's:OPP:->:g'
-		done
-
-		recs=`list_package_recommends $pkg`
-		for rec in $recs ; do
-			echo "$pkg OPP $rec [style=dotted];" | sed -e 's:-:_:g' -e 's:\.:_:g' -e 's:+::g' | sed 's:OPP:->:g'
-		done
-	done | sort | uniq >> ${BUILDHISTORY_DIR_IMAGE}/depends.dot
-	echo "}" >>  ${BUILDHISTORY_DIR_IMAGE}/depends.dot
-
+	done
 	cat ${BUILDHISTORY_DIR_IMAGE}/installed-package-sizes.tmp | sort -n -r | awk '{print $1 "\tKiB " $2}' > ${BUILDHISTORY_DIR_IMAGE}/installed-package-sizes.txt
 	rm ${BUILDHISTORY_DIR_IMAGE}/installed-package-sizes.tmp
 
+	# We're now done with the cache, delete it
+	rm $pkgcache
+
 	# Produce some cut-down graphs (for readability)
 	grep -v kernel_image ${BUILDHISTORY_DIR_IMAGE}/depends.dot | grep -v kernel_2 | grep -v kernel_3 > ${BUILDHISTORY_DIR_IMAGE}/depends-nokernel.dot
 	grep -v libc6 ${BUILDHISTORY_DIR_IMAGE}/depends-nokernel.dot | grep -v libgcc > ${BUILDHISTORY_DIR_IMAGE}/depends-nokernel-nolibc.dot
 	grep -v update_ ${BUILDHISTORY_DIR_IMAGE}/depends-nokernel-nolibc.dot > ${BUILDHISTORY_DIR_IMAGE}/depends-nokernel-nolibc-noupdate.dot
 	grep -v kernel_module ${BUILDHISTORY_DIR_IMAGE}/depends-nokernel-nolibc-noupdate.dot > ${BUILDHISTORY_DIR_IMAGE}/depends-nokernel-nolibc-noupdate-nomodules.dot
-
-	# Workaround for broken shell function dependencies
-	if false ; then
-		get_package_filename
-		list_package_depends
-		list_package_recommends
-	fi
 }
 
 buildhistory_get_imageinfo() {
diff --git a/meta/classes/rootfs_deb.bbclass b/meta/classes/rootfs_deb.bbclass
index a002b1ec02..750a8ca082 100644
--- a/meta/classes/rootfs_deb.bbclass
+++ b/meta/classes/rootfs_deb.bbclass
@@ -96,26 +96,24 @@ list_installed_packages() {
 	if [ "$1" = "arch" ] ; then
 		# Here we want the PACKAGE_ARCH not the deb architecture
 		${DPKG_QUERY_COMMAND} -W -f='${Package} ${PackageArch}\n'
+	elif [ "$1" = "file" ] ; then
+		${DPKG_QUERY_COMMAND} -W -f='${Package} ${Package}_${Version}_${Architecture}.deb\n' | while read pkg pkgfile
+		do
+			fullpath=`find ${DEPLOY_DIR_DEB} -name "$pkgfile" || true`
+			if [ "$fullpath" = "" ] ; then
+				echo "$pkg $pkgfile"
+			else
+				echo "$pkg $fullpath"
+			fi
+		done
 	else
 		${DPKG_QUERY_COMMAND} -W -f='${Package}\n'
 	fi
 }
 
-get_package_filename() {
-	fullname=`find ${DEPLOY_DIR_DEB} -name "$1_*.deb" || true`
-	if [ "$fullname" = "" ] ; then
-		echo $name
-	else
-		echo $fullname
-	fi
-}
-
-list_package_depends() {
-	${DPKG_QUERY_COMMAND} -s $1 | grep ^Depends | sed -e 's/^Depends: //' -e 's/,//g' -e 's:([=<>]* [^ )]*)::g'
-}
-
-list_package_recommends() {
-	${DPKG_QUERY_COMMAND} -s $1 | grep ^Recommends | sed -e 's/^Recommends: //' -e 's/,//g' -e 's:([=<>]* [^ )]*)::g'
+rootfs_list_installed_depends() {
+	# Cheat here a little bit by using the opkg query helper util
+	${DPKG_QUERY_COMMAND} -W -f='Package: ${Package}\nDepends: ${Depends}\nRecommends: ${Recommends}\n\n' | opkg-query-helper.py
 }
 
 rootfs_install_packages() {
diff --git a/meta/classes/rootfs_ipk.bbclass b/meta/classes/rootfs_ipk.bbclass
index 7df97a014b..6cdd8f6062 100644
--- a/meta/classes/rootfs_ipk.bbclass
+++ b/meta/classes/rootfs_ipk.bbclass
@@ -131,33 +131,23 @@ remove_packaging_data_files() {
 list_installed_packages() {
 	if [ "$1" = "arch" ] ; then
 		opkg-cl ${IPKG_ARGS_POST} status | opkg-query-helper.py -a
+	elif [ "$1" = "file" ] ; then
+		opkg-cl ${IPKG_ARGS_POST} status | opkg-query-helper.py -f | while read pkg pkgfile
+		do
+			fullpath=`find ${DEPLOY_DIR_IPK} -name "$pkgfile" || true`
+			if [ "$fullpath" = "" ] ; then
+				echo "$pkg $pkgfile"
+			else
+				echo "$pkg $fullpath"
+			fi
+		done
 	else
 		opkg-cl ${IPKG_ARGS_POST} list_installed | awk '{ print $1 }'
 	fi
 }
 
-get_package_filename() {
-	set +x
-	info=`opkg-cl ${IPKG_ARGS_POST} info $1 | grep -B 7 -A 7 "^Status.* \(\(installed\)\|\(unpacked\)\)" || true`
-	name=`echo "${info}" | awk '/^Package/ {printf $2"_"}'`
-	name=$name`echo "${info}" | awk -F: '/^Version/ {printf $NF"_"}' | sed 's/^\s*//g'`
-	name=$name`echo "${info}" | awk '/^Archi/ {print $2".ipk"}'`
-	set -x
-
-	fullname=`find ${DEPLOY_DIR_IPK} -name "$name" || true`
-	if [ "$fullname" = "" ] ; then
-		echo $name
-	else
-		echo $fullname
-	fi
-}
-
-list_package_depends() {
-	opkg-cl ${IPKG_ARGS_POST} info $1 | grep ^Depends | sed -e 's/^Depends: //' -e 's/,//g' -e 's:([=<>]* [^ )]*)::g'
-}
-
-list_package_recommends() {
-	opkg-cl ${IPKG_ARGS_POST} info $1 | grep ^Recommends | sed -e 's/^Recommends: //' -e 's/,//g' -e 's:([=<>]* [^ )]*)::g'
+rootfs_list_installed_depends() {
+	opkg-cl ${IPKG_ARGS_POST} status | opkg-query-helper.py
 }
 
 rootfs_install_packages() {
diff --git a/meta/classes/rootfs_rpm.bbclass b/meta/classes/rootfs_rpm.bbclass
index 1cc4a84495..c9258dfe39 100644
--- a/meta/classes/rootfs_rpm.bbclass
+++ b/meta/classes/rootfs_rpm.bbclass
@@ -143,40 +143,15 @@ RPM_QUERY_CMD = '${RPM} --root $INSTALL_ROOTFS_RPM -D "_dbpath ${rpmlibdir}" \
 list_installed_packages() {
 	if [ "$1" = "arch" ] ; then
 		${RPM_QUERY_CMD} -qa --qf "[%{NAME} %{ARCH}\n]"
+	elif [ "$1" = "file" ] ; then
+		${RPM_QUERY_CMD} -qa --qf "[%{NAME} %{PACKAGEORIGIN}\n]"
 	else
 		${RPM_QUERY_CMD} -qa --qf "[%{NAME}\n]"
 	fi
 }
 
-get_package_filename() {
-	resolve_package_rpm ${RPMCONF_TARGET_BASE}-base_archs.conf $1
-}
-
-list_package_depends() {
-	pkglist=`list_installed_packages`
-
-	# REQUIRE* lists "soft" requirements (which we know as recommends and RPM refers to
-	# as "suggests") so filter these out with the help of awk
-	for req in `${RPM_QUERY_CMD} -q --qf "[%{REQUIRENAME} %{REQUIREFLAGS}\n]" $1 | awk '{ if( and($2, 0x80000) == 0) print $1 }'`; do
-		if echo "$req" | grep -q "^rpmlib" ; then continue ; fi
-
-		realpkg=""
-		for dep in $pkglist; do
-			if [ "$dep" = "$req" ] ; then
-				realpkg="1"
-				echo $req
-				break
-			fi
-		done
-
-		if [ "$realdep" = "" ] ; then
-			${RPM_QUERY_CMD} -q --whatprovides $req --qf "%{NAME}\n"
-		fi
-	done
-}
-
-list_package_recommends() {
-	${RPM_QUERY_CMD} -q --suggests $1
+rootfs_list_installed_depends() {
+	rpmresolve -d $INSTALL_ROOTFS_RPM/${rpmlibdir}
 }
 
 rootfs_install_packages() {
diff --git a/meta/recipes-devtools/rpm/rpmresolve/rpmresolve.c b/meta/recipes-devtools/rpm/rpmresolve/rpmresolve.c
index 9f6cdf28b8..2d9ed141f4 100644
--- a/meta/recipes-devtools/rpm/rpmresolve/rpmresolve.c
+++ b/meta/recipes-devtools/rpm/rpmresolve/rpmresolve.c
@@ -204,10 +204,104 @@ int processPackages(rpmts *ts, int tscount, const char *packagelistfn, int ignor
     return rc;
 }
 
+int lookupProvider(rpmts ts, const char *req, char **provider)
+{
+    int rc = 0;
+    rpmmi provmi = rpmtsInitIterator(ts, RPMTAG_PROVIDENAME, req, 0);
+    if(provmi) {
+        Header h;
+        if ((h = rpmmiNext(provmi)) != NULL) {
+            HE_t he = (HE_t) memset(alloca(sizeof(*he)), 0, sizeof(*he));
+            he->tag = RPMTAG_NAME;
+            rc = (headerGet(h, he, 0) != 1);
+            if(rc==0)
+                *provider = strdup((char *)he->p.ptr);
+        }
+        (void)rpmmiFree(provmi);
+    }
+    else {
+        rc = -1;
+    }
+    return rc;
+}
+
+int printDepList(rpmts *ts, int tscount)
+{
+    int rc = 0;
+
+    if( tscount > 1 )
+        printf(">1 database specified with dependency list, using first only\n");
+
+    /* Get list of names */
+    rpmdb db = rpmtsGetRdb(ts[0]);
+    ARGV_t names = NULL;
+    rc = rpmdbMireApply(db, RPMTAG_NAME,
+                RPMMIRE_STRCMP, NULL, &names);
+    int nnames = argvCount(names);
+
+    /* Get list of NVRAs */
+    ARGV_t keys = NULL;
+    rc = rpmdbMireApply(db, RPMTAG_NVRA,
+                RPMMIRE_STRCMP, NULL, &keys);
+    if (keys) {
+        int i, j;
+        HE_t he = (HE_t) memset(alloca(sizeof(*he)), 0, sizeof(*he));
+        int nkeys = argvCount(keys);
+        for(i=0; i<nkeys; i++) {
+            rpmmi mi = rpmtsInitIterator(ts[0], RPMTAG_NVRA, keys[i], 0);
+            Header h;
+            if ((h = rpmmiNext(mi)) != NULL) {
+                /* Get name of package */
+                he->tag = RPMTAG_NAME;
+                rc = (headerGet(h, he, 0) != 1);
+                char *name = strdup((char *)he->p.ptr);
+                /* Get its requires */
+                he->tag = RPMTAG_REQUIRENAME;
+                rc = (headerGet(h, he, 0) != 1);
+                ARGV_t reqs = (ARGV_t)he->p.ptr;
+                /* Get its requireflags */
+                he->tag = RPMTAG_REQUIREFLAGS;
+                rc = (headerGet(h, he, 0) != 1);
+                rpmuint32_t *reqflags = (rpmuint32_t *)he->p.ui32p;
+                for(j=0; j<he->c; j++) {
+                    int k;
+                    char *prov = NULL;
+                    for(k=0; k<nnames; k++) {
+                        if(strcmp(names[k], reqs[j]) == 0) {
+                            prov = names[k];
+                            break;
+                        }
+                    }
+                    if(prov) {
+                        if((int)reqflags[j] & 0x80000)
+                            printf("%s|%s [REC]\n", name, prov);
+                        else
+                            printf("%s|%s\n", name, prov);
+                    }
+                    else {
+                        rc = lookupProvider(ts[0], reqs[j], &prov);
+                        if(rc==0 && prov) {
+                            if((int)reqflags[j] & 0x80000)
+                                printf("%s|%s [REC]\n", name, prov);
+                            else
+                                printf("%s|%s\n", name, prov);
+                            free(prov);
+                        }
+                    }
+                }
+                free(name);
+            }
+            (void)rpmmiFree(mi);
+        }
+    }
+
+    return rc;
+}
+
 void usage()
 {
     fprintf(stderr, "OpenEmbedded rpm resolver utility\n");
-    fprintf(stderr, "syntax: rpmresolve [-i] <dblistfile> <packagelistfile>\n");
+    fprintf(stderr, "syntax: rpmresolve [-i] [-d] <dblistfile> <packagelistfile>\n");
 }
 
 int main(int argc, char **argv)
@@ -218,13 +312,17 @@ int main(int argc, char **argv)
     int i;
     int c;
     int ignoremissing = 0;
+    int deplistmode = 0;
 
     opterr = 0;
-    while ((c = getopt (argc, argv, "i")) != -1) {
+    while ((c = getopt (argc, argv, "id")) != -1) {
         switch (c) {
             case 'i':
                 ignoremissing = 1;
                 break;
+            case 'd':
+                deplistmode = 1;
+                break;
             case '?':
                 if(isprint(optopt))
                     fprintf(stderr, "Unknown option `-%c'.\n", optopt);
@@ -258,12 +356,17 @@ int main(int argc, char **argv)
         return 1;
     }
 
-    if( argc - optind < 2 ) {
-        fprintf(stderr, "Please specify package list file\n");
-        return 1;
+    if(deplistmode) {
+        rc = printDepList(ts, tscount);
+    }
+    else {
+        if( argc - optind < 2 ) {
+            fprintf(stderr, "Please specify package list file\n");
+            return 1;
+        }
+        const char *pkglistfn = argv[optind+1];
+        rc = processPackages(ts, tscount, pkglistfn, ignoremissing);
     }
-    const char *pkglistfn = argv[optind+1];
-    rc = processPackages(ts, tscount, pkglistfn, ignoremissing);
 
     for(i=0; i<tscount; i++)
         (void) rpmtsCloseDB(ts[i]);