[PATCH RFC] sstate: Switch from tgz to tar.xz for sstate

* [PATCH RFC] sstate: Switch from tgz to tar.xz for sstate
@ 2016-01-09 16:42 Richard Purdie
  2016-01-11 19:05 ` Andre McCurdy
  0 siblings, 1 reply; 7+ messages in thread
From: Richard Purdie @ 2016-01-09 16:42 UTC (permalink / raw)
  To: openembedded-core

xz compresses with a better compression ratio than gz with similar speed
for compression and decompression. It therefore makes sense to switch
to it for the sstate objects.

As an example, the gcc-cross populate_sysroot object goes from
79,509,871 to 53,031,752 bytes which is a significant improvement.

Signed-off-by: Richard Purdie <richard.purdie@linuxfoundation.org>

diff --git a/meta/classes/buildhistory.bbclass b/meta/classes/buildhistory.bbclass
index 4153e58..734303c 100644
--- a/meta/classes/buildhistory.bbclass
+++ b/meta/classes/buildhistory.bbclass
@@ -537,7 +537,7 @@ python buildhistory_get_extra_sdkinfo() {
         filesizes = {}
         for root, _, files in os.walk('${SDK_OUTPUT}/${SDKPATH}/sstate-cache'):
             for fn in files:
-                if fn.endswith('.tgz'):
+                if fn.endswith('.tar.xz'):
                     fsize = int(math.ceil(float(os.path.getsize(os.path.join(root, fn))) / 1024))
                     task = fn.rsplit(':', 1)[1].split('_', 1)[1].split('.')[0]
                     origtotal = tasksizes.get(task, 0)
diff --git a/meta/classes/populate_sdk_ext.bbclass b/meta/classes/populate_sdk_ext.bbclass
index 3a65c07..4ff5e9e 100644
--- a/meta/classes/populate_sdk_ext.bbclass
+++ b/meta/classes/populate_sdk_ext.bbclass
@@ -189,7 +189,7 @@ python copy_buildsystem () {
     # We don't need sstate do_package files
     for root, dirs, files in os.walk(sstate_out):
         for name in files:
-            if name.endswith("_package.tgz"):
+            if name.endswith("_package.tar.xz"):
                 f = os.path.join(root, name)
                 os.remove(f)
 }
diff --git a/meta/classes/sstate.bbclass b/meta/classes/sstate.bbclass
index 9bef212..d9adf01 100644
--- a/meta/classes/sstate.bbclass
+++ b/meta/classes/sstate.bbclass
@@ -294,8 +294,8 @@ def sstate_installpkg(ss, d):
         oe.path.remove(dir)
 
     sstateinst = d.expand("${WORKDIR}/sstate-install-%s/" % ss['task'])
-    sstatefetch = d.getVar('SSTATE_PKGNAME', True) + '_' + ss['task'] + ".tgz"
-    sstatepkg = d.getVar('SSTATE_PKG', True) + '_' + ss['task'] + ".tgz"
+    sstatefetch = d.getVar('SSTATE_PKGNAME', True) + '_' + ss['task'] + ".tar.xz"
+    sstatepkg = d.getVar('SSTATE_PKG', True) + '_' + ss['task'] + ".tar.xz"
 
     if not os.path.exists(sstatepkg):
         pstaging_fetch(sstatefetch, sstatepkg, d)
@@ -372,7 +372,7 @@ python sstate_hardcode_path_unpack () {
 def sstate_clean_cachefile(ss, d):
     import oe.path
 
-    sstatepkgfile = d.getVar('SSTATE_PATHSPEC', True) + "*_" + ss['task'] + ".tgz*"
+    sstatepkgfile = d.getVar('SSTATE_PATHSPEC', True) + "*_" + ss['task'] + ".tar.xz*"
     bb.note("Removing %s" % sstatepkgfile)
     oe.path.remove(sstatepkgfile)
 
@@ -555,7 +555,7 @@ def sstate_package(ss, d):
     tmpdir = d.getVar('TMPDIR', True)
 
     sstatebuild = d.expand("${WORKDIR}/sstate-build-%s/" % ss['task'])
-    sstatepkg = d.getVar('SSTATE_PKG', True) + '_'+ ss['task'] + ".tgz"
+    sstatepkg = d.getVar('SSTATE_PKG', True) + '_'+ ss['task'] + ".tar.xz"
     bb.utils.remove(sstatebuild, recurse=True)
     bb.utils.mkdirhier(sstatebuild)
     bb.utils.mkdirhier(os.path.dirname(sstatepkg))
@@ -677,14 +677,14 @@ sstate_create_package () {
 	# Need to handle empty directories
 	if [ "$(ls -A)" ]; then
 		set +e
-		tar -czf $TFILE *
+		tar -cJf $TFILE *
 		ret=$?
 		if [ $ret -ne 0 ] && [ $ret -ne 1 ]; then
 			exit 1
 		fi
 		set -e
 	else
-		tar -cz --file=$TFILE --files-from=/dev/null
+		tar -cJ --file=$TFILE --files-from=/dev/null
 	fi
 	chmod 0664 $TFILE
 	mv -f $TFILE ${SSTATE_PKG}
@@ -703,7 +703,7 @@ sstate_create_package () {
 # Will be run from within SSTATE_INSTDIR.
 #
 sstate_unpack_package () {
-	tar -xmvzf ${SSTATE_PKG}
+	tar -xmvJf ${SSTATE_PKG}
 	# Use "! -w ||" to return true for read only files
 	[ ! -w ${SSTATE_PKG} ] || touch --no-dereference ${SSTATE_PKG}
 	[ ! -w ${SSTATE_PKG}.sig ] || [ ! -e ${SSTATE_PKG}.sig ] || touch --no-dereference ${SSTATE_PKG}.sig
@@ -716,7 +716,7 @@ def sstate_checkhashes(sq_fn, sq_task, sq_hash, sq_hashfn, d, siginfo=False):
 
     ret = []
     missed = []
-    extension = ".tgz"
+    extension = ".tar.xz"
     if siginfo:
         extension = extension + ".siginfo"
 
@@ -821,11 +821,11 @@ def sstate_checkhashes(sq_fn, sq_task, sq_hash, sq_hashfn, d, siginfo=False):
         evdata = {'missed': [], 'found': []};
         for task in missed:
             spec, extrapath, tname = getpathcomponents(task, d)
-            sstatefile = d.expand(extrapath + generate_sstatefn(spec, sq_hash[task], d) + "_" + tname + ".tgz")
+            sstatefile = d.expand(extrapath + generate_sstatefn(spec, sq_hash[task], d) + "_" + tname + ".tar.xz")
             evdata['missed'].append( (sq_fn[task], sq_task[task], sq_hash[task], sstatefile ) )
         for task in ret:
             spec, extrapath, tname = getpathcomponents(task, d)
-            sstatefile = d.expand(extrapath + generate_sstatefn(spec, sq_hash[task], d) + "_" + tname + ".tgz")
+            sstatefile = d.expand(extrapath + generate_sstatefn(spec, sq_hash[task], d) + "_" + tname + ".tar.xz")
             evdata['found'].append( (sq_fn[task], sq_task[task], sq_hash[task], sstatefile ) )
         bb.event.fire(bb.event.MetadataEvent("MissedSstate", evdata), d)
 
@@ -914,7 +914,7 @@ python sstate_eventhandler() {
     d = e.data
     # When we write an sstate package we rewrite the SSTATE_PKG
     spkg = d.getVar('SSTATE_PKG', True)
-    if not spkg.endswith(".tgz"):
+    if not spkg.endswith(".tar.xz"):
         taskname = d.getVar("BB_RUNTASK", True)[3:]
         spec = d.getVar('SSTATE_PKGSPEC', True)
         swspec = d.getVar('SSTATE_SWSPEC', True)
@@ -922,7 +922,7 @@ python sstate_eventhandler() {
             d.setVar("SSTATE_PKGSPEC", "${SSTATE_SWSPEC}")
             d.setVar("SSTATE_EXTRAPATH", "")
         sstatepkg = d.getVar('SSTATE_PKG', True)
-        bb.siggen.dump_this_task(sstatepkg + '_' + taskname + ".tgz" ".siginfo", d)
+        bb.siggen.dump_this_task(sstatepkg + '_' + taskname + ".tar.xz" ".siginfo", d)
 }
 
 SSTATE_PRUNE_OBSOLETEWORKDIR = "1"
diff --git a/meta/lib/oeqa/selftest/signing.py b/meta/lib/oeqa/selftest/signing.py
index c33662b..4d545ad 100644
--- a/meta/lib/oeqa/selftest/signing.py
+++ b/meta/lib/oeqa/selftest/signing.py
@@ -111,13 +111,13 @@ class Signing(oeSelfTest):
         bitbake('-c cleansstate %s' % test_recipe)
         bitbake(test_recipe)
 
-        recipe_sig = glob.glob(sstatedir + '/*/*:ed:*_package.tgz.sig')
-        recipe_tgz = glob.glob(sstatedir + '/*/*:ed:*_package.tgz')
+        recipe_sig = glob.glob(sstatedir + '/*/*:ed:*_package.tar.xz.sig')
+        recipe_txz = glob.glob(sstatedir + '/*/*:ed:*_package.tar.xz')
 
         self.assertEqual(len(recipe_sig), 1, 'Failed to find .sig file.')
-        self.assertEqual(len(recipe_tgz), 1, 'Failed to find .tgz file.')
+        self.assertEqual(len(recipe_txz), 1, 'Failed to find .tar.xz file.')
 
-        ret = runCmd('gpg --homedir %s --verify %s %s' % (self.gpg_dir, recipe_sig[0], recipe_tgz[0]))
+        ret = runCmd('gpg --homedir %s --verify %s %s' % (self.gpg_dir, recipe_sig[0], recipe_txz[0]))
         # gpg: Signature made Thu 22 Oct 2015 01:45:09 PM EEST using RSA key ID 61EEFB30
         # gpg: Good signature from "testuser (nocomment) <testuser@email.com>"
         self.assertIn('gpg: Good signature from', ret.output, 'Package signed incorrectly.')
diff --git a/meta/lib/oeqa/selftest/sstatetests.py b/meta/lib/oeqa/selftest/sstatetests.py
index 512cb4f..73e5132 100644
--- a/meta/lib/oeqa/selftest/sstatetests.py
+++ b/meta/lib/oeqa/selftest/sstatetests.py
@@ -55,15 +55,15 @@ class SStateTests(SStateBase):
         bitbake(['-ccleansstate'] + targets)
 
         bitbake(targets)
-        tgz_created = self.search_sstate('|'.join(map(str, [s + '.*?\.tgz$' for s in targets])), distro_specific, distro_nonspecific)
-        self.assertTrue(tgz_created, msg="Could not find sstate .tgz files for: %s" % ', '.join(map(str, targets)))
+        txz_created = self.search_sstate('|'.join(map(str, [s + '.*?\.tar.xz$' for s in targets])), distro_specific, distro_nonspecific)
+        self.assertTrue(txz_created, msg="Could not find sstate .tar.xz files for: %s" % ', '.join(map(str, targets)))
 
         siginfo_created = self.search_sstate('|'.join(map(str, [s + '.*?\.siginfo$' for s in targets])), distro_specific, distro_nonspecific)
         self.assertTrue(siginfo_created, msg="Could not find sstate .siginfo files for: %s" % ', '.join(map(str, targets)))
 
         bitbake(['-ccleansstate'] + targets)
-        tgz_removed = self.search_sstate('|'.join(map(str, [s + '.*?\.tgz$' for s in targets])), distro_specific, distro_nonspecific)
-        self.assertTrue(not tgz_removed, msg="do_cleansstate didn't remove .tgz sstate files for: %s" % ', '.join(map(str, targets)))
+        txz_removed = self.search_sstate('|'.join(map(str, [s + '.*?\.tar.xz$' for s in targets])), distro_specific, distro_nonspecific)
+        self.assertTrue(not txz_removed, msg="do_cleansstate didn't remove .tar.xz sstate files for: %s" % ', '.join(map(str, targets)))
 
     @testcase(977)
     def test_cleansstate_task_distro_specific_nonspecific(self):
@@ -87,8 +87,8 @@ class SStateTests(SStateBase):
         bitbake(['-ccleansstate'] + targets)
 
         bitbake(targets)
-        self.assertTrue(self.search_sstate('|'.join(map(str, [s + '.*?\.tgz$' for s in targets])), distro_specific=False, distro_nonspecific=True) == [], msg="Found distro non-specific sstate for: %s" % ', '.join(map(str, targets)))
-        file_tracker_1 = self.search_sstate('|'.join(map(str, [s + '.*?\.tgz$' for s in targets])), distro_specific=True, distro_nonspecific=False)
+        self.assertTrue(self.search_sstate('|'.join(map(str, [s + '.*?\.tar.xz$' for s in targets])), distro_specific=False, distro_nonspecific=True) == [], msg="Found distro non-specific sstate for: %s" % ', '.join(map(str, targets)))
+        file_tracker_1 = self.search_sstate('|'.join(map(str, [s + '.*?\.tar.xz$' for s in targets])), distro_specific=True, distro_nonspecific=False)
         self.assertTrue(len(file_tracker_1) >= len(targets), msg = "Not all sstate files ware created for: %s" % ', '.join(map(str, targets)))
 
         self.track_for_cleanup(self.distro_specific_sstate + "_old")
@@ -97,7 +97,7 @@ class SStateTests(SStateBase):
 
         bitbake(['-cclean'] + targets)
         bitbake(targets)
-        file_tracker_2 = self.search_sstate('|'.join(map(str, [s + '.*?\.tgz$' for s in targets])), distro_specific=True, distro_nonspecific=False)
+        file_tracker_2 = self.search_sstate('|'.join(map(str, [s + '.*?\.tar.xz$' for s in targets])), distro_specific=True, distro_nonspecific=False)
         self.assertTrue(len(file_tracker_2) >= len(targets), msg = "Not all sstate files ware created for: %s" % ', '.join(map(str, targets)))
 
         not_recreated = [x for x in file_tracker_1 if x not in file_tracker_2]
@@ -146,18 +146,18 @@ class SStateTests(SStateBase):
             if not sstate_arch in sstate_archs_list:
                 sstate_archs_list.append(sstate_arch)
             if target_config[idx] == target_config[-1]:
-                target_sstate_before_build = self.search_sstate(target + '.*?\.tgz$')
+                target_sstate_before_build = self.search_sstate(target + '.*?\.tar.xz$')
             bitbake("-cclean %s" % target)
             result = bitbake(target, ignore_status=True)
             if target_config[idx] == target_config[-1]:
-                target_sstate_after_build = self.search_sstate(target + '.*?\.tgz$')
+                target_sstate_after_build = self.search_sstate(target + '.*?\.tar.xz$')
                 expected_remaining_sstate += [x for x in target_sstate_after_build if x not in target_sstate_before_build if not any(pattern in x for pattern in ignore_patterns)]
             self.remove_config(global_config[idx])
             self.remove_recipeinc(target, target_config[idx])
             self.assertEqual(result.status, 0, msg = "build of %s failed with %s" % (target, result.output))
 
         runCmd("sstate-cache-management.sh -y --cache-dir=%s --remove-duplicated --extra-archs=%s" % (self.sstate_path, ','.join(map(str, sstate_archs_list))))
-        actual_remaining_sstate = [x for x in self.search_sstate(target + '.*?\.tgz$') if not any(pattern in x for pattern in ignore_patterns)]
+        actual_remaining_sstate = [x for x in self.search_sstate(target + '.*?\.tar.xz$') if not any(pattern in x for pattern in ignore_patterns)]
 
         actual_not_expected = [x for x in actual_remaining_sstate if x not in expected_remaining_sstate]
         self.assertFalse(actual_not_expected, msg="Files should have been removed but ware not: %s" % ', '.join(map(str, actual_not_expected)))




^ permalink raw reply related	[flat|nested] 7+ messages in thread