[PATCH 2/3] perf-test: cache unpacked corpus

david at tethera.net david at tethera.net
Mon Dec 3 17:17:03 PST 2012


From: David Bremner <bremner at debian.org>

Unpacking is not really the expensive step (compared to the initial
notmuch new), but this is a pre-requisite to caching the database.
---
 performance-test/.gitignore       |    1 +
 performance-test/Makefile.local   |    2 +-
 performance-test/perf-test-lib.sh |   51 +++++++++++++++++++++----------------
 3 files changed, 31 insertions(+), 23 deletions(-)

diff --git a/performance-test/.gitignore b/performance-test/.gitignore
index 53f2697..7e20f7c 100644
--- a/performance-test/.gitignore
+++ b/performance-test/.gitignore
@@ -1 +1,2 @@
 tmp.*/
+corpus.mail.*/
diff --git a/performance-test/Makefile.local b/performance-test/Makefile.local
index 5d2acbd..eb713d0 100644
--- a/performance-test/Makefile.local
+++ b/performance-test/Makefile.local
@@ -29,4 +29,4 @@ $(TXZFILE):
 download-corpus:
 	wget -O ${TXZFILE} ${DEFAULT_URL}
 
-CLEAN := $(CLEAN) $(dir)/tmp.*
+CLEAN := $(CLEAN) $(dir)/tmp.* $(dir)/corpus.mail.*
diff --git a/performance-test/perf-test-lib.sh b/performance-test/perf-test-lib.sh
index bba793d..9fbf874 100644
--- a/performance-test/perf-test-lib.sh
+++ b/performance-test/perf-test-lib.sh
@@ -35,37 +35,44 @@ then
 	exit 1
 fi
 
+CORPUS_DIR=${TEST_DIRECTORY}/corpus.mail.$corpus_size
 add_email_corpus ()
 {
     rm -rf ${MAIL_DIR}
+    if [ ! -d $CORPUS_DIR ]; then
+	case "$corpus_size" in
+	    small)
+		arg="mail/enron/bailey-s"
+		;;
+	    medium)
+		arg="mail/notmuch-archive"
+		;;
+	    *)
+		arg=mail
+	esac
 
-    case "$1" in
-	--small)
-	    arg="mail/enron/bailey-s"
-	    ;;
-	--medium)
-	    arg="mail/notmuch-archive"
-	    ;;
-	*)
-	    arg=mail
-    esac
+	if command -v pixz > /dev/null; then
+	    XZ=pixz
+	else
+	    XZ=xz
+	fi
 
-    if command -v pixz > /dev/null; then
-	XZ=pixz
-    else
-	XZ=xz
-    fi
+	printf "Unpacking corpus\n"
+	mkdir $CORPUS_DIR
+
+	tar --checkpoint=.5000 --extract --strip-components=2 \
+	    --directory $CORPUS_DIR \
+	    --use-compress-program ${XZ} \
+	    --file ../download/notmuch-email-corpus-${PERFTEST_VERSION}.tar.xz \
+	    notmuch-email-corpus/"$arg"
 
-    printf "Unpacking corpus\n"
-    tar --checkpoint=.5000 --extract --strip-components=1 \
-	--directory ${TMP_DIRECTORY} \
-	--use-compress-program ${XZ} \
-	--file ../download/notmuch-email-corpus-${PERFTEST_VERSION}.tar.xz \
-	notmuch-email-corpus/"$arg"
+	printf "\n"
 
-    printf "\n"
+    fi
+    cp -lr $CORPUS_DIR $MAIL_DIR
 }
 
+
 print_header () {
     printf "[v%4s]               Wall(s)\tUsr(s)\tSys(s)\tRes(K)\tIn(512B)\tOut(512B)\n" \
 	   ${PERFTEST_VERSION}
-- 
1.7.10.4



More information about the notmuch mailing list