Merge pull request #1304 from facebook/largeNbDicts

contrib/largeNbDicts

Author: Cyan4973

Makefile

@@ -88,6 +88,7 @@ contrib: lib
 	$(MAKE) -C contrib/pzstd all
 	$(MAKE) -C contrib/seekable_format/examples all
 	$(MAKE) -C contrib/adaptive-compression all
+	$(MAKE) -C contrib/largeNbDicts all
 
 .PHONY: cleanTabs
 cleanTabs:
@@ -104,6 +105,7 @@ clean:
 	@$(MAKE) -C contrib/pzstd $@ > $(VOID)
 	@$(MAKE) -C contrib/seekable_format/examples $@ > $(VOID)
 	@$(MAKE) -C contrib/adaptive-compression $@ > $(VOID)
+	@$(MAKE) -C contrib/largeNbDicts $@ > $(VOID)
 	@$(RM) zstd$(EXT) zstdmt$(EXT) tmp*
 	@$(RM) -r lz4
 	@echo Cleaning completed

contrib/largeNbDicts/.gitignore

@@ -0,0 +1,2 @@
+# build artifacts
+largeNbDicts

contrib/largeNbDicts/Makefile

@@ -0,0 +1,49 @@
+# ################################################################
+# Copyright (c) 2018-present, Yann Collet, Facebook, Inc.
+# All rights reserved.
+#
+# This source code is licensed under both the BSD-style license (found in the
+# LICENSE file in the root directory of this source tree) and the GPLv2 (found
+# in the COPYING file in the root directory of this source tree).
+# ################################################################
+
+PROGDIR = ../../programs
+LIBDIR  = ../../lib
+
+LIBZSTD = $(LIBDIR)/libzstd.a
+
+CPPFLAGS+= -I$(LIBDIR) -I$(LIBDIR)/common -I$(LIBDIR)/dictBuilder -I$(PROGDIR)
+
+CFLAGS  ?= -O3
+CFLAGS  += -std=gnu99
+DEBUGFLAGS= -Wall -Wextra -Wcast-qual -Wcast-align -Wshadow \
+            -Wstrict-aliasing=1 -Wswitch-enum \
+            -Wstrict-prototypes -Wundef -Wpointer-arith -Wformat-security \
+            -Wvla -Wformat=2 -Winit-self -Wfloat-equal -Wwrite-strings \
+            -Wredundant-decls
+CFLAGS  += $(DEBUGFLAGS) $(MOREFLAGS)
+
+
+default: largeNbDicts
+
+all : largeNbDicts
+
+largeNbDicts: bench.o datagen.o xxhash.o largeNbDicts.c $(LIBZSTD)
+	$(CC) $(CPPFLAGS) $(CFLAGS) $^ $(LDFLAGS) -o $@
+
+.PHONY: $(LIBZSTD)
+$(LIBZSTD):
+	$(MAKE) -C $(LIBDIR) libzstd.a
+
+bench.o  : $(PROGDIR)/bench.c
+	$(CC) $(CPPFLAGS) $(CFLAGS) $^ -c
+
+datagen.o: $(PROGDIR)/datagen.c
+	$(CC) $(CPPFLAGS) $(CFLAGS) $^ -c
+
+xxhash.o : $(LIBDIR)/common/xxhash.c
+	$(CC) $(CPPFLAGS) $(CFLAGS) $^ -c
+
+clean:
+	$(RM) *.o
+	$(RM) largeNbDicts

contrib/largeNbDicts/README.md

@@ -0,0 +1,25 @@
+largeNbDicts
+=====================
+
+`largeNbDicts` is a benchmark test tool
+dedicated to the specific scenario of
+dictionary decompression using a very large number of dictionaries.
+When dictionaries are constantly changing, they are always "cold",
+suffering from increased latency due to cache misses.
+
+The tool is created in a bid to investigate performance for this scenario,
+and experiment mitigation techniques.
+
+Command line :
+```
+largeNbDicts [Options] filename(s)
+
+Options :
+-r           : recursively load all files in subdirectories (default: off)
+-B#          : split input into blocks of size # (default: no split)
+-#           : use compression level # (default: 3)
+-D #         : use # as a dictionary (default: create one)
+-i#          : nb benchmark rounds (default: 6)
+--nbDicts=#  : set nb of dictionaries to # (default: one per block)
+-h           : help (this text)
+```