diff options
| author | Jim Meyering <meyering@fb.com> | 2018-09-06 11:27:01 -0700 |
|---|---|---|
| committer | Jim Meyering <meyering@fb.com> | 2018-10-13 21:19:36 -0700 |
| commit | 41ac7a99647316b5ea77d70199282fa9bbd731d4 (patch) | |
| tree | bdd10dc718134931486a6979f772a216202a1875 | |
| parent | 7179b21b0366062d55e411320ff347c436d05a8a (diff) | |
| download | grep-41ac7a99647316b5ea77d70199282fa9bbd731d4.tar.gz | |
grep: triple initial buffer size: 32k->96k
Changing 32k to 96k gives a 3-23% performance improvement.
All timings ran with this diff on top of commit v3.1-39-g7179b21:
for n in 32 64 96 128; do
echo n=$n
perl -pi -e 's/(INITIAL_BUFSIZE =) \d+/$1 '$n/ src/grep.c &&
make AM_CFLAGS=-O3 WERROR_CFLAGS= >& makerr-$n &&
for needle in 1f2 1f298lkjskjhahjklkj34; do
echo " needle=$needle"
for i in $(seq 10); do
env MALLOC_PERTURB_= time -qf%e src/grep $needle w2000
done 2>&1 |sort -g | tee >(head -1|sed 's/^/ /') > .time-${n}KB-$needle
done
done
Tested searchs: search for a short literal pattern that is not
present in 9.3GB file containing 2000 copies of /usr/dict/words
created via this:
ln -s /usr/share/dict/words k && cat $(yes k|head -2000) > w2000
I ran this command:
env MALLOC_PERTURB_= time src/grep 1f2 w2000
old(32k) vs new elapsed time, best of 10 trials (gcc-9.0.0 20180831, -O3):
32k 64k 96k(%incr) 128k CPU
1.25 1.18 1.16( 7.2) 1.20 i7-4770S@3.10GHz cache=8MB
1.21 1.16 1.17( 3.3) 1.19 Xeon(R) E3-1505M v5 @ 2.80GHz cache=8MB
2.36 2.29 2.29( 3.0) 2.36 Xeon(R) E5-2680 v4 @ 2.40GHz cache=32MB
1.40 1.32 1.31( 6.4) 1.33 i5-6260U @ 1.80GHz cache=4MB
1.31 1.26 1.24( 5.3) 1.23 AMD FX(tm)-4100 cache=2MB (with only 1000 copies)
Searching for a longer string: 1f298lkjskjhahjklkj34
2.03 1.76 1.61(20.7) 1.53 i7-4770S@3.10GHz cache=8MB
1.95 1.70 1.56(20.0) 1.51 Xeon(R) E3-1505M v5 @ 2.80GHz
3.27 2.98 2.84(13.1) 3.02 Xeon(R) E5-2680 v4 @ 2.40GHz
2.48 2.12 1.91(23.0) 1.80 i5-6260U @ 1.80GHz cache=4MB
1.72 1.54 1.46(15.1) 1.41 AMD FX(tm)-4100 cache=2MB
* src/grep.c (INITIAL_BUFSIZE): Triple it: 32kB -> 96kB
| -rw-r--r-- | src/grep.c | 4 |
1 files changed, 3 insertions, 1 deletions
@@ -799,7 +799,6 @@ skipped_file (char const *name, bool command_line, bool is_dir) static char *buffer; /* Base of buffer. */ static size_t bufalloc; /* Allocated buffer size, counting slop. */ -enum { INITIAL_BUFSIZE = 32768 }; /* Initial buffer size, not counting slop. */ static int bufdesc; /* File descriptor. */ static char *bufbeg; /* Beginning of user-visible stuff. */ static char *buflim; /* Limit of user-visible stuff. */ @@ -812,6 +811,9 @@ static bool skip_nuls; /* Skip '\0' in data. */ static bool skip_empty_lines; /* Skip empty lines in data. */ static uintmax_t totalnl; /* Total newline count before lastnl. */ +/* Initial buffer size, not counting slop. */ +enum { INITIAL_BUFSIZE = 96 * 1024 }; + /* Return VAL aligned to the next multiple of ALIGNMENT. VAL can be an integer or a pointer. Both args must be free of side effects. */ #define ALIGN_TO(val, alignment) \ |