@@ -92,20 +92,21 @@ void hits_drops_report_progress(int iter, struct bench_res *res, long delta_ns)
printf("Iter %3d (%7.3lfus): ",
iter, (delta_ns - 1000000000) / 1000.0);
- printf("hits %8.3lfM/s (%7.3lfM/prod), drops %8.3lfM/s\n",
- hits_per_sec, hits_per_prod, drops_per_sec);
+ printf("hits %8.3lfM/s (%7.3lfM/prod), drops %8.3lfM/s, total operations %8.3lfM/s\n",
+ hits_per_sec, hits_per_prod, drops_per_sec, hits_per_sec + drops_per_sec);
}
void hits_drops_report_final(struct bench_res res[], int res_cnt)
{
int i;
- double hits_mean = 0.0, drops_mean = 0.0;
- double hits_stddev = 0.0, drops_stddev = 0.0;
+ double hits_mean = 0.0, drops_mean = 0.0, total_ops_mean = 0.0;
+ double hits_stddev = 0.0, drops_stddev = 0.0, total_ops_stddev = 0.0;
for (i = 0; i < res_cnt; i++) {
hits_mean += res[i].hits / 1000000.0 / (0.0 + res_cnt);
drops_mean += res[i].drops / 1000000.0 / (0.0 + res_cnt);
}
+ total_ops_mean = hits_mean + drops_mean;
if (res_cnt > 1) {
for (i = 0; i < res_cnt; i++) {
@@ -115,14 +116,21 @@ void hits_drops_report_final(struct bench_res res[], int res_cnt)
drops_stddev += (drops_mean - res[i].drops / 1000000.0) *
(drops_mean - res[i].drops / 1000000.0) /
(res_cnt - 1.0);
+ total_ops_stddev += (total_ops_mean -
+ (res[i].hits + res[i].drops) / 1000000.0) *
+ (total_ops_mean - (res[i].hits + res[i].drops) / 1000000.0)
+ / (res_cnt - 1.0);
}
hits_stddev = sqrt(hits_stddev);
drops_stddev = sqrt(drops_stddev);
+ total_ops_stddev = sqrt(total_ops_stddev);
}
printf("Summary: hits %8.3lf \u00B1 %5.3lfM/s (%7.3lfM/prod), ",
hits_mean, hits_stddev, hits_mean / env.producer_cnt);
- printf("drops %8.3lf \u00B1 %5.3lfM/s\n",
+ printf("drops %8.3lf \u00B1 %5.3lfM/s, ",
drops_mean, drops_stddev);
+ printf("total operations %8.3lf \u00B1 %5.3lfM/s\n",
+ total_ops_mean, total_ops_stddev);
}
const char *argp_program_version = "benchmark";
@@ -357,6 +365,8 @@ extern const struct bench bench_pb_custom;
extern const struct bench bench_bloom_filter_lookup;
extern const struct bench bench_bloom_filter_update;
extern const struct bench bench_bloom_filter_false_positive;
+extern const struct bench bench_hashmap_without_bloom_filter;
+extern const struct bench bench_hashmap_with_bloom_filter;
static const struct bench *benchs[] = {
&bench_count_global,
@@ -381,6 +391,8 @@ static const struct bench *benchs[] = {
&bench_bloom_filter_lookup,
&bench_bloom_filter_update,
&bench_bloom_filter_false_positive,
+ &bench_hashmap_without_bloom_filter,
+ &bench_hashmap_with_bloom_filter,
};
static void setup_benchmark()
@@ -337,6 +337,21 @@ static void hashmap_lookup_setup(void)
}
}
+static void hashmap_no_bloom_filter_setup(void)
+{
+ struct bpf_link *link;
+
+ ctx.skel = setup_skeleton(false);
+
+ populate_maps();
+
+ link = bpf_program__attach(ctx.skel->progs.prog_bloom_filter_hashmap_lookup);
+ if (!link) {
+ fprintf(stderr, "failed to attach program!\n");
+ exit(1);
+ }
+}
+
static void measure(struct bench_res *res)
{
long total_hits = 0, total_drops = 0, total_false_hits = 0;
@@ -409,3 +424,25 @@ const struct bench bench_bloom_filter_false_positive = {
.report_progress = false_hits_report_progress,
.report_final = false_hits_report_final,
};
+
+const struct bench bench_hashmap_without_bloom_filter = {
+ .name = "hashmap-without-bloom-filter",
+ .validate = validate,
+ .setup = hashmap_no_bloom_filter_setup,
+ .producer_thread = producer,
+ .consumer_thread = consumer,
+ .measure = measure,
+ .report_progress = hits_drops_report_progress,
+ .report_final = hits_drops_report_final,
+};
+
+const struct bench bench_hashmap_with_bloom_filter = {
+ .name = "hashmap-with-bloom-filter",
+ .validate = validate,
+ .setup = hashmap_lookup_setup,
+ .producer_thread = producer,
+ .consumer_thread = consumer,
+ .measure = measure,
+ .report_progress = hits_drops_report_progress,
+ .report_final = hits_drops_report_final,
+};
@@ -26,3 +26,20 @@ subtitle "value_size: $v bytes, # threads: $t, # hashes: $h"
done
done
done
+
+header "Hashmap without bitset vs. hashmap with bitset (throughput, 8 threads)"
+for v in 2, 4, 8, 16, 40; do
+for h in {1..10}; do
+subtitle "# hashes: $h"
+ for e in 10000 50000 75000 100000 250000 500000 750000 1000000 2500000 5000000; do
+ printf "%'d entries -\n" $e
+ printf "\t"
+ summarize_total "Hashmap without bitset: " \
+ "$($RUN_BENCH --nr_hash_funcs $h --nr_entries $e --value_size $v -p 8 hashmap-without-bloom-filter)"
+ printf "\t"
+ summarize_total "Hashmap with bitset: " \
+ "$($RUN_BENCH --nr_hash_funcs $h --nr_entries $e --value_size $v -p 8 hashmap-with-bloom-filter)"
+ done
+ printf "\n"
+done
+done
@@ -33,6 +33,11 @@ function percentage()
echo "$*" | sed -E "s/.*Percentage\s=\s+([0-9]+\.[0-9]+).*/\1/"
}
+function total()
+{
+ echo "$*" | sed -E "s/.*total operations\s+([0-9]+\.[0-9]+ ± [0-9]+\.[0-9]+M\/s).*/\1/"
+}
+
function summarize()
{
bench="$1"
@@ -46,3 +51,10 @@ function summarize_percentage()
summary=$(echo $2 | tail -n1)
printf "%-20s %s%%\n" "$bench" "$(percentage $summary)"
}
+
+function summarize_total()
+{
+ bench="$1"
+ summary=$(echo $2 | tail -n1)
+ printf "%-20s %s\n" "$bench" "$(total $summary)"
+}
This patch adds benchmark tests for comparing the performance of hashmap lookups without the bloom filter vs. hashmap lookups with the bloom filter. Checking the bloom filter first for whether the element exists should overall enable a higher throughput for hashmap lookups, since if the element does not exist in the bloom filter, we can avoid a costly lookup in the hashmap. On average, using 5 hash functions in the bloom filter tended to perform the best across the widest range of different entry sizes. The benchmark results using 5 hash functions (running on 8 threads on a machine with one numa node, and taking the average of 3 runs) were roughly as follows: value_size = 4 bytes - 10k entries: 30% faster 50k entries: 50% faster 100k entries: 55% faster 500k entres: 80% faster 1 million entries: 120% faster 5 million entries: 135% faster value_size = 8 bytes - 10k entries: 35% faster 50k entries: 55% faster 100k entries: 70% faster 500k entres: 110% faster 1 million entries: 215% faster 5 million entries: 215% faster value_size = 16 bytes - 10k entries: 5% slower 50k entries: 25% faster 100k entries: 35% faster 500k entres: 105% faster 1 million entries: 130% faster 5 million entries: 105% faster value_size = 40 bytes - 10k entries: 5% slower 50k entries: 10% faster 100k entries: 20% faster 500k entres: 45% faster 1 million entries: 60% faster 5 million entries: 75% faster Signed-off-by: Joanne Koong <joannekoong@fb.com> --- tools/testing/selftests/bpf/bench.c | 22 ++++++++--- .../bpf/benchs/bench_bloom_filter_map.c | 37 +++++++++++++++++++ .../bpf/benchs/run_bench_bloom_filter_map.sh | 17 +++++++++ .../selftests/bpf/benchs/run_common.sh | 12 ++++++ 4 files changed, 83 insertions(+), 5 deletions(-)