| Message ID | 20211027234504.30744-1-joannekoong@fb.com (mailing list archive) |
|---|---|
| Headers | show |
| Series | Implement bloom filter map | expand |
On Wed, Oct 27, 2021 at 04:44:59PM -0700, Joanne Koong wrote: > This patchset adds a new kind of bpf map: the bloom filter map. > Bloom filters are a space-efficient probabilistic data structure > used to quickly test whether an element exists in a set. > For a brief overview about how bloom filters work, > https://en.wikipedia.org/wiki/Bloom_filter > may be helpful. > > One example use-case is an application leveraging a bloom filter > map to determine whether a computationally expensive hashmap > lookup can be avoided. If the element was not found in the bloom > filter map, the hashmap lookup can be skipped. > > This patchset includes benchmarks for testing the performance of > the bloom filter for different entry sizes and different number of > hash functions used, as well as comparisons for hashmap lookups > with vs. without the bloom filter. > > A high level overview of this patchset is as follows: > 1/5 - kernel changes for adding bloom filter map > 2/5 - libbpf changes for adding map_extra flags > 3/5 - tests for the bloom filter map > 4/5 - benchmarks for bloom filter lookup/update throughput and false positive > rate > 5/5 - benchmarks for how hashmap lookups perform with vs. without the bloom > filter > > v5 -> v6: > * in 1/5: remove "inline" from the hash function, add check in syscall to > fail out in cases where map_extra is not 0 for non-bloom-filter maps, > fix alignment matching issues, move "map_extra flags" comments to inside > the bpf_attr struct, add bpf_map_info map_extra changes here, add map_extra > assignment in bpf_map_get_info_by_fd, change hash value_size to u32 instead of > a u64 > * in 2/5: remove bpf_map_info map_extra changes, remove TODO comment about > extending BTF arrays to cover u64s, cast to unsigned long long for %llx when > printing out map_extra flags > * in 3/5: use __type(value, ...) instead of __uint(value_size, ...) for values > and keys > * in 4/5: fix wrong bounds for the index when iterating through random values, > update commit message to include update+lookup benchmark results for 8 byte > and 64-byte value sizes, remove explicit global bool initializaton to false > for hashmap_use_bloom and count_false_hits variables Thanks! Only have minor comments in patch 1. belated Acked-by: Martin KaFai Lau <kafai@fb.com>
On Thu, Oct 28, 2021 at 3:10 PM Martin KaFai Lau <kafai@fb.com> wrote: > > On Wed, Oct 27, 2021 at 04:44:59PM -0700, Joanne Koong wrote: > > This patchset adds a new kind of bpf map: the bloom filter map. > > Bloom filters are a space-efficient probabilistic data structure > > used to quickly test whether an element exists in a set. > > For a brief overview about how bloom filters work, > > https://en.wikipedia.org/wiki/Bloom_filter > > may be helpful. > > > > One example use-case is an application leveraging a bloom filter > > map to determine whether a computationally expensive hashmap > > lookup can be avoided. If the element was not found in the bloom > > filter map, the hashmap lookup can be skipped. > > > > This patchset includes benchmarks for testing the performance of > > the bloom filter for different entry sizes and different number of > > hash functions used, as well as comparisons for hashmap lookups > > with vs. without the bloom filter. > > > > A high level overview of this patchset is as follows: > > 1/5 - kernel changes for adding bloom filter map > > 2/5 - libbpf changes for adding map_extra flags > > 3/5 - tests for the bloom filter map > > 4/5 - benchmarks for bloom filter lookup/update throughput and false positive > > rate > > 5/5 - benchmarks for how hashmap lookups perform with vs. without the bloom > > filter > > > > v5 -> v6: > > * in 1/5: remove "inline" from the hash function, add check in syscall to > > fail out in cases where map_extra is not 0 for non-bloom-filter maps, > > fix alignment matching issues, move "map_extra flags" comments to inside > > the bpf_attr struct, add bpf_map_info map_extra changes here, add map_extra > > assignment in bpf_map_get_info_by_fd, change hash value_size to u32 instead of > > a u64 > > * in 2/5: remove bpf_map_info map_extra changes, remove TODO comment about > > extending BTF arrays to cover u64s, cast to unsigned long long for %llx when > > printing out map_extra flags > > * in 3/5: use __type(value, ...) instead of __uint(value_size, ...) for values > > and keys > > * in 4/5: fix wrong bounds for the index when iterating through random values, > > update commit message to include update+lookup benchmark results for 8 byte > > and 64-byte value sizes, remove explicit global bool initializaton to false > > for hashmap_use_bloom and count_false_hits variables > Thanks! Only have minor comments in patch 1. belated > Acked-by: Martin KaFai Lau <kafai@fb.com> Thanks for the detailed review and sorry for pushing too soon. I forced pushed your Ack. Joanne, pls follow up with fixes for patch 1 asap, so we get it cleaned up before the merge window.
On 10/28/21 4:05 PM, Alexei Starovoitov wrote: > On Thu, Oct 28, 2021 at 3:10 PM Martin KaFai Lau <kafai@fb.com> wrote: >> On Wed, Oct 27, 2021 at 04:44:59PM -0700, Joanne Koong wrote: >>> This patchset adds a new kind of bpf map: the bloom filter map. >>> Bloom filters are a space-efficient probabilistic data structure >>> used to quickly test whether an element exists in a set. >>> For a brief overview about how bloom filters work, >>> https://en.wikipedia.org/wiki/Bloom_filter >>> may be helpful. >>> >>> One example use-case is an application leveraging a bloom filter >>> map to determine whether a computationally expensive hashmap >>> lookup can be avoided. If the element was not found in the bloom >>> filter map, the hashmap lookup can be skipped. >>> >>> This patchset includes benchmarks for testing the performance of >>> the bloom filter for different entry sizes and different number of >>> hash functions used, as well as comparisons for hashmap lookups >>> with vs. without the bloom filter. >>> >>> A high level overview of this patchset is as follows: >>> 1/5 - kernel changes for adding bloom filter map >>> 2/5 - libbpf changes for adding map_extra flags >>> 3/5 - tests for the bloom filter map >>> 4/5 - benchmarks for bloom filter lookup/update throughput and false positive >>> rate >>> 5/5 - benchmarks for how hashmap lookups perform with vs. without the bloom >>> filter >>> >>> v5 -> v6: >>> * in 1/5: remove "inline" from the hash function, add check in syscall to >>> fail out in cases where map_extra is not 0 for non-bloom-filter maps, >>> fix alignment matching issues, move "map_extra flags" comments to inside >>> the bpf_attr struct, add bpf_map_info map_extra changes here, add map_extra >>> assignment in bpf_map_get_info_by_fd, change hash value_size to u32 instead of >>> a u64 >>> * in 2/5: remove bpf_map_info map_extra changes, remove TODO comment about >>> extending BTF arrays to cover u64s, cast to unsigned long long for %llx when >>> printing out map_extra flags >>> * in 3/5: use __type(value, ...) instead of __uint(value_size, ...) for values >>> and keys >>> * in 4/5: fix wrong bounds for the index when iterating through random values, >>> update commit message to include update+lookup benchmark results for 8 byte >>> and 64-byte value sizes, remove explicit global bool initializaton to false >>> for hashmap_use_bloom and count_false_hits variables >> Thanks! Only have minor comments in patch 1. belated >> Acked-by: Martin KaFai Lau <kafai@fb.com> > Thanks for the detailed review and sorry for pushing too soon. > I forced pushed your Ack. > > Joanne, pls follow up with fixes for patch 1 asap, so we get it cleaned up > before the merge window. Should the fixes be in a new separate patchset or as v7 of this existing patchset? Thanks.
On Thu, Oct 28, 2021 at 5:24 PM Joanne Koong <joannekoong@fb.com> wrote: > > Thanks for the detailed review and sorry for pushing too soon. > > I forced pushed your Ack. > > > > Joanne, pls follow up with fixes for patch 1 asap, so we get it cleaned up > > before the merge window. > Should the fixes be in a new separate patchset or as v7 of this existing > patchset? Thanks. The v6 was applied to bpf-next. Pls send a fix as another patch.
This patchset adds a new kind of bpf map: the bloom filter map. Bloom filters are a space-efficient probabilistic data structure used to quickly test whether an element exists in a set. For a brief overview about how bloom filters work, https://en.wikipedia.org/wiki/Bloom_filter may be helpful. One example use-case is an application leveraging a bloom filter map to determine whether a computationally expensive hashmap lookup can be avoided. If the element was not found in the bloom filter map, the hashmap lookup can be skipped. This patchset includes benchmarks for testing the performance of the bloom filter for different entry sizes and different number of hash functions used, as well as comparisons for hashmap lookups with vs. without the bloom filter. A high level overview of this patchset is as follows: 1/5 - kernel changes for adding bloom filter map 2/5 - libbpf changes for adding map_extra flags 3/5 - tests for the bloom filter map 4/5 - benchmarks for bloom filter lookup/update throughput and false positive rate 5/5 - benchmarks for how hashmap lookups perform with vs. without the bloom filter v5 -> v6: * in 1/5: remove "inline" from the hash function, add check in syscall to fail out in cases where map_extra is not 0 for non-bloom-filter maps, fix alignment matching issues, move "map_extra flags" comments to inside the bpf_attr struct, add bpf_map_info map_extra changes here, add map_extra assignment in bpf_map_get_info_by_fd, change hash value_size to u32 instead of a u64 * in 2/5: remove bpf_map_info map_extra changes, remove TODO comment about extending BTF arrays to cover u64s, cast to unsigned long long for %llx when printing out map_extra flags * in 3/5: use __type(value, ...) instead of __uint(value_size, ...) for values and keys * in 4/5: fix wrong bounds for the index when iterating through random values, update commit message to include update+lookup benchmark results for 8 byte and 64-byte value sizes, remove explicit global bool initializaton to false for hashmap_use_bloom and count_false_hits variables v4 -> v5: * Change the "bitset map with bloom filter capabilities" to a bloom filter map with max_entries signifying the number of unique entries expected in the bloom filter, remove bitset tests * Reduce verbiage by changing "bloom_filter" to "bloom", and renaming progs to more concise names. * in 2/5: remove "map_extra" from struct definitions that are frozen, create a "bpf_create_map_params" struct to propagate map_extra to the kernel at map creation time, change map_extra to __u64 * in 4/5: check pthread condition variable in a loop when generating initial map data, remove "err" checks where not pragmatic, generate random values for the hashmap in the setup() instead of in the bpf program, add check_args() for checking that there aren't more requested entries than possible unique entries for the specified value size * in 5/5: Update commit message with updated benchmark data v3 -> v4: * Generalize the bloom filter map to be a bitset map with bloom filter capabilities * Add map_extra flags; pass in nr_hash_funcs through lower 4 bits of map_extra for the bitset map * Add tests for the bitset map (non-bloom filter) functionality * In the benchmarks, stats are computed only as monotonic increases, and place stats in a struct instead of as a percpu_array bpf map v2 -> v3: * Add libbpf changes for supporting nr_hash_funcs, instead of passing the number of hash functions through map_flags. * Separate the hashing logic in kernel/bpf/bloom_filter.c into a helper function v1 -> v2: * Remove libbpf changes, and pass the number of hash functions through map_flags instead. * Default to using 5 hash functions if no number of hash functions is specified. * Use set_bit instead of spinlocks in the bloom filter bitmap. This improved the speed significantly. For example, using 5 hash functions with 100k entries, there was roughly a 35% speed increase. * Use jhash2 (instead of jhash) for u32-aligned value sizes. This increased the speed by roughly 5 to 15%. When using jhash2 on value sizes non-u32 aligned (truncating any remainder bits), there was not a noticeable difference. * Add test for using the bloom filter as an inner map. * Reran the benchmarks, updated the commit messages to correspond to the new results. Joanne Koong (5): bpf: Add bloom filter map implementation libbpf: Add "map_extra" as a per-map-type extra flag selftests/bpf: Add bloom filter map test cases bpf/benchs: Add benchmark tests for bloom filter throughput + false positive bpf/benchs: Add benchmarks for comparing hashmap lookups w/ vs. w/out bloom filter include/linux/bpf.h | 1 + include/linux/bpf_types.h | 1 + include/uapi/linux/bpf.h | 9 + kernel/bpf/Makefile | 2 +- kernel/bpf/bloom_filter.c | 195 +++++++ kernel/bpf/syscall.c | 24 +- kernel/bpf/verifier.c | 19 +- tools/include/uapi/linux/bpf.h | 9 + tools/lib/bpf/bpf.c | 27 +- tools/lib/bpf/bpf_gen_internal.h | 2 +- tools/lib/bpf/gen_loader.c | 3 +- tools/lib/bpf/libbpf.c | 38 +- tools/lib/bpf/libbpf.h | 3 + tools/lib/bpf/libbpf.map | 2 + tools/lib/bpf/libbpf_internal.h | 25 +- tools/testing/selftests/bpf/Makefile | 6 +- tools/testing/selftests/bpf/bench.c | 60 ++- tools/testing/selftests/bpf/bench.h | 3 + .../bpf/benchs/bench_bloom_filter_map.c | 477 ++++++++++++++++++ .../bpf/benchs/run_bench_bloom_filter_map.sh | 45 ++ .../bpf/benchs/run_bench_ringbufs.sh | 30 +- .../selftests/bpf/benchs/run_common.sh | 60 +++ .../bpf/prog_tests/bloom_filter_map.c | 204 ++++++++ .../selftests/bpf/progs/bloom_filter_bench.c | 153 ++++++ .../selftests/bpf/progs/bloom_filter_map.c | 82 +++ 25 files changed, 1429 insertions(+), 51 deletions(-) create mode 100644 kernel/bpf/bloom_filter.c create mode 100644 tools/testing/selftests/bpf/benchs/bench_bloom_filter_map.c create mode 100755 tools/testing/selftests/bpf/benchs/run_bench_bloom_filter_map.sh create mode 100644 tools/testing/selftests/bpf/benchs/run_common.sh create mode 100644 tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c create mode 100644 tools/testing/selftests/bpf/progs/bloom_filter_bench.c create mode 100644 tools/testing/selftests/bpf/progs/bloom_filter_map.c