From: Yafang Shao <laoar.shao@gmail.com>
To: ast@kernel.org, daniel@iogearbox.net, andrii@kernel.org,
kafai@fb.com, songliubraving@fb.com, yhs@fb.com,
john.fastabend@gmail.com, kpsingh@kernel.org, sdf@google.com,
haoluo@google.com, jolsa@kernel.org, horenc@vt.edu,
xiyou.wangcong@gmail.com, houtao1@huawei.com
Cc: bpf@vger.kernel.org, Yafang Shao <laoar.shao@gmail.com>
Subject: [PATCH bpf-next v4 03/18] bpf: hashtab memory usage
Date: Sun, 5 Mar 2023 12:46:00 +0000 [thread overview]
Message-ID: <20230305124615.12358-4-laoar.shao@gmail.com> (raw)
In-Reply-To: <20230305124615.12358-1-laoar.shao@gmail.com>
htab_map_mem_usage() is introduced to calculate hashmap memory usage. In
this helper, some small memory allocations are ignore, as their size is
quite small compared with the total size. The inner_map_meta in
hash_of_map is also ignored.
The result for hashtab as follows,
- before this change
1: hash name count_map flags 0x1 <<<< no prealloc, fully set
key 16B value 24B max_entries 1048576 memlock 41943040B
2: hash name count_map flags 0x1 <<<< no prealloc, none set
key 16B value 24B max_entries 1048576 memlock 41943040B
3: hash name count_map flags 0x0 <<<< prealloc
key 16B value 24B max_entries 1048576 memlock 41943040B
The memlock is always a fixed size whatever it is preallocated or
not, and whatever the count of allocated elements is.
- after this change
1: hash name count_map flags 0x1 <<<< non prealloc, fully set
key 16B value 24B max_entries 1048576 memlock 117441536B
2: hash name count_map flags 0x1 <<<< non prealloc, non set
key 16B value 24B max_entries 1048576 memlock 16778240B
3: hash name count_map flags 0x0 <<<< prealloc
key 16B value 24B max_entries 1048576 memlock 109056000B
The memlock now is hashtab actually allocated.
The result for percpu hash map as follows,
- before this change
4: percpu_hash name count_map flags 0x0 <<<< prealloc
key 16B value 24B max_entries 1048576 memlock 822083584B
5: percpu_hash name count_map flags 0x1 <<<< no prealloc
key 16B value 24B max_entries 1048576 memlock 822083584B
- after this change
4: percpu_hash name count_map flags 0x0
key 16B value 24B max_entries 1048576 memlock 897582080B
5: percpu_hash name count_map flags 0x1
key 16B value 24B max_entries 1048576 memlock 922748736B
At worst, the difference can be 10x, for example,
- before this change
6: hash name count_map flags 0x0
key 4B value 4B max_entries 1048576 memlock 8388608B
- after this change
6: hash name count_map flags 0x0
key 4B value 4B max_entries 1048576 memlock 83889408B
Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Acked-by: Hou Tao <houtao1@huawei.com>
---
kernel/bpf/hashtab.c | 43 +++++++++++++++++++++++++++++++++++++++++++
1 file changed, 43 insertions(+)
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 653aeb4..0df4b0c 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -2190,6 +2190,44 @@ static int bpf_for_each_hash_elem(struct bpf_map *map, bpf_callback_t callback_f
return num_elems;
}
+static u64 htab_map_mem_usage(const struct bpf_map *map)
+{
+ struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+ u32 value_size = round_up(htab->map.value_size, 8);
+ bool prealloc = htab_is_prealloc(htab);
+ bool percpu = htab_is_percpu(htab);
+ bool lru = htab_is_lru(htab);
+ u64 num_entries;
+ u64 usage = sizeof(struct bpf_htab);
+
+ usage += sizeof(struct bucket) * htab->n_buckets;
+ usage += sizeof(int) * num_possible_cpus() * HASHTAB_MAP_LOCK_COUNT;
+ if (prealloc) {
+ num_entries = map->max_entries;
+ if (htab_has_extra_elems(htab))
+ num_entries += num_possible_cpus();
+
+ usage += htab->elem_size * num_entries;
+
+ if (percpu)
+ usage += value_size * num_possible_cpus() * num_entries;
+ else if (!lru)
+ usage += sizeof(struct htab_elem *) * num_possible_cpus();
+ } else {
+#define LLIST_NODE_SZ sizeof(struct llist_node)
+
+ num_entries = htab->use_percpu_counter ?
+ percpu_counter_sum(&htab->pcount) :
+ atomic_read(&htab->count);
+ usage += (htab->elem_size + LLIST_NODE_SZ) * num_entries;
+ if (percpu) {
+ usage += (LLIST_NODE_SZ + sizeof(void *)) * num_entries;
+ usage += value_size * num_possible_cpus() * num_entries;
+ }
+ }
+ return usage;
+}
+
BTF_ID_LIST_SINGLE(htab_map_btf_ids, struct, bpf_htab)
const struct bpf_map_ops htab_map_ops = {
.map_meta_equal = bpf_map_meta_equal,
@@ -2206,6 +2244,7 @@ static int bpf_for_each_hash_elem(struct bpf_map *map, bpf_callback_t callback_f
.map_seq_show_elem = htab_map_seq_show_elem,
.map_set_for_each_callback_args = map_set_for_each_callback_args,
.map_for_each_callback = bpf_for_each_hash_elem,
+ .map_mem_usage = htab_map_mem_usage,
BATCH_OPS(htab),
.map_btf_id = &htab_map_btf_ids[0],
.iter_seq_info = &iter_seq_info,
@@ -2227,6 +2266,7 @@ static int bpf_for_each_hash_elem(struct bpf_map *map, bpf_callback_t callback_f
.map_seq_show_elem = htab_map_seq_show_elem,
.map_set_for_each_callback_args = map_set_for_each_callback_args,
.map_for_each_callback = bpf_for_each_hash_elem,
+ .map_mem_usage = htab_map_mem_usage,
BATCH_OPS(htab_lru),
.map_btf_id = &htab_map_btf_ids[0],
.iter_seq_info = &iter_seq_info,
@@ -2378,6 +2418,7 @@ static void htab_percpu_map_seq_show_elem(struct bpf_map *map, void *key,
.map_seq_show_elem = htab_percpu_map_seq_show_elem,
.map_set_for_each_callback_args = map_set_for_each_callback_args,
.map_for_each_callback = bpf_for_each_hash_elem,
+ .map_mem_usage = htab_map_mem_usage,
BATCH_OPS(htab_percpu),
.map_btf_id = &htab_map_btf_ids[0],
.iter_seq_info = &iter_seq_info,
@@ -2397,6 +2438,7 @@ static void htab_percpu_map_seq_show_elem(struct bpf_map *map, void *key,
.map_seq_show_elem = htab_percpu_map_seq_show_elem,
.map_set_for_each_callback_args = map_set_for_each_callback_args,
.map_for_each_callback = bpf_for_each_hash_elem,
+ .map_mem_usage = htab_map_mem_usage,
BATCH_OPS(htab_lru_percpu),
.map_btf_id = &htab_map_btf_ids[0],
.iter_seq_info = &iter_seq_info,
@@ -2534,6 +2576,7 @@ static void htab_of_map_free(struct bpf_map *map)
.map_fd_sys_lookup_elem = bpf_map_fd_sys_lookup_elem,
.map_gen_lookup = htab_of_map_gen_lookup,
.map_check_btf = map_check_no_btf,
+ .map_mem_usage = htab_map_mem_usage,
BATCH_OPS(htab),
.map_btf_id = &htab_map_btf_ids[0],
};
--
1.8.3.1
next prev parent reply other threads:[~2023-03-05 12:46 UTC|newest]
Thread overview: 20+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-03-05 12:45 [PATCH bpf-next v4 00/18] bpf: bpf memory usage Yafang Shao
2023-03-05 12:45 ` [PATCH bpf-next v4 01/18] bpf: add new map ops ->map_mem_usage Yafang Shao
2023-03-05 12:45 ` [PATCH bpf-next v4 02/18] bpf: lpm_trie memory usage Yafang Shao
2023-03-05 12:46 ` Yafang Shao [this message]
2023-03-05 12:46 ` [PATCH bpf-next v4 04/18] bpf: arraymap " Yafang Shao
2023-03-05 12:46 ` [PATCH bpf-next v4 05/18] bpf: stackmap " Yafang Shao
2023-03-05 12:46 ` [PATCH bpf-next v4 06/18] bpf: reuseport_array " Yafang Shao
2023-03-05 12:46 ` [PATCH bpf-next v4 07/18] bpf: ringbuf " Yafang Shao
2023-03-05 12:46 ` [PATCH bpf-next v4 08/18] bpf: bloom_filter " Yafang Shao
2023-03-05 12:46 ` [PATCH bpf-next v4 09/18] bpf: cpumap " Yafang Shao
2023-03-05 12:46 ` [PATCH bpf-next v4 10/18] bpf: devmap " Yafang Shao
2023-03-05 12:46 ` [PATCH bpf-next v4 11/18] bpf: queue_stack_maps " Yafang Shao
2023-03-05 12:46 ` [PATCH bpf-next v4 12/18] bpf: bpf_struct_ops " Yafang Shao
2023-03-05 12:46 ` [PATCH bpf-next v4 13/18] bpf: local_storage " Yafang Shao
2023-03-05 12:46 ` [PATCH bpf-next v4 14/18] bpf, net: bpf_local_storage " Yafang Shao
2023-03-05 12:46 ` [PATCH bpf-next v4 15/18] bpf, net: sock_map " Yafang Shao
2023-03-05 12:46 ` [PATCH bpf-next v4 16/18] bpf, net: xskmap " Yafang Shao
2023-03-05 12:46 ` [PATCH bpf-next v4 17/18] bpf: offload map " Yafang Shao
2023-03-05 12:46 ` [PATCH bpf-next v4 18/18] bpf: enforce all maps having memory usage callback Yafang Shao
2023-03-07 17:40 ` [PATCH bpf-next v4 00/18] bpf: bpf memory usage patchwork-bot+netdevbpf
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20230305124615.12358-4-laoar.shao@gmail.com \
--to=laoar.shao@gmail.com \
--cc=andrii@kernel.org \
--cc=ast@kernel.org \
--cc=bpf@vger.kernel.org \
--cc=daniel@iogearbox.net \
--cc=haoluo@google.com \
--cc=horenc@vt.edu \
--cc=houtao1@huawei.com \
--cc=john.fastabend@gmail.com \
--cc=jolsa@kernel.org \
--cc=kafai@fb.com \
--cc=kpsingh@kernel.org \
--cc=sdf@google.com \
--cc=songliubraving@fb.com \
--cc=xiyou.wangcong@gmail.com \
--cc=yhs@fb.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox