On Wed, Mar 24, 2021 at 11:53 PM Yonghong Song <yhs@xxxxxx> wrote:
>
> Currently, types/tags hash table has fixed HASHTAGS__BITS = 15.
> That means the number of buckets will be 1UL << 15 = 32768.
> In my experiments, a thin-LTO built vmlinux has roughly 9M entries
> in types table and 5.2M entries in tags table. So the number
> of buckets is too less for an efficient lookup. This patch
> refactored the code to allow the number of buckets to be changed.
>
> In addition, currently hashtags__fn(key) return value is
> assigned to uint16_t. Change to uint32_t as in a later patch
> the number of hashtag bits can be increased to be more than 16.
>
> Signed-off-by: Yonghong Song <yhs@xxxxxx>
> ---
> dwarf_loader.c | 48 +++++++++++++++++++++++++++++++++++++-----------
> 1 file changed, 37 insertions(+), 11 deletions(-)
>
> diff --git a/dwarf_loader.c b/dwarf_loader.c
> index c106919..a02ef23 100644
> --- a/dwarf_loader.c
> +++ b/dwarf_loader.c
> @@ -50,7 +50,12 @@ struct strings *strings;
> #define DW_FORM_implicit_const 0x21
> #endif
>
> -#define hashtags__fn(key) hash_64(key, HASHTAGS__BITS)
> +static uint32_t hashtags__bits = 15;
> +
> +uint32_t hashtags__fn(Dwarf_Off key)
> +{
> + return hash_64(key, hashtags__bits);
I vaguely remember pahole patch that updated hash function to use the
same one as libbpf's hashmap is using. Arnaldo, wasn't that patch
accepted?
But more to the point, I think hashtags__fn() should probably preserve
all 64 bits of the hash?
> +}
>
> bool no_bitfield_type_recode = true;
>
> @@ -102,9 +107,6 @@ static void dwarf_tag__set_spec(struct dwarf_tag *dtag, dwarf_off_ref spec)
> *(dwarf_off_ref *)(dtag + 1) = spec;
> }
>
> -#define HASHTAGS__BITS 15
> -#define HASHTAGS__SIZE (1UL << HASHTAGS__BITS)
> -
> #define obstack_chunk_alloc malloc
> #define obstack_chunk_free free
>
> @@ -118,22 +120,41 @@ static void *obstack_zalloc(struct obstack *obstack, size_t size)
> }
>
> struct dwarf_cu {
> - struct hlist_head hash_tags[HASHTAGS__SIZE];
> - struct hlist_head hash_types[HASHTAGS__SIZE];
> + struct hlist_head *hash_tags;
> + struct hlist_head *hash_types;
> struct obstack obstack;
> struct cu *cu;
> struct dwarf_cu *type_unit;
> };
>
> -static void dwarf_cu__init(struct dwarf_cu *dcu)
> +static int dwarf_cu__init(struct dwarf_cu *dcu)
> {
> + uint64_t hashtags_size = 1UL << hashtags__bits;
I wish pahole could just use libbpf's dynamically resized hashmap,
instead of hard-coding maximum size like this :(
Arnaldo, libbpf is not going to expose its hashmap as public API, but
if you'd like to use it, feel free to just copy/paste the code. It
hasn't change for a while and is unlikely to change (unless some day
we decide to make more efficient open-addressing implementation).
> + dcu->hash_tags = malloc(sizeof(struct hlist_head) * hashtags_size);
> + if (!dcu->hash_tags)
> + return -ENOMEM;
> +
> + dcu->hash_types = malloc(sizeof(struct hlist_head) * hashtags_size);
> + if (!dcu->hash_types) {
> + free(dcu->hash_tags);
> + return -ENOMEM;
> + }
> +
[...]
