[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CAErzpmsn5v3QMCdRjE0f-dqUSRXE-XMKccF-wMauNOXOoPehxg@mail.gmail.com>
Date: Wed, 14 Jan 2026 10:00:44 +0800
From: Donglin Peng <dolinux.peng@...il.com>
To: Andrii Nakryiko <andrii.nakryiko@...il.com>
Cc: ast@...nel.org, eddyz87@...il.com, zhangxiaoqin@...omi.com,
ihor.solodrai@...ux.dev, linux-kernel@...r.kernel.org, bpf@...r.kernel.org,
Donglin Peng <pengdonglin@...omi.com>, Alan Maguire <alan.maguire@...cle.com>,
Andrii Nakryiko <andrii@...nel.org>
Subject: Re: [PATCH bpf-next v12 10/11] libbpf: Optimize the performance of determine_ptr_size
On Wed, Jan 14, 2026 at 8:30 AM Andrii Nakryiko
<andrii.nakryiko@...il.com> wrote:
>
> On Fri, Jan 9, 2026 at 5:00 AM Donglin Peng <dolinux.peng@...il.com> wrote:
> >
> > From: Donglin Peng <pengdonglin@...omi.com>
> >
> > Leverage the performance improvement of btf__find_by_name_kind() when
> > BTF is sorted. For sorted BTF, the function uses binary search with
> > O(log n) complexity instead of linear search, providing significant
> > performance benefits, especially for large BTF like vmlinux.
> >
> > Cc: Eduard Zingerman <eddyz87@...il.com>
> > Cc: Alexei Starovoitov <ast@...nel.org>
> > Cc: Andrii Nakryiko <andrii.nakryiko@...il.com>
> > Cc: Alan Maguire <alan.maguire@...cle.com>
> > Cc: Ihor Solodrai <ihor.solodrai@...ux.dev>
> > Cc: Xiaoqin Zhang <zhangxiaoqin@...omi.com>
> > Signed-off-by: Donglin Peng <pengdonglin@...omi.com>
> > Acked-by: Eduard Zingerman <eddyz87@...il.com>
> > Acked-by: Andrii Nakryiko <andrii@...nel.org>
> > ---
> > tools/lib/bpf/btf.c | 20 ++++++--------------
> > 1 file changed, 6 insertions(+), 14 deletions(-)
> >
>
> This change will be beneficial only if btf is sorted, otherwise the
> previous approach is generally faster. So on older kernels this will
> be significantly slower.
Yes, I agree.
>
> If we want to optimize determine_ptr_size() at all, I think we will
> have to take into account whether BTF is sorted or not.
>
> Or just not bother at all with this optimization.
>
> I'll drop this patch.
Yes, that's correct. The actual lookup executes only once, so the
optimization provides limited value.
>
>
> > diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
> > index 9a864de59597..918d9fa6ec36 100644
> > --- a/tools/lib/bpf/btf.c
> > +++ b/tools/lib/bpf/btf.c
> > @@ -659,29 +659,21 @@ static int determine_ptr_size(const struct btf *btf)
> > "int long unsigned",
> > };
> > const struct btf_type *t;
> > - const char *name;
> > - int i, j, n;
> > + int i, id;
> >
> > if (btf->base_btf && btf->base_btf->ptr_sz > 0)
> > return btf->base_btf->ptr_sz;
> >
> > - n = btf__type_cnt(btf);
> > - for (i = 1; i < n; i++) {
> > - t = btf__type_by_id(btf, i);
> > - if (!btf_is_int(t))
> > + for (i = 0; i < ARRAY_SIZE(long_aliases); i++) {
> > + id = btf__find_by_name_kind(btf, long_aliases[i], BTF_KIND_INT);
> > + if (id < 0)
> > continue;
> >
> > + t = btf__type_by_id(btf, id);
> > if (t->size != 4 && t->size != 8)
> > continue;
> >
> > - name = btf__name_by_offset(btf, t->name_off);
> > - if (!name)
> > - continue;
> > -
> > - for (j = 0; j < ARRAY_SIZE(long_aliases); j++) {
> > - if (strcmp(name, long_aliases[j]) == 0)
> > - return t->size;
> > - }
> > + return t->size;
> > }
> >
> > return -1;
> > --
> > 2.34.1
> >
Powered by blists - more mailing lists