Re: [External] Re: [PATCH] bpf: avoid grabbing spin_locks of all cpus when no free elems

[Feng Zhou]

在 2022/5/20 上午12:12, Alexei Starovoitov 写道:
> On Wed, May 18, 2022 at 8:12 PM Feng Zhou <zhoufeng.zf@xxxxxxxxxxxxx> wrote:
> > 在 2022/5/19 上午4:39, Yonghong Song 写道:
> > > On 5/17/22 11:57 PM, Feng Zhou wrote:
> > > > 在 2022/5/18 下午2:32, Alexei Starovoitov 写道:
> > > > > On Tue, May 17, 2022 at 11:27 PM Feng zhou
> > > > > <zhoufeng.zf@xxxxxxxxxxxxx> wrote:
> > > > > > From: Feng Zhou <zhoufeng.zf@xxxxxxxxxxxxx>
> > > > > >
> > > > > > We encountered bad case on big system with 96 CPUs that
> > > > > > alloc_htab_elem() would last for 1ms. The reason is that after the
> > > > > > prealloc hashtab has no free elems, when trying to update, it will
> > > > > > still
> > > > > > grab spin_locks of all cpus. If there are multiple update users, the
> > > > > > competition is very serious.
> > > > > >
> > > > > > So this patch add is_empty in pcpu_freelist_head to check freelist
> > > > > > having free or not. If having, grab spin_lock, or check next cpu's
> > > > > > freelist.
> > > > > >
> > > > > > Before patch: hash_map performance
> > > > > > ./map_perf_test 1
> > > could you explain what parameter '1' means here?
> > This code is here:
> > samples/bpf/map_perf_test_user.c
> > samples/bpf/map_perf_test_kern.c
> > parameter '1' means testcase flag, test hash_map's performance
> > parameter '2048' means test hash_map's performance when free=0.
> > testcase flag '2048' is added by myself to reproduce the problem phenomenon.
> Please convert it to selftests/bpf/bench,
> so that everyone can reproduce the issue you're seeing
> and can assess whether it's a real issue or a corner case.
>
> Also please avoid adding indent in the patch.
> Instead of
>   if (!s->extralist.is_empty) {
>    .. churn
>
> do
>
>   if (s->extralist.is_empty)

Ok, will do. Thanks.