* [PATCH bpf-next] bpf: Mitigate latency spikes associated with freeing non-preallocated htab
@ 2024-03-26 8:12 Yafang Shao
2024-03-26 16:50 ` Yonghong Song
0 siblings, 1 reply; 3+ messages in thread
From: Yafang Shao @ 2024-03-26 8:12 UTC (permalink / raw
To: ast, daniel, john.fastabend, andrii, martin.lau, eddyz87, song,
yonghong.song, kpsingh, sdf, haoluo, jolsa
Cc: bpf, Yafang Shao
Following the recent upgrade of one of our BPF programs, we encountered
significant latency spikes affecting other applications running on the same
host. After thorough investigation, we identified that these spikes were
primarily caused by the prolonged duration required to free a
non-preallocated htab with approximately 2 million keys.
Notably, our kernel configuration lacks the presence of CONFIG_PREEMPT. In
scenarios where kernel execution extends excessively, other threads might
be starved of CPU time, resulting in latency issues across the system. To
mitigate this, we've adopted a proactive approach by incorporating
cond_resched() calls within the kernel code. This ensures that during
lengthy kernel operations, the scheduler is invoked periodically to provide
opportunities for other threads to execute.
Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
---
kernel/bpf/hashtab.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 3a088a5349bc..d3d5aad045cc 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -1489,6 +1489,7 @@ static void delete_all_elements(struct bpf_htab *htab)
hlist_nulls_for_each_entry_safe(l, n, head, hash_node) {
hlist_nulls_del_rcu(&l->hash_node);
htab_elem_free(htab, l);
+ cond_resched();
}
}
migrate_enable();
--
2.30.1 (Apple Git-130)
^ permalink raw reply related [flat|nested] 3+ messages in thread
* Re: [PATCH bpf-next] bpf: Mitigate latency spikes associated with freeing non-preallocated htab
2024-03-26 8:12 [PATCH bpf-next] bpf: Mitigate latency spikes associated with freeing non-preallocated htab Yafang Shao
@ 2024-03-26 16:50 ` Yonghong Song
2024-03-27 3:05 ` Yafang Shao
0 siblings, 1 reply; 3+ messages in thread
From: Yonghong Song @ 2024-03-26 16:50 UTC (permalink / raw
To: Yafang Shao, ast, daniel, john.fastabend, andrii, martin.lau,
eddyz87, song, kpsingh, sdf, haoluo, jolsa
Cc: bpf
On 3/26/24 1:12 AM, Yafang Shao wrote:
> Following the recent upgrade of one of our BPF programs, we encountered
> significant latency spikes affecting other applications running on the same
> host. After thorough investigation, we identified that these spikes were
> primarily caused by the prolonged duration required to free a
> non-preallocated htab with approximately 2 million keys.
>
> Notably, our kernel configuration lacks the presence of CONFIG_PREEMPT. In
> scenarios where kernel execution extends excessively, other threads might
> be starved of CPU time, resulting in latency issues across the system. To
> mitigate this, we've adopted a proactive approach by incorporating
> cond_resched() calls within the kernel code. This ensures that during
> lengthy kernel operations, the scheduler is invoked periodically to provide
> opportunities for other threads to execute.
>
> Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
> ---
> kernel/bpf/hashtab.c | 1 +
> 1 file changed, 1 insertion(+)
>
> diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
> index 3a088a5349bc..d3d5aad045cc 100644
> --- a/kernel/bpf/hashtab.c
> +++ b/kernel/bpf/hashtab.c
> @@ -1489,6 +1489,7 @@ static void delete_all_elements(struct bpf_htab *htab)
> hlist_nulls_for_each_entry_safe(l, n, head, hash_node) {
> hlist_nulls_del_rcu(&l->hash_node);
> htab_elem_free(htab, l);
> + cond_resched();
> }
should we put cond_resched() here inside the top 'for' loop, but outside
the bucket loop? Do you really have a long link list for a particular bucket?
Otherwise, the patch looks good to me. In hashtab.c, we have cond_resched()
in some other places to mitigate similar issues.
> }
> migrate_enable();
^ permalink raw reply [flat|nested] 3+ messages in thread
* Re: [PATCH bpf-next] bpf: Mitigate latency spikes associated with freeing non-preallocated htab
2024-03-26 16:50 ` Yonghong Song
@ 2024-03-27 3:05 ` Yafang Shao
0 siblings, 0 replies; 3+ messages in thread
From: Yafang Shao @ 2024-03-27 3:05 UTC (permalink / raw
To: Yonghong Song
Cc: ast, daniel, john.fastabend, andrii, martin.lau, eddyz87, song,
kpsingh, sdf, haoluo, jolsa, bpf
On Wed, Mar 27, 2024 at 12:50 AM Yonghong Song <yonghong.song@linux.dev> wrote:
>
>
> On 3/26/24 1:12 AM, Yafang Shao wrote:
> > Following the recent upgrade of one of our BPF programs, we encountered
> > significant latency spikes affecting other applications running on the same
> > host. After thorough investigation, we identified that these spikes were
> > primarily caused by the prolonged duration required to free a
> > non-preallocated htab with approximately 2 million keys.
> >
> > Notably, our kernel configuration lacks the presence of CONFIG_PREEMPT. In
> > scenarios where kernel execution extends excessively, other threads might
> > be starved of CPU time, resulting in latency issues across the system. To
> > mitigate this, we've adopted a proactive approach by incorporating
> > cond_resched() calls within the kernel code. This ensures that during
> > lengthy kernel operations, the scheduler is invoked periodically to provide
> > opportunities for other threads to execute.
> >
> > Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
> > ---
> > kernel/bpf/hashtab.c | 1 +
> > 1 file changed, 1 insertion(+)
> >
> > diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
> > index 3a088a5349bc..d3d5aad045cc 100644
> > --- a/kernel/bpf/hashtab.c
> > +++ b/kernel/bpf/hashtab.c
> > @@ -1489,6 +1489,7 @@ static void delete_all_elements(struct bpf_htab *htab)
> > hlist_nulls_for_each_entry_safe(l, n, head, hash_node) {
> > hlist_nulls_del_rcu(&l->hash_node);
> > htab_elem_free(htab, l);
> > + cond_resched();
> > }
>
> should we put cond_resched() here inside the top 'for' loop, but outside
> the bucket loop? Do you really have a long link list for a particular bucket?
We haven't monitored a long list for a particular bucket. Will change it.
Thanks for your suggestion.
> Otherwise, the patch looks good to me. In hashtab.c, we have cond_resched()
> in some other places to mitigate similar issues.
>
> > }
> > migrate_enable();
--
Regards
Yafang
^ permalink raw reply [flat|nested] 3+ messages in thread
end of thread, other threads:[~2024-03-27 3:06 UTC | newest]
Thread overview: 3+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2024-03-26 8:12 [PATCH bpf-next] bpf: Mitigate latency spikes associated with freeing non-preallocated htab Yafang Shao
2024-03-26 16:50 ` Yonghong Song
2024-03-27 3:05 ` Yafang Shao
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.