From: Michal Swiatkowski <michal.swiatkowski@linux•intel.com>
To: Paul Menzel <pmenzel@molgen•mpg.de>
Cc: Michal Swiatkowski <michal.swiatkowski@linux•intel.com>,
intel-wired-lan@lists•osuosl.org, netdev@vger•kernel.org,
Jacob Keller <jacob.e.keller@intel•com>
Subject: Re: [Intel-wired-lan] [PATCH iwl-next v1] ice: lower default irq/queue counts on high-core systems
Date: Thu, 16 Oct 2025 10:45:19 +0200 [thread overview]
Message-ID: <aPCwn1jZDl+7+F1i@mev-dev.igk.intel.com> (raw)
In-Reply-To: <d6a90d0d-55f9-467a-b414-5ced78d12c54@molgen.mpg.de>
On Thu, Oct 16, 2025 at 09:44:43AM +0200, Paul Menzel wrote:
> Dear Michal,
>
>
> Thank you for the patch. I’d mention the 64 in the summary:
>
Sure, I will add it.
> > ice: lower default irq/queue counts to 64 on > 64 core systems
>
>
> Am 16.10.25 um 08:22 schrieb Michal Swiatkowski:
> > On some high-core systems loading ice driver with default values can
> > lead to queue/irq exhaustion. It will result in no additional resources
> > for SR-IOV.
> >
> > In most cases there is no performance reason for more than 64 queues.
> > Limit the default value to 64. Still, using ethtool the number of
> > queues can be changed up to num_online_cpus().
> >
> > This change affects only the default queue amount on systems with more
> > than 64 cores.
>
> Please document a specific system and steps to reproduce the issue.
>
> Please also document how to override the value.
Ok, will add.
>
> > Reviewed-by: Jacob Keller <jacob.e.keller@intel•com>
> > Signed-off-by: Michal Swiatkowski <michal.swiatkowski@linux•intel.com>
> > ---
> > drivers/net/ethernet/intel/ice/ice.h | 20 ++++++++++++++++++++
> > drivers/net/ethernet/intel/ice/ice_irq.c | 6 ++++--
> > drivers/net/ethernet/intel/ice/ice_lib.c | 8 ++++----
> > 3 files changed, 28 insertions(+), 6 deletions(-)
> >
> > diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
> > index 3d4d8b88631b..354ec2950ff3 100644
> > --- a/drivers/net/ethernet/intel/ice/ice.h
> > +++ b/drivers/net/ethernet/intel/ice/ice.h
> > @@ -1133,4 +1133,24 @@ static inline struct ice_hw *ice_get_primary_hw(struct ice_pf *pf)
> > else
> > return &pf->adapter->ctrl_pf->hw;
> > }
> > +
> > +/**
> > + * ice_capped_num_cpus - normalize the number of CPUs to a reasonable limit
> > + *
> > + * This function returns the number of online CPUs, but caps it at suitable
> > + * default to prevent excessive resource allocation on systems with very high
> > + * CPU counts.
> > + *
> > + * Note: suitable default is currently at 64, which is reflected in default_cpus
> > + * constant. In most cases there is no much benefit for more than 64 and it is a
>
> no*t* much
>
Will fix
> > + * power of 2 number.
> > + *
> > + * Return: number of online CPUs, capped at suitable default.
> > + */
> > +static inline u16 ice_capped_num_cpus(void)
>
> Why not return `unsigned int` or `size_t`?
>
Just because u16 is used for queue counts, but I can go with unsigned
int, makes more sense as num_online_cpus() is returning unsigned int.
> > +{
> > + const int default_cpus = 64;
> > +
> > + return min(num_online_cpus(), default_cpus);
> > +}
> > #endif /* _ICE_H_ */
> > diff --git a/drivers/net/ethernet/intel/ice/ice_irq.c b/drivers/net/ethernet/intel/ice/ice_irq.c
> > index 30801fd375f0..df4d847ca858 100644
> > --- a/drivers/net/ethernet/intel/ice/ice_irq.c
> > +++ b/drivers/net/ethernet/intel/ice/ice_irq.c
> > @@ -106,9 +106,11 @@ static struct ice_irq_entry *ice_get_irq_res(struct ice_pf *pf,
> > #define ICE_RDMA_AEQ_MSIX 1
> > static int ice_get_default_msix_amount(struct ice_pf *pf)
> > {
> > - return ICE_MIN_LAN_OICR_MSIX + num_online_cpus() +
> > + u16 cpus = ice_capped_num_cpus();
> > +
> > + return ICE_MIN_LAN_OICR_MSIX + cpus +
> > (test_bit(ICE_FLAG_FD_ENA, pf->flags) ? ICE_FDIR_MSIX : 0) +
> > - (ice_is_rdma_ena(pf) ? num_online_cpus() + ICE_RDMA_AEQ_MSIX : 0);
> > + (ice_is_rdma_ena(pf) ? cpus + ICE_RDMA_AEQ_MSIX : 0);
> > }
> > /**
> > diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
> > index bac481e8140d..3c5f8a4b6c6d 100644
> > --- a/drivers/net/ethernet/intel/ice/ice_lib.c
> > +++ b/drivers/net/ethernet/intel/ice/ice_lib.c
> > @@ -159,12 +159,12 @@ static void ice_vsi_set_num_desc(struct ice_vsi *vsi)
> > static u16 ice_get_rxq_count(struct ice_pf *pf)
> > {
> > - return min(ice_get_avail_rxq_count(pf), num_online_cpus());
> > + return min(ice_get_avail_rxq_count(pf), ice_capped_num_cpus());
> > }
> > static u16 ice_get_txq_count(struct ice_pf *pf)
> > {
> > - return min(ice_get_avail_txq_count(pf), num_online_cpus());
> > + return min(ice_get_avail_txq_count(pf), ice_capped_num_cpus());
> > }
> > /**
> > @@ -907,13 +907,13 @@ static void ice_vsi_set_rss_params(struct ice_vsi *vsi)
> > if (vsi->type == ICE_VSI_CHNL)
> > vsi->rss_size = min_t(u16, vsi->num_rxq, max_rss_size);
> > else
> > - vsi->rss_size = min_t(u16, num_online_cpus(),
> > + vsi->rss_size = min_t(u16, ice_capped_num_cpus(),
> > max_rss_size);
> > vsi->rss_lut_type = ICE_LUT_PF;
> > break;
> > case ICE_VSI_SF:
> > vsi->rss_table_size = ICE_LUT_VSI_SIZE;
> > - vsi->rss_size = min_t(u16, num_online_cpus(), max_rss_size);
> > + vsi->rss_size = min_t(u16, ice_capped_num_cpus(), max_rss_size);
> > vsi->rss_lut_type = ICE_LUT_VSI;
> > break;
> > case ICE_VSI_VF:
>
> With the changes addressed, feel free to add:
>
> Reviewed-by: Paul Menzel <pmenzel@molgen•mpg.de>
>
Thanks
>
> Kind regards,
>
> Paul
next prev parent reply other threads:[~2025-10-16 8:47 UTC|newest]
Thread overview: 8+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-10-16 6:22 [PATCH iwl-next v1] ice: lower default irq/queue counts on high-core systems Michal Swiatkowski
2025-10-16 7:44 ` [Intel-wired-lan] " Paul Menzel
2025-10-16 8:45 ` Michal Swiatkowski [this message]
2025-10-16 15:36 ` Alexander Lobakin
2025-10-17 5:03 ` Przemek Kitszel
2025-10-17 7:30 ` Michal Swiatkowski
2025-10-17 14:35 ` Alexander Lobakin
2025-10-22 7:09 ` Michal Swiatkowski
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=aPCwn1jZDl+7+F1i@mev-dev.igk.intel.com \
--to=michal.swiatkowski@linux$(echo .)intel.com \
--cc=intel-wired-lan@lists$(echo .)osuosl.org \
--cc=jacob.e.keller@intel$(echo .)com \
--cc=netdev@vger$(echo .)kernel.org \
--cc=pmenzel@molgen$(echo .)mpg.de \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
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