From: Nitesh Lal <nilal@redhat.com> To: Thomas Gleixner <tglx@linutronix.de>, Jesse Brandeburg <jesse.brandeburg@intel.com>, Robin Murphy <robin.murphy@arm.com>, Marcelo Tosatti <mtosatti@redhat.com> Cc: Ingo Molnar <mingo@kernel.org>, linux-kernel@vger.kernel.org, intel-wired-lan@lists.osuosl.org, jbrandeb@kernel.org, "frederic@kernel.org" <frederic@kernel.org>, "juri.lelli@redhat.com" <juri.lelli@redhat.com>, Alex Belits <abelits@marvell.com>, "linux-api@vger.kernel.org" <linux-api@vger.kernel.org>, "bhelgaas@google.com" <bhelgaas@google.com>, "linux-pci@vger.kernel.org" <linux-pci@vger.kernel.org>, "rostedt@goodmis.org" <rostedt@goodmis.org>, "peterz@infradead.org" <peterz@infradead.org>, "davem@davemloft.net" <davem@davemloft.net>, "akpm@linux-foundation.org" <akpm@linux-foundation.org>, "sfr@canb.auug.org.au" <sfr@canb.auug.org.au>, "stephen@networkplumber.org" <stephen@networkplumber.org>, "rppt@linux.vnet.ibm.com" <rppt@linux.vnet.ibm.com>, "jinyuqi@huawei.com" <jinyuqi@huawei.com>, "zhangshaokun@hisilicon.com" <zhangshaokun@hisilicon.com>, netdev@vger.kernel.org, chris.friesen@windriver.com, Marc Zyngier <maz@kernel.org>, Neil Horman <nhorman@tuxdriver.com>, pjwaskiewicz@gmail.com Subject: Re: [PATCH tip:irq/core v1] genirq: remove auto-set of the mask when setting the hint Date: Thu, 20 May 2021 20:03:38 -0400 [thread overview] Message-ID: <CAFki+LkB1sk3mOv4dd1D-SoPWHOs28ZwN-PqL_6xBk=Qkm40Lw@mail.gmail.com> (raw) In-Reply-To: <CAFki+L=eQoMq+mWhw_jVT-biyuDXpxbXY5nO+F6HvCtpbG9V2w@mail.gmail.com> On Thu, May 20, 2021 at 5:57 PM Nitesh Lal <nilal@redhat.com> wrote: > > On Mon, May 17, 2021 at 8:23 PM Nitesh Lal <nilal@redhat.com> wrote: > > > > On Mon, May 17, 2021 at 8:04 PM Thomas Gleixner <tglx@linutronix.de> wrote: > > > > > > On Mon, May 17 2021 at 18:44, Nitesh Lal wrote: > > > > On Mon, May 17, 2021 at 4:48 PM Thomas Gleixner <tglx@linutronix.de> wrote: > > > >> The hint was added so that userspace has a better understanding where it > > > >> should place the interrupt. So if irqbalanced ignores it anyway, then > > > >> what's the point of the hint? IOW, why is it still used drivers? > > > >> > > > > Took a quick look at the irqbalance repo and saw the following commit: > > > > > > > > dcc411e7bf remove affinity_hint infrastructure > > > > > > > > The commit message mentions that "PJ is redesiging how affinity hinting > > > > works in the kernel, the future model will just tell us to ignore an IRQ, > > > > and the kernel will handle placement for us. As such we can remove the > > > > affinity_hint recognition entirely". > > > > > > No idea who PJ is. I really love useful commit messages. Maybe Neil can > > > shed some light on that. > > > > > > > This does indicate that apparently, irqbalance moved away from the usage of > > > > affinity_hint. However, the next question is what was this future > > > > model? > > > > > > I might have missed something in the last 5 years, but that's the first > > > time I hear about someone trying to cleanup that thing. > > > > > > > I don't know but I can surely look into it if that helps or maybe someone > > > > here already knows about it? > > > > > > I CC'ed Neil :) > > > > Thanks, I have added PJ Waskiewicz as well who I think was referred in > > that commit message as PJ. > > > > > > > > >> Now there is another aspect to that. What happens if irqbalanced does > > > >> not run at all and a driver relies on the side effect of the hint > > > >> setting the initial affinity. Bah... > > > >> > > > > > > > > Right, but if they only rely on this API so that the IRQs are spread across > > > > all the CPUs then that issue is already resolved and these other drivers > > > > should not regress because of changing this behavior. Isn't it? > > > > > > Is that true for all architectures? > > > > Unfortunately, I don't know and that's probably why we have to be careful. > > I think here to ensure that we are not breaking any of the drivers we have > to first analyze all the existing drivers and understand how they are using > this API. > AFAIK there are three possible scenarios: > > - A driver use this API to spread the IRQs > + For this case we should be safe considering the spreading is naturally > done from the IRQ subsystem itself. Forgot to mention another thing in the above case is to determine whether it is true for all architectures or not as Thomas mentioned. > > - A driver use this API to actually set the hint > + These drivers should have no functional impact because of this revert > > - Driver use this API to force a certain affinity mask > + In this case we have to replace the API with the irq_force_affinity() > > I can start looking into the individual drivers, however, testing them will > be a challenge. > > Any thoughts? > > -- > Thanks > Nitesh -- Thanks Nitesh
WARNING: multiple messages have this Message-ID (diff)
From: Nitesh Lal <nilal@redhat.com> To: intel-wired-lan@osuosl.org Subject: [Intel-wired-lan] [PATCH tip:irq/core v1] genirq: remove auto-set of the mask when setting the hint Date: Thu, 20 May 2021 20:03:38 -0400 [thread overview] Message-ID: <CAFki+LkB1sk3mOv4dd1D-SoPWHOs28ZwN-PqL_6xBk=Qkm40Lw@mail.gmail.com> (raw) In-Reply-To: <CAFki+L=eQoMq+mWhw_jVT-biyuDXpxbXY5nO+F6HvCtpbG9V2w@mail.gmail.com> On Thu, May 20, 2021 at 5:57 PM Nitesh Lal <nilal@redhat.com> wrote: > > On Mon, May 17, 2021 at 8:23 PM Nitesh Lal <nilal@redhat.com> wrote: > > > > On Mon, May 17, 2021 at 8:04 PM Thomas Gleixner <tglx@linutronix.de> wrote: > > > > > > On Mon, May 17 2021 at 18:44, Nitesh Lal wrote: > > > > On Mon, May 17, 2021 at 4:48 PM Thomas Gleixner <tglx@linutronix.de> wrote: > > > >> The hint was added so that userspace has a better understanding where it > > > >> should place the interrupt. So if irqbalanced ignores it anyway, then > > > >> what's the point of the hint? IOW, why is it still used drivers? > > > >> > > > > Took a quick look at the irqbalance repo and saw the following commit: > > > > > > > > dcc411e7bf remove affinity_hint infrastructure > > > > > > > > The commit message mentions that "PJ is redesiging how affinity hinting > > > > works in the kernel, the future model will just tell us to ignore an IRQ, > > > > and the kernel will handle placement for us. As such we can remove the > > > > affinity_hint recognition entirely". > > > > > > No idea who PJ is. I really love useful commit messages. Maybe Neil can > > > shed some light on that. > > > > > > > This does indicate that apparently, irqbalance moved away from the usage of > > > > affinity_hint. However, the next question is what was this future > > > > model? > > > > > > I might have missed something in the last 5 years, but that's the first > > > time I hear about someone trying to cleanup that thing. > > > > > > > I don't know but I can surely look into it if that helps or maybe someone > > > > here already knows about it? > > > > > > I CC'ed Neil :) > > > > Thanks, I have added PJ Waskiewicz as well who I think was referred in > > that commit message as PJ. > > > > > > > > >> Now there is another aspect to that. What happens if irqbalanced does > > > >> not run at all and a driver relies on the side effect of the hint > > > >> setting the initial affinity. Bah... > > > >> > > > > > > > > Right, but if they only rely on this API so that the IRQs are spread across > > > > all the CPUs then that issue is already resolved and these other drivers > > > > should not regress because of changing this behavior. Isn't it? > > > > > > Is that true for all architectures? > > > > Unfortunately, I don't know and that's probably why we have to be careful. > > I think here to ensure that we are not breaking any of the drivers we have > to first analyze all the existing drivers and understand how they are using > this API. > AFAIK there are three possible scenarios: > > - A driver use this API to spread the IRQs > + For this case we should be safe considering the spreading is naturally > done from the IRQ subsystem itself. Forgot to mention another thing in the above case is to determine whether it is true for all architectures or not as Thomas mentioned. > > - A driver use this API to actually set the hint > + These drivers should have no functional impact because of this revert > > - Driver use this API to force a certain affinity mask > + In this case we have to replace the API with the irq_force_affinity() > > I can start looking into the individual drivers, however, testing them will > be a challenge. > > Any thoughts? > > -- > Thanks > Nitesh -- Thanks Nitesh
next prev parent reply other threads:[~2021-05-21 0:04 UTC|newest] Thread overview: 71+ messages / expand[flat|nested] mbox.gz Atom feed top 2021-05-01 2:18 [PATCH tip:irq/core v1] genirq: remove auto-set of the mask when setting the hint Jesse Brandeburg 2021-05-01 2:18 ` [Intel-wired-lan] " Jesse Brandeburg 2021-05-04 12:15 ` Robin Murphy 2021-05-04 12:15 ` [Intel-wired-lan] " Robin Murphy 2021-05-04 14:29 ` Nitesh Lal 2021-05-04 14:29 ` [Intel-wired-lan] " Nitesh Lal 2021-05-04 16:23 ` Jesse Brandeburg 2021-05-04 16:23 ` [Intel-wired-lan] " Jesse Brandeburg 2021-05-17 16:57 ` Nitesh Lal 2021-05-17 16:57 ` [Intel-wired-lan] " Nitesh Lal 2021-05-17 17:26 ` Robin Murphy 2021-05-17 17:26 ` [Intel-wired-lan] " Robin Murphy 2021-05-17 18:08 ` Thomas Gleixner 2021-05-17 18:08 ` [Intel-wired-lan] " Thomas Gleixner 2021-05-17 18:50 ` Robin Murphy 2021-05-17 18:50 ` [Intel-wired-lan] " Robin Murphy 2021-05-17 19:08 ` Thomas Gleixner 2021-05-17 19:08 ` [Intel-wired-lan] " Thomas Gleixner 2021-05-17 19:43 ` Thomas Gleixner 2021-05-17 19:43 ` [Intel-wired-lan] " Thomas Gleixner 2021-05-17 20:18 ` Thomas Gleixner 2021-05-17 20:18 ` [Intel-wired-lan] " Thomas Gleixner 2021-05-17 18:21 ` Nitesh Lal 2021-05-17 18:21 ` [Intel-wired-lan] " Nitesh Lal 2021-05-17 19:47 ` Thomas Gleixner 2021-05-17 19:47 ` [Intel-wired-lan] " Thomas Gleixner 2021-05-17 21:13 ` Nitesh Lal 2021-05-17 21:13 ` [Intel-wired-lan] " Nitesh Lal 2021-05-17 20:48 ` Thomas Gleixner 2021-05-17 20:48 ` [Intel-wired-lan] " Thomas Gleixner 2021-05-17 22:44 ` Nitesh Lal 2021-05-17 22:44 ` [Intel-wired-lan] " Nitesh Lal 2021-05-18 0:03 ` Thomas Gleixner 2021-05-18 0:03 ` [Intel-wired-lan] " Thomas Gleixner 2021-05-18 0:23 ` Nitesh Lal 2021-05-18 0:23 ` [Intel-wired-lan] " Nitesh Lal 2021-05-20 21:57 ` Nitesh Lal 2021-05-20 21:57 ` [Intel-wired-lan] " Nitesh Lal 2021-05-21 0:03 ` Nitesh Lal [this message] 2021-05-21 0:03 ` Nitesh Lal 2021-05-21 11:56 ` Thomas Gleixner 2021-05-21 11:56 ` [Intel-wired-lan] " Thomas Gleixner 2021-05-21 12:03 ` [PATCH] genirq: Provide new interfaces for affinity hints Thomas Gleixner 2021-05-21 12:03 ` [Intel-wired-lan] " Thomas Gleixner 2021-05-21 15:45 ` Lijun Pan 2021-05-21 15:45 ` [Intel-wired-lan] " Lijun Pan 2021-05-21 21:45 ` Thomas Gleixner 2021-05-21 21:45 ` [Intel-wired-lan] " Thomas Gleixner 2021-05-21 16:13 ` Nitesh Lal 2021-05-21 16:13 ` [Intel-wired-lan] " Nitesh Lal 2021-05-21 21:48 ` Thomas Gleixner 2021-05-21 21:48 ` [Intel-wired-lan] " Thomas Gleixner 2021-06-04 20:35 ` Nitesh Lal 2021-06-04 20:35 ` [Intel-wired-lan] " Nitesh Lal 2021-05-27 10:03 ` Shung-Hsi Yu 2021-05-27 10:03 ` [Intel-wired-lan] " Shung-Hsi Yu 2021-05-27 10:21 ` Shung-Hsi Yu 2021-05-27 10:21 ` [Intel-wired-lan] " Shung-Hsi Yu 2021-05-27 13:06 ` Nitesh Lal 2021-05-27 13:06 ` [Intel-wired-lan] " Nitesh Lal 2021-05-28 7:20 ` Shung-Hsi Yu 2021-05-28 7:20 ` [Intel-wired-lan] " Shung-Hsi Yu 2021-06-07 17:00 ` Nitesh Lal 2021-06-07 17:00 ` [Intel-wired-lan] " Nitesh Lal 2021-06-14 16:12 ` Nitesh Lal 2021-06-14 16:12 ` [Intel-wired-lan] " Nitesh Lal 2021-05-21 13:46 ` [PATCH tip:irq/core v1] genirq: remove auto-set of the mask when setting the hint Nitesh Lal 2021-05-21 13:46 ` [Intel-wired-lan] " Nitesh Lal 2021-05-21 15:15 ` Thomas Gleixner 2021-05-21 15:15 ` [Intel-wired-lan] " Thomas Gleixner 2021-12-10 19:54 ` [tip: irq/core] genirq: Provide new interfaces for affinity hints tip-bot2 for Thomas Gleixner
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='CAFki+LkB1sk3mOv4dd1D-SoPWHOs28ZwN-PqL_6xBk=Qkm40Lw@mail.gmail.com' \ --to=nilal@redhat.com \ --cc=abelits@marvell.com \ --cc=akpm@linux-foundation.org \ --cc=bhelgaas@google.com \ --cc=chris.friesen@windriver.com \ --cc=davem@davemloft.net \ --cc=frederic@kernel.org \ --cc=intel-wired-lan@lists.osuosl.org \ --cc=jbrandeb@kernel.org \ --cc=jesse.brandeburg@intel.com \ --cc=jinyuqi@huawei.com \ --cc=juri.lelli@redhat.com \ --cc=linux-api@vger.kernel.org \ --cc=linux-kernel@vger.kernel.org \ --cc=linux-pci@vger.kernel.org \ --cc=maz@kernel.org \ --cc=mingo@kernel.org \ --cc=mtosatti@redhat.com \ --cc=netdev@vger.kernel.org \ --cc=nhorman@tuxdriver.com \ --cc=peterz@infradead.org \ --cc=pjwaskiewicz@gmail.com \ --cc=robin.murphy@arm.com \ --cc=rostedt@goodmis.org \ --cc=rppt@linux.vnet.ibm.com \ --cc=sfr@canb.auug.org.au \ --cc=stephen@networkplumber.org \ --cc=tglx@linutronix.de \ --cc=zhangshaokun@hisilicon.com \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
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.