From: Keith Busch <kbusch@kernel.org>
To: Sumit Saxena <sumit.saxena@broadcom.com>
Cc: Christoph Hellwig <hch@infradead.org>,
"Martin K . Petersen" <martin.petersen@oracle.com>,
Jens Axboe <axboe@kernel.dk>,
"James E . J . Bottomley" <James.Bottomley@hansenpartnership.com>,
linux-scsi@vger.kernel.org, linux-block@vger.kernel.org,
Adam Radford <aradford@gmail.com>,
Khalid Aziz <khalid@gonehiking.org>,
Adaptec OEM Raid Solutions <aacraid@microsemi.com>,
Matthew Wilcox <willy@infradead.org>,
Hannes Reinecke <hare@suse.com>,
"Juergen E . Fischer" <fischer@norbit.de>,
Russell King <linux@armlinux.org.uk>,
linux-arm-kernel@lists.infradead.org,
Finn Thain <fthain@linux-m68k.org>,
Michael Schmitz <schmitzmic@gmail.com>,
Anil Gurumurthy <anil.gurumurthy@qlogic.com>,
Sudarsana Kalluru <sudarsana.kalluru@qlogic.com>,
Oliver Neukum <oliver@neukum.org>, Ali Akcaagac <aliakc@web.de>,
Jamie Lenehan <lenehan@twibble.org>,
Ram Vegesna <ram.vegesna@broadcom.com>,
target-devel@vger.kernel.org,
Bradley Grove <linuxdrivers@attotech.com>,
Satish Kharat <satishkh@cisco.com>,
Sesidhar Baddela <sebaddel@cisco.com>,
Karan Tilak Kumar <kartilak@cisco.com>,
Yihang Li <liyihang9@h-partners.com>,
Don Brace <don.brace@microchip.com>,
storagedev@microchip.com,
HighPoint Linux Team <linux@highpoint-tech.com>,
Tyrel Datwyler <tyreld@linux.ibm.com>,
Madhavan Srinivasan <maddy@linux.ibm.com>,
Michael Ellerman <mpe@ellerman.id.au>,
Nicholas Piggin <npiggin@gmail.com>,
Christophe Leroy <chleroy@kernel.org>,
linuxppc-dev@lists.ozlabs.org, Brian King <brking@us.ibm.com>,
Lee Duncan <lduncan@suse.com>, Chris Leech <cleech@redhat.com>,
Mike Christie <michael.christie@oracle.com>,
open-iscsi@googlegroups.com, Justin Tee <justin.tee@broadcom.com>,
Paul Ely <paul.ely@broadcom.com>,
Kashyap Desai <kashyap.desai@broadcom.com>,
Shivasharan S <shivasharan.srikanteshwara@broadcom.com>,
Chandrakanth Patil <chandrakanth.patil@broadcom.com>,
megaraidlinux.pdl@broadcom.com,
Sathya Prakash Veerichetty <sathya.prakash@broadcom.com>,
Sreekanth Reddy <sreekanth.reddy@broadcom.com>,
mpi3mr-linuxdrv.pdl@broadcom.com,
Suganath Prabu Subramani <suganath-prabu.subramani@broadcom.com>,
Ranjan Kumar <ranjan.kumar@broadcom.com>,
MPT-FusionLinux.pdl@broadcom.com,
Daniel Palmer <daniel@thingy.jp>,
GOTO Masanori <gotom@debian.or.jp>,
YOKOTA Hiroshi <yokota@netlab.is.tsukuba.ac.jp>,
Jack Wang <jinpu.wang@cloud.ionos.com>,
Geoff Levand <geoff@infradead.org>, Michael Reed <mdr@sgi.com>,
Nilesh Javali <njavali@marvell.com>,
GR-QLogic-Storage-Upstream@marvell.com,
Narsimhulu Musini <nmusini@cisco.com>,
"K . Y . Srinivasan" <kys@microsoft.com>,
Haiyang Zhang <haiyangz@microsoft.com>,
Wei Liu <wei.liu@kernel.org>, Dexuan Cui <decui@microsoft.com>,
Long Li <longli@microsoft.com>,
linux-hyperv@vger.kernel.org,
"Michael S . Tsirkin" <mst@redhat.com>,
Jason Wang <jasowang@redhat.com>,
Paolo Bonzini <pbonzini@redhat.com>,
Stefan Hajnoczi <stefanha@redhat.com>,
Eugenio Perez <eperezma@redhat.com>,
virtualization@lists.linux.dev,
Vishal Bhakta <vishal.bhakta@broadcom.com>,
bcm-kernel-feedback-list@broadcom.com,
Juergen Gross <jgross@suse.com>,
Stefano Stabellini <sstabellini@kernel.org>,
Oleksandr Tyshchenko <oleksandr_tyshchenko@epam.com>,
xen-devel@lists.xenproject.org,
Bart Van Assche <bvanassche@acm.org>
Subject: Re: [PATCH v3 3/4] block: drop shared-tag fairness throttling
Date: Wed, 10 Jun 2026 10:35:59 -0600 [thread overview]
Message-ID: <aimSb9I0Vl-68hy9@kbusch-mbp> (raw)
In-Reply-To: <CAL2rwxr1uGshb1o=jvP2OnBffNz2cKXj8tHuAUCN5HFuy2vB_g@mail.gmail.com>
On Wed, Jun 10, 2026 at 09:16:11PM +0530, Sumit Saxena wrote:
> The motivation for this change stems from performance issue we
> encountered due to false sharing of the 'nr_active_requests_shared_tags'
> counter
> on certain CPU architectures. I initially submitted a patch to move that
> counter to
> its own cache line to avoid conflicts with 'nr_requests' and other hot
> fields
> (see:
> https://patchwork.kernel.org/project/linux-scsi/patch/20260402074637.92417-3-sumit.saxena@broadcom.com/
> ).
>
> During the review, Bart shared his work, which eliminates the
> counter entirely by removing the fairness throttling. My testing confirmed
> that
> this approach resolved the performance issues and improved IOPS.
> This patch is part of a larger set, and I have reported the cumulative
> performance
> improvements in the cover letter.
So the problem is just the atomic operation accounting overhead? I
previously thought the device just really needed to consume all the tags
to hit performance.
next prev parent reply other threads:[~2026-06-10 16:36 UTC|newest]
Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-06-09 12:17 [PATCH v3 0/4] scsi/block: NUMA-local scan allocations, shared-tag path cleanup, and SCSI I/O counters Sumit Saxena
2026-06-09 12:18 ` [PATCH v3 1/4] scsi: scan: allocate sdev and starget on the NUMA node of the host adapter Sumit Saxena
2026-06-09 13:49 ` John Garry
2026-06-10 6:00 ` Hannes Reinecke
2026-06-09 12:18 ` [PATCH v3 2/4] scsi: host: allocate struct Scsi_Host " Sumit Saxena
2026-06-09 13:03 ` John Garry
2026-06-10 5:59 ` Hannes Reinecke
2026-06-10 15:37 ` Stefan Hajnoczi
2026-06-09 12:18 ` [PATCH v3 3/4] block: drop shared-tag fairness throttling Sumit Saxena
2026-06-10 6:14 ` Christoph Hellwig
2026-06-10 15:46 ` Sumit Saxena
2026-06-10 15:46 ` Sumit Saxena
2026-06-10 16:35 ` Keith Busch [this message]
2026-06-11 10:43 ` Sumit Saxena
2026-06-11 10:43 ` Sumit Saxena
2026-06-10 16:03 ` Bart Van Assche
2026-06-10 6:18 ` Hannes Reinecke
2026-06-10 16:05 ` Bart Van Assche
2026-06-17 7:32 ` Sumit Saxena
2026-06-09 12:18 ` [PATCH v3 4/4] scsi: use percpu counters for iostat counters in struct scsi_device Sumit Saxena
2026-06-09 13:15 ` John Garry
2026-06-11 15:27 ` Sumit Saxena
2026-06-10 6:21 ` Hannes Reinecke
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=aimSb9I0Vl-68hy9@kbusch-mbp \
--to=kbusch@kernel.org \
--cc=GR-QLogic-Storage-Upstream@marvell.com \
--cc=James.Bottomley@hansenpartnership.com \
--cc=MPT-FusionLinux.pdl@broadcom.com \
--cc=aacraid@microsemi.com \
--cc=aliakc@web.de \
--cc=anil.gurumurthy@qlogic.com \
--cc=aradford@gmail.com \
--cc=axboe@kernel.dk \
--cc=bcm-kernel-feedback-list@broadcom.com \
--cc=brking@us.ibm.com \
--cc=bvanassche@acm.org \
--cc=chandrakanth.patil@broadcom.com \
--cc=chleroy@kernel.org \
--cc=cleech@redhat.com \
--cc=daniel@thingy.jp \
--cc=decui@microsoft.com \
--cc=don.brace@microchip.com \
--cc=eperezma@redhat.com \
--cc=fischer@norbit.de \
--cc=fthain@linux-m68k.org \
--cc=geoff@infradead.org \
--cc=gotom@debian.or.jp \
--cc=haiyangz@microsoft.com \
--cc=hare@suse.com \
--cc=hch@infradead.org \
--cc=jasowang@redhat.com \
--cc=jgross@suse.com \
--cc=jinpu.wang@cloud.ionos.com \
--cc=justin.tee@broadcom.com \
--cc=kartilak@cisco.com \
--cc=kashyap.desai@broadcom.com \
--cc=khalid@gonehiking.org \
--cc=kys@microsoft.com \
--cc=lduncan@suse.com \
--cc=lenehan@twibble.org \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-block@vger.kernel.org \
--cc=linux-hyperv@vger.kernel.org \
--cc=linux-scsi@vger.kernel.org \
--cc=linux@armlinux.org.uk \
--cc=linux@highpoint-tech.com \
--cc=linuxdrivers@attotech.com \
--cc=linuxppc-dev@lists.ozlabs.org \
--cc=liyihang9@h-partners.com \
--cc=longli@microsoft.com \
--cc=maddy@linux.ibm.com \
--cc=martin.petersen@oracle.com \
--cc=mdr@sgi.com \
--cc=megaraidlinux.pdl@broadcom.com \
--cc=michael.christie@oracle.com \
--cc=mpe@ellerman.id.au \
--cc=mpi3mr-linuxdrv.pdl@broadcom.com \
--cc=mst@redhat.com \
--cc=njavali@marvell.com \
--cc=nmusini@cisco.com \
--cc=npiggin@gmail.com \
--cc=oleksandr_tyshchenko@epam.com \
--cc=oliver@neukum.org \
--cc=open-iscsi@googlegroups.com \
--cc=paul.ely@broadcom.com \
--cc=pbonzini@redhat.com \
--cc=ram.vegesna@broadcom.com \
--cc=ranjan.kumar@broadcom.com \
--cc=sathya.prakash@broadcom.com \
--cc=satishkh@cisco.com \
--cc=schmitzmic@gmail.com \
--cc=sebaddel@cisco.com \
--cc=shivasharan.srikanteshwara@broadcom.com \
--cc=sreekanth.reddy@broadcom.com \
--cc=sstabellini@kernel.org \
--cc=stefanha@redhat.com \
--cc=storagedev@microchip.com \
--cc=sudarsana.kalluru@qlogic.com \
--cc=suganath-prabu.subramani@broadcom.com \
--cc=sumit.saxena@broadcom.com \
--cc=target-devel@vger.kernel.org \
--cc=tyreld@linux.ibm.com \
--cc=virtualization@lists.linux.dev \
--cc=vishal.bhakta@broadcom.com \
--cc=wei.liu@kernel.org \
--cc=willy@infradead.org \
--cc=xen-devel@lists.xenproject.org \
--cc=yokota@netlab.is.tsukuba.ac.jp \
/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: link
Be 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.