Re: [PATCH 7/8] blk-mq: create hctx for each present CPU

spread MSI(-X) vectors to all possible CPUs V2 · Christoph Hellwig <hch@lst.de> · 2017-06-03
[PATCH 1/8] genirq: allow assigning affinity to present but not online CPUs · Christoph Hellwig <hch@lst.de> · 2017-06-03
Re: [PATCH 1/8] genirq: allow assigning affinity to present but not online CPUs · Sagi Grimberg <sagi@grimberg.me> · 2017-06-04
Re: [PATCH 1/8] genirq: allow assigning affinity to present but not online CPUs · Thomas Gleixner <hidden> · 2017-06-17
[PATCH 2/8] genirq: move pending helpers to internal.h · Christoph Hellwig <hch@lst.de> · 2017-06-03
Re: [PATCH 2/8] genirq: move pending helpers to internal.h · Sagi Grimberg <sagi@grimberg.me> · 2017-06-04
[PATCH 3/8] genirq/affinity: factor out a irq_affinity_set helper · Christoph Hellwig <hch@lst.de> · 2017-06-03
Re: [PATCH 3/8] genirq/affinity: factor out a irq_affinity_set helper · Sagi Grimberg <sagi@grimberg.me> · 2017-06-04
Re: [PATCH 3/8] genirq/affinity: factor out a irq_affinity_set helper · Thomas Gleixner <hidden> · 2017-06-16
Re: [PATCH 3/8] genirq/affinity: factor out a irq_affinity_set helper · Thomas Gleixner <hidden> · 2017-06-16
Re: [PATCH 3/8] genirq/affinity: factor out a irq_affinity_set helper · Thomas Gleixner <hidden> · 2017-06-16
Re: [PATCH 3/8] genirq/affinity: factor out a irq_affinity_set helper · Thomas Gleixner <hidden> · 2017-06-17
[PATCH 4/8] genirq/affinity: assign vectors to all present CPUs · Christoph Hellwig <hch@lst.de> · 2017-06-03
Re: [PATCH 4/8] genirq/affinity: assign vectors to all present CPUs · Sagi Grimberg <sagi@grimberg.me> · 2017-06-04
[PATCH 5/8] genirq/affinity: update CPU affinity for CPU hotplug events · Christoph Hellwig <hch@lst.de> · 2017-06-03
Re: [PATCH 5/8] genirq/affinity: update CPU affinity for CPU hotplug events · Thomas Gleixner <hidden> · 2017-06-16
Re: [PATCH 5/8] genirq/affinity: update CPU affinity for CPU hotplug events · Thomas Gleixner <hidden> · 2017-06-16
[PATCH 7/8] blk-mq: create hctx for each present CPU · Christoph Hellwig <hch@lst.de> · 2017-06-03
Re: [PATCH 7/8] blk-mq: create hctx for each present CPU · Sagi Grimberg <sagi@grimberg.me> · 2017-06-04
Re: [PATCH 7/8] blk-mq: create hctx for each present CPU · Ming Lei <hidden> · 2017-06-07
Re: [PATCH 7/8] blk-mq: create hctx for each present CPU · Christoph Hellwig <hch@lst.de> · 2017-06-07
Re: [PATCH 7/8] blk-mq: create hctx for each present CPU · Ming Lei <hidden> · 2017-06-08
Re: [PATCH 7/8] blk-mq: create hctx for each present CPU · Omar Sandoval <osandov@osandov.com> · 2017-06-07
Re: [PATCH 7/8] blk-mq: create hctx for each present CPU · Christoph Hellwig <hch@lst.de> · 2017-06-08
[PATCH 8/8] nvme: allocate queues for all possible CPUs · Christoph Hellwig <hch@lst.de> · 2017-06-03
Re: [PATCH 8/8] nvme: allocate queues for all possible CPUs · Sagi Grimberg <sagi@grimberg.me> · 2017-06-04
[PATCH 6/8] blk-mq: include all present CPUs in the default queue mapping · Christoph Hellwig <hch@lst.de> · 2017-06-03
Re: [PATCH 6/8] blk-mq: include all present CPUs in the default queue mapping · Sagi Grimberg <sagi@grimberg.me> · 2017-06-04
Re: spread MSI(-X) vectors to all possible CPUs V2 · Christoph Hellwig <hch@lst.de> · 2017-06-16
Re: spread MSI(-X) vectors to all possible CPUs V2 · Thomas Gleixner <hidden> · 2017-06-16

From: Omar Sandoval <osandov@osandov.com>
Date: 2017-06-07 22:04:15
Also in: linux-nvme, lkml

On Sat, Jun 03, 2017 at 04:04:02PM +0200, Christoph Hellwig wrote:

Currently we only create hctx for online CPUs, which can lead to a lot
of churn due to frequent soft offline / online operations.  Instead
allocate one for each present CPU to avoid this and dramatically simplify
the code.

Signed-off-by: Christoph Hellwig <hch@lst.de>

Oh man, this cleanup is great. Did you run blktests on this? block/008
does a bunch of hotplugging while I/O is running.

`h`	back out one level
`j`	next message in thread
`k`	previous message in thread
`l`	drill in
`Esc`	close help / fold thread tree
`?`	toggle this help