From: Sinan Kaya <okaya@codeaurora.org>
To: Logan Gunthorpe <logang@deltatee.com>
Cc: Christoph Hellwig <hch@lst.de>, Sagi Grimberg <sagi@grimberg.me>,
"James E.J. Bottomley" <jejb@linux.vnet.ibm.com>,
"Martin K. Petersen" <martin.petersen@oracle.com>,
Jens Axboe <axboe@kernel.dk>,
Steve Wise <swise@opengridcomputing.com>,
Stephen Bates <sbates@raithlin.com>,
Max Gurtovoy <maxg@mellanox.com>,
Dan Williams <dan.j.williams@intel.com>,
Keith Busch <keith.busch@intel.com>,
Jason Gunthorpe <jgunthorpe@obsidianresearch.com>,
linux-pci@vger.kernel.org, linux-scsi@vger.kernel.org,
linux-nvme@lists.infradead.org, linux-rdma@vger.kernel.org,
linux-nvdimm@lists.01.org, linux-kernel@vger.kernel.org,
Alex Williamson <alex.williamson@redhat.com>,
Bjorn Helgaas <bhelgaas@google.com>
Subject: Re: [RFC 1/8] Introduce Peer-to-Peer memory (p2pmem) device
Date: Sun, 2 Apr 2017 17:03:53 -0400 [thread overview]
Message-ID: <bed80d4e-7709-5991-498e-0ac361ca96a6@codeaurora.org> (raw)
In-Reply-To: <63d73995-4dfa-6270-ca13-972e0628011b@deltatee.com>
On 4/2/2017 1:21 PM, Logan Gunthorpe wrote:
>> This is when the BIOS date helps so that you don't break existing systems.
> I'm not that worried about this code breaking existing systems. There
> are significant trade-offs with using p2pmem (ie. you are quite likely
> sacrificing performance for memory QOS or upstream PCI bandwidth), and
> therefore the user _has_ to specifically say to use it. This is why
> we've put a flag in the nvme target code that defaults to off. Thus we
> are not going to have a situation where people upgrade their kernels and
> see broken or slow systems. People _have_ to make the decision to turn
> it on and decide based on their use case whether it's appropriate.
>
OK. I didn't know the feature was not enabled by default. This is even
easier now.
Push the decision all the way to the user. Let them decide whether they
want this feature to work on a root port connected port or under the
switch.
>> We can't guarentee all switches will work either. See above for instructions
>> on when this feature should be enabled.
> It's a lot easier to say that all switches will work than it is for root
> ports. This is essentially what switches are designed for, so I'd be
> surprised to find one that doesn't work. Root ports are the trouble here
> seeing it's a lot more likely for them to be designed without
> considering that traffic needs to move between ports efficiently. If we
> do find extremely broken switches that don't support this then we'd
> probably want to create a black list for that. Also, there's
> significantly fewer PCI switch products on the market than there are
> root port instances, so a black list would be much easier to manage there.
>
I thought the issue was feature didn't work at all with some root ports
or there was some kind of memory corruption issue that you were trying to
avoid with the existing systems.
If you are just worried about performance, the switch recommendation belongs
to your particular product tuning guide or a howto document not into the
actual code itself.
I think you should get rid of all pci searching business in your code.
--
Sinan Kaya
Qualcomm Datacenter Technologies, Inc. as an affiliate of Qualcomm Technologies, Inc.
Qualcomm Technologies, Inc. is a member of the Code Aurora Forum, a Linux Foundation Collaborative Project.
next prev parent reply other threads:[~2017-04-02 21:03 UTC|newest]
Thread overview: 81+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-03-30 22:12 [RFC 0/8] Copy Offload with Peer-to-Peer PCI Memory Logan Gunthorpe
[not found] ` <1490911959-5146-1-git-send-email-logang-OTvnGxWRz7hWk0Htik3J/w@public.gmane.org>
2017-03-30 22:12 ` [RFC 1/8] Introduce Peer-to-Peer memory (p2pmem) device Logan Gunthorpe
[not found] ` <1490911959-5146-2-git-send-email-logang-OTvnGxWRz7hWk0Htik3J/w@public.gmane.org>
2017-03-31 18:49 ` Sinan Kaya
[not found] ` <cb102386-0314-a3a3-ed44-b42debdf1512-sgV2jX0FEOL9JmXXK+q4OQ@public.gmane.org>
2017-03-31 21:23 ` Logan Gunthorpe
[not found] ` <7158f2e8-2016-f398-e77f-0fcbe6cb41dd-OTvnGxWRz7hWk0Htik3J/w@public.gmane.org>
2017-03-31 21:38 ` Sinan Kaya
[not found] ` <e6a74aeb-9f54-51c5-8ad9-3b6fb92c03b3-sgV2jX0FEOL9JmXXK+q4OQ@public.gmane.org>
2017-03-31 22:42 ` Logan Gunthorpe
[not found] ` <0280fbb4-ba9e-ac64-6bb3-b72590a54e57-OTvnGxWRz7hWk0Htik3J/w@public.gmane.org>
2017-03-31 23:51 ` Sinan Kaya
[not found] ` <0ae27bca-21be-b89c-aba4-6cc9766ebd7b-sgV2jX0FEOL9JmXXK+q4OQ@public.gmane.org>
2017-04-01 1:57 ` Logan Gunthorpe
[not found] ` <c8edc480-a2ac-a763-8438-18f3396db483-OTvnGxWRz7hWk0Htik3J/w@public.gmane.org>
2017-04-01 2:17 ` okaya-sgV2jX0FEOL9JmXXK+q4OQ
2017-04-01 22:16 ` Logan Gunthorpe
2017-04-02 2:26 ` Sinan Kaya
[not found] ` <f0448277-9381-5c3d-d194-1efa1d1b44a6-sgV2jX0FEOL9JmXXK+q4OQ@public.gmane.org>
2017-04-02 17:21 ` Logan Gunthorpe
2017-04-02 21:03 ` Sinan Kaya [this message]
2017-04-03 4:26 ` Logan Gunthorpe
[not found] ` <ef507444-d3e5-0454-86a0-b5c4ae4b4dd9-OTvnGxWRz7hWk0Htik3J/w@public.gmane.org>
2017-04-25 11:58 ` Marta Rybczynska
[not found] ` <117239810.400362790.1493121533234.JavaMail.zimbra-FNhOzJFKnXGHXe+LvDLADg@public.gmane.org>
2017-04-25 16:58 ` Logan Gunthorpe
2017-03-30 22:12 ` [RFC 2/8] cxgb4: setup pcie memory window 4 and create p2pmem region Logan Gunthorpe
[not found] ` <1490911959-5146-3-git-send-email-logang-OTvnGxWRz7hWk0Htik3J/w@public.gmane.org>
2017-04-04 10:42 ` Sagi Grimberg
[not found] ` <f269d9e1-8dcf-7970-382e-cb0d9a020efc-NQWnxTmZq1alnMjI0IkVqw@public.gmane.org>
2017-04-04 15:56 ` Logan Gunthorpe
2017-04-05 15:41 ` Steve Wise
2017-03-30 22:12 ` [RFC 3/8] nvmet: Use p2pmem in nvme target Logan Gunthorpe
2017-04-04 10:40 ` Sagi Grimberg
[not found] ` <bce6b009-7756-3cf7-5053-2628b26c8d97-NQWnxTmZq1alnMjI0IkVqw@public.gmane.org>
2017-04-04 16:16 ` Logan Gunthorpe
[not found] ` <ec05b7d9-8dfd-8227-84d2-7d391df32219-OTvnGxWRz7hWk0Htik3J/w@public.gmane.org>
2017-04-06 5:47 ` Sagi Grimberg
[not found] ` <0689e764-bf04-6da2-3b7d-2cbf0b6b94a0-NQWnxTmZq1alnMjI0IkVqw@public.gmane.org>
2017-04-06 15:52 ` Logan Gunthorpe
2017-03-30 22:12 ` [RFC 4/8] p2pmem: Add debugfs "stats" file Logan Gunthorpe
[not found] ` <1490911959-5146-5-git-send-email-logang-OTvnGxWRz7hWk0Htik3J/w@public.gmane.org>
2017-04-04 10:46 ` Sagi Grimberg
[not found] ` <95928b70-0148-7297-8f5e-5031d996bb98-NQWnxTmZq1alnMjI0IkVqw@public.gmane.org>
2017-04-04 17:25 ` Logan Gunthorpe
2017-04-05 15:43 ` Steve Wise
2017-03-30 22:12 ` [RFC 5/8] scatterlist: Modify SG copy functions to support io memory Logan Gunthorpe
[not found] ` <1490911959-5146-6-git-send-email-logang-OTvnGxWRz7hWk0Htik3J/w@public.gmane.org>
2017-03-31 7:09 ` Christoph Hellwig
[not found] ` <20170331070950.GA9059-wEGCiKHe2LqWVfeAwA7xHQ@public.gmane.org>
2017-03-31 15:41 ` Logan Gunthorpe
[not found] ` <435d4471-436b-87e6-8827-c9fc6cbdde2c-OTvnGxWRz7hWk0Htik3J/w@public.gmane.org>
2017-04-03 21:20 ` Logan Gunthorpe
[not found] ` <445bc352-75d7-438f-96ef-c2411215628d-OTvnGxWRz7hWk0Htik3J/w@public.gmane.org>
2017-04-03 21:44 ` Dan Williams
[not found] ` <CAPcyv4g=MHbjbY0GFPoLq3wAGwhcC7813O7iLUWGEChWh0M7Dw-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2017-04-03 22:10 ` Logan Gunthorpe
[not found] ` <ff0dd5ec-2562-9f1d-1335-d0a8813f2f50-OTvnGxWRz7hWk0Htik3J/w@public.gmane.org>
2017-04-03 22:47 ` Dan Williams
[not found] ` <CAPcyv4gx4g3Ry_A99yTodqwm2vH72oMSLKAKF7iEsmG5G4TcbQ-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2017-04-03 23:12 ` Logan Gunthorpe
[not found] ` <22930db3-a194-8b60-5aab-4a8add1ddc55-OTvnGxWRz7hWk0Htik3J/w@public.gmane.org>
2017-04-04 0:07 ` Dan Williams
[not found] ` <CAPcyv4gL=Z42x52So1iL-MNhPY67Pktz3c0J_h0tj_60TowNuQ-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2017-04-07 17:59 ` Logan Gunthorpe
2017-03-30 22:12 ` [RFC 6/8] nvmet: Be careful about using iomem accesses when dealing with p2pmem Logan Gunthorpe
[not found] ` <1490911959-5146-7-git-send-email-logang-OTvnGxWRz7hWk0Htik3J/w@public.gmane.org>
2017-04-04 10:59 ` Sagi Grimberg
[not found] ` <080b68b4-eba3-861c-4f29-5d829425b5e7-NQWnxTmZq1alnMjI0IkVqw@public.gmane.org>
2017-04-04 15:46 ` Jason Gunthorpe
[not found] ` <20170404154629.GA13552-ePGOBjL8dl3ta4EC/59zMFaTQe2KTcn/@public.gmane.org>
2017-04-04 17:21 ` Logan Gunthorpe
2017-04-06 5:33 ` Sagi Grimberg
2017-04-06 16:35 ` Jason Gunthorpe
[not found] ` <4df229d8-8124-664a-9bc4-6401bc034be1-NQWnxTmZq1alnMjI0IkVqw@public.gmane.org>
2017-04-06 16:02 ` Logan Gunthorpe
2017-04-07 11:19 ` Stephen Bates
[not found] ` <3E85B4D4-9EBC-4299-8209-2D8740947764-pv7U853sEMVWk0Htik3J/w@public.gmane.org>
2017-04-10 8:29 ` Sagi Grimberg
[not found] ` <7fcc3ac8-8b96-90f5-3942-87f999c7499d-NQWnxTmZq1alnMjI0IkVqw@public.gmane.org>
2017-04-10 16:03 ` Logan Gunthorpe
2017-03-30 22:12 ` [RFC 7/8] p2pmem: Support device removal Logan Gunthorpe
2017-04-12 5:22 ` [RFC 0/8] Copy Offload with Peer-to-Peer PCI Memory Benjamin Herrenschmidt
[not found] ` <1491974532.7236.43.camel-XVmvHMARGAS8U2dJNN8I7kB+6BGkLq7r@public.gmane.org>
2017-04-12 17:09 ` Logan Gunthorpe
[not found] ` <5ac22496-56ec-025d-f153-140001d2a7f9-OTvnGxWRz7hWk0Htik3J/w@public.gmane.org>
2017-04-12 21:55 ` Benjamin Herrenschmidt
[not found] ` <1492034124.7236.77.camel-XVmvHMARGAS8U2dJNN8I7kB+6BGkLq7r@public.gmane.org>
2017-04-13 21:22 ` Logan Gunthorpe
[not found] ` <81888a1e-eb0d-cbbc-dc66-0a09c32e4ea2-OTvnGxWRz7hWk0Htik3J/w@public.gmane.org>
2017-04-13 22:37 ` Benjamin Herrenschmidt
2017-04-13 23:26 ` Bjorn Helgaas
[not found] ` <20170413232631.GB24910-1RhO1Y9PlrlHTL0Zs8A6p5iNqAH0jzoTYJqu5kTmcBRl57MIdRCFDg@public.gmane.org>
2017-04-14 4:16 ` Jason Gunthorpe
[not found] ` <20170414041656.GA30694-ePGOBjL8dl3ta4EC/59zMFaTQe2KTcn/@public.gmane.org>
2017-04-14 4:40 ` Logan Gunthorpe
[not found] ` <08c32f0d-6c7c-b65f-6453-dde0d7c173d1-OTvnGxWRz7hWk0Htik3J/w@public.gmane.org>
2017-04-14 11:37 ` Benjamin Herrenschmidt
[not found] ` <1492169879.25766.4.camel-XVmvHMARGAS8U2dJNN8I7kB+6BGkLq7r@public.gmane.org>
2017-04-14 11:39 ` Benjamin Herrenschmidt
2017-04-14 11:37 ` Benjamin Herrenschmidt
[not found] ` <1492169849.25766.3.camel-XVmvHMARGAS8U2dJNN8I7kB+6BGkLq7r@public.gmane.org>
2017-04-14 17:30 ` Logan Gunthorpe
[not found] ` <630c1c63-ff17-1116-e069-2b8f93e50fa2-OTvnGxWRz7hWk0Htik3J/w@public.gmane.org>
2017-04-14 19:04 ` Bjorn Helgaas
[not found] ` <20170414190452.GA15679-1RhO1Y9PlrlHTL0Zs8A6p5iNqAH0jzoTYJqu5kTmcBRl57MIdRCFDg@public.gmane.org>
2017-04-14 22:07 ` Benjamin Herrenschmidt
[not found] ` <1492207643.25766.18.camel-XVmvHMARGAS8U2dJNN8I7kB+6BGkLq7r@public.gmane.org>
2017-04-15 17:41 ` Logan Gunthorpe
2017-04-15 22:09 ` Dan Williams
[not found] ` <CAPcyv4jUeKzKDARp6Z35kdPLKnP-M6aF8X5KpOx55CLyjnj4dA-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2017-04-16 3:01 ` Benjamin Herrenschmidt
[not found] ` <1492311719.25766.37.camel-XVmvHMARGAS8U2dJNN8I7kB+6BGkLq7r@public.gmane.org>
2017-04-16 4:46 ` Logan Gunthorpe
2017-04-16 15:53 ` Dan Williams
[not found] ` <CAPcyv4iqnz1B00Q3xG-nGrLXdOyB7ditxmwZyotksLFgUqr+jA-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2017-04-16 16:34 ` Logan Gunthorpe
[not found] ` <5e43818e-8c6b-8be8-23ff-b798633d2a73-OTvnGxWRz7hWk0Htik3J/w@public.gmane.org>
2017-04-16 22:31 ` Benjamin Herrenschmidt
[not found] ` <1492381907.25766.49.camel-XVmvHMARGAS8U2dJNN8I7kB+6BGkLq7r@public.gmane.org>
2017-04-24 7:36 ` Knut Omang
[not found] ` <1493019397.3171.118.camel-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org>
2017-04-24 16:14 ` Logan Gunthorpe
[not found] ` <9b6c0830-a728-c7ca-e6c6-2135f3f760ed-OTvnGxWRz7hWk0Htik3J/w@public.gmane.org>
2017-04-25 6:30 ` Knut Omang
[not found] ` <1493101803.3171.246.camel-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org>
2017-04-25 17:03 ` Logan Gunthorpe
[not found] ` <0cc95df5-b9dd-6493-15fe-771d535c1020-OTvnGxWRz7hWk0Htik3J/w@public.gmane.org>
2017-04-25 21:23 ` Stephen Bates
2017-04-25 21:23 ` Stephen Bates
2017-04-16 22:26 ` Benjamin Herrenschmidt
[not found] ` <bff1e503-95a9-e19f-bfd9-0ff962c63a81-OTvnGxWRz7hWk0Htik3J/w@public.gmane.org>
2017-04-15 22:17 ` Benjamin Herrenschmidt
[not found] ` <1492294628.25766.33.camel-XVmvHMARGAS8U2dJNN8I7kB+6BGkLq7r@public.gmane.org>
2017-04-16 5:36 ` Logan Gunthorpe
2017-03-30 22:12 ` [RFC 8/8] p2pmem: Added char device user interface Logan Gunthorpe
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=bed80d4e-7709-5991-498e-0ac361ca96a6@codeaurora.org \
--to=okaya@codeaurora.org \
--cc=alex.williamson@redhat.com \
--cc=axboe@kernel.dk \
--cc=bhelgaas@google.com \
--cc=dan.j.williams@intel.com \
--cc=hch@lst.de \
--cc=jejb@linux.vnet.ibm.com \
--cc=jgunthorpe@obsidianresearch.com \
--cc=keith.busch@intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-nvdimm@lists.01.org \
--cc=linux-nvme@lists.infradead.org \
--cc=linux-pci@vger.kernel.org \
--cc=linux-rdma@vger.kernel.org \
--cc=linux-scsi@vger.kernel.org \
--cc=logang@deltatee.com \
--cc=martin.petersen@oracle.com \
--cc=maxg@mellanox.com \
--cc=sagi@grimberg.me \
--cc=sbates@raithlin.com \
--cc=swise@opengridcomputing.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: link
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