From: Miklos Szeredi <mszeredi@redhat.com>
To: Matthew Wilcox <willy@infradead.org>
Cc: Boaz Harrosh <boazh@netapp.com>,
linux-fsdevel <linux-fsdevel@vger.kernel.org>,
Ric Wheeler <rwheeler@redhat.com>,
Steve French <smfrench@gmail.com>,
Steven Whitehouse <swhiteho@redhat.com>,
Jefff moyer <jmoyer@redhat.com>, Sage Weil <sweil@redhat.com>,
Jan Kara <jack@suse.cz>, Amir Goldstein <amir73il@gmail.com>,
Andy Rudof <andy.rudoff@intel.com>,
Anna Schumaker <Anna.Schumaker@netapp.com>,
Amit Golander <Amit.Golander@netapp.com>,
Sagi Manole <sagim@netapp.com>,
Shachar Sharon <Shachar.Sharon@netapp.com>
Subject: Re: [RFC 1/7] mm: Add new vma flag VM_LOCAL_CPU
Date: Wed, 14 Mar 2018 12:31:22 +0100 [thread overview]
Message-ID: <CAOssrKdffjmUPpsnzyZudtk9kvT7mXfgMG4fzJvFRQqo5Li79A@mail.gmail.com> (raw)
In-Reply-To: <20180314111750.GA29631@bombadil.infradead.org>
On Wed, Mar 14, 2018 at 12:17 PM, Matthew Wilcox <willy@infradead.org> wrote:
> On Wed, Mar 14, 2018 at 09:20:57AM +0100, Miklos Szeredi wrote:
>> On Tue, Mar 13, 2018 at 7:56 PM, Matthew Wilcox <willy@infradead.org> wrote:
>> > On Tue, Mar 13, 2018 at 07:15:46PM +0200, Boaz Harrosh wrote:
>> >> On a call to mmap an mmap provider (like an FS) can put
>> >> this flag on vma->vm_flags.
>> >>
>> >> This tells the Kernel that the vma will be used from a single
>> >> core only and therefore invalidation of PTE(s) need not a
>> >> wide CPU scheduling
>> >>
>> >> The motivation of this flag is the ZUFS project where we want
>> >> to optimally map user-application buffers into a user-mode-server
>> >> execute the operation and efficiently unmap.
>> >
>> > I've been looking at something similar, and I prefer my approach,
>> > although I'm not nearly as far along with my implementation as you are.
>> >
>> > My approach is also to add a vm_flags bit, tentatively called VM_NOTLB.
>> > The page fault handler refuses to insert any TLB entries into the process
>> > address space. But follow_page_mask() will return the appropriate struct
>> > page for it. This should be enough for O_DIRECT accesses to work as
>> > you'll get the appropriate scatterlists built.
>> >
>> > I suspect Boaz has already done a lot of thinking about this and doesn't
>> > need the explanation, but here's how it looks for anyone following along
>> > at home:
>> >
>> > Process A calls read().
>> > Kernel allocates a page cache page for it and calls the filesystem through
>> > ->readpages (or ->readpage).
>> > Filesystem calls the managing process to get the data for that page.
>> > Managing process draws a pentagram and summons Beelzebub (or runs Perl;
>> > whichever you find more scary).
>> > Managing process notifies the filesystem that the page is now full of data.
>> > Filesystem marks the page as being Uptodate and unlocks it.
>> > Process was waiting on the page lock, wakes up and copies the data from the
>> > page cache into userspace. read() is complete.
>> >
>> > What we're concerned about here is what to do after the managing process
>> > tells the kernel that the read is complete. Clearly allowing the managing
>> > process continued access to the page is Bad as the page may be freed by the
>> > page cache and then reused for something else. Doing a TLB shootdown is
>> > expensive. So Boaz's approach is to have the process promise that it won't
>> > have any other thread look at it. My approach is to never allow the page
>> > to have load/store access from userspace; it can only be passed to other
>> > system calls.
>>
>> This all seems to revolve around the fact that userspace fs server
>> process needs to copy something into userspace client's buffer, right?
>>
>> Instead of playing with memory mappings, why not just tell the kernel
>> *what* to copy?
>>
>> While in theory not as generic, I don't see any real limitations (you
>> don't actually need the current contents of the buffer in the read
>> case and vica verse in the write case).
>>
>> And we already have an interface for this: splice(2). What am I
>> missing? What's the killer argument in favor of the above messing
>> with tlb caches etc, instead of just letting the kernel do the dirty
>> work.
>
> Great question. You're completely right that the question is how to tell
> the kernel what to copy. The problem is that splice() can only write to
> the first page of a pipe. So you need one pipe per outstanding request,
> which can easily turn into thousands of file descriptors. If we enhanced
> splice() so it could write to any page in a pipe, then I think splice()
> would be the perfect interface.
Don't know your usecase, but afaict zufs will have one queue per cpu.
Having one pipe/cpu doesn't sound too bad.
But yeah, there's plenty of room for improvement in the splice
interface. Just needs a killer app like this :)
Thanks,
Miklos
next prev parent reply other threads:[~2018-03-14 11:31 UTC|newest]
Thread overview: 39+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-03-13 17:14 [RFC 0/7] first draft of ZUFS - the Kernel part Boaz Harrosh
2018-03-13 17:15 ` [RFC 1/7] mm: Add new vma flag VM_LOCAL_CPU Boaz Harrosh
2018-03-13 18:56 ` Matthew Wilcox
2018-03-14 8:20 ` Miklos Szeredi
2018-03-14 11:17 ` Matthew Wilcox
2018-03-14 11:31 ` Miklos Szeredi [this message]
2018-03-14 11:45 ` Matthew Wilcox
2018-03-14 14:49 ` Miklos Szeredi
2018-03-14 14:57 ` Matthew Wilcox
2018-03-14 15:39 ` Miklos Szeredi
[not found] ` <CAON-v2ygEDCn90C9t-zadjsd5GRgj0ECqntQSDDtO_Zjk=KoVw@mail.gmail.com>
2018-03-14 16:48 ` Matthew Wilcox
2018-03-14 21:41 ` Boaz Harrosh
2018-03-15 8:47 ` Miklos Szeredi
2018-03-15 15:27 ` Boaz Harrosh
2018-03-15 15:34 ` Matthew Wilcox
2018-03-15 15:58 ` Boaz Harrosh
2018-03-15 16:10 ` Miklos Szeredi
2018-03-15 16:30 ` Boaz Harrosh
2018-03-15 20:42 ` Miklos Szeredi
2018-04-25 12:21 ` Boaz Harrosh
2018-05-07 10:46 ` Miklos Szeredi
2018-03-13 17:17 ` [RFC 2/7] fs: Add the ZUF filesystem to the build + License Boaz Harrosh
2018-03-13 20:16 ` Andreas Dilger
2018-03-14 17:21 ` Boaz Harrosh
2018-03-15 4:21 ` Andreas Dilger
2018-03-15 13:58 ` Boaz Harrosh
2018-03-13 17:18 ` [RFC 3/7] zuf: Preliminary Documentation Boaz Harrosh
2018-03-13 20:32 ` Randy Dunlap
2018-03-14 18:01 ` Boaz Harrosh
2018-03-14 19:16 ` Randy Dunlap
2018-03-13 17:22 ` [RFC 4/7] zuf: zuf-rootfs && zuf-core Boaz Harrosh
2018-03-13 17:36 ` Boaz Harrosh
2018-03-14 12:56 ` Nikolay Borisov
2018-03-14 18:34 ` Boaz Harrosh
2018-03-13 17:25 ` [RFC 5/7] zus: Devices && mounting Boaz Harrosh
2018-03-13 17:38 ` Boaz Harrosh
2018-03-13 17:28 ` [RFC 6/7] zuf: Filesystem operations Boaz Harrosh
2018-03-13 17:39 ` Boaz Harrosh
2018-03-13 17:32 ` [RFC 7/7] zuf: Write/Read && mmap implementation Boaz Harrosh
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=CAOssrKdffjmUPpsnzyZudtk9kvT7mXfgMG4fzJvFRQqo5Li79A@mail.gmail.com \
--to=mszeredi@redhat.com \
--cc=Amit.Golander@netapp.com \
--cc=Anna.Schumaker@netapp.com \
--cc=Shachar.Sharon@netapp.com \
--cc=amir73il@gmail.com \
--cc=andy.rudoff@intel.com \
--cc=boazh@netapp.com \
--cc=jack@suse.cz \
--cc=jmoyer@redhat.com \
--cc=linux-fsdevel@vger.kernel.org \
--cc=rwheeler@redhat.com \
--cc=sagim@netapp.com \
--cc=smfrench@gmail.com \
--cc=sweil@redhat.com \
--cc=swhiteho@redhat.com \
--cc=willy@infradead.org \
/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;
as well as URLs for NNTP newsgroup(s).