From: Miklos Szeredi <miklos@szeredi.hu>
To: Boaz Harrosh <openosd@gmail.com>
Cc: Boaz Harrosh <boaz@plexistor.com>,
linux-fsdevel <linux-fsdevel@vger.kernel.org>,
Anna Schumaker <Anna.Schumaker@netapp.com>,
Al Viro <viro@zeniv.linux.org.uk>,
Matt Benjamin <mbenjami@redhat.com>,
Miklos Szeredi <mszeredi@redhat.com>,
Amir Goldstein <amir73il@gmail.com>,
Sagi Manole <sagim@netapp.com>,
Matthew Wilcox <willy@infradead.org>,
Dan Williams <dan.j.williams@intel.com>
Subject: Re: [PATCHSET v02 00/16] zuf: ZUFS Zero-copy User-mode FileSystem
Date: Thu, 26 Sep 2019 15:48:59 +0200 [thread overview]
Message-ID: <CAJfpegswpiuwHaAgo1kY2PWutjFtA_h-N_bMSaKA2MEsXkFXfA@mail.gmail.com> (raw)
In-Reply-To: <e66f4a0a-c88f-67a8-a785-d618aa79be44@gmail.com>
On Thu, Sep 26, 2019 at 2:48 PM Boaz Harrosh <openosd@gmail.com> wrote:
>
> On 26/09/2019 10:11, Miklos Szeredi wrote:
> > I found a big scheduler scalability bottleneck that is caused by
> > update of mm->cpu_bitmap at context switch. This can be worked
> > around by using shared memory instead of shared page tables, which is
> > a bit of a pain, but it does prove the point. Thought about fixing
> > the cpu_bitmap cacheline pingpong, but didn't really get anywhere.
> >
>
> I'm not sure what is the scalability bottleneck you are seeing above.
> With zufs I have a very good scalability, almost flat up to the
> number of CPUs, and/or the limit of the memory bandwith if I'm accessing
> pmem.
This was *really* noticable with NUMA and many cpus (>64).
> Miklos would you please have some bandwith to review my code? it would
> make me very happy and calm. Your input is very valuable to me.
Sure, will look at the patches.
Thanks,
Miklos
next prev parent reply other threads:[~2019-09-26 13:49 UTC|newest]
Thread overview: 30+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-09-26 2:07 [PATCHSET v02 00/16] zuf: ZUFS Zero-copy User-mode FileSystem Boaz Harrosh
2019-09-26 2:07 ` [PATCH 01/16] fs: Add the ZUF filesystem to the build + License Boaz Harrosh
2019-09-26 2:07 ` [PATCH 02/16] MAINTAINERS: Add the ZUFS maintainership Boaz Harrosh
2019-09-26 2:07 ` [PATCH 03/16] zuf: Preliminary Documentation Boaz Harrosh
2019-09-26 2:07 ` [PATCH 04/16] zuf: zuf-rootfs Boaz Harrosh
2019-09-26 2:07 ` [PATCH 05/16] zuf: zuf-core The ZTs Boaz Harrosh
2019-09-26 2:07 ` [PATCH 06/16] zuf: Multy Devices Boaz Harrosh
2019-09-26 2:07 ` [PATCH 07/16] zuf: mounting Boaz Harrosh
2019-09-26 2:07 ` [PATCH 08/16] zuf: Namei and directory operations Boaz Harrosh
2019-09-26 2:07 ` [PATCH 09/16] zuf: readdir operation Boaz Harrosh
2019-09-26 2:07 ` [PATCH 10/16] zuf: symlink Boaz Harrosh
2019-09-26 2:07 ` [PATCH 11/16] zuf: Write/Read implementation Boaz Harrosh
[not found] ` <db90d73233484d251755c5a0cb7ee570b3fc9d19.camel@netapp.com>
2019-10-29 20:15 ` Matthew Wilcox
2019-11-14 14:04 ` Boaz Harrosh
2019-11-14 15:15 ` Boaz Harrosh
2019-11-14 16:08 ` Schumaker, Anna
2019-09-26 2:07 ` [PATCH 12/16] zuf: mmap & sync Boaz Harrosh
2019-09-26 2:07 ` [PATCH 13/16] zuf: More file operation Boaz Harrosh
2019-09-26 2:07 ` [PATCH 14/16] zuf: ioctl implementation Boaz Harrosh
2019-09-26 2:07 ` [PATCH 15/16] zuf: xattr && acl implementation Boaz Harrosh
2019-09-26 2:07 ` [PATCH 16/16] zuf: Support for dynamic-debug of zusFSs Boaz Harrosh
2019-09-26 7:11 ` [PATCHSET v02 00/16] zuf: ZUFS Zero-copy User-mode FileSystem Miklos Szeredi
2019-09-26 9:41 ` Bernd Schubert
2019-09-26 11:27 ` Boaz Harrosh
2019-09-26 12:12 ` Bernd Schubert
2019-09-26 12:24 ` Boaz Harrosh
2019-09-26 13:45 ` Miklos Szeredi
2019-09-26 12:48 ` Boaz Harrosh
2019-09-26 13:48 ` Miklos Szeredi [this message]
2019-09-26 11:41 ` 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=CAJfpegswpiuwHaAgo1kY2PWutjFtA_h-N_bMSaKA2MEsXkFXfA@mail.gmail.com \
--to=miklos@szeredi.hu \
--cc=Anna.Schumaker@netapp.com \
--cc=amir73il@gmail.com \
--cc=boaz@plexistor.com \
--cc=dan.j.williams@intel.com \
--cc=linux-fsdevel@vger.kernel.org \
--cc=mbenjami@redhat.com \
--cc=mszeredi@redhat.com \
--cc=openosd@gmail.com \
--cc=sagim@netapp.com \
--cc=viro@zeniv.linux.org.uk \
--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).