From: Paul Menzel <pmenzel@molgen.mpg.de>
To: Andreas Dilger <adilger@dilger.ca>
Cc: Linux FS-devel Mailing List <linux-fsdevel@vger.kernel.org>,
Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
Donald Buczek <buczek@molgen.mpg.de>
Subject: Re: File system for scratch space (in HPC cluster)
Date: Fri, 25 Oct 2019 10:35:34 +0200 [thread overview]
Message-ID: <c09eccc9-c067-c121-e9ae-8e3f32d8c80b@molgen.mpg.de> (raw)
In-Reply-To: <2794A217-0A93-44C1-B0A2-A67504A711F0@dilger.ca>
[-- Attachment #1: Type: text/plain, Size: 1462 bytes --]
Dear Andreas,
On 2019-10-24 19:51, Andreas Dilger wrote:
> On Oct 24, 2019, at 4:43 AM, Paul Menzel <pmenzel@molgen.mpg.de>
> wrote:
>> In our cluster, we offer scratch space for temporary files. As
>> these files are temporary, we do not need any safety requirements
>> – especially not those when the system crashes or shuts down. So
>> no `sync` is for example needed.
>>
>> Are there file systems catering to this need? I couldn’t find any?
>> Maybe I missed some options for existing file systems.
>
> How big do you need the scratch filesystem to be? Is it local to
> the node or does it need to be shared between nodes?
In this case local.
> If it needs to be large and shared between nodes then Lustre is
> typically used for this. If it is local and relatively small you
> could consider using tmpfs backed by swab on an NVMe flash device
> (M.2 or U.2, Optane if you can afford it) inside the node.
>
> That way you get RAM-like performance for many files, with a larger
> capacity than RAM when needed (tmpfs can use swap).
>
> You might consider to mount a new tmpfs filesystem per job (no
> formatting is needed for tmpfs), and then unmount it when the job is
> done, so that the old files are automatically cleaned up.
That is a good idea, but probably not practical for 10 TB. Out of
curiosity, what is the limit for “relatively small” in your
experience?
Kind regards,
Paul
[-- Attachment #2: S/MIME Cryptographic Signature --]
[-- Type: application/pkcs7-signature, Size: 5174 bytes --]
prev parent reply other threads:[~2019-10-25 8:35 UTC|newest]
Thread overview: 7+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-10-24 10:43 File system for scratch space (in HPC cluster) Paul Menzel
2019-10-24 14:55 ` Theodore Y. Ts'o
2019-10-24 15:01 ` Boaz Harrosh
2019-10-24 20:34 ` Theodore Y. Ts'o
2019-10-25 8:33 ` Paul Menzel
2019-10-24 17:51 ` Andreas Dilger
2019-10-25 8:35 ` Paul Menzel [this message]
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=c09eccc9-c067-c121-e9ae-8e3f32d8c80b@molgen.mpg.de \
--to=pmenzel@molgen.mpg.de \
--cc=adilger@dilger.ca \
--cc=buczek@molgen.mpg.de \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.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).