All of lore.kernel.org
 help / color / mirror / Atom feed
From: Lucas Stach <l.stach@pengutronix.de>
To: "Ralf Groß" <ralf.gross+xfs@gmail.com>, linux-xfs@vger.kernel.org
Subject: Re: memory requirements for a 400TB fs with reflinks
Date: Tue, 23 Mar 2021 10:31:55 +0100	[thread overview]
Message-ID: <3ffb0db477970d6dfc5fbf170fa8afdb03f71061.camel@pengutronix.de> (raw)
In-Reply-To: <CANSSxy=d2Tihu8dXUFQmRwYWHNdcGQoSQAkZpePD-8NOV+d5dw@mail.gmail.com>

Hi Ralf,

Am Montag, dem 22.03.2021 um 17:50 +0100 schrieb Ralf Groß:
> No advice or rule of thumb regarding needed memory for xfs_repair?

xfs_repair can be quite a memory hog, however the memory requirements
are mostly related to the amount of metadata in the FS, not so much
with the overall size of the FS. So a small FS with a ton of small
files will require much more RAM on a repair run than a big FS with
only a few big files.

However, xfs_repair makes linear passes over its workingset, so it
works really well with swap. Our backupservers are handling filesystems
with ~400GB of metadata (size of the metadump) and are only equipped
with 64GB RAM. For the worst-case where a xfs_repair run might be
needed they simply have a 1TB SSD to be used as swap for the repair
run.

Regards,
Lucas

> Ralf
> 
> 
> Am Sa., 20. März 2021 um 19:01 Uhr schrieb Ralf Groß <ralf.gross+xfs@gmail.com>:
> > 
> > Hi,
> > 
> > I plan to deploy a couple of Linux (RHEL 8.x) server as Veeam backup
> > repositories. Base for this might be high density server with 58 x
> > 16TB disks, 2x  RAID 60, each with its own raid controller and 28
> > disks. So each RAID 6 has 14 disks, + 2 globale spare.
> > 
> > I wonder what memory requirement such a server would have, is there
> > any special requirement regarding reflinks? I remember that xfs_repair
> > has been a problem in the past, but my experience with this is from 10
> > years ago. Currently I plan to use 192GB RAM, this would be perfect as
> > it utilizes 6 memory channels and 16GB DIMMs are not so expensive.
> > 
> > Thanks - Ralf



      parent reply	other threads:[~2021-03-23  9:32 UTC|newest]

Thread overview: 6+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-03-20 18:01 memory requirements for a 400TB fs with reflinks Ralf Groß
2021-03-22 16:50 ` Ralf Groß
2021-03-22 21:50   ` Dave Chinner
2021-03-23  9:39     ` Ralf Groß
2021-03-23 22:02       ` Dave Chinner
2021-03-23  9:31   ` Lucas Stach [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=3ffb0db477970d6dfc5fbf170fa8afdb03f71061.camel@pengutronix.de \
    --to=l.stach@pengutronix.de \
    --cc=linux-xfs@vger.kernel.org \
    --cc=ralf.gross+xfs@gmail.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.