From: Greg 'groggy' Lehey <grog@lemis.com>
To: John Gilmore <gnu@toad.com>
Cc: TUHS main list <tuhs@minnie.tuhs.org>
Subject: Re: [TUHS] tunefs -m 5%
Date: Sat, 6 Mar 2021 12:16:48 +1100 [thread overview]
Message-ID: <20210306011648.GA80491@eureka.lemis.com> (raw)
In-Reply-To: <25189.1614937832@hop.toad.com>
[-- Attachment #1: Type: text/plain, Size: 2272 bytes --]
I haven't redirected this reply to COFF, though I was considering
doing so: it
On Friday, 5 March 2021 at 1:50:32 -0800, John Gilmore wrote:
> John P. Linderman <jpl.jpl@gmail.com> wrote:
>> I have several 12 TB disks scattered about my house. 5% of 12TB is 600GB.
>
> At one point in hystery, ext2 performance was reported to suffer badly
> if there was less than 5% of disk space available in an active
> filesystem. My naive belief, probably informed by older and wiser heads
> around Sun, was that when the file system was >95% full, ext2 spent a
> lot of time seeking around in free lists finding single allocatable
> blocks. And there were no built-in "defragmentation" programs that
> could easily fix that.
This appears to have been inherited from UFS. My recollection is
pretty much the same for UFS, and even the man page entry for EXT4 is
closely related to UFS newfs(8):
Linux:
-m reserved-blocks-percentage
Specify the percentage of the filesystem blocks reserved for
the
super-user. This avoids fragmentation, and allows
root-owned
daemons, such as syslogd(8), to continue to function
correctly
after non-privileged processes are prevented from writing to
the
filesystem. The default percentage is 5%.
FreBSD:
-m free-space
The percentage of space reserved from normal users; the minimum
free space threshold. The default value used is defined by
MINFREE from <ufs/ffs/fs.h>, currently 8%. See tunefs(8) for
more details on how to set this option.
And I can confirm that file systems slow down significantly after the
last 1% of free space has been used.
> Is that still a performance constraint in ext4, which has had a few
> decades to work out those edge performance issues?
Hopefully Ted will comment. But UFS has had even more decades. And
arguably 600 GB on a modern disk is less of a concern than 15 MB on a
300 MB disk 40 years ago.
Greg
--
Sent from my desktop computer.
Finger grog@lemis.com for PGP public key.
See complete headers for address and phone numbers.
This message is digitally signed. If your Microsoft mail program
reports problems, please read http://lemis.com/broken-MUA
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 163 bytes --]
next prev parent reply other threads:[~2021-03-06 1:17 UTC|newest]
Thread overview: 73+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-03-04 16:52 [TUHS] tabs vs spaces - entab, detab Will Senn
2021-03-04 16:59 ` Clem Cole
2021-03-04 18:31 ` arnold
2021-03-04 19:23 ` Nemo Nusquam
2021-03-04 19:37 ` Steve Nickolas
2021-03-04 19:50 ` Rob Pike
2021-03-04 21:20 ` Robert Clausecker
2021-03-04 21:25 ` Will Senn
2021-03-05 9:58 ` John Gilmore
2021-03-06 21:31 ` Dave Horsfall
2021-03-06 21:38 ` Larry McVoy
2021-03-06 22:05 ` Clem Cole
2021-03-15 3:02 ` John Cowan
2021-03-15 18:15 ` Steffen Nurpmeso
2021-03-15 21:19 ` Bakul Shah
2021-03-15 23:47 ` Steffen Nurpmeso
2021-03-16 3:10 ` Earl Baugh
2021-03-15 21:08 ` Dave Horsfall
2021-03-15 21:12 ` Steve Nickolas
2021-03-15 21:24 ` Dave Horsfall
2021-03-15 22:06 ` Adam Thornton
2021-03-16 13:25 ` arnold
2021-03-17 5:10 ` Greg 'groggy' Lehey
2021-03-06 21:40 ` Steve Nickolas
2021-03-04 18:48 ` emanuel stiebler
2021-03-05 0:44 ` John Cowan
2021-03-05 0:55 ` Larry McVoy
2021-03-05 1:09 ` George Michaelson
2021-03-05 1:21 ` Larry McVoy
2021-03-05 1:29 ` Richard Salz
2021-03-04 18:33 ` John P. Linderman
2021-03-04 21:24 ` Greg 'groggy' Lehey
2021-03-04 21:27 ` Will Senn
2021-03-04 21:29 ` Greg 'groggy' Lehey
2021-03-04 21:42 ` Will Senn
2021-03-04 21:48 ` John P. Linderman
2021-03-04 22:08 ` Andy Kosela
2021-03-04 22:12 ` Greg 'groggy' Lehey
2021-03-05 14:13 ` Steffen Nurpmeso
2021-03-05 20:24 ` John Cowan
2021-03-05 21:51 ` Bakul Shah
2021-03-06 23:43 ` Steffen Nurpmeso
2021-03-05 0:15 ` Jon Steinhart
2021-03-06 21:22 ` Dave Horsfall
2021-03-06 23:58 ` Bakul Shah
2021-03-07 0:03 ` Jon Steinhart
2021-03-07 0:25 ` Steve Nickolas
2021-03-07 9:16 ` Brantley Coile
2021-03-05 9:50 ` [TUHS] tunefs -m 5% John Gilmore
2021-03-05 15:01 ` Grant Taylor via TUHS
2021-03-05 15:32 ` Theodore Ts'o
2021-03-06 1:18 ` Greg 'groggy' Lehey
2021-03-06 1:52 ` Warner Losh
2021-03-06 21:45 ` Dave Horsfall
2021-03-06 22:03 ` Larry McVoy
2021-03-09 4:59 ` Greg 'groggy' Lehey
2021-03-06 23:52 ` David Barto
2021-03-06 1:16 ` Greg 'groggy' Lehey [this message]
2021-03-04 22:10 ` [TUHS] tabs vs spaces - entab, detab Greg A. Woods
2021-03-05 1:41 ` alan
2021-03-05 1:55 ` alan
2021-03-05 2:06 ` Will Senn
2021-03-05 17:08 ` Clem Cole
2021-03-05 17:19 ` Richard Salz
2021-03-05 19:39 ` Lawrence Stewart
2021-03-05 19:51 ` Dan Halbert
2021-03-08 1:52 ` Will Senn
2021-03-05 16:43 ` Scot Jenkins via TUHS
2021-03-05 22:23 ` Bakul Shah
2021-03-06 20:51 ` Dave Horsfall
2021-03-06 21:01 ` Jon Steinhart
2021-03-06 21:19 ` Larry McVoy
2021-03-06 22:01 ` Clem Cole
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=20210306011648.GA80491@eureka.lemis.com \
--to=grog@lemis.com \
--cc=gnu@toad.com \
--cc=tuhs@minnie.tuhs.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).