From: maarten <maarten@ultratux.net>
To: linux-raid@vger.kernel.org
Subject: Re: Spares and partitioning huge disks
Date: Mon, 10 Jan 2005 22:21:46 +0100 [thread overview]
Message-ID: <200501102221.46018.maarten@ultratux.net> (raw)
In-Reply-To: <200501102009.j0AK9C922554@www.watkins-home.com>
On Monday 10 January 2005 21:09, Guy wrote:
> I use ext3 filesystems. No problems with performance (that I know of).
> I have never tried any others.
Reportedly, deleting a big (>2GB) file under XFS is way faster than under
ext3, but I never verified this myself. I barely ever ran ext3, I went with
my distros' default, which was Reiserfs.
Deleting huge files is a special case though, so it does not make much sense
to benchmark or tune for that. But in this special case it matters.
> Do you think the performance difference of the various filesystems would
> affect your PVR?
Ehm, no. Well, not the raid-5 overhead at least. The FS helps the GUI being
more 'snappy'. It has been reported that ext3 takes a real long time to
delete huge files (up to several seconds or more) (unconfirmed by me).
This is what a copy of a 5GB file and subsequent delete does on my system:
-rw-r--r-- 1 root root 4909077650 Jan 10 04:43 file
dozer:/mnt/store # time cp file away
real 3m15.778s
user 0m0.640s
sys 0m45.230s
dozer:/mnt/store # time rm away
real 0m0.237s
user 0m0.000s
sys 0m0.020s
(This was while the machine was idle, no recordings going on)
But the machine IS starved for CPU and bus bandwidth; the cpu should be almost
fully pegged with recording up to two simultaneous channels, compressing
realtime(!) in mpeg4 from two cheap bttv cards (at 480x480 rez, 2600 Kbps).
Therefore it is the fastest CPU I could afford back in last spring, an Athlon
XP 2600. The machine is also overclocked from 200 FSB to 233, yielding a 38
MHz PCI bus. Strangely enough, despite there being 5 PCI cards, amongst which
two disk I/O controllers, this seems to work just fine. It's been tested
in-depth by recording shows daily for months and it crashes rarely ( meaning
< once a month which is not too bad, considering ). Maybe the bigass Zalman
copper CPU cooler and the 12cm fan hovering above it help there, too ;-)
At the beginning it ran off a single 160GB disk, so when I switched to raid-5
I was very afraid that either the extra CPU load, the extra IRQ load or the
bus bandwidth would saturate, thus killing performance. You see, the PCI bus
is fairly loaded too, since not only does it have to handle the various ATA
controllers, but two uncompressed videostreams from the TV cards as well.
So all in all, the overhead of raid seems insignificant to me, or the code is
very well optimized indeed :-)
Maarten
next prev parent reply other threads:[~2005-01-10 21:21 UTC|newest]
Thread overview: 94+ messages / expand[flat|nested] mbox.gz Atom feed top
2005-01-06 14:16 Spares and partitioning huge disks maarten
2005-01-06 16:46 ` Guy
2005-01-06 17:08 ` maarten
2005-01-06 17:31 ` Guy
2005-01-06 18:18 ` maarten
[not found] ` <41DD83DA.9040609@h3c.com>
2005-01-06 19:42 ` maarten
2005-01-07 20:59 ` Mario Holbe
2005-01-07 21:57 ` Guy
2005-01-08 10:22 ` Mario Holbe
2005-01-08 12:19 ` maarten
2005-01-08 16:33 ` Guy
2005-01-08 16:58 ` maarten
2005-01-08 14:52 ` Frank van Maarseveen
2005-01-08 15:50 ` Mario Holbe
2005-01-08 16:32 ` Guy
2005-01-08 17:16 ` maarten
2005-01-08 18:55 ` Guy
2005-01-08 19:25 ` maarten
2005-01-08 20:33 ` Mario Holbe
2005-01-08 23:01 ` maarten
2005-01-09 10:10 ` Mario Holbe
2005-01-09 16:23 ` Guy
2005-01-09 16:36 ` Michael Tokarev
2005-01-09 17:52 ` Peter T. Breuer
2005-01-09 17:59 ` Michael Tokarev
2005-01-09 18:34 ` Peter T. Breuer
2005-01-09 20:28 ` Guy
2005-01-09 20:47 ` Peter T. Breuer
2005-01-10 7:19 ` Peter T. Breuer
2005-01-10 9:05 ` Guy
2005-01-10 9:38 ` Peter T. Breuer
2005-01-10 12:31 ` Peter T. Breuer
2005-01-10 13:19 ` Peter T. Breuer
2005-01-10 18:37 ` Peter T. Breuer
2005-01-11 11:34 ` Peter T. Breuer
2005-01-08 23:09 ` Guy
2005-01-09 0:56 ` maarten
2005-01-13 2:05 ` Neil Brown
2005-01-13 4:55 ` Guy
2005-01-13 9:27 ` Peter T. Breuer
2005-01-13 15:53 ` Guy
2005-01-13 17:16 ` Peter T. Breuer
2005-01-13 20:40 ` Guy
2005-01-13 23:32 ` Peter T. Breuer
2005-01-14 2:43 ` Guy
2005-01-08 16:49 ` maarten
2005-01-08 19:01 ` maarten
2005-01-10 16:34 ` maarten
2005-01-10 16:36 ` Gordon Henderson
2005-01-10 17:10 ` maarten
2005-01-16 16:19 ` 4 questions. Chieftec chassis case CA-01B, resync times, selecting ide driver module loading, raid5 :2 drives on same ide channel Mitchell Laks
2005-01-16 17:53 ` Gordon Henderson
2005-01-16 18:22 ` Maarten
2005-01-16 19:39 ` Guy
2005-01-16 20:55 ` Maarten
2005-01-16 21:58 ` Guy
2005-01-10 17:13 ` Spares and partitioning huge disks Guy
2005-01-10 17:35 ` hard disk re-locates bad block on read Guy
2005-01-11 14:34 ` Tom Coughlan
2005-01-11 22:43 ` Guy
2005-01-12 13:51 ` Tom Coughlan
2005-01-10 18:24 ` Spares and partitioning huge disks maarten
2005-01-10 20:09 ` Guy
2005-01-10 21:21 ` maarten [this message]
2005-01-11 1:04 ` maarten
2005-01-10 18:40 ` maarten
2005-01-10 19:41 ` Guy
2005-01-12 11:41 ` RAID-6 Gordon Henderson
2005-01-13 2:11 ` RAID-6 Neil Brown
2005-01-15 16:12 ` RAID-6 Gordon Henderson
2005-01-17 8:04 ` RAID-6 Turbo Fredriksson
2005-01-11 10:09 ` Spares and partitioning huge disks KELEMEN Peter
2005-01-09 19:33 ` Frank van Maarseveen
2005-01-09 21:26 ` maarten
2005-01-09 22:29 ` Frank van Maarseveen
2005-01-09 23:16 ` maarten
2005-01-10 8:15 ` Frank van Maarseveen
2005-01-14 17:29 ` Dieter Stueken
2005-01-14 17:46 ` maarten
2005-01-14 19:14 ` Derek Piper
2005-01-15 0:13 ` Michael Tokarev
2005-01-15 9:34 ` Peter T. Breuer
2005-01-15 9:54 ` Mikael Abrahamsson
2005-01-15 10:31 ` Brad Campbell
2005-01-15 11:10 ` Mikael Abrahamsson
2005-01-15 10:33 ` Peter T. Breuer
2005-01-15 11:07 ` Mikael Abrahamsson
2005-01-09 23:20 ` Guy
2005-01-10 7:42 ` Gordon Henderson
2005-01-10 9:03 ` Guy
2005-01-10 12:21 ` Stats... [RE: Spares and partitioning huge disks] Gordon Henderson
2005-01-10 0:42 ` Spares and partitioning huge disks Guy
-- strict thread matches above, loose matches on Subject: below --
2005-01-13 9:53 Bene Martin
2005-01-13 10:11 ` Peter T. Breuer
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=200501102221.46018.maarten@ultratux.net \
--to=maarten@ultratux.net \
--cc=linux-raid@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).