Re: Areca vs. ZFS performance testing.

Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]
From: Jeremy Chadwick
Date: Thursday, October 30, 2008 - 8:32 pm

Cross-posting this to freebsd-fs, as I'm sure people there will have
other recommendations.  (This is one of those rare cross-posting
situations.....)

On Fri, Oct 31, 2008 at 01:14:55PM +1000, Danny Carroll wrote:

I think these sets of tests are good.  There are some others I'd like to
see, but they'd only be applicable if the 1231-ML has hardware cache.  I
can mention what those are if the card does have hardware caching.


The general concept is: "the more RAM the better".  However, if you're
using RELENG_7, then there's not much point (speaking solely about ZFS)
to getting more than maybe 3 or 4GB; you're still limited to a 2GB kmap
maximum.

Regarding size of the array vs. memory usage: as long as you tune kmem
and ZFS ARC, you shouldn't have much trouble.  There have been some
key people reporting lately that they run very large ZFS arrays without
issue, with proper tuning.

Also, just a reminder: do not pick a value of 2048M for kmem_size or
kmem_size_max; the machine won't boot/work.  You shouldn't go above
something like 1536M, although some have tuned slightly above that
with success.  (You need to remember that there is more to kernel
memory allocation than just this, so you don't want to exhaust it all
assigning it to kmap.  Hope that makes sense...)


Only on CURRENT; 7.x cannot, and AFAIK, will never be able to, as the
engineering efforts required to fix it are too great.

I look forward to seeing your numbers.  Someone here might be able to
compile them into some graphs and other whatnots to make things easier
for future readers.

Thanks for doing all of this!

-- 
| Jeremy Chadwick                                jdc at parodius.com |
| Parodius Networking                       http://www.parodius.com/ |
| UNIX Systems Administrator                  Mountain View, CA, USA |
| Making life hard for others since 1977.              PGP: 4BD6C0CB |

_______________________________________________
freebsd-fs@freebsd.org mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-fs
To unsubscribe, send any mail to "freebsd-fs-unsubscribe@freebsd.org"
Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]

Messages in current thread:
Re: Areca vs. ZFS performance testing., Jeremy Chadwick, (Thu Oct 30, 8:32 pm)
Re: Areca vs. ZFS performance testing., Danny Carroll, (Thu Oct 30, 9:07 pm)
Re: Areca vs. ZFS performance testing., Jeremy Chadwick, (Thu Oct 30, 9:34 pm)
Re: Areca vs. ZFS performance testing., Andrew Snow, (Thu Oct 30, 9:44 pm)
Re: Areca vs. ZFS performance testing., Danny Carroll, (Thu Oct 30, 9:47 pm)
Re: Areca vs. ZFS performance testing., Danny Carroll, (Thu Oct 30, 9:50 pm)
Re: Areca vs. ZFS performance testing., Danny Carroll, (Thu Oct 30, 9:55 pm)
Re: Areca vs. ZFS performance testing., Peter Schuller, (Sun Nov 2, 8:09 am)
Re: Areca vs. ZFS performance testing. , Dieter, (Wed Nov 12, 3:57 pm)
Re: Areca vs. ZFS performance testing., Danny Carroll, (Wed Nov 12, 10:46 pm)
Re: Areca vs. ZFS performance testing., Jeremy Chadwick, (Thu Nov 13, 12:43 am)
Re: Areca vs. ZFS performance testing., Willem Jan Withagen, (Thu Nov 13, 1:32 am)
Re: Areca vs. ZFS performance testing., Danny Carroll, (Thu Nov 13, 4:09 am)
Re: Areca vs. ZFS performance testing., Danny Carroll, (Thu Nov 13, 6:59 am)
Re: Areca vs. ZFS performance testing., Nikolay Denev, (Thu Nov 13, 8:06 am)
Re: Areca vs. ZFS performance testing., Scott Long, (Thu Nov 13, 9:49 am)
Re: Areca vs. ZFS performance testing., Danny Carroll, (Thu Nov 13, 1:46 pm)
Re: Areca vs. ZFS performance testing., Danny Carroll, (Thu Nov 13, 1:59 pm)
Re: Areca vs. ZFS performance testing., Eirik Øverby, (Sun Nov 16, 1:27 pm)
Re: Areca vs. ZFS performance testing., Danny Carroll, (Sun Nov 16, 8:15 pm)
Re: Areca vs. ZFS performance testing., Matt Simerson, (Sun Nov 16, 11:06 pm)
Re: Areca vs. ZFS performance testing., Jeremy Chadwick, (Mon Nov 17, 12:08 am)
Re: Areca vs. ZFS performance testing., Wes Morgan, (Mon Nov 17, 4:26 am)
Re: Areca vs. ZFS performance testing., Danny Carroll, (Mon Nov 17, 4:43 am)
Re: Areca vs. ZFS performance testing., Matt Simerson, (Mon Nov 17, 2:04 pm)
Re: Areca vs. ZFS performance testing., Matt Simerson, (Mon Nov 17, 3:07 pm)
Re: Areca vs. ZFS performance testing., Danny Carroll, (Mon Nov 17, 4:46 pm)
RE: Areca vs. ZFS performance testing., Jan Mikkelsen, (Tue Dec 2, 3:38 am)
RE: Areca vs. ZFS performance testing., Wes Morgan, (Tue Dec 2, 5:04 am)
Re: Areca vs. ZFS performance testing., Danny Carroll, (Wed Jan 7, 5:33 pm)
Re: Areca vs. ZFS performance testing., Zaphod Beeblebrox, (Thu Jan 8, 12:40 am)
Re: Areca vs. ZFS performance testing., Koen Smits, (Thu Jan 8, 12:48 am)
Re: Areca vs. ZFS performance testing., Nikolay Denev, (Thu Jan 8, 2:19 am)
Re: Areca vs. ZFS performance testing., Danny Carroll, (Thu Jan 8, 7:30 pm)
Re: Areca vs. ZFS performance testing., Koen Smits, (Fri Jan 9, 1:46 am)
Re: Areca vs. ZFS performance testing., Danny Carroll, (Fri Jan 9, 2:02 am)
Re: Areca vs. ZFS performance testing., Koen Smits, (Fri Jan 9, 8:58 am)
Re: Areca vs. ZFS performance testing., Andrew Snow, (Fri Jan 9, 7:38 pm)
Re: Areca vs. ZFS performance testing., Danny Carroll, (Fri Jan 9, 9:58 pm)
Re: Areca vs. ZFS performance testing., Danny Carroll, (Tue Jan 20, 11:40 pm