All of lore.kernel.org
 help / color / mirror / Atom feed
From: Brock Nanson <brock@nanson.org>
To: Guy <bugzilla@watkins-home.com>
Cc: 'Brian Pontius' <linuxboy123@mindspring.com>, linux-raid@vger.kernel.org
Subject: Re: Md cache?
Date: Thu, 03 Jun 2004 13:16:54 -0700	[thread overview]
Message-ID: <40BF8736.10101@nanson.org> (raw)
In-Reply-To: <200406031922.i53JMS315198@watkins-home.com>

My IBM ServeRAID 3HB's do.  But as you say, many don't.  A UPS with a 
communications cable and shutdown software is really the only solution.

Brock

Guy wrote:

> With hardware RAID the write cache has battery backup.  So, the RAID system
> will not lose data when the power fails.  It will finish the writes when the
> power returns.
> 
> I don't think the hardware RAID cards have a battery.  The external self
> contained RAID systems that I have worked with do have batteries.
> 
> Anyone know?  Do any RAID cards have batteries?
> 
> Guy
> 
> -----Original Message-----
> From: linux-raid-owner@vger.kernel.org
> [mailto:linux-raid-owner@vger.kernel.org] On Behalf Of Brian Pontius
> Sent: Thursday, June 03, 2004 2:14 PM
> To: Neil Brown
> Cc: linux-raid@vger.kernel.org
> Subject: Re: Md cache?
> 
> I apologze for being unclear.
> 
> As I did comparisons between software and hardware raid,  one of the
> advantage
> s that I noticed with hardware raid was cache (both read and write). With
> hard
> ware it is usually larger giving some increase in performance.  I was
> looking
> for a way to allocate more system memory specifically to be the md cache
> area
> to give that extra feature of that hardware raid. This would especially be
> ben
> efitial for a NAS that has a dedicated purpose to fast reliable storage.
> 
> 
> Thanks for your time.
> Brian Pontius
> 
> 
> -----Original Message-----
> From: Neil Brown <neilb@cse.unsw.edu.au>
> Sent: Jun 2, 2004 10:10 PM
> To: Brian Pontius <linuxboy123@mindspring.com>
> Cc: linux-raid@vger.kernel.org
> Subject: Re: Md cache?
> 
> On Wednesday June 2, linuxboy123@mindspring.com wrote:
> 
>>to all,
>>
>>Is anyone aware of a way to cause the md devices to use some system memory
> 
> as a write cache? (maybe through mdadm?).  I have looked everywhere and
> cannot seem to find anything about such a feature.
> 
>>If not, anyone  know if this is a possibility for the future, Neil?
> 
> 
> What is it exactly that you want.
> 
> All device IO is cached in memory before being written to the device.
> The only real value of a cache with a RAID array is if it we a
> non-volatile cache.  Is that what you were thinking of.
> 
> NeilBrown
> 
> -
> To unsubscribe from this list: send the line "unsubscribe linux-raid" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
> 
> 
> -
> To unsubscribe from this list: send the line "unsubscribe linux-raid" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html

  reply	other threads:[~2004-06-03 20:16 UTC|newest]

Thread overview: 7+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2004-06-03 18:13 Md cache? Brian Pontius
2004-06-03 19:22 ` Guy
2004-06-03 20:16   ` Brock Nanson [this message]
2004-06-03 21:38     ` Guy
  -- strict thread matches above, loose matches on Subject: below --
2004-06-03  1:48 Brian Pontius
2004-06-03  2:10 ` Neil Brown
2004-06-03  3:03 ` Daniel Pittman

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=40BF8736.10101@nanson.org \
    --to=brock@nanson.org \
    --cc=bugzilla@watkins-home.com \
    --cc=linux-raid@vger.kernel.org \
    --cc=linuxboy123@mindspring.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.