Re: Cluster and attached RAID performance

Even if you add Veritas Clustering (or, whatever it's called, nowadays), I
presume you'd have the same issue--in this case, it seems simply to be the
hardware configuration...?

Thanks.
"Geoff N. Hiten" <SQLCraftsman@xxxxxxxxx> wrote in message
news:ubcForenGHA.5096@xxxxxxxxxxxxxxxxxxxxxxx
The write cache issue is inherent to Microsoft clustering. Yet another
reason to hire an expert to walk you through your first cluster
deployment. Most vendors won't bring a SQL clustering expert in unless it
is a very big sale.

--
Geoff N. Hiten
Senior Database Administrator
Microsoft SQL Server MVP





"David Day" <DavidDay22@xxxxxxxxxxx> wrote in message
news:1151765224.359336.208660@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
Before I purchased my equipment I asked about whether my configuration
would work, and it does function. However their was no advice
regarding performance. The turning off the write cache shouldn't be
buried so deep in the documention. All the documentation I read just
got your systems up and running, I haven't found much about performance
tuning.

Bill Bradley wrote:
Again...Dell didn't tell us about this tiny issue. We would not have
bought
this...

Thanks.
"Geoff N. Hiten" <SQLCraftsman@xxxxxxxxx> wrote in message
news:OpueLlLnGHA.620@xxxxxxxxxxxxxxxxxxxxxxx
It helps if you don't spend your budget on solutions that don't work.
That saves a lot to spend on solutions that do work. :)

--
Geoff N. Hiten
Senior Database Administrator
Microsoft SQL Server MVP


"Bill Bradley" <wdbradley3@xxxxxxxxxxx> wrote in message
news:uUzajNLnGHA.3784@xxxxxxxxxxxxxxxxxxxxxxx
Yeah...we have that tiny little problem with money, too...

Thanks.
"David Day" <DavidDay22@xxxxxxxxxxx> wrote in message
news:1151701425.822775.51920@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
The solution is to use a SAN such as the EMC CX300 that handles
write
caching. Of course the problem I have to tell senior management how
much more money they are going to have to spend.


Bill Bradley wrote:
Well...that sucks. Funny...Dell never mentioned this to us...

I presume, if we just ran it standalone, from one server, it'd work
better?

Thanks.
"Geoff N. Hiten" <SQLCraftsman@xxxxxxxxx> wrote in message
news:%23wVg053mGHA.1760@xxxxxxxxxxxxxxxxxxxxxxx
I am surprised that you are getting even 50% of the stand-alone
system
performance. A PV-220 has no internal cache, instead it relies on
the
cache on board the PERC4 cards in each host. Since the hosts are
clustered, all write cache is turned off on the PERC cards to
avoid
data
corruption during a failover. This is why I don't recommend SCSI
based
clusters except when you use enclosures with embedded cache.

--
Geoff N. Hiten
Senior Database Administrator
Microsoft SQL Server MVP



"Bill Bradley" <wdbradley3@xxxxxxxxxxx> wrote in message
news:uMPe8a3mGHA.4212@xxxxxxxxxxxxxxxxxxxxxxx
I have a SQL cluster consisting of the following:

2 ea Dell PE-2850 servers, dual 3.2 GHz CPU, 4 GB RAM, 2-36
GB/RAID-1
for C:, same for D:, all drives U320/15K. running Win2K3EntSP1
and
SQL2K5SP1. Connected to cluster with Dell PERC4/DC in each
server

1 ea Dell PV-220 cabinet (up to 14 drives, 13 when clustered)
with
following discrete arrays, all U320/15K:

2-18 GB/RAID1 Quorum Volume
2-36 GB/RAID1 LOGS
2-36 GB/RAID1 MSDTC
6-73 GB/RAID5 SQL DB
1-73 GB HotSwap

Original server was a single Dell PE-2650, dual 2.8 GHz CPU, 4
GB
RAM,
5-18GB/RAID-5 U320/15K, running Win2KAS and SQL2KSP4.

Performance of the new setup is 50% of the old one! User is
pissed.

I was told a few things:

Don't mix drive sizes (but, I thought, they are in discrete
arrays,
NOT JBOD)
Too many drives on one RAID controller (no choice on that,
only
one
connector from each server).

Anyone have ideas on this?

Thanks!













.

Relevant Pages

  • Re: Cluster and WriteBack Caching
    ... Write-back caching cannot be used on host controllers in a cluster without ... failover clustering and can sync the cache correctly, ... > Mike Epprecht, Microsoft SQL Server MVP ...
    (microsoft.public.sqlserver.setup)
  • Re: Clustering with NAS
    ... Whilst I appreciate that clustering with NAS is ... >> Mike Epprecht, Microsoft SQL Server MVP ...
    (microsoft.public.sqlserver.clustering)
  • Re: How do I fix this cluster???
    ... could not be found to complete setup. ... >Introduction to Microsoft SQL Server 2000 Clustering ... >Microsoft SQL Server 2000 Failover Clustering Disaster ...
    (microsoft.public.sqlserver.clustering)
  • Re: Cluster and attached RAID performance
    ... Veritas Clustering and SQL are not a particularly good mix. ... the cache coherency issue is endemic to every clustering scenario ... Senior Database Administrator ... Microsoft SQL Server MVP ...
    (microsoft.public.sqlserver.clustering)
  • Re: Cluster and attached RAID performance
    ... The write cache issue is inherent to Microsoft clustering. ... Senior Database Administrator ... Microsoft SQL Server MVP ...
    (microsoft.public.sqlserver.clustering)
Loading