hyper threading: processors

Showing posts with label processors. Show all posts

Wednesday, March 7, 2012

HyperThreading with SQL Server 2000

Hi:

I have a server with 4 processors with hyperthreading, so my Windows Server 2003 Enterprise Edition see 8 processors. I have installed SQL Server 2000 Enterprise Edition and see 8 processors. The question is : if i install SQL Server 2000 Standard Edition, how many processors see and use 4 or 8 ?

I know that i have to license only 4 processors according to the Microsoft License, but,really, how many processors see and use?.sqlserver will see all logical processsors (i.e. 8) but you should limit the paralellism to only to 4 (physical) to avoid possible internal para blocking (i.e. max degree of paralellism).

Leaving HT on is a good thing but it's useless to allow all 8 schedulers to work on a single query.|||Why did you enable hyper-threading?

Even M$ admits that you probably are better off w/out it|||Because my server have this property by default then the operating system use this, i did think that use that was better for perfomance...i'm confuse. :confused:|||Rob is an MVP and does a lot of sql server work

http://www.sqlteam.com/forums/topic.asp?TOPIC_ID=55887

Also, it's a lot of excess for a 10-20% (10 more likely) Perf gain...Plus you have a quad...I don't even think they list a quad

http://support.microsoft.com/default.aspx/kb/322385|||Please take a look at Kevin's article , Bare Metal Tuning (will require sqlmag sub to access the article).
http://www.windowsitpro.com/SQLServer/Article/ArticleID/46492/SQLServer_46492.html

In general, HT does give a boost in SQL perf (20-30% gain according to the TPC-C he and a Performance Engr from HP did). If you have an app that pushes L1/L2 cache heavily, turning off HT would only then be a good idea.

Hyper-Threading with SQL 2000 Standard

We just purchased a quad processor server running windows
2003. The processors are xeon so they have HTT
capability. Will SQL200 recognize all eight logical
processor or will it only see four. I wan't to find out
before we install SQL 2000. Thanks.With sp3 it should use all eight.
--
Tibor Karaszi, SQL Server MVP
Archive at: http://groups.google.com/groups?oi=djq&as_ugroup=microsoft.public.sqlserver
"Stephen" <anonymous@.discussions.microsoft.com> wrote in message
news:297901c3af9b$78aa3c40$a601280a@.phx.gbl...
> We just purchased a quad processor server running windows
> 2003. The processors are xeon so they have HTT
> capability. Will SQL200 recognize all eight logical
> processor or will it only see four. I wan't to find out
> before we install SQL 2000. Thanks.|||Here's a good white-paper on hyper-threading for various Windows OS'
http://www.microsoft.com/windows2000/server/evaluation/performance/reports/hyperthread.asp
"Tibor Karaszi" <tibor.please_reply_to_public_forum.karaszi@.cornerstone.se> wrote in message news:<OS1YGh6rDHA.2456@.TK2MSFTNGP12.phx.gbl>...
> With sp3 it should use all eight.
> --
> Tibor Karaszi, SQL Server MVP
> Archive at: http://groups.google.com/groups?oi=djq&as_ugroup=microsoft.public.sqlserver
>
> "Stephen" <anonymous@.discussions.microsoft.com> wrote in message
> news:297901c3af9b$78aa3c40$a601280a@.phx.gbl...
> > We just purchased a quad processor server running windows
> > 2003. The processors are xeon so they have HTT
> > capability. Will SQL200 recognize all eight logical
> > processor or will it only see four. I wan't to find out
> > before we install SQL 2000. Thanks.

Hyperthreading SQL Server 7 - HELP!

Could you clarify the following.
We are looking to buy a quad xeon box (ie 8 virtual processors). From
reading MS documentation it looks like W2K Server won't cut it - we
will need to move to W2K Advanced Server, correct?
Secondly, will Sql Server 7 support 8 virtual processors under such a
scenario?
Thirdly, based on our proposed box 4 x 2.0 GHz Xeon + 2 Gb RAM - for
more performance would you increase the processor speed (eg to 2.5GHz)
or add more RAM (eg to 4 Gb, or more)?
Many Thanks,
StewartI think win2k server ONLY supports 2 physical procs, so you'll neet Advanced
Server...I think you'll also need sql 7 Enterprise to support 4 procs...
Please make sure SQL 7 Enterprise will run on W2k Advanced Server... ( I
think it will, but be safe and double check..)
"Stewart" <windsurfin_stew@.yahoo.com.au> wrote in message
news:9373ee00.0308112138.1cb2f916@.posting.google.com...
> Could you clarify the following.
> We are looking to buy a quad xeon box (ie 8 virtual processors). From
> reading MS documentation it looks like W2K Server won't cut it - we
> will need to move to W2K Advanced Server, correct?
> Secondly, will Sql Server 7 support 8 virtual processors under such a
> scenario?
> Thirdly, based on our proposed box 4 x 2.0 GHz Xeon + 2 Gb RAM - for
> more performance would you increase the processor speed (eg to 2.5GHz)
> or add more RAM (eg to 4 Gb, or more)?
> Many Thanks,
> Stewart|||Win 2K server supports 4 Procs.
Here is a good doc on Microsoft , Win2K and hyperthreading
http://www.microsoft.com/windows2000/docs/hyperthreading.doc
--
--
Allan Mitchell (Microsoft SQL Server MVP)
MCSE,MCDBA
www.SQLDTS.com
I support PASS - the definitive, global community
for SQL Server professionals - http://www.sqlpass.org
"Wayne Snyder" <wsnyder@.computeredservices.com> wrote in message
news:ue9wXLLYDHA.1640@.TK2MSFTNGP10.phx.gbl...
> I think win2k server ONLY supports 2 physical procs, so you'll neet
Advanced
> Server...I think you'll also need sql 7 Enterprise to support 4 procs...
> Please make sure SQL 7 Enterprise will run on W2k Advanced Server... ( I
> think it will, but be safe and double check..)
> "Stewart" <windsurfin_stew@.yahoo.com.au> wrote in message
> news:9373ee00.0308112138.1cb2f916@.posting.google.com...
> > Could you clarify the following.
> >
> > We are looking to buy a quad xeon box (ie 8 virtual processors). From
> > reading MS documentation it looks like W2K Server won't cut it - we
> > will need to move to W2K Advanced Server, correct?
> >
> > Secondly, will Sql Server 7 support 8 virtual processors under such a
> > scenario?
> >
> > Thirdly, based on our proposed box 4 x 2.0 GHz Xeon + 2 Gb RAM - for
> > more performance would you increase the processor speed (eg to 2.5GHz)
> > or add more RAM (eg to 4 Gb, or more)?
> >
> > Many Thanks,
> >
> > Stewart
>|||As for your performance question. You will definitely buy more power by
adding memory instead of CPU here. Go with 4GB RAM.
"Allan Mitchell" <allan@.no-spam.sqldts.com> wrote in message
news:e3GbgjLYDHA.1280@.tk2msftngp13.phx.gbl...
> Win 2K server supports 4 Procs.
> Here is a good doc on Microsoft , Win2K and hyperthreading
> http://www.microsoft.com/windows2000/docs/hyperthreading.doc
> --
> --
> Allan Mitchell (Microsoft SQL Server MVP)
> MCSE,MCDBA
> www.SQLDTS.com
> I support PASS - the definitive, global community
> for SQL Server professionals - http://www.sqlpass.org
>
> "Wayne Snyder" <wsnyder@.computeredservices.com> wrote in message
> news:ue9wXLLYDHA.1640@.TK2MSFTNGP10.phx.gbl...
> > I think win2k server ONLY supports 2 physical procs, so you'll neet
> Advanced
> > Server...I think you'll also need sql 7 Enterprise to support 4
procs...
> > Please make sure SQL 7 Enterprise will run on W2k Advanced Server... ( I
> > think it will, but be safe and double check..)
> > "Stewart" <windsurfin_stew@.yahoo.com.au> wrote in message
> > news:9373ee00.0308112138.1cb2f916@.posting.google.com...
> > > Could you clarify the following.
> > >
> > > We are looking to buy a quad xeon box (ie 8 virtual processors). From
> > > reading MS documentation it looks like W2K Server won't cut it - we
> > > will need to move to W2K Advanced Server, correct?
> > >
> > > Secondly, will Sql Server 7 support 8 virtual processors under such a
> > > scenario?
> > >
> > > Thirdly, based on our proposed box 4 x 2.0 GHz Xeon + 2 Gb RAM - for
> > > more performance would you increase the processor speed (eg to 2.5GHz)
> > > or add more RAM (eg to 4 Gb, or more)?
> > >
> > > Many Thanks,
> > >
> > > Stewart
> >
> >
>|||SQL Server 7.0 Standard Edition will only support 4 processors, and it can't
tell the difference between physical and logical processors. So, if you
want it to use all 8 logical processors on your proposed configuration
you'll want to purchase Enterprise Edition. In addition, 2GB of memory is
marginal for this sized configuration if you are really worried about
maximum performance. So you'll want more memory and Enterprise Edition to
support that additional memory. With 7.0 the best you can do for memory is
the /3GB switch. So the maximum useful memory on the system is going to be
4GB.
An alternative is to stick with Standard Edition and just have it use one
logical processor on each physical processor. Background tasks (Windows
processes, SQL Agent, etc.) will make some use of the additional logical
processors. Keep in mind that the additional logical processors don't
double system performance anyway, most of the data I've heard suggests
they'll give you about a 20% boost. And if you make heavy use of parallel
query then they might actually lead to some pathological conditions that
degrade performance. Finally, with Standard Edition you'd still be limited
to 2GB of memory, which in the long run is your most likely bottleneck.
--
Hal Berenson, SQL Server MVP
True Mountain Group LLC
"Stewart" <windsurfin_stew@.yahoo.com.au> wrote in message
news:9373ee00.0308112138.1cb2f916@.posting.google.com...
> Could you clarify the following.
> We are looking to buy a quad xeon box (ie 8 virtual processors). From
> reading MS documentation it looks like W2K Server won't cut it - we
> will need to move to W2K Advanced Server, correct?
> Secondly, will Sql Server 7 support 8 virtual processors under such a
> scenario?
> Thirdly, based on our proposed box 4 x 2.0 GHz Xeon + 2 Gb RAM - for
> more performance would you increase the processor speed (eg to 2.5GHz)
> or add more RAM (eg to 4 Gb, or more)?
> Many Thanks,
> Stewart

Hyperthreading killing performance of simple query?

We have a new server, 4 physical dual core processors, with hyperthreading,
so it shows up as 16 logical processors.
A simple query joining 3 tables, a distinct, an order by, with maxdop set to
0, takes over 2 seconds. With maxdop set to 1, it takes 200 milliseconds.
setting maxdop between 1 and 15, pretty linear time progression.
Does this sound sane? Is there some magic matrix where under load a higher
maxdop will result in this simple query running faster than where there is
no load (the current case)
Thanks in advance!
DerrickDerrick,
It is true: Parallelism does not alway help. In fact, for some queries it
may make them perform abysmally.
Although I do not do this personally, several posters recommend setting an
OLTP server to a maximum degree of parallelism of 1. They indicate good
success and few discernable problems because of the setting.
I do follow the guideline to limit the server's maximum degree of
parallelism to the number of physical chips, which in your case would be 4.
Then, if a query is troubled we can specifically run it at MAXDOP 1.
FWIW,
RLF
"Derrick" <derrick1298@.excite.com> wrote in message
news:%23E%23LO250HHA.5644@.TK2MSFTNGP05.phx.gbl...
> We have a new server, 4 physical dual core processors, with
> hyperthreading, so it shows up as 16 logical processors.
> A simple query joining 3 tables, a distinct, an order by, with maxdop set
> to 0, takes over 2 seconds. With maxdop set to 1, it takes 200
> milliseconds. setting maxdop between 1 and 15, pretty linear time
> progression.
> Does this sound sane? Is there some magic matrix where under load a
> higher maxdop will result in this simple query running faster than where
> there is no load (the current case)
> Thanks in advance!
> Derrick
>|||Russell,
Thanks for the info, one more q, so would you reccomend hyperthreading be
enabled, or disabled?
We ran tests both ways and turning hyperthreading off does not seem the way
to go based on our results, does that match up with what you have seen/read?
Thanks again,
Derrick
"Russell Fields" <russellfields@.nomail.com> wrote in message
news:eJddSQ60HHA.3788@.TK2MSFTNGP02.phx.gbl...
> Derrick,
> It is true: Parallelism does not alway help. In fact, for some queries it
> may make them perform abysmally.
> Although I do not do this personally, several posters recommend setting an
> OLTP server to a maximum degree of parallelism of 1. They indicate good
> success and few discernable problems because of the setting.
> I do follow the guideline to limit the server's maximum degree of
> parallelism to the number of physical chips, which in your case would be
> 4. Then, if a query is troubled we can specifically run it at MAXDOP 1.
> FWIW,
> RLF
> "Derrick" <derrick1298@.excite.com> wrote in message
> news:%23E%23LO250HHA.5644@.TK2MSFTNGP05.phx.gbl...
>> We have a new server, 4 physical dual core processors, with
>> hyperthreading, so it shows up as 16 logical processors.
>> A simple query joining 3 tables, a distinct, an order by, with maxdop set
>> to 0, takes over 2 seconds. With maxdop set to 1, it takes 200
>> milliseconds. setting maxdop between 1 and 15, pretty linear time
>> progression.
>> Does this sound sane? Is there some magic matrix where under load a
>> higher maxdop will result in this simple query running faster than where
>> there is no load (the current case)
>> Thanks in advance!
>> Derrick
>|||Derrick,
Lara Rubbelke made these comments:
http://blogs.digineer.com/blogs/larar/archive/2006/11/13/maximum-degree-of-parallelism-and-hyperthreading.aspx
He links to Slava Ok's
http://blogs.msdn.com/slavao/archive/2005/11/12/492119.aspx
Their bottom seems to be, do not enable hyperthreading unless you have
proved it will help you.
RLF
"Derrick" <derrick1298@.excite.com> wrote in message
news:u1F0WU60HHA.464@.TK2MSFTNGP02.phx.gbl...
> Russell,
> Thanks for the info, one more q, so would you reccomend hyperthreading be
> enabled, or disabled?
> We ran tests both ways and turning hyperthreading off does not seem the
> way to go based on our results, does that match up with what you have
> seen/read?
> Thanks again,
> Derrick
>
> "Russell Fields" <russellfields@.nomail.com> wrote in message
> news:eJddSQ60HHA.3788@.TK2MSFTNGP02.phx.gbl...
>> Derrick,
>> It is true: Parallelism does not alway help. In fact, for some queries it
>> may make them perform abysmally.
>> Although I do not do this personally, several posters recommend setting
>> an OLTP server to a maximum degree of parallelism of 1. They indicate
>> good success and few discernable problems because of the setting.
>> I do follow the guideline to limit the server's maximum degree of
>> parallelism to the number of physical chips, which in your case would be
>> 4. Then, if a query is troubled we can specifically run it at MAXDOP 1.
>> FWIW,
>> RLF
>> "Derrick" <derrick1298@.excite.com> wrote in message
>> news:%23E%23LO250HHA.5644@.TK2MSFTNGP05.phx.gbl...
>> We have a new server, 4 physical dual core processors, with
>> hyperthreading, so it shows up as 16 logical processors.
>> A simple query joining 3 tables, a distinct, an order by, with maxdop
>> set to 0, takes over 2 seconds. With maxdop set to 1, it takes 200
>> milliseconds. setting maxdop between 1 and 15, pretty linear time
>> progression.
>> Does this sound sane? Is there some magic matrix where under load a
>> higher maxdop will result in this simple query running faster than where
>> there is no load (the current case)
>> Thanks in advance!
>> Derrick
>>
>

Hyperthreading killing performance of simple query?

HYPER-THREADING configuration hints

Hi
We have a SQL 2000 ENTERPRISE, running on four Hyper-threaded processors, 8
GIG of Memory, Windows SERVER 2003, connected to EMC.
Does anybody have any general rules for configuration for such a server
(it's going to be OLTP) Should we set the affinity to only use the "REAL"
processors. Should we allow all processors to be used for parallelism or
just the "REAL" ones. Anything else we need to consider?
Right now during load testing we are seeing a lot of CXPACKET waits.
Thanks
Paul
Try setting your MAXDOP to use just 4 processors first and see how that
goes.
Andrew J. Kelly SQL MVP
"Paul" <xx@.nospam.com> wrote in message
news:%23AGSkbP0EHA.1264@.TK2MSFTNGP12.phx.gbl...
> Hi
> We have a SQL 2000 ENTERPRISE, running on four Hyper-threaded processors,
> 8
> GIG of Memory, Windows SERVER 2003, connected to EMC.
> Does anybody have any general rules for configuration for such a server
> (it's going to be OLTP) Should we set the affinity to only use the "REAL"
> processors. Should we allow all processors to be used for parallelism or
> just the "REAL" ones. Anything else we need to consider?
> Right now during load testing we are seeing a lot of CXPACKET waits.
> Thanks
> Paul
>
|||I have used the number of physical processors minus 1 as a stating point. In
you case I would start with 3 and work down from there, testing after each
change. Your mileage will vary based on the number of concurrent users and
the types of queries they are executing.
Rob
"Paul" wrote:

> Hi
> We have a SQL 2000 ENTERPRISE, running on four Hyper-threaded processors, 8
> GIG of Memory, Windows SERVER 2003, connected to EMC.
> Does anybody have any general rules for configuration for such a server
> (it's going to be OLTP) Should we set the affinity to only use the "REAL"
> processors. Should we allow all processors to be used for parallelism or
> just the "REAL" ones. Anything else we need to consider?
> Right now during load testing we are seeing a lot of CXPACKET waits.
> Thanks
> Paul
>
>

HYPER-THREADING configuration hints

Hi
We have a SQL 2000 ENTERPRISE, running on four Hyper-threaded processors, 8
GIG of Memory, Windows SERVER 2003, connected to EMC.
Does anybody have any general rules for configuration for such a server
(it's going to be OLTP) Should we set the affinity to only use the "REAL"
processors. Should we allow all processors to be used for parallelism or
just the "REAL" ones. Anything else we need to consider?
Right now during load testing we are seeing a lot of CXPACKET waits.
Thanks
PaulTry setting your MAXDOP to use just 4 processors first and see how that
goes.
Andrew J. Kelly SQL MVP
"Paul" <xx@.nospam.com> wrote in message
news:%23AGSkbP0EHA.1264@.TK2MSFTNGP12.phx.gbl...
> Hi
> We have a SQL 2000 ENTERPRISE, running on four Hyper-threaded processors,
> 8
> GIG of Memory, Windows SERVER 2003, connected to EMC.
> Does anybody have any general rules for configuration for such a server
> (it's going to be OLTP) Should we set the affinity to only use the "REAL"
> processors. Should we allow all processors to be used for parallelism or
> just the "REAL" ones. Anything else we need to consider?
> Right now during load testing we are seeing a lot of CXPACKET waits.
> Thanks
> Paul
>|||I have used the number of physical processors minus 1 as a stating point. In
you case I would start with 3 and work down from there, testing after each
change. Your mileage will vary based on the number of concurrent users and
the types of queries they are executing.
Rob
"Paul" wrote:

> Hi
> We have a SQL 2000 ENTERPRISE, running on four Hyper-threaded processors,
8
> GIG of Memory, Windows SERVER 2003, connected to EMC.
> Does anybody have any general rules for configuration for such a server
> (it's going to be OLTP) Should we set the affinity to only use the "REAL"
> processors. Should we allow all processors to be used for parallelism or
> just the "REAL" ones. Anything else we need to consider?
> Right now during load testing we are seeing a lot of CXPACKET waits.
> Thanks
> Paul
>
>

HYPER-THREADING configuration hints

Hi
We have a SQL 2000 ENTERPRISE, running on four Hyper-threaded processors, 8
GIG of Memory, Windows SERVER 2003, connected to EMC.
Does anybody have any general rules for configuration for such a server
(it's going to be OLTP) Should we set the affinity to only use the "REAL"
processors. Should we allow all processors to be used for parallelism or
just the "REAL" ones. Anything else we need to consider?
Right now during load testing we are seeing a lot of CXPACKET waits.
Thanks
PaulTry setting your MAXDOP to use just 4 processors first and see how that
goes.
--
Andrew J. Kelly SQL MVP
"Paul" <xx@.nospam.com> wrote in message
news:%23AGSkbP0EHA.1264@.TK2MSFTNGP12.phx.gbl...
> Hi
> We have a SQL 2000 ENTERPRISE, running on four Hyper-threaded processors,
> 8
> GIG of Memory, Windows SERVER 2003, connected to EMC.
> Does anybody have any general rules for configuration for such a server
> (it's going to be OLTP) Should we set the affinity to only use the "REAL"
> processors. Should we allow all processors to be used for parallelism or
> just the "REAL" ones. Anything else we need to consider?
> Right now during load testing we are seeing a lot of CXPACKET waits.
> Thanks
> Paul
>|||I have used the number of physical processors minus 1 as a stating point. In
you case I would start with 3 and work down from there, testing after each
change. Your mileage will vary based on the number of concurrent users and
the types of queries they are executing.
Rob
"Paul" wrote:
> Hi
> We have a SQL 2000 ENTERPRISE, running on four Hyper-threaded processors, 8
> GIG of Memory, Windows SERVER 2003, connected to EMC.
> Does anybody have any general rules for configuration for such a server
> (it's going to be OLTP) Should we set the affinity to only use the "REAL"
> processors. Should we allow all processors to be used for parallelism or
> just the "REAL" ones. Anything else we need to consider?
> Right now during load testing we are seeing a lot of CXPACKET waits.
> Thanks
> Paul
>
>

Hyperthreading

Hi,
We are using a quad Xeon with hyperthreading. Windows 2000 and SQL Server "see" 8 processors. We have scheduled SQL to only use CPUs 0,1,2,3. The server is a dedicated database server. Has anyone done much work with hyperthreading? Is our approach sensible?
Ken"Ken Ng" <anonymous@.discussions.microsoft.com> wrote in message
news:72043C98-B317-4CA2-A97D-36AC17A5ABA0@.microsoft.com...
> Hi,
> We are using a quad Xeon with hyperthreading. Windows 2000 and SQL Server
"see" 8 processors. We have scheduled SQL to only use CPUs 0,1,2,3. The
server is a dedicated database server. Has anyone done much work with
hyperthreading? Is our approach sensible?
>
This will essentially disable hyperthreading for SQL server since CPUs
0,1,2,3 are the first logical processesors on each chip. So the system will
run basically like a non-hyperthreading 4-way server.
But you should get better performance if you let SQL Server schedule threads
on all 8 logical processors. The point of HT is that scheduling 2 threads
on each physical processor allows a higher utilization of internal CPU
resources, and results in a higher throughput than switching between the 2
threads.
David|||i have not found anything in SQL Server that benefits from
HT in a useful manner.
however, HT and parallel execution plans may in certain
circumstances have potentially crippling effect.
i suggest that HT be disabled unless you have conducted a
reasonably comphrensive test on whether there are any ill
effects
>--Original Message--
>Hi,
>We are using a quad Xeon with hyperthreading. Windows
2000 and SQL Server "see" 8 processors. We have scheduled
SQL to only use CPUs 0,1,2,3. The server is a dedicated
database server. Has anyone done much work with
hyperthreading? Is our approach sensible?
>Ken
>.
>|||In my tests performance with HT switched ON was about 15%
WORSE than with HT switched OFF. Physical processor is a
physical processor and when SQL Server creates parallel
execution plan and is trying to run simultaneously two
subqueries on the same physical processor, it creates a
bottleneck.
Cheers,
Alex|||I have no evidence for this, but if parallellism is not used (for
example just OLTP), then I expect a HT system to perform 15% better than
the same system with HT disabled. If parallellism is used (sometimes),
then I guess it is better to turn off HT.
Gert-Jan
joe chang wrote:
> i have not found anything in SQL Server that benefits from
> HT in a useful manner.
> however, HT and parallel execution plans may in certain
> circumstances have potentially crippling effect.
> i suggest that HT be disabled unless you have conducted a
> reasonably comphrensive test on whether there are any ill
> effects
> >--Original Message--
> >Hi,
> >
> >We are using a quad Xeon with hyperthreading. Windows
> 2000 and SQL Server "see" 8 processors. We have scheduled
> SQL to only use CPUs 0,1,2,3. The server is a dedicated
> database server. Has anyone done much work with
> hyperthreading? Is our approach sensible?
> >
> >Ken
> >.
> >|||> This will essentially disable hyperthreading for SQL server since CPUs
> 0,1,2,3 are the first logical processesors on each chip. So the system will
> run basically like a non-hyperthreading 4-way server.
However, the OS can still use the other 4 logical processors.
--
Tibor Karaszi, SQL Server MVP
Archive at: http://groups.google.com/groups?oi=djq&as_ugroup=microsoft.public.sqlserver
"David Browne" <davidbaxterbrowne no potted meat@.hotmail.com> wrote in message
news:e1d$qQPuDHA.2448@.TK2MSFTNGP09.phx.gbl...
> "Ken Ng" <anonymous@.discussions.microsoft.com> wrote in message
> news:72043C98-B317-4CA2-A97D-36AC17A5ABA0@.microsoft.com...
> > Hi,
> >
> > We are using a quad Xeon with hyperthreading. Windows 2000 and SQL Server
> "see" 8 processors. We have scheduled SQL to only use CPUs 0,1,2,3. The
> server is a dedicated database server. Has anyone done much work with
> hyperthreading? Is our approach sensible?
> >
> This will essentially disable hyperthreading for SQL server since CPUs
> 0,1,2,3 are the first logical processesors on each chip. So the system will
> run basically like a non-hyperthreading 4-way server.
> But you should get better performance if you let SQL Server schedule threads
> on all 8 logical processors. The point of HT is that scheduling 2 threads
> on each physical processor allows a higher utilization of internal CPU
> resources, and results in a higher throughput than switching between the 2
> threads.
> David
>|||Thanks for the replies folks. From the discussion I deduce that HT may not be that beneficial for SQL per se. In our case, by limiting SQL to CPU 0,1,2,3 we seem to be disabling HT for SQL but enabling the extra 4 (logical) processors i.e. CPU 4,5,6,7 to be used by the o/s. This seems to be a reasonable approach
Many Thank
Ken Ng

Hyperthreading

Hi,
I have a 4 processor server with hyperthreading enabled. The
processors show up in SQL as Processors 0-7. My question is, which numbers
are physical processors and which numbers are the virtual/hyperthreaded
processors? The reason I want to know is that I want to take away 1 physical
and 1 virtual processor from the processors that SQL is allowed to use.
Thanks,
ScottThe firmware/hardware manufacturers are recommended by Intel to make it like following:
Phy0 = Log0
Phy1 = Log1
Phy2 = Log2
Phy3 = Log3
Phy0 = Log4
Phy1 = Log5
Phy2 = Log6
Phy3 = Log7
--
Tibor Karaszi, SQL Server MVP
http://www.karaszi.com/sqlserver/default.asp
http://www.solidqualitylearning.com/
Blog: http://solidqualitylearning.com/blogs/tibor/
"Scott" <Scott@.discussions.microsoft.com> wrote in message
news:9095D9D1-FE9A-4536-8BA7-96FF93634660@.microsoft.com...
> Hi,
> I have a 4 processor server with hyperthreading enabled. The
> processors show up in SQL as Processors 0-7. My question is, which numbers
> are physical processors and which numbers are the virtual/hyperthreaded
> processors? The reason I want to know is that I want to take away 1 physical
> and 1 virtual processor from the processors that SQL is allowed to use.
> Thanks,
> Scott|||"Tibor Karaszi" <tibor_please.no.email_karaszi@.hotmail.nomail.com> wrote in
message news:eE9lDgcmFHA.3544@.TK2MSFTNGP15.phx.gbl...
> The firmware/hardware manufacturers are recommended by Intel to make it
> like following:
> Phy0 = Log0
> Phy1 = Log1
> Phy2 = Log2
> Phy3 = Log3
> Phy0 = Log4
> Phy1 = Log5
> Phy2 = Log6
> Phy3 = Log7
>
So if I am reading this correctly, if I wanted to remove the 4th processor
(both physical and hyperthreaded), I would remove the Log3 and Log7...
Rick Sawtell|||So, 0-3 are physical processors and 4-7 are virtual/hyperthreaded?
"Tibor Karaszi" wrote:
> The firmware/hardware manufacturers are recommended by Intel to make it like following:
> Phy0 = Log0
> Phy1 = Log1
> Phy2 = Log2
> Phy3 = Log3
> Phy0 = Log4
> Phy1 = Log5
> Phy2 = Log6
> Phy3 = Log7
> --
> Tibor Karaszi, SQL Server MVP
> http://www.karaszi.com/sqlserver/default.asp
> http://www.solidqualitylearning.com/
> Blog: http://solidqualitylearning.com/blogs/tibor/
>
> "Scott" <Scott@.discussions.microsoft.com> wrote in message
> news:9095D9D1-FE9A-4536-8BA7-96FF93634660@.microsoft.com...
> > Hi,
> > I have a 4 processor server with hyperthreading enabled. The
> > processors show up in SQL as Processors 0-7. My question is, which numbers
> > are physical processors and which numbers are the virtual/hyperthreaded
> > processors? The reason I want to know is that I want to take away 1 physical
> > and 1 virtual processor from the processors that SQL is allowed to use.
> >
> > Thanks,
> > Scott
>|||> So if I am reading this correctly, if I wanted to remove the 4th processor (both physical and
> hyperthreaded), I would remove the Log3 and Log7...
Yep.
--
Tibor Karaszi, SQL Server MVP
http://www.karaszi.com/sqlserver/default.asp
http://www.solidqualitylearning.com/
Blog: http://solidqualitylearning.com/blogs/tibor/
"Rick Sawtell" <r_sawtell@.hotmail.com> wrote in message
news:ejUJKjcmFHA.3336@.tk2msftngp13.phx.gbl...
> "Tibor Karaszi" <tibor_please.no.email_karaszi@.hotmail.nomail.com> wrote in message
> news:eE9lDgcmFHA.3544@.TK2MSFTNGP15.phx.gbl...
>> The firmware/hardware manufacturers are recommended by Intel to make it like following:
>> Phy0 = Log0
>> Phy1 = Log1
>> Phy2 = Log2
>> Phy3 = Log3
>> Phy0 = Log4
>> Phy1 = Log5
>> Phy2 = Log6
>> Phy3 = Log7
>>
> So if I am reading this correctly, if I wanted to remove the 4th processor (both physical and
> hyperthreaded), I would remove the Log3 and Log7...
>
> Rick Sawtell
>|||I'm not sure that you refer to the two logical processors on one physical processor as
"virtual/hyperthreader" vs "physical". But, yes, you get the idea.
--
Tibor Karaszi, SQL Server MVP
http://www.karaszi.com/sqlserver/default.asp
http://www.solidqualitylearning.com/
Blog: http://solidqualitylearning.com/blogs/tibor/
"Scott" <Scott@.discussions.microsoft.com> wrote in message
news:0B568019-6053-43F8-8B35-D79FBEF32C9D@.microsoft.com...
> So, 0-3 are physical processors and 4-7 are virtual/hyperthreaded?
>
> "Tibor Karaszi" wrote:
>> The firmware/hardware manufacturers are recommended by Intel to make it like following:
>> Phy0 = Log0
>> Phy1 = Log1
>> Phy2 = Log2
>> Phy3 = Log3
>> Phy0 = Log4
>> Phy1 = Log5
>> Phy2 = Log6
>> Phy3 = Log7
>> --
>> Tibor Karaszi, SQL Server MVP
>> http://www.karaszi.com/sqlserver/default.asp
>> http://www.solidqualitylearning.com/
>> Blog: http://solidqualitylearning.com/blogs/tibor/
>>
>> "Scott" <Scott@.discussions.microsoft.com> wrote in message
>> news:9095D9D1-FE9A-4536-8BA7-96FF93634660@.microsoft.com...
>> > Hi,
>> > I have a 4 processor server with hyperthreading enabled. The
>> > processors show up in SQL as Processors 0-7. My question is, which numbers
>> > are physical processors and which numbers are the virtual/hyperthreaded
>> > processors? The reason I want to know is that I want to take away 1 physical
>> > and 1 virtual processor from the processors that SQL is allowed to use.
>> >
>> > Thanks,
>> > Scott
>>|||Actually even though they suggest that there are several variations. There
is a utility on Intel's web site (somewhere<g>) that will supposedly show
you the layout for that particular configuration.
--
Andrew J. Kelly SQL MVP
"Tibor Karaszi" <tibor_please.no.email_karaszi@.hotmail.nomail.com> wrote in
message news:eE9lDgcmFHA.3544@.TK2MSFTNGP15.phx.gbl...
> The firmware/hardware manufacturers are recommended by Intel to make it
> like following:
> Phy0 = Log0
> Phy1 = Log1
> Phy2 = Log2
> Phy3 = Log3
> Phy0 = Log4
> Phy1 = Log5
> Phy2 = Log6
> Phy3 = Log7
> --
> Tibor Karaszi, SQL Server MVP
> http://www.karaszi.com/sqlserver/default.asp
> http://www.solidqualitylearning.com/
> Blog: http://solidqualitylearning.com/blogs/tibor/
>
> "Scott" <Scott@.discussions.microsoft.com> wrote in message
> news:9095D9D1-FE9A-4536-8BA7-96FF93634660@.microsoft.com...
>> Hi,
>> I have a 4 processor server with hyperthreading enabled. The
>> processors show up in SQL as Processors 0-7. My question is, which
>> numbers
>> are physical processors and which numbers are the virtual/hyperthreaded
>> processors? The reason I want to know is that I want to take away 1
>> physical
>> and 1 virtual processor from the processors that SQL is allowed to use.
>> Thanks,
>> Scott
>

hyperthreaded processors running on win2k

My company is currently deploying new hardware for our new hosting site. We
have all new servers. 4 of them are running Win2k standard server and are
web servers, and 3 of them are win2k advanced servers running SQL Server
2000.
These servers have dual Xeons, so if hyperthreading is on, win2k sees 4
procs.
We have been working on tracking down speed issues for quite a while and
recently realized (by accident) , that the webservers run WAY faster when
hyperthreading is turned off. We are using MS Application Center Test for
load testing, so that's how we determined the performance gain.
I've been trying to find a clear cut answer about whether or not you should
use hyperthreading on win2k server, but I haven't found one. Although I have
seen several references to this issue and seen posts of people saying to
shut if off. It seems win2k doesn't know the difference between logical and
physical processors, so maybe that's why it's not good for win2k. ?
Does anyone know where I could find more info on this? We're going to turn
off hyperthreading on the webservers obviously because they perform better,
but I'm wondering if we will see performance gains by also shutting of
hyperthreading on the win2k SQL Servers. ?
Any insight into this would be great.
Thanks.
Personally, I have had fairly good experience with Hyperthreading. First,
make sure you are on build 816 or later. There were some significant
HT-friendly modifications in that build. The easiest way is to download the
818 security hotfix and apply it. That way, you do not have to open a case
to get it. Regardless, you must be on SP2 or higher to get SQL to count the
processors correctly for licensing purposes.
Finally, 2 virtual HT processors run about 20-30% faster using SQL than the
same processer set to non HT. SQL still counts them as full processors for
parallelism, meaning that you can over-parallel a query and drag system
performance down. I manually set MAX DEGREE OF PARALLELISM (MAXDOP) to no
higher than the actual physical processor count.
Geoff N. Hiten
Microsoft SQL Server MVP
Senior Database Administrator
Careerbuilder.com
I support the Professional Association for SQL Server
www.sqlpass.org
"Mark" <maxmann@.kc.rr.com> wrote in message
news:uyOJwARJEHA.1312@.TK2MSFTNGP12.phx.gbl...
> My company is currently deploying new hardware for our new hosting site.
We
> have all new servers. 4 of them are running Win2k standard server and are
> web servers, and 3 of them are win2k advanced servers running SQL Server
> 2000.
> These servers have dual Xeons, so if hyperthreading is on, win2k sees 4
> procs.
> We have been working on tracking down speed issues for quite a while and
> recently realized (by accident) , that the webservers run WAY faster when
> hyperthreading is turned off. We are using MS Application Center Test for
> load testing, so that's how we determined the performance gain.
> I've been trying to find a clear cut answer about whether or not you
should
> use hyperthreading on win2k server, but I haven't found one. Although I
have
> seen several references to this issue and seen posts of people saying to
> shut if off. It seems win2k doesn't know the difference between logical
and
> physical processors, so maybe that's why it's not good for win2k. ?
> Does anyone know where I could find more info on this? We're going to
turn
> off hyperthreading on the webservers obviously because they perform
better,
> but I'm wondering if we will see performance gains by also shutting of
> hyperthreading on the win2k SQL Servers. ?
>
> Any insight into this would be great.
> Thanks.
>

hyperthreaded processors running on win2k

My company is currently deploying new hardware for our new hosting site. We
have all new servers. 4 of them are running Win2k standard server and are
web servers, and 3 of them are win2k advanced servers running SQL Server
2000.
These servers have dual Xeons, so if hyperthreading is on, win2k sees 4
procs.
We have been working on tracking down speed issues for quite a while and
recently realized (by accident) , that the webservers run WAY faster when
hyperthreading is turned off. We are using MS Application Center Test for
load testing, so that's how we determined the performance gain.
I've been trying to find a clear cut answer about whether or not you should
use hyperthreading on win2k server, but I haven't found one. Although I have
seen several references to this issue and seen posts of people saying to
shut if off. It seems win2k doesn't know the difference between logical and
physical processors, so maybe that's why it's not good for win2k. ?
Does anyone know where I could find more info on this? We're going to turn
off hyperthreading on the webservers obviously because they perform better,
but I'm wondering if we will see performance gains by also shutting of
hyperthreading on the win2k SQL Servers. ?
Any insight into this would be great.
Thanks.Personally, I have had fairly good experience with Hyperthreading. First,
make sure you are on build 816 or later. There were some significant
HT-friendly modifications in that build. The easiest way is to download the
818 security hotfix and apply it. That way, you do not have to open a case
to get it. Regardless, you must be on SP2 or higher to get SQL to count the
processors correctly for licensing purposes.
Finally, 2 virtual HT processors run about 20-30% faster using SQL than the
same processer set to non HT. SQL still counts them as full processors for
parallelism, meaning that you can over-parallel a query and drag system
performance down. I manually set MAX DEGREE OF PARALLELISM (MAXDOP) to no
higher than the actual physical processor count.
--
Geoff N. Hiten
Microsoft SQL Server MVP
Senior Database Administrator
Careerbuilder.com
I support the Professional Association for SQL Server
www.sqlpass.org
"Mark" <maxmann@.kc.rr.com> wrote in message
news:uyOJwARJEHA.1312@.TK2MSFTNGP12.phx.gbl...
> My company is currently deploying new hardware for our new hosting site.
We
> have all new servers. 4 of them are running Win2k standard server and are
> web servers, and 3 of them are win2k advanced servers running SQL Server
> 2000.
> These servers have dual Xeons, so if hyperthreading is on, win2k sees 4
> procs.
> We have been working on tracking down speed issues for quite a while and
> recently realized (by accident) , that the webservers run WAY faster when
> hyperthreading is turned off. We are using MS Application Center Test for
> load testing, so that's how we determined the performance gain.
> I've been trying to find a clear cut answer about whether or not you
should
> use hyperthreading on win2k server, but I haven't found one. Although I
have
> seen several references to this issue and seen posts of people saying to
> shut if off. It seems win2k doesn't know the difference between logical
and
> physical processors, so maybe that's why it's not good for win2k. ?
> Does anyone know where I could find more info on this? We're going to
turn
> off hyperthreading on the webservers obviously because they perform
better,
> but I'm wondering if we will see performance gains by also shutting of
> hyperthreading on the win2k SQL Servers. ?
>
> Any insight into this would be great.
> Thanks.
>

hyperthreaded processors running on win2k

My company is currently deploying new hardware for our new hosting site. We
have all new servers. 4 of them are running Win2k standard server and are
web servers, and 3 of them are win2k advanced servers running SQL Server
2000.
These servers have dual Xeons, so if hyperthreading is on, win2k sees 4
procs.
We have been working on tracking down speed issues for quite a while and
recently realized (by accident) , that the webservers run WAY faster when
hyperthreading is turned off. We are using MS Application Center Test for
load testing, so that's how we determined the performance gain.
I've been trying to find a clear cut answer about whether or not you should
use hyperthreading on win2k server, but I haven't found one. Although I have
seen several references to this issue and seen posts of people saying to
shut if off. It seems win2k doesn't know the difference between logical and
physical processors, so maybe that's why it's not good for win2k. ?
Does anyone know where I could find more info on this? We're going to turn
off hyperthreading on the webservers obviously because they perform better,
but I'm wondering if we will see performance gains by also shutting of
hyperthreading on the win2k SQL Servers. ?
Any insight into this would be great.
Thanks.Personally, I have had fairly good experience with Hyperthreading. First,
make sure you are on build 816 or later. There were some significant
HT-friendly modifications in that build. The easiest way is to download the
818 security hotfix and apply it. That way, you do not have to open a case
to get it. Regardless, you must be on SP2 or higher to get SQL to count the
processors correctly for licensing purposes.
Finally, 2 virtual HT processors run about 20-30% faster using SQL than the
same processer set to non HT. SQL still counts them as full processors for
parallelism, meaning that you can over-parallel a query and drag system
performance down. I manually set MAX degree OF PARALLELISM (MAXDOP) to no
higher than the actual physical processor count.
Geoff N. Hiten
Microsoft SQL Server MVP
Senior Database Administrator
Careerbuilder.com
I support the Professional Association for SQL Server
www.sqlpass.org
"Mark" <maxmann@.kc.rr.com> wrote in message
news:uyOJwARJEHA.1312@.TK2MSFTNGP12.phx.gbl...
> My company is currently deploying new hardware for our new hosting site.
We
> have all new servers. 4 of them are running Win2k standard server and are
> web servers, and 3 of them are win2k advanced servers running SQL Server
> 2000.
> These servers have dual Xeons, so if hyperthreading is on, win2k sees 4
> procs.
> We have been working on tracking down speed issues for quite a while and
> recently realized (by accident) , that the webservers run WAY faster when
> hyperthreading is turned off. We are using MS Application Center Test for
> load testing, so that's how we determined the performance gain.
> I've been trying to find a clear cut answer about whether or not you
should
> use hyperthreading on win2k server, but I haven't found one. Although I
have
> seen several references to this issue and seen posts of people saying to
> shut if off. It seems win2k doesn't know the difference between logical
and
> physical processors, so maybe that's why it's not good for win2k. ?
> Does anyone know where I could find more info on this? We're going to
turn
> off hyperthreading on the webservers obviously because they perform
better,
> but I'm wondering if we will see performance gains by also shutting of
> hyperthreading on the win2k SQL Servers. ?
>
> Any insight into this would be great.
> Thanks.
>

Sunday, February 19, 2012

Hyper Threading - Good or Bad?

Ello,

We have quite a few SQL Servers running on servers with hyper threaded enabled processors. We have always left hyper threading on, even on our very busy servers but i've recently begun to question this due to comments i have received.

All our servers run SQL 2000 SP3a as "support" for hyper threading was added in SP3a

So... What do you think of Hyper Threading any why?Never had the need...I'll have to read up on this....|||OK, I'll go with gimicky

www.microsoft.com/sql/howtobuy/SQLonHTT.doc

Just scale the box|||Thanks Brett.

It will be good to compare notes, my hunt for information has not found much for or against yet although when trouble shooting we are now always advised to turn it off...

This link to a newgroup article raised my eyebrow
News Group (http://groups.google.co.uk/group/microsoft.public.sqlserver.server/browse_frm/thread/99860c74db9d183/af9e69650569f1db?lnk=st&q=hyper+threading+%2B+SQL+performance&rnum=2&hl=en#af9e69650569f1db)

Quoting a MVP from the link he says

The problem with a HT CPU that the 2 simultaneous threads running on the CPU both contend for the *same* L1, L2 and L3 processor cache. During heavy processing, you may actually have the 2 clearing each other's cache. This results in each having to go to main system RAM to work.

But read the whole thing for context as he also talks about parallelism|||Yes i read that but the other post has spurred me on to get the internet shovel out and keep hunting for more information and post for peoples experiences.

:D|||I have been told that Windows Server 2003 has better support for Hyperthreading. If you can, get your SQL Servers running on 2003, and all should be well. We have had no problems on 2003, or 2000, though.

Hyper Threading

Hi All,
Does anyone know if there are any issues with HT processors and either SQL
2000 or MSDE 2000?
Thanks
I've never heard of any or seen any myself (and we've been running SQL
2000 instances on hyper-threaded CPUs for some time). Admittedly we
don't play with MSDE but it's the same code-base.
I think at that level it's the OS implementation that may or may not
have issues, not the app server (i.e. SQL Server). SQL Server just
presents the work for a specific logical processor to the O/S kernel to
deal with.
*mike hodgson* |/ database administrator/ | mallesons stephen jaques
*T* +61 (2) 9296 3668 |* F* +61 (2) 9296 3885 |* M* +61 (408) 675 907
*E* mailto:mike.hodgson@.mallesons.nospam.com |* W* http://www.mallesons.com
Jason Fischer wrote:

>Hi All,
>Does anyone know if there are any issues with HT processors and either SQL
>2000 or MSDE 2000?
>Thanks
>
>
|||Hi Mike,
I had just read a whole lot of things saying that you should set your SQL Server up for the number of Physical processors and not logical.
Thanks
"Mike Hodgson" <mike.hodgson@.mallesons.nospam.com> wrote in message news:OvIdEUUdFHA.3808@.TK2MSFTNGP14.phx.gbl...
I've never heard of any or seen any myself (and we've been running SQL 2000 instances on hyper-threaded CPUs for some time). Admittedly we don't play with MSDE but it's the same code-base.
I think at that level it's the OS implementation that may or may not have issues, not the app server (i.e. SQL Server). SQL Server just presents the work for a specific logical processor to the O/S kernel to deal with.
mike hodgson | database administrator | mallesons stephen jaques
T +61 (2) 9296 3668 | F +61 (2) 9296 3885 | M +61 (408) 675 907
E mailto:mike.hodgson@.mallesons.nospam.com | W http://www.mallesons.com
Jason Fischer wrote:
Hi All,
Does anyone know if there are any issues with HT processors and either SQL
2000 or MSDE 2000?
Thanks
|||Interesting. Did those things you read say why? Were they referring to
processor affinity, licensing or something else? (We've been running a
couple clusters on dual-proc hyper-threaded Xeon boxes (showing 4
logical procs) for some time with no processor related problems that I'm
aware of.)
*mike hodgson* |/ database administrator/ | mallesons stephen jaques
*T* +61 (2) 9296 3668 |* F* +61 (2) 9296 3885 |* M* +61 (408) 675 907
*E* mailto:mike.hodgson@.mallesons.nospam.com |* W* http://www.mallesons.com
Jason Fischer wrote:
[vbcol=seagreen]
> Hi Mike,
> I had just read a whole lot of things saying that you should set your
> SQL Server up for the number of Physical processors and not logical.
> Thanks
>
> "Mike Hodgson" <mike.hodgson@.mallesons.nospam.com
> <mailto:mike.hodgson@.mallesons.nospam.com>> wrote in message
> news:OvIdEUUdFHA.3808@.TK2MSFTNGP14.phx.gbl...
> I've never heard of any or seen any myself (and we've been running
> SQL 2000 instances on hyper-threaded CPUs for some time).
> Admittedly we don't play with MSDE but it's the same code-base.
> I think at that level it's the OS implementation that may or may
> not have issues, not the app server (i.e. SQL Server). SQL Server
> just presents the work for a specific logical processor to the O/S
> kernel to deal with.
> --
> *mike hodgson* |/ database administrator/ | mallesons stephen jaques
> *T* +61 (2) 9296 3668 |* F* +61 (2) 9296 3885 |* M* +61 (408) 675 907
> *E* mailto:mike.hodgson@.mallesons.nospam.com |* W*
> http://www.mallesons.com
>
> Jason Fischer wrote:
|||Hi Mike,
The articles mentioned something about L2, L3 chace being overwritten due to HT causing a slow down instead of an increase in spead. The SQL statements just take longer, the moment they set SQL Server to just use the number of Physical processors, everything goes back to normal.
I will try and find the articles again and post the links, but will be away from a PC for 2 weeks, so it might be a while before I post again.
Thanks
"Mike Hodgson" <mike.hodgson@.mallesons.nospam.com> wrote in message news:eg0xCTfdFHA.3032@.TK2MSFTNGP10.phx.gbl...
Interesting. Did those things you read say why? Were they referring to processor affinity, licensing or something else? (We've been running a couple clusters on dual-proc hyper-threaded Xeon boxes (showing 4 logical procs) for some time with no processor related problems that I'm aware of.)
mike hodgson | database administrator | mallesons stephen jaques
T +61 (2) 9296 3668 | F +61 (2) 9296 3885 | M +61 (408) 675 907
E mailto:mike.hodgson@.mallesons.nospam.com | W http://www.mallesons.com
Jason Fischer wrote:
Hi Mike,
I had just read a whole lot of things saying that you should set your SQL Server up for the number of Physical processors and not logical.
Thanks
"Mike Hodgson" <mike.hodgson@.mallesons.nospam.com> wrote in message news:OvIdEUUdFHA.3808@.TK2MSFTNGP14.phx.gbl...
I've never heard of any or seen any myself (and we've been running SQL 2000 instances on hyper-threaded CPUs for some time). Admittedly we don't play with MSDE but it's the same code-base.
I think at that level it's the OS implementation that may or may not have issues, not the app server (i.e. SQL Server). SQL Server just presents the work for a specific logical processor to the O/S kernel to deal with.
mike hodgson | database administrator | mallesons stephen jaques
T +61 (2) 9296 3668 | F +61 (2) 9296 3885 | M +61 (408) 675 907
E mailto:mike.hodgson@.mallesons.nospam.com | W http://www.mallesons.com
Jason Fischer wrote:
Hi All,
Does anyone know if there are any issues with HT processors and either SQL
2000 or MSDE 2000?
Thanks

Hyper Threading

Hi All,
Does anyone know if there are any issues with HT processors and either SQL
2000 or MSDE 2000?
ThanksI've never heard of any or seen any myself (and we've been running SQL
2000 instances on hyper-threaded CPUs for some time). Admittedly we
don't play with MSDE but it's the same code-base.
I think at that level it's the OS implementation that may or may not
have issues, not the app server (i.e. SQL Server). SQL Server just
presents the work for a specific logical processor to the O/S kernel to
deal with.
*mike hodgson* |/ database administrator/ | mallesons stephen jaques
*T* +61 (2) 9296 3668 |* F* +61 (2) 9296 3885 |* M* +61 (408) 675 907
*E* mailto:mike.hodgson@.mallesons.nospam.com |* W* http://www.mallesons.com
Jason Fischer wrote:

>Hi All,
>Does anyone know if there are any issues with HT processors and either SQL
>2000 or MSDE 2000?
>Thanks
>
>|||Hi Mike,
I had just read a whole lot of things saying that you should set your SQL Se
rver up for the number of Physical processors and not logical.
Thanks
"Mike Hodgson" <mike.hodgson@.mallesons.nospam.com> wrote in message news:OvI
dEUUdFHA.3808@.TK2MSFTNGP14.phx.gbl...
I've never heard of any or seen any myself (and we've been running SQL 2000
instances on hyper-threaded CPUs for some time). Admittedly we don't play w
ith MSDE but it's the same code-base.
I think at that level it's the OS implementation that may or may not have is
sues, not the app server (i.e. SQL Server). SQL Server just presents the wo
rk for a specific logical processor to the O/S kernel to deal with.
mike hodgson | database administrator | mallesons stephen jaques
T +61 (2) 9296 3668 | F +61 (2) 9296 3885 | M +61 (408) 675 907
E mailto:mike.hodgson@.mallesons.nospam.com | W http://www.mallesons.com
Jason Fischer wrote:
Hi All,
Does anyone know if there are any issues with HT processors and either SQL
2000 or MSDE 2000?
Thanks|||Interesting. Did those things you read say why? Were they referring to
processor affinity, licensing or something else? (We've been running a
couple clusters on dual-proc hyper-threaded Xeon boxes (showing 4
logical procs) for some time with no processor related problems that I'm
aware of.)
*mike hodgson* |/ database administrator/ | mallesons stephen jaques
*T* +61 (2) 9296 3668 |* F* +61 (2) 9296 3885 |* M* +61 (408) 675 907
*E* mailto:mike.hodgson@.mallesons.nospam.com |* W* http://www.mallesons.com
Jason Fischer wrote:
[vbcol=seagreen]
> Hi Mike,
> I had just read a whole lot of things saying that you should set your
> SQL Server up for the number of Physical processors and not logical.
> Thanks
>
> "Mike Hodgson" <mike.hodgson@.mallesons.nospam.com
> <mailto:mike.hodgson@.mallesons.nospam.com>> wrote in message
> news:OvIdEUUdFHA.3808@.TK2MSFTNGP14.phx.gbl...
> I've never heard of any or seen any myself (and we've been running
> SQL 2000 instances on hyper-threaded CPUs for some time).
> Admittedly we don't play with MSDE but it's the same code-base.
> I think at that level it's the OS implementation that may or may
> not have issues, not the app server (i.e. SQL Server). SQL Server
> just presents the work for a specific logical processor to the O/S
> kernel to deal with.
> --
> *mike hodgson* |/ database administrator/ | mallesons stephen jaques
> *T* +61 (2) 9296 3668 |* F* +61 (2) 9296 3885 |* M* +61 (408) 675 907
> *E* mailto:mike.hodgson@.mallesons.nospam.com |* W*
> http://www.mallesons.com
>
> Jason Fischer wrote:
>|||Hi Mike,
The articles mentioned something about L2, L3 chace being overwritten due to
HT causing a slow down instead of an increase in spead. The SQL statements
just take longer, the moment they set SQL Server to just use the number of P
hysical processors, everything goes back to normal.
I will try and find the articles again and post the links, but will be away
from a PC for 2 weeks, so it might be a while before I post again.
Thanks
"Mike Hodgson" <mike.hodgson@.mallesons.nospam.com> wrote in message news:eg0
xCTfdFHA.3032@.TK2MSFTNGP10.phx.gbl...
Interesting. Did those things you read say why? Were they referring to pro
cessor affinity, licensing or something else? (We've been running a couple
clusters on dual-proc hyper-threaded Xeon boxes (showing 4 logical procs) fo
r some time with no processor related problems that I'm aware of.)
mike hodgson | database administrator | mallesons stephen jaques
T +61 (2) 9296 3668 | F +61 (2) 9296 3885 | M +61 (408) 675 907
E mailto:mike.hodgson@.mallesons.nospam.com | W http://www.mallesons.com
Jason Fischer wrote:
Hi Mike,
I had just read a whole lot of things saying that you should set your SQL Se
rver up for the number of Physical processors and not logical.
Thanks
"Mike Hodgson" <mike.hodgson@.mallesons.nospam.com> wrote in message news:OvI
dEUUdFHA.3808@.TK2MSFTNGP14.phx.gbl...
I've never heard of any or seen any myself (and we've been running SQL 2000
instances on hyper-threaded CPUs for some time). Admittedly we don't play w
ith MSDE but it's the same code-base.
I think at that level it's the OS implementation that may or may not have is
sues, not the app server (i.e. SQL Server). SQL Server just presents the wo
rk for a specific logical processor to the O/S kernel to deal with.
mike hodgson | database administrator | mallesons stephen jaques
T +61 (2) 9296 3668 | F +61 (2) 9296 3885 | M +61 (408) 675 907
E mailto:mike.hodgson@.mallesons.nospam.com | W http://www.mallesons.com
Jason Fischer wrote:
Hi All,
Does anyone know if there are any issues with HT processors and either SQL
2000 or MSDE 2000?
Thanks

Hyper Threading

Hi All,
Does anyone know if there are any issues with HT processors and either SQL
2000 or MSDE 2000?
ThanksThis is a multi-part message in MIME format.
--080700010501060407070309
Content-Type: text/plain; charset=ISO-8859-1; format=flowed
Content-Transfer-Encoding: 7bit
I've never heard of any or seen any myself (and we've been running SQL
2000 instances on hyper-threaded CPUs for some time). Admittedly we
don't play with MSDE but it's the same code-base.
I think at that level it's the OS implementation that may or may not
have issues, not the app server (i.e. SQL Server). SQL Server just
presents the work for a specific logical processor to the O/S kernel to
deal with.
--
*mike hodgson* |/ database administrator/ | mallesons stephen jaques
*T* +61 (2) 9296 3668 |* F* +61 (2) 9296 3885 |* M* +61 (408) 675 907
*E* mailto:mike.hodgson@.mallesons.nospam.com |* W* http://www.mallesons.com
Jason Fischer wrote:
>Hi All,
>Does anyone know if there are any issues with HT processors and either SQL
>2000 or MSDE 2000?
>Thanks
>
>
--080700010501060407070309
Content-Type: text/html; charset=ISO-8859-1
Content-Transfer-Encoding: 7bit
<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN">
<html>
<head>
<meta content="text/html;charset=ISO-8859-1" http-equiv="Content-Type">
<title></title>
</head>
<body bgcolor="#ffffff" text="#000000">
<tt>I've never heard of any or seen any myself (and we've been running
SQL 2000 instances on hyper-threaded CPUs for some time). Admittedly
we don't play with MSDE but it's the same code-base. 
 
I think at that level it's the OS implementation that may or may not
have issues, not the app server (i.e. SQL Server). SQL Server just
presents the work for a specific logical processor to the O/S kernel to
deal with. 
</tt>
<div class="moz-signature">
<title></title>
<meta http-equiv="Content-Type" content="text/html; ">
-- 
 mike
hodgson | database administrator
| mallesons stephen jaques 
T +61 (2) 9296 3668 | F +61
(2) 9296 3885 | M +61
(408) 675 907 
E
<a href="http://links.10026.com/?link=mailto:mike.hodgson@.mallesons.nospam.com">
mailto:mike.hodgson@.mallesons.nospam.com</a> | W <a href="http://links.10026.com/?link=/">http://www.mallesons.com">
http://www.mallesons.com</a> 
</div>
 
 
Jason Fischer wrote:
<blockquote cite="mideHTk3GUdFHA.3184@.TK2MSFTNGP15.phx.gbl" type="cite">
<pre wrap="">Hi All,
Does anyone know if there are any issues with HT processors and either SQL
2000 or MSDE 2000?
Thanks
</pre>
</blockquote>
</body>
</html>
--080700010501060407070309--|||This is a multi-part message in MIME format.
--=_NextPart_000_0008_01C57634.DCC06360
Content-Type: text/plain;
charset="iso-8859-1"
Content-Transfer-Encoding: quoted-printable
Hi Mike,
I had just read a whole lot of things saying that you should set your =SQL Server up for the number of Physical processors and not logical.
Thanks
"Mike Hodgson" <mike.hodgson@.mallesons.nospam.com> wrote in message =news:OvIdEUUdFHA.3808@.TK2MSFTNGP14.phx.gbl...
I've never heard of any or seen any myself (and we've been running SQL =2000 instances on hyper-threaded CPUs for some time). Admittedly we =don't play with MSDE but it's the same code-base.
I think at that level it's the OS implementation that may or may not =have issues, not the app server (i.e. SQL Server). SQL Server just =presents the work for a specific logical processor to the O/S kernel to =deal with.
--
mike hodgson | database administrator | mallesons stephen jaques
T +61 (2) 9296 3668 | F +61 (2) 9296 3885 | M +61 (408) 675 907
E mailto:mike.hodgson@.mallesons.nospam.com | W =http://www.mallesons.com=20
Jason Fischer wrote: Hi All,
Does anyone know if there are any issues with HT processors and either =SQL 2000 or MSDE 2000?
Thanks
--=_NextPart_000_0008_01C57634.DCC06360
Content-Type: text/html;
charset="iso-8859-1"
Content-Transfer-Encoding: quoted-printable
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN">
&

Hi Mike,
I had just read a whole lot of things =saying that you should set your SQL Server up for the number of Physical processors =and not logical.
Thanks
"Mike Hodgson" wrote in message news:OvIdEUUdFHA.3808=@.TK2MSFTNGP14.phx.gbl...I've never heard of any or seen any myself (and we've been running SQL 2000 = instances on hyper-threaded CPUs for some time). Admittedly we =don't play with MSDE but it's the same code-base.I think at that =level it's the OS implementation that may or may not have issues, not the app =server (i.e. SQL Server). SQL Server just presents the work for a =specific logical processor to the O/S kernel to deal with.
--mike =hodgson | database =administrator | mallesons =stephen jaquesT +61 (2) 9296 3668 | F +61 (2) 9296 3885 | M +61 (408) 675 907E mailto:mike.hodgson@.mal=lesons.nospam.com | W http://www.mallesons.com Jason Fischer wrote: Hi All,
Does anyone know if there are any issues with HT processors and either =SQL 2000 or MSDE 2000?
Thanks

--=_NextPart_000_0008_01C57634.DCC06360--|||This is a multi-part message in MIME format.
--020104030608090806080107
Content-Type: text/plain; charset=ISO-8859-1; format=flowed
Content-Transfer-Encoding: 7bit
Interesting. Did those things you read say why? Were they referring to
processor affinity, licensing or something else? (We've been running a
couple clusters on dual-proc hyper-threaded Xeon boxes (showing 4
logical procs) for some time with no processor related problems that I'm
aware of.)
--
*mike hodgson* |/ database administrator/ | mallesons stephen jaques
*T* +61 (2) 9296 3668 |* F* +61 (2) 9296 3885 |* M* +61 (408) 675 907
*E* mailto:mike.hodgson@.mallesons.nospam.com |* W* http://www.mallesons.com
Jason Fischer wrote:
> Hi Mike,
> I had just read a whole lot of things saying that you should set your
> SQL Server up for the number of Physical processors and not logical.
> Thanks
>
> "Mike Hodgson" <mike.hodgson@.mallesons.nospam.com
> <mailto:mike.hodgson@.mallesons.nospam.com>> wrote in message
> news:OvIdEUUdFHA.3808@.TK2MSFTNGP14.phx.gbl...
> I've never heard of any or seen any myself (and we've been running
> SQL 2000 instances on hyper-threaded CPUs for some time).
> Admittedly we don't play with MSDE but it's the same code-base.
> I think at that level it's the OS implementation that may or may
> not have issues, not the app server (i.e. SQL Server). SQL Server
> just presents the work for a specific logical processor to the O/S
> kernel to deal with.
> --
> *mike hodgson* |/ database administrator/ | mallesons stephen jaques
> *T* +61 (2) 9296 3668 |* F* +61 (2) 9296 3885 |* M* +61 (408) 675 907
> *E* mailto:mike.hodgson@.mallesons.nospam.com |* W*
> http://www.mallesons.com
>
> Jason Fischer wrote:
>>Hi All,
>>Does anyone know if there are any issues with HT processors and either SQL
>>2000 or MSDE 2000?
>>Thanks
>>
>>
--020104030608090806080107
Content-Type: text/html; charset=ISO-8859-1
Content-Transfer-Encoding: 7bit
<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN">
<html>
<head>
<meta content="text/html;charset=ISO-8859-1" http-equiv="Content-Type">
<title></title>
</head>
<body bgcolor="#ffffff" text="#000000">
<tt>Interesting. Did those things you read say why? Were they
referring to processor affinity, licensing or something else? (We've
been running a couple clusters on dual-proc hyper-threaded Xeon boxes
(showing 4 logical procs) for some time with no processor related
problems that I'm aware of.)</tt> 
<div class="moz-signature">
<title></title>
<meta http-equiv="Content-Type" content="text/html; ">
-- 
 mike
hodgson | database administrator
| mallesons stephen jaques 
T +61 (2) 9296 3668 | F +61
(2) 9296 3885 | M +61
(408) 675 907 
E
<a href="http://links.10026.com/?link=mailto:mike.hodgson@.mallesons.nospam.com">
mailto:mike.hodgson@.mallesons.nospam.com</a> | W <a href="http://links.10026.com/?link=/">http://www.mallesons.com">
http://www.mallesons.com</a> 
</div>
 
 
Jason Fischer wrote:
<blockquote cite="midOTigIFedFHA.2736@.TK2MSFTNGP12.phx.gbl" type="cite">
<title></title>
<meta http-equiv="Content-Type" content="text/html;charset=ISO-8859-1">
<meta content="MSHTML 6.00.2900.2668" name="GENERATOR">
<style></style>
<div>Hi Mike,</div>
<div> </div>
<div>I had just read a whole lot of
things saying that you should set your SQL Server up for the number of
Physical processors and not logical.</div>
<div> </div>
<div>Thanks</div>
<div> </div>
<blockquote
style="border-left: 2px solid rgb(0, 0, 0); padding-right: 0px; padding-left: 5px; margin-left: 5px; margin-right: 0px;"
dir="ltr">
<div>"Mike Hodgson" <<a
href="http://links.10026.com/?link=mailto:mike.hodgson@.mallesons.nospam.com">mike.hodgson@.mallesons.nospam.com</a>>
wrote in message <a href="http://links.10026.com/?link=news:OvIdEUUdFHA.3808@.TK2MSFTNGP14.phx.gbl">news:OvIdEUUdFHA.3808@.TK2MSFTNGP14.phx.gbl</a>...</div>
<tt>I've never heard of any or seen any myself (and we've been
running SQL 2000 instances on hyper-threaded CPUs for some time).
Admittedly we don't play with MSDE but it's the same code-base. 
 
I think at that level it's the OS implementation that may or may not
have issues, not the app server (i.e. SQL Server). SQL Server just
presents the work for a specific logical processor to the O/S kernel to
deal with. 
</tt>
<div class="moz-signature">
-- 
mike
hodgson | database administrator
| mallesons stephen jaques 
T +61 (2) 9296 3668 | F +61 (2) 9296 3885 | M +61 (408) 675 907 
E <a href="http://links.10026.com/?link=mailto:mike.hodgson@.mallesons.nospam.com">mailto:mike.hodgson@.mallesons.nospam.com</a>
| W <a href="http://links.10026.com/?link=http://www.mallesons.com</a>">http://www.mallesons.com">http://www.mallesons.com</a>

</div>
 
 
Jason Fischer wrote:
<blockquote cite="mideHTk3GUdFHA.3184@.TK2MSFTNGP15.phx.gbl"
type="cite">
<pre wrap="">Hi All,
Does anyone know if there are any issues with HT processors and either SQL
2000 or MSDE 2000?
Thanks
</pre>
</blockquote>
</blockquote>
</blockquote>
</body>
</html>
--020104030608090806080107--|||This is a multi-part message in MIME format.
--=_NextPart_000_000E_01C57724.460926A0
Content-Type: text/plain;
charset="iso-8859-1"
Content-Transfer-Encoding: quoted-printable
Hi Mike,
The articles mentioned something about L2, L3 chace being overwritten =due to HT causing a slow down instead of an increase in spead. The SQL =statements just take longer, the moment they set SQL Server to just use =the number of Physical processors, everything goes back to normal.
I will try and find the articles again and post the links, but will be =away from a PC for 2 weeks, so it might be a while before I post again.
Thanks
"Mike Hodgson" <mike.hodgson@.mallesons.nospam.com> wrote in message =news:eg0xCTfdFHA.3032@.TK2MSFTNGP10.phx.gbl...
Interesting. Did those things you read say why? Were they referring =to processor affinity, licensing or something else? (We've been running =a couple clusters on dual-proc hyper-threaded Xeon boxes (showing 4 =logical procs) for some time with no processor related problems that I'm =aware of.)
--
mike hodgson | database administrator | mallesons stephen jaques
T +61 (2) 9296 3668 | F +61 (2) 9296 3885 | M +61 (408) 675 907
E mailto:mike.hodgson@.mallesons.nospam.com | W =http://www.mallesons.com=20
Jason Fischer wrote: Hi Mike,
I had just read a whole lot of things saying that you should set =your SQL Server up for the number of Physical processors and not =logical.
Thanks
"Mike Hodgson" <mike.hodgson@.mallesons.nospam.com> wrote in =message news:OvIdEUUdFHA.3808@.TK2MSFTNGP14.phx.gbl...
I've never heard of any or seen any myself (and we've been running =SQL 2000 instances on hyper-threaded CPUs for some time). Admittedly we =don't play with MSDE but it's the same code-base.
I think at that level it's the OS implementation that may or may =not have issues, not the app server (i.e. SQL Server). SQL Server just =presents the work for a specific logical processor to the O/S kernel to =deal with.
--
mike hodgson | database administrator | mallesons stephen jaques
T +61 (2) 9296 3668 | F +61 (2) 9296 3885 | M +61 (408) 675 907
E mailto:mike.hodgson@.mallesons.nospam.com | W =http://www.mallesons.com=20
Jason Fischer wrote: Hi All,
Does anyone know if there are any issues with HT processors and either =SQL 2000 or MSDE 2000?
Thanks
--=_NextPart_000_000E_01C57724.460926A0
Content-Type: text/html;
charset="iso-8859-1"
Content-Transfer-Encoding: quoted-printable
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN">
&

Hi Mike,
The articles mentioned something about =L2, L3 chace being overwritten due to HT causing a slow down instead of an increase =in spead. The SQL statements just take longer, the moment they set SQL Server to =just use the number of Physical processors, everything goes back to =normal.
I will try and find the articles again =and post the links, but will be away from a PC for 2 weeks, so it might be a while =before I post again.
Thanks
"Mike Hodgson" wrote in message news:eg0xCTfdFHA.3032=@.TK2MSFTNGP10.phx.gbl...Interesting. Did those things you read say why? Were they referring to =processor affinity, licensing or something else? (We've been running a =couple clusters on dual-proc hyper-threaded Xeon boxes (showing 4 logical =procs) for some time with no processor related problems that I'm aware =of.)
--mike =hodgson | database =administrator | mallesons =stephen jaquesT +61 (2) 9296 3668 | F +61 (2) 9296 3885 | M +61 (408) 675 907E mailto:mike.hodgson@.mal=lesons.nospam.com | W http://www.mallesons.com Jason Fischer wrote:
Hi Mike,

I had just read a whole lot of =things saying that you should set your SQL Server up for the number of Physical =processors and not logical.

Thanks

"Mike Hodgson" wrote in message news:OvIdEUUdFHA.3808=@.TK2MSFTNGP14.phx.gbl...I've never heard of any or seen any myself (and we've been running SQL =2000 instances on hyper-threaded CPUs for some time). Admittedly =we don't play with MSDE but it's the same code-base.I think at that =level it's the OS implementation that may or may not have issues, not =the app server (i.e. SQL Server). SQL Server just presents the work =for a specific logical processor to the O/S kernel to deal =with.
--mike =hodgson | database =administrator | mallesons =stephen =jaquesT =+61 (2) 9296 3668 | F +61 (2) 9296 =3885 | M +61 (408) 675 907E mailto:mike.hodgson@.mal=lesons.nospam.com | W http://www.mallesons.com Jason Fischer wrote: Hi All,
Does anyone know if there are any issues with HT processors and either =SQL 2000 or MSDE 2000?
Thanks =

--=_NextPart_000_000E_01C57724.460926A0--

Wednesday, March 7, 2012

HyperThreading with SQL Server 2000

Hyper-Threading with SQL 2000 Standard

Hyperthreading SQL Server 7 - HELP!

Hyperthreading killing performance of simple query?

Hyperthreading killing performance of simple query?

Hyperthreading killing performance of simple query?

HYPER-THREADING configuration hints

HYPER-THREADING configuration hints

HYPER-THREADING configuration hints

Hyperthreading

Hyperthreading

Hyperthreading

Hyperthreading

hyperthreaded processors running on win2k

hyperthreaded processors running on win2k

hyperthreaded processors running on win2k

Sunday, February 19, 2012

Hyper Threading - Good or Bad?

Hyper Threading

Hyper Threading

Hyper Threading

hyper threading

Blog Archive

About Me