Leon Rosenberg wrote:
Well, personally I had collywobbles before we've gone on 2 cpu
machines, but it went well. I mean, as long as you are one cpu machine
you can be sure that your threads are never really concurrent and
atomic operations remain atomic (like ++) but in case of 2 cpus you
start
From: Darryl L. Miles [mailto:[EMAIL PROTECTED]
Subject: Re: Performance tricks with multiple tomcat instances
I would hope that JIT compiler engineers would as a minimum
implicitly add the lock instruction before all operations
on primitive types declared volatile
Caldarale, Charles R wrote:
From: Darryl L. Miles [mailto:[EMAIL PROTECTED]
Subject: Re: Performance tricks with multiple tomcat instances
I would hope that JIT compiler engineers would as a minimum
implicitly add the lock instruction before all operations
on primitive types declared
Chuck, Darryl
I'd like to thank you both on the amazing insights of concurrency.
Learned a lot today :-)
thanx
leon
-
To unsubscribe, e-mail: [EMAIL PROTECTED]
For additional commands, e-mail: [EMAIL PROTECTED]
Hi,
we are testing a new server, to check whether we can achieve higher
performance/hardware cost ratio.
The new toy is a 4-cpu double core opteron:
processor : 0
vendor_id : AuthenticAMD
cpu family : 15
model : 33
model name : Dual Core AMD Opteron(tm) Processor
From: Leon Rosenberg [mailto:[EMAIL PROTECTED]
Subject: Performance tricks with multiple tomcat instances
One of my assumption for relative bad performance is the gc. If I
install 2 or 4 tomcat instances on the same machine, I assume that if
I'm lucky the gc in the separate VMs will run
, Charles R [EMAIL PROTECTED] wrote:
From: Leon Rosenberg [mailto:[EMAIL PROTECTED]
Subject: Performance tricks with multiple tomcat instances
One of my assumption for relative bad performance is the gc. If I
install 2 or 4 tomcat instances on the same machine, I assume that if
I'm lucky the gc
servers)...
leon
On 3/9/06, Caldarale, Charles R [EMAIL PROTECTED] wrote:
From: Leon Rosenberg [mailto:[EMAIL PROTECTED]
Subject: Performance tricks with multiple tomcat instances
One of my assumption for relative bad performance is the gc. If I
install 2 or 4 tomcat instances on the same
From: Leon Rosenberg [mailto:[EMAIL PROTECTED]
Subject: Re: Performance tricks with multiple tomcat instances
so with 4 tomcats I should reduce the number of gc threads to 2 per vm
and with 2 tomcats to 4 for vm to have the same number of threads as
with single tomcat, and hope
On 3/9/06, Filip Hanik - Dev Lists [EMAIL PROTECTED] wrote:
If I were to add my two cents, I would say the OS scheduler, the bus,
memory access all will play their part.
ie, I think you will get more juice out of 8 single CPU machines each
running a tomcat, than one machine with 8 CPU's, as
On 3/9/06, Caldarale, Charles R [EMAIL PROTECTED] wrote:
From: Leon Rosenberg [mailto:[EMAIL PROTECTED]
Subject: Re: Performance tricks with multiple tomcat instances
so with 4 tomcats I should reduce the number of gc threads to 2 per vm
and with 2 tomcats to 4 for vm to have the same
Leon Rosenberg wrote:
On 3/9/06, Filip Hanik - Dev Lists [EMAIL PROTECTED] wrote:
If I were to add my two cents, I would say the OS scheduler, the bus,
memory access all will play their part.
ie, I think you will get more juice out of 8 single CPU machines each
running a tomcat, than one
On 3/9/06, Filip Hanik - Dev Lists [EMAIL PROTECTED] wrote:
he he, thats where bladeservers come in, of course, they are not cheap,
and you'd probably need a SAN! ;)
yeah... and this is the point where the tco skyrockets ;:-)
Filip
Leon
-Original Message-
From: Leon Rosenberg [mailto:[EMAIL PROTECTED]
Sent: Thursday, March 09, 2006 10:28 AM
To: Tomcat Users List
Subject: Re: Performance tricks with multiple
tomcat instances
On 3/9/06, Filip Hanik - Dev Lists [EMAIL PROTECTED] wrote:
If I were to add my two
On 3/9/06, Justin Greene [EMAIL PROTECTED] wrote:
-Original Message-
From: Leon Rosenberg [mailto:[EMAIL PROTECTED]
Sent: Thursday, March 09, 2006 10:28 AM
To: Tomcat Users List
Subject: Re: Performance tricks with multiple
tomcat instances
On 3/9/06, Filip Hanik - Dev
From: Leon Rosenberg [mailto:[EMAIL PROTECTED]
Subject: Re: Performance tricks with multiple tomcat instances
I mean, as long as you are one cpu machine you can be
sure that your threads are never really concurrent and
atomic operations remain atomic (like ++) but in case
of 2 cpus you
-Original Message-
From: Leon Rosenberg [mailto:[EMAIL PROTECTED]
Sent: Thursday, March 09, 2006 3:06 PM
To: Tomcat Users List
Subject: Re: Performance tricks with multiple
tomcat instances
On 3/9/06, Justin Greene [EMAIL PROTECTED] wrote:
-Original Message-
From
On 3/9/06, Caldarale, Charles R [EMAIL PROTECTED] wrote:
From: Leon Rosenberg [mailto:[EMAIL PROTECTED]
Subject: Re: Performance tricks with multiple tomcat instances
I mean, as long as you are one cpu machine you can be
sure that your threads are never really concurrent and
atomic
On 3/9/06, Caldarale, Charles R [EMAIL PROTECTED] wrote:
From: Leon Rosenberg [mailto:[EMAIL PROTECTED]
Subject: Re: Performance tricks with multiple tomcat instances
I mean, as long as you are one cpu machine you can be
sure that your threads are never really concurrent and
atomic
From: Leon Rosenberg [mailto:[EMAIL PROTECTED]
Subject: Re: Performance tricks with multiple tomcat instances
In particular, assignment to variables of any type except
long or double is atomic.
Note this is _assignment_ not arithmetic. Depending on the capabilities
of the underlying
From: Leon Rosenberg [mailto:[EMAIL PROTECTED]
Subject: Re: Performance tricks with multiple tomcat instances
Hmm, I always thought operations which are declared atomic
are guaranted to be executed at once, for example addition.
Addition is normally not atomic; assignment normally
Caldarale, Charles R wrote:
The select capability isn't required to implement the behavior I
described. Once the request is read in over the wire, the request
object is passed off to a worker thread, and the reader thread goes back
for another one. I'm going to have to dig deeper into the
From: Filip Hanik - Dev Lists [mailto:[EMAIL PROTECTED]
Subject: Re: Performance tricks with multiple tomcat instances
the select (non blocking) capability would be required
if you wanna do keep alive connections with less threads
than connections
that is why BEA early on did what Tomcat
Caldarale, Charles R wrote:
From: Filip Hanik - Dev Lists [mailto:[EMAIL PROTECTED]
Subject: Re: Performance tricks with multiple tomcat instances
the select (non blocking) capability would be required
if you wanna do keep alive connections with less threads
than connections
that is why BEA
From: Filip Hanik - Dev Lists [mailto:[EMAIL PROTECTED]
Subject: Re: Performance tricks with multiple tomcat instances
Tomcat APR will use one thread per connection. but APR also has non
blocking option.
Does Tomcat use the non-blocking option? (I haven't looked at the APR
code at all
Caldarale, Charles R wrote:
From: Filip Hanik - Dev Lists [mailto:[EMAIL PROTECTED]
Subject: Re: Performance tricks with multiple tomcat instances
Tomcat APR will use one thread per connection. but APR also has non
blocking option.
Does Tomcat use the non-blocking option? (I haven't
26 matches
Mail list logo