More slower CPUs vs. fewer faster CPUs
I was wondering if it would be better to have three or four relatively slower CPUs than having only two faster ones. I think I remember that Ixora says fewer faster CPUs is better because the CPUs are constantly negotiating who should do what. The more CPUs exist the more time-consuming the debate (this is very simplified, I realize). Jonathan Lewis in Practical Oracle8i: Building Efficient Databases, Adison Wesley, p. says the opposite. Is this another one of those questions that has "it depends" as the only answer? Or that has very plausible theoretical answers that are mitigated in real life? I imagine that the I/O patterns play a part in the validity of either answer. Has anyone on this list tested to see which would be faster? We are on Compaq Tru64 UNIX alphas, upgrading to ES-40s with up to four CPUs. My database is a mix (mess) of background tables for web apps, ad hoc querying, sporadic intensive data loads and in the near future: replication. Opinons? TIA Patrice Boivin Systems Analyst (Oracle Certified DBA) Systems Admin Operations | Admin. et Exploit. des systmes Technology Services| Services technologiques Informatics Branch | Direction de l'informatique Maritimes Region, DFO | Rgion des Maritimes, MPO E-Mail: [EMAIL PROTECTED] mailto:[EMAIL PROTECTED] -- Please see the official ORACLE-L FAQ: http://www.orafaq.com -- Author: Boivin, Patrice J INET: [EMAIL PROTECTED] Fat City Network Services-- (858) 538-5051 FAX: (858) 538-5051 San Diego, California-- Public Internet access / Mailing Lists To REMOVE yourself from this mailing list, send an E-Mail message to: [EMAIL PROTECTED] (note EXACT spelling of 'ListGuru') and in the message BODY, include a line containing: UNSUB ORACLE-L (or the name of mailing list you want to be removed from). You may also send the HELP command for other information (like subscribing).
Re: More slower CPUs vs. fewer faster CPUs
And don't forget Oracle Power Unit Licensing costs? # cpus is a multiplier. [EMAIL PROTECTED] 02/23 8:20 AM I was wondering if it would be better to have three or four relatively slower CPUs than having only two faster ones. I think I remember that Ixora says fewer faster CPUs is better because the CPUs are constantly negotiating who should do what. The more CPUs exist the more time-consuming the debate (this is very simplified, I realize). Jonathan Lewis in Practical Oracle8i: Building Efficient Databases, Adison Wesley, p. says the opposite. Is this another one of those questions that has "it depends" as the only answer? Or that has very plausible theoretical answers that are mitigated in real life? I imagine that the I/O patterns play a part in the validity of either answer. Has anyone on this list tested to see which would be faster? We are on Compaq Tru64 UNIX alphas, upgrading to ES-40s with up to four CPUs. My database is a mix (mess) of background tables for web apps, ad hoc querying, sporadic intensive data loads and in the near future: replication. Opinons? TIA Patrice Boivin Systems Analyst (Oracle Certified DBA) Systems Admin Operations | Admin. et Exploit. des systmes Technology Services| Services technologiques Informatics Branch | Direction de l'informatique Maritimes Region, DFO | Rgion des Maritimes, MPO E-Mail: [EMAIL PROTECTED] mailto:[EMAIL PROTECTED] -- Please see the official ORACLE-L FAQ: http://www.orafaq.com -- Author: Boivin, Patrice J INET: [EMAIL PROTECTED] Fat City Network Services-- (858) 538-5051 FAX: (858) 538-5051 San Diego, California-- Public Internet access / Mailing Lists To REMOVE yourself from this mailing list, send an E-Mail message to: [EMAIL PROTECTED] (note EXACT spelling of 'ListGuru') and in the message BODY, include a line containing: UNSUB ORACLE-L (or the name of mailing list you want to be removed from). You may also send the HELP command for other information (like subscribing). -- Please see the official ORACLE-L FAQ: http://www.orafaq.com -- Author: Gene Sais INET: [EMAIL PROTECTED] Fat City Network Services-- (858) 538-5051 FAX: (858) 538-5051 San Diego, California-- Public Internet access / Mailing Lists To REMOVE yourself from this mailing list, send an E-Mail message to: [EMAIL PROTECTED] (note EXACT spelling of 'ListGuru') and in the message BODY, include a line containing: UNSUB ORACLE-L (or the name of mailing list you want to be removed from). You may also send the HELP command for other information (like subscribing).
RE: More slower CPUs vs. fewer faster CPUs
I realize too that it depends on the number of concurrent user sessions. Patrice Boivin Systems Analyst (Oracle Certified DBA) -Original Message- From: Boivin, Patrice J [SMTP:[EMAIL PROTECTED]] Sent: Friday, February 23, 2001 9:20 AM To: Multiple recipients of list ORACLE-L Subject:More slower CPUs vs. fewer faster CPUs I was wondering if it would be better to have three or four relatively slower CPUs than having only two faster ones. I think I remember that Ixora says fewer faster CPUs is better because the CPUs are constantly negotiating who should do what. The more CPUs exist the more time-consuming the debate (this is very simplified, I realize). Jonathan Lewis in Practical Oracle8i: Building Efficient Databases, Adison Wesley, p. says the opposite. Is this another one of those questions that has "it depends" as the only answer? Or that has very plausible theoretical answers that are mitigated in real life? I imagine that the I/O patterns play a part in the validity of either answer. Has anyone on this list tested to see which would be faster? We are on Compaq Tru64 UNIX alphas, upgrading to ES-40s with up to four CPUs. My database is a mix (mess) of background tables for web apps, ad hoc querying, sporadic intensive data loads and in the near future: replication. Opinons? TIA Patrice Boivin Systems Analyst (Oracle Certified DBA) Systems Admin Operations | Admin. et Exploit. des systmes Technology Services| Services technologiques Informatics Branch | Direction de l'informatique Maritimes Region, DFO | Rgion des Maritimes, MPO E-Mail: [EMAIL PROTECTED] mailto:[EMAIL PROTECTED] -- Please see the official ORACLE-L FAQ: http://www.orafaq.com -- Author: Boivin, Patrice J INET: [EMAIL PROTECTED] Fat City Network Services-- (858) 538-5051 FAX: (858) 538-5051 San Diego, California-- Public Internet access / Mailing Lists To REMOVE yourself from this mailing list, send an E-Mail message to: [EMAIL PROTECTED] (note EXACT spelling of 'ListGuru') and in the message BODY, include a line containing: UNSUB ORACLE-L (or the name of mailing list you want to be removed from). You may also send the HELP command for other information (like subscribing). -- Please see the official ORACLE-L FAQ: http://www.orafaq.com -- Author: Boivin, Patrice J INET: [EMAIL PROTECTED] Fat City Network Services-- (858) 538-5051 FAX: (858) 538-5051 San Diego, California-- Public Internet access / Mailing Lists To REMOVE yourself from this mailing list, send an E-Mail message to: [EMAIL PROTECTED] (note EXACT spelling of 'ListGuru') and in the message BODY, include a line containing: UNSUB ORACLE-L (or the name of mailing list you want to be removed from). You may also send the HELP command for other information (like subscribing).
Re: More slower CPUs vs. fewer faster CPUs
..and so is the speed of the processors "Gene Sais" [EMAIL PROTECTED] 02/23/01 09:01AM And don't forget Oracle Power Unit Licensing costs? # cpus is a multiplier. [EMAIL PROTECTED] 02/23 8:20 AM I was wondering if it would be better to have three or four relatively slower CPUs than having only two faster ones. I think I remember that Ixora says fewer faster CPUs is better because the CPUs are constantly negotiating who should do what. The more CPUs exist the more time-consuming the debate (this is very simplified, I realize). Jonathan Lewis in Practical Oracle8i: Building Efficient Databases, Adison Wesley, p. says the opposite. Is this another one of those questions that has "it depends" as the only answer? Or that has very plausible theoretical answers that are mitigated in real life? I imagine that the I/O patterns play a part in the validity of either answer. Has anyone on this list tested to see which would be faster? We are on Compaq Tru64 UNIX alphas, upgrading to ES-40s with up to four CPUs. My database is a mix (mess) of background tables for web apps, ad hoc querying, sporadic intensive data loads and in the near future: replication. Opinons? TIA Patrice Boivin Systems Analyst (Oracle Certified DBA) Systems Admin Operations | Admin. et Exploit. des systmes Technology Services| Services technologiques Informatics Branch | Direction de l'informatique Maritimes Region, DFO | Rgion des Maritimes, MPO E-Mail: [EMAIL PROTECTED] mailto:[EMAIL PROTECTED] -- Please see the official ORACLE-L FAQ: http://www.orafaq.com -- Author: Boivin, Patrice J INET: [EMAIL PROTECTED] Fat City Network Services-- (858) 538-5051 FAX: (858) 538-5051 San Diego, California-- Public Internet access / Mailing Lists To REMOVE yourself from this mailing list, send an E-Mail message to: [EMAIL PROTECTED] (note EXACT spelling of 'ListGuru') and in the message BODY, include a line containing: UNSUB ORACLE-L (or the name of mailing list you want to be removed from). You may also send the HELP command for other information (like subscribing). -- Please see the official ORACLE-L FAQ: http://www.orafaq.com -- Author: Gene Sais INET: [EMAIL PROTECTED] Fat City Network Services-- (858) 538-5051 FAX: (858) 538-5051 San Diego, California-- Public Internet access / Mailing Lists To REMOVE yourself from this mailing list, send an E-Mail message to: [EMAIL PROTECTED] (note EXACT spelling of 'ListGuru') and in the message BODY, include a line containing: UNSUB ORACLE-L (or the name of mailing list you want to be removed from). You may also send the HELP command for other information (like subscribing). -- Please see the official ORACLE-L FAQ: http://www.orafaq.com -- Author: William Beilstein INET: [EMAIL PROTECTED] Fat City Network Services-- (858) 538-5051 FAX: (858) 538-5051 San Diego, California-- Public Internet access / Mailing Lists To REMOVE yourself from this mailing list, send an E-Mail message to: [EMAIL PROTECTED] (note EXACT spelling of 'ListGuru') and in the message BODY, include a line containing: UNSUB ORACLE-L (or the name of mailing list you want to be removed from). You may also send the HELP command for other information (like subscribing).
RE: More slower CPUs vs. fewer faster CPUs
The following discussion assumes "big buss SMP" not MPP or any of its derivations. Your mileage may vary. If you have one CPU then all of the multiple CPU code in the kernel is not used. There is a penalty that is paid for the second and subsequent cpu's. So, the answer is... it depends! If your particular version of Unix scales well WITH YOUR WORKLOAD, you might expect to get something like 95% of the second CPU. If it does not scale well, then you might get 80% of the CPU. Subsequent CPU's give even less value. If CPU #2 gave 90% of CPU #1 then CPU #3 can be expected to give 90% of CPU #2! So with 3 CPU's you get a total of 2.71 times the power of the one CPU system. CPU #1 = 1.0, CPU #2 = 0.9, CPU #3 = 0.81 1.0 + 0.9 + 0.81 = 2.71 So all other things being equal, fewer CPU's is better. One is best. Unfortunately, all other things are never equal. Brian -- Please see the official ORACLE-L FAQ: http://www.orafaq.com -- Author: Brian D. Silverio INET: [EMAIL PROTECTED] Fat City Network Services-- (858) 538-5051 FAX: (858) 538-5051 San Diego, California-- Public Internet access / Mailing Lists To REMOVE yourself from this mailing list, send an E-Mail message to: [EMAIL PROTECTED] (note EXACT spelling of 'ListGuru') and in the message BODY, include a line containing: UNSUB ORACLE-L (or the name of mailing list you want to be removed from). You may also send the HELP command for other information (like subscribing).