Poor performance on VMWare

Hello I want to know some expert opinion about one IDS 12.10.FC3WE test that I ha= ve currently executing in two machines. This machines are: SRV1: (+7 years old) HP Proliant DL585 G1 - 4xAMD Opteron 820 2.3GHz (2 cores x processor for a total of 8 cores) - 16 GB RAM - Local HDD on 146GB Ultra320 SCSI - Informix storage: cooked files - Red Hat 5.9 x64 SRV2: VMWare Virtual server - 8xvCPU (reported as AMD Opteron 6176 SE 2,3GHz) - 16 GB RAM - SAN (HP EVA6500) HDD on 2TB 7.2K EVA SAS MDL disk pool (Mapped RAW LUN) - SAN conectivity: 1Gbps iSCSI (server side) 10Gbps (SAN side) - Informix storage: cooked files - Red Hat 6.5 x64 With these technical data, I am expected that the SRV2 results were better = than the SRV2 ones (and more knowing the SRV1 "age"). When I ran some scripts, stored procedures (SPL) and update statistics, I w= as surprised by the results. The massive write operations were slightly bet= ter on SRV2 (import was 40% faster in SRV2), but the scripts envolving heav= y reading operations were about 1,5 times slow in the best cases, reaching = 2,5 times slow in the worse cases. In this unexpected scenario, I looked for an IDS independent benchmarking t= ool and I found a suite called "phoronix test suite" (PTS). I was decided t= o find the bottleneck in SRV2... but again the results of the PTS surprised= me. I ran various test, with the following results: - pts/SmallPT (CPU test. Less is better) > SRV1: 192 > SRV2: 141 (better) - pts/Apache (CPU test. More is better) > SRV1: 7017.65 > SRV2: 9547.57 (be= tter) - pts/aio-stress (I/O test. Random Write. More is better) > SRV1: 22.06 > S= RV2: 881.51 (better) - pts/iozone (I/O test. Read Performance: 1MB record / 2GB file. More is be= tter) > SRV1: 728.09 > SRV2: 2008.14 (better) - pts/iozone (I/O test. Read Performance: 1MB record / 4GB file. More is be= tter) > SRV1: 824.98 > SRV2: 1985.23 (better) - pts/iozone (I/O test. Read Performance: 1MB record / 8GB file. More is be= tter) > SRV1: 768.30 > SRV2: 1906.90(better) - pts/iozone (I/O test. Read Performance: 4KB record / 2GB file. More is be= tter) > SRV1: 1016.75 > SRV2: 2113.92 (better) - pts/iozone (I/O test. Read Performance: 4KB record / 4GB file. More is be= tter) > SRV1: 1071.86 > SRV2: 1953.93 (better) - pts/iozone (I/O test. Read Performance: 4KB record / 8GB file. More is be= tter) > SRV1: 1086.07 > SRV2: 1794.42 (better) - pts/iozone (I/O test. Write Performance: 1MB record / 2GB file. More is b= etter) > SRV1: 25.38 > SRV2: 97.64 (better) - pts/iozone (I/O test. Write Performance: 1MB record / 4GB file. More is b= etter) > SRV1: 26.28 > SRV2: 114.04 (better) - pts/iozone (I/O test. Write Performance: 1MB record / 8GB file. More is b= etter) > SRV1: 28.36 > SRV2: 144.49 (better) - pts/iozone (I/O test. Write Performance: 4KB record / 2GB file. More is b= etter) > SRV1: 26.17 > SRV2: 91.99 (better) - pts/iozone (I/O test. Write Performance: 4KB record / 4GB file. More is b= etter) > SRV1: 26.35 > SRV2: 108.19 (better) - pts/iozone (I/O test. Write Performance: 4KB record / 8GB file. More is b= etter) > SRV1: 28.62 > SRV2: 144.37 (better) - pts/ramspeed (RAM test. Add integer. More is better) > SRV1: 3533.75 > SR= V2: 6782.31 (better) - pts/ramspeed (RAM test. Copy integer. More is better) > SRV1: 3418.95 > S= RV2: 6782.31 (better) - pts/ramspeed (RAM test. Scale integer. More is better) > SRV1: 3448.33 > = SRV2: 6776.20 (better) - pts/ramspeed (RAM test. Triad integer. More is better) > SRV1: 3499.36 > = SRV2: 6536.23 (better) - pts/ramspeed (RAM test. Average integer. More is better) > SRV1: 3453.82 = > SRV2: 6851.13 (better) - pts/ramspeed (RAM test. Add floating point. More is better) > SRV1: 3955.= 16 > SRV2: 7241.65 (better) - pts/ramspeed (RAM test. Copy floating point. More is better) > SRV1: 3599= .66 > SRV2: 7178.45 (better) - pts/ramspeed (RAM test. Scale floating point. More is better) > SRV1: 339= 9.08 > SRV2: 7286.11 (better) - pts/ramspeed (RAM test. Triad floating point. More is better) > SRV1: 385= 5.18 > SRV2: 7461.69 (better) - pts/ramspeed (RAM test. Average floating point. More is better) > SRV1: 3= 647.64 > SRV2: 7351.95 (better) In these test, SRV2 outperforms SRV1 in a clear and consistent way in any o= f the evaluated fields (Processor, I/O and Memory). But the IDS 12.10.FC3WE= still runs slowly in SRV2 when I execute massive read operations (by examp= le, update statistics over my test db is 136% more slow than the same opera= tion on SRV1). The IDS config is exactly the same in the two servers (oncon= fig copied from one to other). One thing I observed is that the SRV2's virtual processors shows more activ= ity than the SRV1's ones when I execute any IDS operation. Also is the same= thing with the "top" utility in the operating system command line. This is= a "contradiction?" with the SRV2's better PTS CPU tests . I do not identify or suspect any possible reason who explain the poor SRV2 = performance... any ideas? Thanks in advance and excuse me if the english is not quite good... :-( -- Javier Perez Arenal - jperez@uniovi.es<mailto:jperez@uniovi.es> Jefe del Area T=E9cnica de Inform=E1tica y Comunicaciones Vicerrectorado de Campus, Inform=E1tica e Infraestructuras Universidad de Oviedo Edificio Severo Ochoa C/ Fernando Bongera s/n, Campus del Cristo 33006 - Oviedo, Asturias --Boundary_(ID_B1ApZu83LpmDOByskPtisQ)

Hello, Javier. My personal opinion is that you might have a better performance, but you should not use the same onconfig file. 1) Are you really using cooked files? If so, please forget them. Change your chunks to raw devices, and make sure you are not using a bad RAID level in your storage. 2) You could start a performance tunning process after topic 1 is solved. Informix 12 have several features that might benefit your performance, even in VMs environments. Eg: are you using cpu vp memory caches? Are you using RTO policies? Are you using alice index cleaner mode (OLTP system)? 3) You might also check other topics, but as a start phase, I´d go for all of mentioned ones first. Hope it helps. Regards. Alexandre Marini IBM Informix Certified Professional v10 / v11.50 / v11.70 / v12.10 IBM Information Management Informix Technical Professional IBM Infosphere DataStage Technical Professional Informix Senior DBA - Orizon Brasil BRIUG website administrator Informix independent consultant > To: ids@iiug.org > From: jperez@uniovi.es > Subject: Poor performance on VMWare [33099] > Date: Mon, 26 May 2014 09:44:07 -0400 > > Hello > > I want to know some expert opinion about one IDS 12.10.FC3WE test that I ha= > ve currently executing in two machines. This machines are: > > SRV1: (+7 years old) HP Proliant DL585 G1 > - 4xAMD Opteron 820 2.3GHz (2 cores x processor for a total of 8 cores) > - 16 GB RAM > - Local HDD on 146GB Ultra320 SCSI > - Informix storage: cooked files > - Red Hat 5.9 x64 > > SRV2: VMWare Virtual server > - 8xvCPU (reported as AMD Opteron 6176 SE 2,3GHz) > - 16 GB RAM > - SAN (HP EVA6500) HDD on 2TB 7.2K EVA SAS MDL disk pool (Mapped RAW LUN) > - SAN conectivity: 1Gbps iSCSI (server side) 10Gbps (SAN side) > - Informix storage: cooked files > - Red Hat 6.5 x64 > > With these technical data, I am expected that the SRV2 results were better = > than the SRV2 ones (and more knowing the SRV1 "age"). > > When I ran some scripts, stored procedures (SPL) and update statistics, I w= > as surprised by the results. The massive write operations were slightly bet= > ter on SRV2 (import was 40% faster in SRV2), but the scripts envolving heav= > y reading operations were about 1,5 times slow in the best cases, reaching = > 2,5 times slow in the worse cases. > > In this unexpected scenario, I looked for an IDS independent benchmarking t= > ool and I found a suite called "phoronix test suite" (PTS). I was decided t= > o find the bottleneck in SRV2... but again the results of the PTS surprised= > me. I ran various test, with the following results: > > - pts/SmallPT (CPU test. Less is better) > SRV1: 192 > SRV2: 141 (better) > - pts/Apache (CPU test. More is better) > SRV1: 7017.65 > SRV2: 9547.57 (be= > tter) > - pts/aio-stress (I/O test. Random Write. More is better) > SRV1: 22.06 > S= > RV2: 881.51 (better) > - pts/iozone (I/O test. Read Performance: 1MB record / 2GB file. More is be= > tter) > SRV1: 728.09 > SRV2: 2008.14 (better) > - pts/iozone (I/O test. Read Performance: 1MB record / 4GB file. More is be= > tter) > SRV1: 824.98 > SRV2: 1985.23 (better) > - pts/iozone (I/O test. Read Performance: 1MB record / 8GB file. More is be= > tter) > SRV1: 768.30 > SRV2: 1906.90(better) > - pts/iozone (I/O test. Read Performance: 4KB record / 2GB file. More is be= > tter) > SRV1: 1016.75 > SRV2: 2113.92 (better) > - pts/iozone (I/O test. Read Performance: 4KB record / 4GB file. More is be= > tter) > SRV1: 1071.86 > SRV2: 1953.93 (better) > - pts/iozone (I/O test. Read Performance: 4KB record / 8GB file. More is be= > tter) > SRV1: 1086.07 > SRV2: 1794.42 (better) > - pts/iozone (I/O test. Write Performance: 1MB record / 2GB file. More is b= > etter) > SRV1: 25.38 > SRV2: 97.64 (better) > - pts/iozone (I/O test. Write Performance: 1MB record / 4GB file. More is b= > etter) > SRV1: 26.28 > SRV2: 114.04 (better) > - pts/iozone (I/O test. Write Performance: 1MB record / 8GB file. More is b= > etter) > SRV1: 28.36 > SRV2: 144.49 (better) > - pts/iozone (I/O test. Write Performance: 4KB record / 2GB file. More is b= > etter) > SRV1: 26.17 > SRV2: 91.99 (better) > - pts/iozone (I/O test. Write Performance: 4KB record / 4GB file. More is b= > etter) > SRV1: 26.35 > SRV2: 108.19 (better) > - pts/iozone (I/O test. Write Performance: 4KB record / 8GB file. More is b= > etter) > SRV1: 28.62 > SRV2: 144.37 (better) > - pts/ramspeed (RAM test. Add integer. More is better) > SRV1: 3533.75 > SR= > V2: 6782.31 (better) > - pts/ramspeed (RAM test. Copy integer. More is better) > SRV1: 3418.95 > S= > RV2: 6782.31 (better) > - pts/ramspeed (RAM test. Scale integer. More is better) > SRV1: 3448.33 > = > SRV2: 6776.20 (better) > - pts/ramspeed (RAM test. Triad integer. More is better) > SRV1: 3499.36 > = > SRV2: 6536.23 (better) > - pts/ramspeed (RAM test. Average integer. More is better) > SRV1: 3453.82 = > > SRV2: 6851.13 (better) > - pts/ramspeed (RAM test. Add floating point. More is better) > SRV1: 3955.= > 16 > SRV2: 7241.65 (better) > - pts/ramspeed (RAM test. Copy floating point. More is better) > SRV1: 3599= > ..66 > SRV2: 7178.45 (better) > - pts/ramspeed (RAM test. Scale floating point. More is better) > SRV1: 339= > 9.08 > SRV2: 7286.11 (better) > - pts/ramspeed (RAM test. Triad floating point. More is better) > SRV1: 385= > 5.18 > SRV2: 7461.69 (better) > - pts/ramspeed (RAM test. Average floating point. More is better) > SRV1: 3= > 647.64 > SRV2: 7351.95 (better) > > In these test, SRV2 outperforms SRV1 in a clear and consistent way in any o= > f the evaluated fields (Processor, I/O and Memory). But the IDS 12.10.FC3WE= > still runs slowly in SRV2 when I execute massive read operations (by examp= > le, update statistics over my test db is 136% more slow than the same opera= > tion on SRV1). The IDS config is exactly the same in the two servers (oncon= > fig copied from one to other). > > One thing I observed is that the SRV2's virtual processors shows more activ= > ity than the SRV1's ones when I execute any IDS operation. Also is the same= > thing with the "top" utility in the operating system command line. This is= > a "contradiction?" with the SRV2's better PTS CPU tests . > > I do not identify or suspect any possible reason who explain the poor SRV2 = > performance... any ideas? > > Thanks in advance and excuse me if the english is not quite good... :-( > > -- > Javier Perez Arenal - jperez@uniovi.es<mailto:jperez@uniovi.es> > Jefe del Area T=E9cnica de Inform=E1tica y Comunicaciones > Vicerrectorado de Campus, Inform=E1tica e Infraestructuras > Universidad de Oviedo > Edificio Severo Ochoa > C/ Fernando Bongera s/n, Campus del Cristo > 33006 - Oviedo, Asturias > > --Boundary_(ID_B1ApZu83LpmDOByskPtisQ) > > > ******************************************************************************* > Forum Note: Use "Reply" to post a response in the discussion forum. >

You example provided of update statistics is probably not the best exam= ple. The assumption made is that update statistics of an older Informix serv= er is the same as a new Informix server and that a majority of the time it is doing I/= O. Update statisticshas been changed significantly over time and it can end up doing work t= o cleanup older style indexes which are inefficient. John F. Miller III STSM, Lead Architect miller3@us.ibm.com 503-747-1366 IBM Informix Dynamic Server (IDS) ids-bounces@iiug.org wrote on 05/26/2014 07:26:09 AM: > From: "Alexandre Marini" <alexandre@briug.org> > To: ids@iiug.org, > Date: 05/26/2014 07:27 AM > Subject: RE: Poor performance on VMWare [33100] > Sent by: ids-bounces@iiug.org > > Hello, Javier. > My personal opinion is that you might have a better performance, but = you > should not use the same onconfig file. > > 1) Are you really using cooked files? If so, please forget them. Chan= ge your > chunks to raw devices, and make sure you are not using a bad RAID lev= el in > your storage. > > 2) You could start a performance tunning process after topic 1 is sol= ved. > Informix 12 have several features that might benefit your > performance, even in > VMs environments. Eg: are you using cpu vp memory caches? Are you usi= ng RTO > policies? Are you using alice index cleaner mode (OLTP system)? > > 3) You might also check other topics, but as a start phase, I=B4d go = for all of > mentioned ones first. > > Hope it helps. > Regards. > > Alexandre Marini > IBM Informix Certified Professional v10 / v11.50 / v11.70 / v12.10 > > IBM Information Management Informix Technical Professional > > IBM Infosphere DataStage Technical Professional > Informix Senior DBA - Orizon Brasil > BRIUG website administrator > Informix independent consultant > > > To: ids@iiug.org > > From: jperez@uniovi.es > > Subject: Poor performance on VMWare [33099] > > Date: Mon, 26 May 2014 09:44:07 -0400 > > > > Hello > > > > I want to know some expert opinion about one IDS 12.10.FC3WE test > that I ha=3D > > ve currently executing in two machines. This machines are: > > > > SRV1: (+7 years old) HP Proliant DL585 G1 > > - 4xAMD Opteron 820 2.3GHz (2 cores x processor for a total of 8 co= res) > > - 16 GB RAM > > - Local HDD on 146GB Ultra320 SCSI > > - Informix storage: cooked files > > - Red Hat 5.9 x64 > > > > SRV2: VMWare Virtual server > > - 8xvCPU (reported as AMD Opteron 6176 SE 2,3GHz) > > - 16 GB RAM > > - SAN (HP EVA6500) HDD on 2TB 7.2K EVA SAS MDL disk pool (Mapped RA= W LUN) > > - SAN conectivity: 1Gbps iSCSI (server side) 10Gbps (SAN side) > > - Informix storage: cooked files > > - Red Hat 6.5 x64 > > > > With these technical data, I am expected that the SRV2 results > were better =3D > > than the SRV2 ones (and more knowing the SRV1 "age"). > > > > When I ran some scripts, stored procedures (SPL) and update > statistics, I w=3D > > as surprised by the results. The massive write operations were > slightly bet=3D > > ter on SRV2 (import was 40% faster in SRV2), but the scripts > envolving heav=3D > > y reading operations were about 1,5 times slow in the best cases, > reaching =3D > > 2,5 times slow in the worse cases. > > > > In this unexpected scenario, I looked for an IDS independent > benchmarking t=3D > > ool and I found a suite called "phoronix test suite" (PTS). I was > decided t=3D > > o find the bottleneck in SRV2... but again the results of the PTS > surprised=3D > > me. I ran various test, with the following results: > > > > - pts/SmallPT (CPU test. Less is better) > SRV1: 192 > SRV2: 141 (better) > > - pts/Apache (CPU test. More is better) > SRV1: 7017.65 > SRV2: > 9547.57 (be=3D > > tter) > > - pts/aio-stress (I/O test. Random Write. More is better) > SRV1: > 22.06 > S=3D > > RV2: 881.51 (better) > > - pts/iozone (I/O test. Read Performance: 1MB record / 2GB file. > More is be=3D > > tter) > SRV1: 728.09 > SRV2: 2008.14 (better) > > - pts/iozone (I/O test. Read Performance: 1MB record / 4GB file. > More is be=3D > > tter) > SRV1: 824.98 > SRV2: 1985.23 (better) > > - pts/iozone (I/O test. Read Performance: 1MB record / 8GB file. > More is be=3D > > tter) > SRV1: 768.30 > SRV2: 1906.90(better) > > - pts/iozone (I/O test. Read Performance: 4KB record / 2GB file. > More is be=3D > > tter) > SRV1: 1016.75 > SRV2: 2113.92 (better) > > - pts/iozone (I/O test. Read Performance: 4KB record / 4GB file. > More is be=3D > > tter) > SRV1: 1071.86 > SRV2: 1953.93 (better) > > - pts/iozone (I/O test. Read Performance: 4KB record / 8GB file. > More is be=3D > > tter) > SRV1: 1086.07 > SRV2: 1794.42 (better) > > - pts/iozone (I/O test. Write Performance: 1MB record / 2GB file. > More is b=3D > > etter) > SRV1: 25.38 > SRV2: 97.64 (better) > > - pts/iozone (I/O test. Write Performance: 1MB record / 4GB file. > More is b=3D > > etter) > SRV1: 26.28 > SRV2: 114.04 (better) > > - pts/iozone (I/O test. Write Performance: 1MB record / 8GB file. > More is b=3D > > etter) > SRV1: 28.36 > SRV2: 144.49 (better) > > - pts/iozone (I/O test. Write Performance: 4KB record / 2GB file. > More is b=3D > > etter) > SRV1: 26.17 > SRV2: 91.99 (better) > > - pts/iozone (I/O test. Write Performance: 4KB record / 4GB file. > More is b=3D > > etter) > SRV1: 26.35 > SRV2: 108.19 (better) > > - pts/iozone (I/O test. Write Performance: 4KB record / 8GB file. > More is b=3D > > etter) > SRV1: 28.62 > SRV2: 144.37 (better) > > - pts/ramspeed (RAM test. Add integer. More is better) > SRV1: > 3533.75 > SR=3D > > V2: 6782.31 (better) > > - pts/ramspeed (RAM test. Copy integer. More is better) > SRV1: > 3418.95 > S=3D > > RV2: 6782.31 (better) > > - pts/ramspeed (RAM test. Scale integer. More is better) > SRV1: > 3448.33 > =3D > > SRV2: 6776.20 (better) > > - pts/ramspeed (RAM test. Triad integer. More is better) > SRV1: > 3499.36 > =3D > > SRV2: 6536.23 (better) > > - pts/ramspeed (RAM test. Average integer. More is better) > SRV1:3453.82 =3D > > > SRV2: 6851.13 (better) > > - pts/ramspeed (RAM test. Add floating point. More is better) > > SRV1: 3955.=3D > > 16 > SRV2: 7241.65 (better) > > - pts/ramspeed (RAM test. Copy floating point. More is better) > > SRV1: 3599=3D > > ..66 > SRV2: 7178.45 (better) > > - pts/ramspeed (RAM test. Scale floating point. More is better) > > SRV1: 339=3D > > 9.08 > SRV2: 7286.11 (better) > > - pts/ramspeed (RAM test. Triad floating point. More is better) > > SRV1: 385=3D > > 5.18 > SRV2: 7461.69 (better) > > - pts/ramspeed (RAM test. Average floating point. More is better) > > SRV1: 3=3D > > 647.64 > SRV2: 7351.95 (better) > > > > In these test, SRV2 outperforms SRV1 in a clear and consistent wayi= n any o=3D > > f the evaluated fields (Processor, I/O and Memory). But the IDS > 12.10.FC3WE=3D > > still runs slowly in SRV2 when I execute massive read operations (b= y examp=3D > > le, update statistics over my

Thanks Alexandre! I will follow your advices, but IMHO I do not expect any significative per= formance improvements. The IDS version is the same in the two servers and i= n both I use cooked files, therefore, I supose that if I move the dbspaces = to raw devices in both servers, the improvements will be equivalent too. Again, thanks for your help. Best regards. -- Javier Perez Arenal - jperez@uniovi.es Jefe del Area T=E9cnica de Inform=E1tica y Comunicaciones=20 Vicerrectorado de Campus, Inform=E1tica e Infraestructuras Universidad de Oviedo=20 Edificio Severo Ochoa=20 C/ Fernando Bongera s/n, Campus del Cristo 33006 - Oviedo, Asturias -----Mensaje original----- De: ids-bounces@iiug.org [mailto:ids-bounces@iiug.org] En nombre de Alexand= re Marini Enviado el: lunes, 26 de mayo de 2014 16:26 Para: ids@iiug.org Asunto: RE: Poor performance on VMWare [33100] Hello, Javier.=20 My personal opinion is that you might have a better performance, but you sh= ould not use the same onconfig file.=20 1) Are you really using cooked files? If so, please forget them. Change you= r chunks to raw devices, and make sure you are not using a bad RAID level i= n your storage.=20 2) You could start a performance tunning process after topic 1 is solved.=20 Informix 12 have several features that might benefit your performance, even= in VMs environments. Eg: are you using cpu vp memory caches? Are you using= RTO policies? Are you using alice index cleaner mode (OLTP system)?=20 3) You might also check other topics, but as a start phase, I=B4d go for al= l of mentioned ones first.=20 Hope it helps.=20 Regards.=20 Alexandre Marini IBM Informix Certified Professional v10 / v11.50 / v11.70 / v12.10=20 IBM Information Management Informix Technical Professional=20 IBM Infosphere DataStage Technical Professional Informix Senior DBA - Orizo= n Brasil BRIUG website administrator Informix independent consultant=20 > To: ids@iiug.org > From: jperez@uniovi.es > Subject: Poor performance on VMWare [33099] > Date: Mon, 26 May 2014 09:44:07 -0400 >=20 > Hello >=20 > I want to know some expert opinion about one IDS 12.10.FC3WE test that=20 > I ha=3D ve currently executing in two machines. This machines are: >=20 > SRV1: (+7 years old) HP Proliant DL585 G1 > - 4xAMD Opteron 820 2.3GHz (2 cores x processor for a total of 8=20 > cores) > - 16 GB RAM > - Local HDD on 146GB Ultra320 SCSI > - Informix storage: cooked files > - Red Hat 5.9 x64 >=20 > SRV2: VMWare Virtual server > - 8xvCPU (reported as AMD Opteron 6176 SE 2,3GHz) > - 16 GB RAM > - SAN (HP EVA6500) HDD on 2TB 7.2K EVA SAS MDL disk pool (Mapped RAW=20 > LUN) > - SAN conectivity: 1Gbps iSCSI (server side) 10Gbps (SAN side) > - Informix storage: cooked files > - Red Hat 6.5 x64 >=20 > With these technical data, I am expected that the SRV2 results were=20 > better =3D than the SRV2 ones (and more knowing the SRV1 "age"). >=20 > When I ran some scripts, stored procedures (SPL) and update=20 > statistics, I w=3D as surprised by the results. The massive write=20 > operations were slightly bet=3D ter on SRV2 (import was 40% faster in=20 > SRV2), but the scripts envolving heav=3D y reading operations were about= =20 > 1,5 times slow in the best cases, reaching =3D > 2,5 times slow in the worse cases.=20 >=20 > In this unexpected scenario, I looked for an IDS independent=20 > benchmarking t=3D ool and I found a suite called "phoronix test suite"=20 > (PTS). I was decided t=3D o find the bottleneck in SRV2... but again the= =20 > results of the PTS surprised=3D me. I ran various test, with the followin= g results: >=20 > - pts/SmallPT (CPU test. Less is better) > SRV1: 192 > SRV2: 141=20 > (better) > - pts/Apache (CPU test. More is better) > SRV1: 7017.65 > SRV2:=20 > 9547.57 (be=3D > tter) > - pts/aio-stress (I/O test. Random Write. More is better) > SRV1:=20 > 22.06 > S=3D > RV2: 881.51 (better) > - pts/iozone (I/O test. Read Performance: 1MB record / 2GB file. More=20 > is be=3D > tter) > SRV1: 728.09 > SRV2: 2008.14 (better) > - pts/iozone (I/O test. Read Performance: 1MB record / 4GB file. More=20 > is be=3D > tter) > SRV1: 824.98 > SRV2: 1985.23 (better) > - pts/iozone (I/O test. Read Performance: 1MB record / 8GB file. More=20 > is be=3D > tter) > SRV1: 768.30 > SRV2: 1906.90(better) > - pts/iozone (I/O test. Read Performance: 4KB record / 2GB file. More=20 > is be=3D > tter) > SRV1: 1016.75 > SRV2: 2113.92 (better) > - pts/iozone (I/O test. Read Performance: 4KB record / 4GB file. More=20 > is be=3D > tter) > SRV1: 1071.86 > SRV2: 1953.93 (better) > - pts/iozone (I/O test. Read Performance: 4KB record / 8GB file. More=20 > is be=3D > tter) > SRV1: 1086.07 > SRV2: 1794.42 (better) > - pts/iozone (I/O test. Write Performance: 1MB record / 2GB file. More=20 > is b=3D > etter) > SRV1: 25.38 > SRV2: 97.64 (better) > - pts/iozone (I/O test. Write Performance: 1MB record / 4GB file. More=20 > is b=3D > etter) > SRV1: 26.28 > SRV2: 114.04 (better) > - pts/iozone (I/O test. Write Performance: 1MB record / 8GB file. More=20 > is b=3D > etter) > SRV1: 28.36 > SRV2: 144.49 (better) > - pts/iozone (I/O test. Write Performance: 4KB record / 2GB file. More=20 > is b=3D > etter) > SRV1: 26.17 > SRV2: 91.99 (better) > - pts/iozone (I/O test. Write Performance: 4KB record / 4GB file. More=20 > is b=3D > etter) > SRV1: 26.35 > SRV2: 108.19 (better) > - pts/iozone (I/O test. Write Performance: 4KB record / 8GB file. More=20 > is b=3D > etter) > SRV1: 28.62 > SRV2: 144.37 (better) > - pts/ramspeed (RAM test. Add integer. More is better) > SRV1: 3533.75=20 > > SR=3D > V2: 6782.31 (better) > - pts/ramspeed (RAM test. Copy integer. More is better) > SRV1:=20 > 3418.95 > S=3D > RV2: 6782.31 (better) > - pts/ramspeed (RAM test. Scale integer. More is better) > SRV1:=20 > 3448.33 > =3D > SRV2: 6776.20 (better) > - pts/ramspeed (RAM test. Triad integer. More is better) > SRV1:=20 > 3499.36 > =3D > SRV2: 6536.23 (better) > - pts/ramspeed (RAM test. Average integer. More is better) > SRV1:=20 > 3453.82 =3D > > SRV2: 6851.13 (better) > - pts/ramspeed (RAM test. Add floating point. More is better) > SRV1:=20 > 3955.=3D > 16 > SRV2: 7241.65 (better) > - pts/ramspeed (RAM test. Copy floating point. More is better) > SRV1:=20 > 3599=3D > ..66 > SRV2: 7178.45 (better) > - pts/ramspeed (RAM test. Scale floating point. More is better) >=20 > SRV1: 339=3D > 9.08 > SRV2: 7286.11 (better) > - pts/ramspeed (RAM test. Triad floating point. More is better) >=20 > SRV1: 385=3D > 5.18 > SRV2: 7461.69 (better) > - pts/ramspeed (RAM test. Average floating point. More is better) >=20 > SRV1: 3=3D > 647.64 > SRV2: 7351.95 (better) >=20 > In these test, SRV2 outperforms SRV1 in a clear and consistent way in=20 > any o=3D f the evaluated fields (Processor, I/O and Memory). But the IDS= =20 > 12.10.FC3WE=3D still runs slowly in SRV2 when I execute massive read=20 > operations (by examp=3D le, update statistics over my test db is 136%=20 > more slow than the same opera=3D tion o

Hello John! The versi=F3n of IDS is the same in my both servers (12.10 FC3). The diffe= rences are in the hardware. One of the servers is a 7 years old phisical ma= chine (HP Proliant 585 G1) and the other is a virtual server over VMWare on= modern hardware (HP Proliant 385 G7). I suppose that update statistics is a heavy read process and maybe I could= be in a mistake. In any case, the update statistics process is significati= vely slow in the virtual server compared to the "old" phisycal one, and thi= s is unexpected to me, because all the phoronix tests (CPU, Memory and HDD)= are better in the virtual server. Thank you very much for your interest. Best regards. -- Javier Perez Arenal - jperez@uniovi.es Jefe del Area T=E9cnica de Inform=E1tica y Comunicaciones=20 Vicerrectorado de Campus, Inform=E1tica e Infraestructuras Universidad de Oviedo=20 Edificio Severo Ochoa=20 C/ Fernando Bongera s/n, Campus del Cristo 33006 - Oviedo, Asturias -----Mensaje original----- De: ids-bounces@iiug.org [mailto:ids-bounces@iiug.org] En nombre de John Mi= ller iii Enviado el: martes, 27 de mayo de 2014 19:31 Para: ids@iiug.org Asunto: RE: Poor performance on VMWare [33108] You example provided of update statistics is probably not the best exam=3D = ple.=20 The assumption made is that update statistics of an older Informix serv=3D = er is the same as a new Informix server and that a majority of the time it = is doing I/=3D O.=20 Update statisticshas been changed significantly over time and it can end up doing work t=3D = o cleanup older style indexes which are inefficient.=20 John F. Miller III STSM, Lead Architect miller3@us.ibm.com 503-747-1366 IBM Informix Dynamic Server (IDS)=20 ids-bounces@iiug.org wrote on 05/26/2014 07:26:09 AM:=20 > From: "Alexandre Marini" <alexandre@briug.org> > To: ids@iiug.org, > Date: 05/26/2014 07:27 AM > Subject: RE: Poor performance on VMWare [33100] Sent by:=20 > ids-bounces@iiug.org >=20 > Hello, Javier.=20 > My personal opinion is that you might have a better performance, but =3D you=20 > should not use the same onconfig file.=20 >=20 > 1) Are you really using cooked files? If so, please forget them. Chan=3D ge your=20 > chunks to raw devices, and make sure you are not using a bad RAID lev=3D el in=20 > your storage.=20 >=20 > 2) You could start a performance tunning process after topic 1 is sol=3D ved.=20 > Informix 12 have several features that might benefit your=20 > performance, even in=20 > VMs environments. Eg: are you using cpu vp memory caches? Are you usi=3D= =20 ng=20 RTO=20 > policies? Are you using alice index cleaner mode (OLTP system)?=20 >=20 > 3) You might also check other topics, but as a start phase, I=3DB4d go = =3D=20 for=20 all of=20 > mentioned ones first.=20 >=20 > Hope it helps.=20 > Regards.=20 >=20 > Alexandre Marini=20 > IBM Informix Certified Professional v10 / v11.50 / v11.70 / v12.10=20 >=20 > IBM Information Management Informix Technical Professional=20 >=20 > IBM Infosphere DataStage Technical Professional=20 > Informix Senior DBA - Orizon Brasil=20 > BRIUG website administrator=20 > Informix independent consultant=20 >=20 > > To: ids@iiug.org=20 > > From: jperez@uniovi.es=20 > > Subject: Poor performance on VMWare [33099]=20 > > Date: Mon, 26 May 2014 09:44:07 -0400=20 > >=20 > > Hello=20 > >=20 > > I want to know some expert opinion about one IDS 12.10.FC3WE test=20 > that I ha=3D3D=20 > > ve currently executing in two machines. This machines are:=20 > >=20 > > SRV1: (+7 years old) HP Proliant DL585 G1=20 > > - 4xAMD Opteron 820 2.3GHz (2 cores x processor for a total of 8 co=3D= =20 res)=20 > > - 16 GB RAM=20 > > - Local HDD on 146GB Ultra320 SCSI=20 > > - Informix storage: cooked files=20 > > - Red Hat 5.9 x64=20 > >=20 > > SRV2: VMWare Virtual server=20 > > - 8xvCPU (reported as AMD Opteron 6176 SE 2,3GHz)=20 > > - 16 GB RAM=20 > > - SAN (HP EVA6500) HDD on 2TB 7.2K EVA SAS MDL disk pool (Mapped RA=3D= =20 W=20 LUN)=20 > > - SAN conectivity: 1Gbps iSCSI (server side) 10Gbps (SAN side)=20 > > - Informix storage: cooked files=20 > > - Red Hat 6.5 x64=20 > >=20 > > With these technical data, I am expected that the SRV2 results=20 > were better =3D3D=20 > > than the SRV2 ones (and more knowing the SRV1 "age").=20 > >=20 > > When I ran some scripts, stored procedures (SPL) and update=20 > statistics, I w=3D3D=20 > > as surprised by the results. The massive write operations were=20 > slightly bet=3D3D=20 > > ter on SRV2 (import was 40% faster in SRV2), but the scripts=20 > envolving heav=3D3D=20 > > y reading operations were about 1,5 times slow in the best cases,=20 > reaching =3D3D=20 > > 2,5 times slow in the worse cases.=20 > >=20 > > In this unexpected scenario, I looked for an IDS independent=20 > benchmarking t=3D3D=20 > > ool and I found a suite called "phoronix test suite" (PTS). I was=20 > decided t=3D3D=20 > > o find the bottleneck in SRV2... but again the results of the PTS=20 > surprised=3D3D=20 > > me. I ran various test, with the following results:=20 > >=20 > > - pts/SmallPT (CPU test. Less is better) > SRV1: 192 > SRV2: 141=20 (better)=20 > > - pts/Apache (CPU test. More is better) > SRV1: 7017.65 > SRV2:=20 > 9547.57 (be=3D3D=20 > > tter)=20 > > - pts/aio-stress (I/O test. Random Write. More is better) > SRV1:=20 > 22.06 > S=3D3D=20 > > RV2: 881.51 (better)=20 > > - pts/iozone (I/O test. Read Performance: 1MB record / 2GB file.=20 > More is be=3D3D=20 > > tter) > SRV1: 728.09 > SRV2: 2008.14 (better)=20 > > - pts/iozone (I/O test. Read Performance: 1MB record / 4GB file.=20 > More is be=3D3D=20 > > tter) > SRV1: 824.98 > SRV2: 1985.23 (better)=20 > > - pts/iozone (I/O test. Read Performance: 1MB record / 8GB file.=20 > More is be=3D3D=20 > > tter) > SRV1: 768.30 > SRV2: 1906.90(better)=20 > > - pts/iozone (I/O test. Read Performance: 4KB record / 2GB file.=20 > More is be=3D3D=20 > > tter) > SRV1: 1016.75 > SRV2: 2113.92 (better)=20 > > - pts/iozone (I/O test. Read Performance: 4KB record / 4GB file.=20 > More is be=3D3D=20 > > tter) > SRV1: 1071.86 > SRV2: 1953.93 (better)=20 > > - pts/iozone (I/O test. Read Performance: 4KB record / 8GB file.=20 > More is be=3D3D=20 > > tter) > SRV1: 1086.07 > SRV2: 1794.42 (better)=20 > > - pts/iozone (I/O test. Write Performance: 1MB record / 2GB file.=20 > More is b=3D3D=20 > > etter) > SRV1: 25.38 > SRV2: 97.64 (better)=20 > > - pts/iozone (I/O test. Write Performance: 1MB record / 4GB file.=20 > More is b=3D3D=20 > > etter) > SRV1: 26.28 > SRV2: 114.04 (better)=20 > > - pts/iozone (I/O test. Write Performance: 1MB record / 8GB file.=20 > More is b=3D3D=20 > > etter) > SRV1: 28.36 > SRV2: 144.49 (better)=20 > > - pts/iozone (I/O test. Write Performance: 4KB record / 2GB file.=20 > More is b=3D3D=20 > > etter) > SRV1: 26.17 > SRV2: 91.99 (better)=20 > > - pts/iozone (I/O test. Write Performance: 4KB record / 4GB file.=20 > More is b=3D3D=20@@NL@

Hi Javier, Very interesting (and topical) topic. Interesting to note SRVR1 is on RH 5.3 and SRVR2 is on (virtual) RH 6.3 From onstat -g ath, do you see "kaio" in both servers? When you start up the engine, there should be quite a few messages reported up to "On-line mode" ... can you post them? JJ

Hi Jon The onstat -g ath command: [informix@ifx1 ~]$ onstat -g ath | grep kaio 45 48dd0d30 0 3 IO Idle 8c= pu* kaio 46 48dd20e0 0 3 IO Idle 1c= pu* kaio 73 49408698 0 3 IO Idle 10c= pu* kaio 79 492237b8 0 3 IO Idle 9c= pu* kaio 85 49223530 0 3 IO Idle 11c= pu* kaio 92 494509b8 0 3 IO Idle 12c= pu* kaio I ran also onstat -g iov with this results (I think this could be relevant= ): [informix@ifx1 ~]$ onstat -g iov IBM Informix Dynamic Server Version 12.10.FC3WE -- On-Line -- Up 00:13:13 -=- 5840896 Kbytes AIO I/O vps: class/vp/id s io/s totalops dskread dskwrite dskcopy wakeups io/wup e= rrors tempops fifo 7 0 i 0.0 0 0 0 0 1 0.0 = 0 0 kio -1 0 i 50.5 39984 39963 21 0 58051 0.7 = 0 0 kio -1 1 i 55.0 43565 43543 22 0 62181 0.7 = 0 0 kio -1 2 i 28.5 22558 22547 11 0 33011 0.7 = 0 0 kio -1 3 i 41.6 32908 32896 12 0 47171 0.7 = 0 0 kio -1 4 i 7.8 6173 6171 2 0 9215 0.7 = 0 0 kio -1 5 i 1.4 1100 1094 6 0 1450 0.8 = 0 0 msc 6 0 i 0.0 5 0 0 0 6 0.8 = 0 5 aio 5 0 i 62.8 49777 48764 837 0 49690 1.0 = 0 49607 aio 17 1 i 0.5 373 148 224 0 415 0.9 = 0 370 aio 18 2 i 0.3 218 148 69 0 196 1.1 = 0 214 aio 19 3 i 0.1 59 3 55 0 34 1.7 = 0 56 aio 20 4 i 0.1 44 0 43 0 26 1.7 = 0 40 aio 21 5 i 0.0 35 1 34 0 23 1.5 = 0 32 pio 4 0 i 0.0 0 0 0 0 1 0.0 = 0 0 lio 3 0 i 0.0 0 0 0 0 1 0.0 = 0 0 ... and this is the online.log fragment corresponding to the RDBMS start: Fri May 30 09:35:14 2014 09:35:14 Requested shared memory segment size rounded from 4498176KB to 44= 99456KB 09:35:14 Shared memory segment will use huge pages. 09:35:14 Segment locked: addr=3D0x95e00000, size=3D4607442944 09:35:19 Successfully added a bufferpool of page size 2K. 09:35:20 Event alarms enabled. ALARMPROG =3D '/opt/IBM/informix/etc/alarm= program.sh' 09:35:20 Booting Language <c> from module <> 09:35:20 Loading Module <CNULL> 09:35:20 Booting Language <builtin> from module <> 09:35:20 Loading Module <BUILTINNULL> 09:35:25 Affinitied VP 8 to phys proc 1 09:35:25 Affinitied VP 9 to phys proc 2 09:35:26 Affinitied VP 10 to phys proc 3 09:35:26 Affinitied VP 11 to phys proc 4 09:35:26 Affinitied VP 12 to phys proc 5 09:35:26 Affinitied VP 1 to phys proc 0 09:35:26 Affinitied VP 12 to phys proc 5 09:35:26 Affinitied VP 10 to phys proc 3 09:35:26 Affinitied VP 9 to phys proc 2 09:35:26 Affinitied VP 8 to phys proc 1 09:35:26 Affinitied VP 11 to phys proc 4 09:35:26 DR: DRAUTO is 0 (Off) 09:35:26 DR: ENCRYPT_HDR is 0 (HDR encryption Disabled) 09:35:26 Event notification facility epoll enabled. 09:35:27 IBM Informix Dynamic Server Version 12.10.FC3WE Software Serial N= umber AAA#B000000 09:35:29 IBM Informix Dynamic Server Initialized -- Shared Memory Initiali= zed. 09:35:29 Started 1 B-tree scanners. 09:35:29 B-tree scanner threshold set at 5000. 09:35:29 B-tree scanner range scan size set to -1. 09:35:29 B-tree scanner ALICE mode set to 6. 09:35:29 B-tree scanner index compression level set to med. 09:35:29 Physical Recovery Started at Page (8:23219). 09:35:29 Physical Recovery Complete: 0 Pages Examined, 0 Pages Restored. 09:35:30 Logical Recovery Started. 09:35:30 12 recovery worker threads will be started. 09:35:30 Logical Recovery has reached the transaction cleanup phase. 09:35:30 Logical Recovery Complete. 0 Committed, 0 Rolled Back, 0 Open, 0 Bad Locks 09:35:32 Onconfig parameter LOGFILES modified from 4 to 20. 09:35:32 Dataskip is now OFF for all dbspaces 09:35:33 Checkpoint Completed: duration was 1 seconds. 09:35:33 Fri May 30 - loguniq 201, logpos 0x4dac0c0, timestamp: 0x73c6b4c = Interval: 685 09:35:33 Maximum server connections 0 09:35:33 Checkpoint Statistics - Avg. Txn Block Time 0.000, # Txns blocked= 0, Plog used 3, Llog used 1 09:35:33 On-Line Mode 09:35:34 SCHAPI: Started dbScheduler thread. 09:35:36 Booting Language <spl> from module <> 09:35:36 Loading Module <SPLNULL> 09:35:36 Auto Registration is synced 09:35:36 SCHAPI: Started 2 dbWorker threads. 09:35:37 Defragmenter cleaner thread now running 09:35:37 Defragmenter cleaner thread cleaned:0 partitions Sorry for the delay in my answer, but I am investigating this issue in my = free time. Thanks in advance! -- Javier Perez Arenal - jperez@uniovi.es Jefe del Area T=E9cnica de Inform=E1tica y Comunicaciones=20 Vicerrectorado de Campus, Inform=E1tica e Infraestructuras Universidad de Oviedo=20 Edificio Severo Ochoa=20 C/ Fernando Bongera s/n, Campus del Cristo 33006 - Oviedo, Asturias -----Mensaje original----- De: ids-bounces@iiug.org [mailto:ids-bounces@iiug.org] En nombre de JON RIT= SON Enviado el: mi=E9rcoles, 28 de mayo de 2014 18:01 Para: ids@iiug.org Asunto: Re: RE: Poor performance on VMWare [33118] Hi Javier,=20 Very interesting (and topical) topic.=20 Interesting to note SRVR1 is on RH 5.3 and SRVR2 is on (virtual) RH 6.3=20 >From onstat -g ath, do you see "kaio" in both servers?=20 When you start up the engine, there should be quite a few messages reported= up to "On-line mode" ... can you post them?=20 JJ=20 ***************************************************************************= **** Forum Note: Use "Reply" to post a response in the discussion forum.=20

Turn off affinity. It only helps on Numa architecture machines and can hurt performance on most systems. Not your main problem I think, but ... Art Art S. Kagel, Principal Consultant ASK Database Management Blog: http://informix-myview.blogspot.com/ Disclaimer: Please keep in mind that my own opinions are my own opinions and do not reflect on the IIUG, nor any other organization with which I am associated either explicitly, implicitly, or by inference. Neither do those opinions reflect those of other individuals affiliated with any entity with which I am affiliated nor those of the entities themselves. On Fri, May 30, 2014 at 3:53 AM, JAVIER PEREZ ARENAL <jperez@uniovi.es> wrote: > Hi Jon > > The onstat -g ath command: > > [informix@ifx1 ~]$ onstat -g ath | grep kaio > 45 48dd0d30 0 3 IO Idle 8c= > pu* kaio > 46 48dd20e0 0 3 IO Idle 1c= > pu* kaio > 73 49408698 0 3 IO Idle 10c= > pu* kaio > 79 492237b8 0 3 IO Idle 9c= > pu* kaio > 85 49223530 0 3 IO Idle 11c= > pu* kaio > 92 494509b8 0 3 IO Idle 12c= > pu* kaio > > I ran also onstat -g iov with this results (I think this could be relevant= > ): > > [informix@ifx1 ~]$ onstat -g iov > > IBM Informix Dynamic Server Version 12.10.FC3WE -- On-Line -- Up 00:13:13 > -=> - 5840896 Kbytes > > AIO I/O vps: > class/vp/id s io/s totalops dskread dskwrite dskcopy wakeups io/wup e= > rrors tempops > fifo 7 0 i 0.0 0 0 0 0 1 0.0 = > 0 0 > kio -1 0 i 50.5 39984 39963 21 0 58051 0.7 = > 0 0 > kio -1 1 i 55.0 43565 43543 22 0 62181 0.7 = > 0 0 > kio -1 2 i 28.5 22558 22547 11 0 33011 0.7 = > 0 0 > kio -1 3 i 41.6 32908 32896 12 0 47171 0.7 = > 0 0 > kio -1 4 i 7.8 6173 6171 2 0 9215 0.7 = > 0 0 > kio -1 5 i 1.4 1100 1094 6 0 1450 0.8 = > 0 0 > msc 6 0 i 0.0 5 0 0 0 6 0.8 = > 0 5 > aio 5 0 i 62.8 49777 48764 837 0 49690 1.0 = > 0 49607 > aio 17 1 i 0.5 373 148 224 0 415 0.9 = > 0 370 > aio 18 2 i 0.3 218 148 69 0 196 1.1 = > 0 214 > aio 19 3 i 0.1 59 3 55 0 34 1.7 = > 0 56 > aio 20 4 i 0.1 44 0 43 0 26 1.7 = > 0 40 > aio 21 5 i 0.0 35 1 34 0 23 1.5 = > 0 32 > pio 4 0 i 0.0 0 0 0 0 1 0.0 = > 0 0 > lio 3 0 i 0.0 0 0 0 0 1 0.0 = > 0 0 > > .... and this is the online.log fragment corresponding to the RDBMS start: > > Fri May 30 09:35:14 2014 > > 09:35:14 Requested shared memory segment size rounded from 4498176KB to 44= > 99456KB > 09:35:14 Shared memory segment will use huge pages. > 09:35:14 Segment locked: addr=3D0x95e00000, size=3D4607442944 > 09:35:19 Successfully added a bufferpool of page size 2K. > > 09:35:20 Event alarms enabled. ALARMPROG =3D '/opt/IBM/informix/etc/alarm= > program.sh' > 09:35:20 Booting Language <c> from module <> > 09:35:20 Loading Module <CNULL> > 09:35:20 Booting Language <builtin> from module <> > 09:35:20 Loading Module <BUILTINNULL> > 09:35:25 Affinitied VP 8 to phys proc 1 > 09:35:25 Affinitied VP 9 to phys proc 2 > 09:35:26 Affinitied VP 10 to phys proc 3 > 09:35:26 Affinitied VP 11 to phys proc 4 > 09:35:26 Affinitied VP 12 to phys proc 5 > 09:35:26 Affinitied VP 1 to phys proc 0 > 09:35:26 Affinitied VP 12 to phys proc 5 > 09:35:26 Affinitied VP 10 to phys proc 3 > 09:35:26 Affinitied VP 9 to phys proc 2 > 09:35:26 Affinitied VP 8 to phys proc 1 > 09:35:26 Affinitied VP 11 to phys proc 4 > 09:35:26 DR: DRAUTO is 0 (Off) > 09:35:26 DR: ENCRYPT_HDR is 0 (HDR encryption Disabled) > 09:35:26 Event notification facility epoll enabled. > 09:35:27 IBM Informix Dynamic Server Version 12.10.FC3WE Software Serial N= > umber AAA#B000000 > 09:35:29 IBM Informix Dynamic Server Initialized -- Shared Memory Initiali= > zed. > > 09:35:29 Started 1 B-tree scanners. > 09:35:29 B-tree scanner threshold set at 5000. > 09:35:29 B-tree scanner range scan size set to -1. > 09:35:29 B-tree scanner ALICE mode set to 6. > 09:35:29 B-tree scanner index compression level set to med. > 09:35:29 Physical Recovery Started at Page (8:23219). > 09:35:29 Physical Recovery Complete: 0 Pages Examined, 0 Pages Restored. > 09:35:30 Logical Recovery Started. > 09:35:30 12 recovery worker threads will be started. > 09:35:30 Logical Recovery has reached the transaction cleanup phase. > 09:35:30 Logical Recovery Complete. > > 0 Committed, 0 Rolled Back, 0 Open, 0 Bad Locks > > 09:35:32 Onconfig parameter LOGFILES modified from 4 to 20. > 09:35:32 Dataskip is now OFF for all dbspaces > 09:35:33 Checkpoint Completed: duration was 1 seconds. > 09:35:33 Fri May 30 - loguniq 201, logpos 0x4dac0c0, timestamp: 0x73c6b4c = > Interval: 685 > > 09:35:33 Maximum server connections 0 > 09:35:33 Checkpoint Statistics - Avg. Txn Block Time 0.000, # Txns blocked= > 0, Plog used 3, Llog used 1 > > 09:35:33 On-Line Mode > 09:35:34 SCHAPI: Started dbScheduler thread. > 09:35:36 Booting Language <spl> from module <> > 09:35:36 Loading Module <SPLNULL> > 09:35:36 Auto Registration is synced > 09:35:36 SCHAPI: Started 2 dbWorker threads. > 09:35:37 Defragmenter cleaner thread now running > 09:35:37 Defragmenter cleaner thread cleaned:0 partitions > > Sorry for the delay in my answer, but I am investigating this issue in my = > free time. > > Thanks in advance! > > -- > Javier Perez Arenal - jperez@uniovi.es > Jefe del Area T=E9cnica de Inform=E1tica y Comunicaciones=20 > Vicerrectorado de Campus, Inform=E1tica e Infraestructuras > Universidad de Oviedo=20 > Edificio Severo Ochoa=20 > C/ Fernando Bongera s/n, Campus del Cristo > 33006 - Oviedo, Asturias > > -----Mensaje original----- > De: ids-bounces@iiug.org [mailto:ids-bounces@iiug.org] En nombre de JON > RIT= > SON > Enviado el: mi=E9rcoles, 28 de mayo de 2014 18:01 > Para: ids@iiug.org > Asunto: Re: RE: Poor performance on VMWare [33118] > > Hi Javier,=20 > > Very interesting (and topical) topic.=20 > > Interesting to note SRVR1 is on RH 5.3 and SRVR2 is on (virtual) RH 6.3=20 > > >From onstat -g ath, do you see "kaio" in both servers?=20 > > When you start up the engine, there should be quite a few messages > reported= > up to "On-line mode" ... can you post them?=20 > > JJ=20 > > > ***************************************************************************= > **** > Forum Note: Use "Reply" to post a response in the discussion forum.=20 > > > > ******************************************************************************* > Forum Note: Use "Reply" to post a response in the discussion forum. > > --089e0149401ae3a1ca04fa9b73d2