Re: Slow OS calls on one chip type

"Bartlomiej Lidke" <ohggurnq@rcs.cy.rot13.invalid> wrote in message news:hrsh37$v2i$1@news.onet.pl... > Art Kagel <art.kagel@gmail.com> wrote: >> The BIG problem are the 6.7MILLION failed calls to the OS close() >> system call! > > they propably come from a post fork/clone loop that is clearing > the file descriptors before a new shell is being called using execve > (something like for (i=3; i<65536; i++) close(i)) > > each '!echo "something"' line produces extra 65536-3 failed (EBADF) > 'close' calls > > 'close' on non-valid file desciptors can be easily benchmarked on > both systems just to be sure that it is not a kernel issue > > also the strace can show what happens between execve and write(1,..) > call (from "echo") on both systems (like scanning NFS directories > that are on the PATH or LD_LIBRARY_PATH or something like that) Art's reply is nowhere present on comp.databases.informix. I STILL think there's a problem with the feed .... Anyway, could somcseone else with RHEL 5.3 on AMD procs try it? Thanks!!!!: $ time dbaccess sysmaster < crap5.sql Database selected. Hello World Hello World Hello World ... Hello World Hello World Database closed. real 0m6.714s user 0m0.017s sys 0m0.041s $ cat crap5.sql!echo "Hello World" !echo "Hello World" !echo "Hello World" !echo "Hello World" !echo "Hello World" !echo "Hello World" !echo "Hello World" !echo "Hello World" !echo "Hello World" !echo "Hello World" !echo "Hello World" !echo "Hello World" !echo "Hello World" !echo "Hello World" !echo "Hello World" !echo "Hello World" !echo "Hello World" !echo "Hello World" !echo "Hello World" !echo "Hello World" !echo "Hello World" !echo "Hello World" !echo "Hello World" !echo "Hello World" !echo "Hello World" !echo "Hello World" !echo "Hello World" !echo "Hello World" !echo "Hello World" !echo "Hello World" !echo "Hello World" !echo "Hello World" !echo "Hello World" !echo "Hello World" !echo "Hello World" !echo "Hello World" !echo "Hello World" !echo "Hello World" !echo "Hello World" !echo "Hello World" !echo "Hello World" !echo "Hello World" !echo "Hello World" !echo "Hello World" !echo "Hello World" !echo "Hello World" !echo "Hello World" !echo "Hello World" !echo "Hello World" !echo "Hello World" !echo "Hello World" !echo "Hello World" !echo "Hello World" !echo "Hello World" !echo "Hello World" !echo "Hello World" !echo "Hello World" !echo "Hello World" !echo "Hello World" !echo "Hello World" !echo "Hello World" !echo "Hello World" !echo "Hello World" !echo "Hello World"

Closest I have quick access to is Ubuntu 9 on AMD Athlon 64 X2 4200+: $ uname -a Linux galadriel-ii 2.6.31-21-generic #59-Ubuntu SMP Wed Mar 24 07:28:27 UTC2010 x86_64 GNU/Linux $ $ time dbaccess sysmaster - <crap5.sql Database selected. Hello World Hello World ... Hello World Hello World Database closed. real 0m0.570s user 0m0.000s sys 0m0.050s $ $ cat /proc/cpuinfoprocessor : 0 vendor_id : AuthenticAMD cpu family : 15 model : 43 model name : AMD Athlon(tm) 64 X2 Dual Core Processor 4200+ stepping : 1 cpu MHz : 1000.000 cache size : 512 KB physical id : 0 siblings : 2 core id : 0 cpu cores : 2 apicid : 0 initial apicid : 0 fpu : yes fpu_exception : yes cpuid level : 1 wp : yes flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt lm 3dnowext 3dnow rep_good pni la hf_lm cmp_legacy bogomips : 1990.15 TLB size : 1024 4K pages clflush size : 64 cache_alignment : 64 address sizes : 40 bits physical, 48 bits virtual power management: ts fid vid ttp processor : 1 vendor_id : AuthenticAMD cpu family : 15 model : 43 model name : AMD Athlon(tm) 64 X2 Dual Core Processor 4200+ stepping : 1 cpu MHz : 1000.000 cache size : 512 KB physical id : 0 siblings : 2 core id : 1 cpu cores : 2 apicid : 1 initial apicid : 1 fpu : yes fpu_exception : yes cpuid level : 1 wp : yes flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt lm 3dnowext 3dnow rep_good pni la hf_lm cmp_legacy bogomips : 1990.15 TLB size : 1024 4K pages clflush size : 64 cache_alignment : 64 address sizes : 40 bits physical, 48 bits virtual power management: ts fid vid ttp Art Art S. Kagel Advanced DataTools (www.advancedatatools.com) IIUG Board of Directors (art@iiug.org) See you at the 2010 IIUG Informix Conference April 25-28, 2010 Overland Park (Kansas City), KS www.iiug.org/conf Disclaimer: Please keep in mind that my own opinions are my own opinions and do not reflect on my employer, Advanced DataTools, 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 Wed, May 5, 2010 at 6:38 PM, Neil Truby <neil.truby@ardenta.com> wrote: > "Bartlomiej Lidke" <ohggurnq@rcs.cy.rot13.invalid> wrote in message > news:hrsh37$v2i$1@news.onet.pl... > > Art Kagel <art.kagel@gmail.com> wrote: > >> The BIG problem are the 6.7MILLION failed calls to the OS close() > >> system call! > > > > they propably come from a post fork/clone loop that is clearing > > the file descriptors before a new shell is being called using execve > > (something like for (i=3; i<65536; i++) close(i)) > > > > each '!echo "something"' line produces extra 65536-3 failed (EBADF) > > 'close' calls > > > > 'close' on non-valid file desciptors can be easily benchmarked on > > both systems just to be sure that it is not a kernel issue > > > > also the strace can show what happens between execve and write(1,..) > > call (from "echo") on both systems (like scanning NFS directories > > that are on the PATH or LD_LIBRARY_PATH or something like that) > > Art's reply is nowhere present on comp.databases.informix. I STILL think > there's a problem with the feed .... > > Anyway, could somcseone else with RHEL 5.3 on AMD procs try it? > Thanks!!!!: > $ time dbaccess sysmaster < crap5.sql> > Database selected. > > Hello World > Hello World > Hello World > ... > Hello World > Hello World > > > Database closed. > > > real 0m6.714s > user 0m0.017s > sys 0m0.041s > > $ cat crap5.sql> !echo "Hello World" > !echo "Hello World" > !echo "Hello World" > !echo "Hello World" > !echo "Hello World" > !echo "Hello World" > !echo "Hello World" > !echo "Hello World" > !echo "Hello World" > !echo "Hello World" > !echo "Hello World" > !echo "Hello World" > !echo "Hello World" > !echo "Hello World" > !echo "Hello World" > !echo "Hello World" > !echo "Hello World" > !echo "Hello World" > !echo "Hello World" > !echo "Hello World" > !echo "Hello World" > !echo "Hello World" > !echo "Hello World" > !echo "Hello World" > !echo "Hello World" > !echo "Hello World" > !echo "Hello World" > !echo "Hello World" > !echo "Hello World" > !echo "Hello World" > !echo "Hello World" > !echo "Hello World" > !echo "Hello World" > !echo "Hello World" > !echo "Hello World" > !echo "Hello World" > !echo "Hello World" > !echo "Hello World" > !echo "Hello World" > !echo "Hello World" > !echo "Hello World" > !echo "Hello World" > !echo "Hello World" > !echo "Hello World" > !echo "Hello World" > !echo "Hello World" > !echo "Hello World" > !echo "Hello World" > !echo "Hello World" > !echo "Hello World" > !echo "Hello World" > !echo "Hello World" > !echo "Hello World" > !echo "Hello World" > !echo "Hello World" > !echo "Hello World" > !echo "Hello World" > !echo "Hello World" > !echo "Hello World" > !echo "Hello World" > !echo "Hello World" > !echo "Hello World" > !echo "Hello World" > !echo "Hello World" > > > > > > > _______________________________________________ > Informix-list mailing list > Informix-list@iiug.org > http://www.iiug.org/mailman/listinfo/informix-list >