(BHello. (BI tried performance test of version 8.0.0 beta4 by osdl-dbt-1. (BThe result is that throughput of version 8 fell to about 70 percent (Bcompared with V7.4.6. (BTest result is below. (measurement was repeated 3 times) (B (B------------------------------------------------------- (BHardware spec $B!!(BCPU$B!!!!!!(BPentium $B-7(B 531.986 MHz $B!!(BMemory$B!!!!(B125660 Kb (B------------------------------------------------------- (BSoftware version $B!!(BOS$B!!(BLinux Kernel:2.4.21-4.EL $B!!(BDistribution: Red Hat Enterprise Linux AS release 3 (B------------------------------------------------------- (BResult$B!J(Btransaction per second$B!K(B (B first second third (B 7.4.6 $B!!(B 6.8 6.8 5.9 (B 8.0 beta4 4.3 4.6 $B!!(B4.4 (B------------------------------------------------------- (BParameter of DBT1,PostgreSQL $B!!(BDatabase Size (items): 1000 $B!!(BDatabase Size (customers): 10 $B!!(Bnumber of cache: 1 $B!!(Bnumber of connections between cache and database: 10 $B!!(Bnumber of application server: 1 $B!!(Bnumber of connections between server and database: 20 $B!!(Bnumber of drivers: 1 $B!!(Beus/driver: 100 $B!!(Brampuprate/driver: 60 $B!!(Bduration/driver: 900 $B!!(Bthinktime/driver: 1.6 $B!!(BPut WAL on different driver: 0 $B!!(BPut pgsql_tmp on different driver: 0 $B!!(Bdatabase parameters: -i -c listen_addresses='*' $B!!(Bshmmax: 33554432 (B------------------------------------------------------- (B (B- Both version 8 and version 7 are performed under the same condition. (B- Tuning of adjustment of a parameter was not carried out at all. (B- The server and client process are performed in the same machine. (B (BIs there the weak point on the performance in version 8.0.0 ? (B (BAny help would greatly appreciated. (B (B kondou (B (B---------------------------(end of broadcast)--------------------------- (BTIP 3: if posting/reading through Usenet, please send an appropriate (B subscribe-nomail command to [EMAIL PROTECTED] so that your (B message can get through to the mailing list cleanly