need help for Informix 5.10 slowness in I/O

Our Informix 5.10 under Sequent ptx 4.4 has encountered slowness issue. The major cause is due to the disk I/O contention. Below is the output of the command, sar -d 10, as you can see that the contention occurred in disk area (data: sd02010, sd02011, sd02012, sd02013, and mirror: sd02110, sd02111, sd02112, sd02113). This was the result from consolidation of the large table extends into one extend, which is a good practice recommended by Online 5. However this practice causes the disk I/O contention! What is the best way to manage the data distribution? We have stored the data in the separated dbspace from the rootdbs. Is there anyway to adjust the data among the disks since 5.10 doesn't support the table fragment? Another option is to increase the BUFFER number (currently set as 28000). What's the best number? The application system here doesn't use the transaction. So LRUS = 32, LRU_MAX_DIRTY = 8 , and LRU_MIN_DIRTY = 3. They appear not good. What's the best figures to reduce the disk I/O? Your prompt suggestion will be appreciated. Alex. 703-762-5020 === DYNIX/ptx numaq 4.0 V4.4.4 i386 05/01/00 10:26:35 device %busy avque r+w/s blks/s avwait avserv 10:26:37 sd01001 3 1.0 3 41 0.0 11.7 sd01002 4 1.0 3 18 0.0 13.3 sd01003 3 1.0 3 41 0.0 10.0 sd02000 2 1.0 2 17 0.0 8.0 sd02001 5 1.0 4 32 0.0 12.2 sd02002 2 1.0 2 12 0.0 12.5 sd02003 7 1.0 4 26 0.0 15.6 sd02010 95 5.0 82 896 46.2 11.6 sd02011 99 15.3 82 828 172.7 12.1 sd02012 91 4.4 79 808 38.7 11.4 sd02013 99 6.0 79 859 62.7 12.5 sd02100 2 1.0 2 16 0.0 10.0 sd02101 4 1.0 4 32 0.0 10.0 sd02102 3 1.0 3 28 0.0 10.0 sd02103 1 1.0 1 8 0.0 15.0 sd02110 89 4.9 80 772 43.9 11.2 sd02111 92 6.2 81 892 58.7 11.4 sd02112 94 5.3 88 856 45.7 10.7 sd02113 100 13.4 84 777 147.1 11.9

Alex, you need to post just a bit more information. This does look like disk contentionbut whether there is an Informix solution or an OS one is not clear yet. Please post: tbstat -P tbstat -d tbstat -D tbstat -F tbstat -R tbstat -u and the length of time since the last time tbstat -z was run before these reports were taken if after startup. Also what kind of drives are these (ie 1GB, 2GB, etc.; manufacturer & interface[SCSI-II, SCSI-III, etc.]). Art S. Kagel "Chen, Alex" wrote: > > Our Informix 5.10 under Sequent ptx 4.4 has encountered slowness issue. The > major cause is due to the disk I/O contention. Below is the output of the > command, sar -d 10, as you can see that the contention occurred in disk area > (data: sd02010, sd02011, sd02012, sd02013, and mirror: sd02110, sd02111, > sd02112, sd02113). This was the result from consolidation of the large table > extends into one extend, which is a good practice recommended by Online 5. > However this practice causes the disk I/O contention! What is the best way > to manage the data distribution? We have stored the data in the separated > dbspace from the rootdbs. Is there anyway to adjust the data among the disks > since 5.10 doesn't support the table fragment? > > Another option is to increase the BUFFER number (currently set as 28000). > What's the best number? The application system here doesn't use the > transaction. So LRUS = 32, LRU_MAX_DIRTY = 8 , and LRU_MIN_DIRTY = 3. They > appear not good. What's the best figures to reduce the disk I/O? Your prompt > suggestion will be appreciated. > > Alex. > 703-762-5020 > === > > DYNIX/ptx numaq 4.0 V4.4.4 i386 05/01/00 > > 10:26:35 device %busy avque r+w/s blks/s avwait avserv > > 10:26:37 sd01001 3 1.0 3 41 0.0 11.7 > sd01002 4 1.0 3 18 0.0 13.3 > sd01003 3 1.0 3 41 0.0 10.0 > sd02000 2 1.0 2 17 0.0 8.0 > sd02001 5 1.0 4 32 0.0 12.2 > sd02002 2 1.0 2 12 0.0 12.5 > sd02003 7 1.0 4 26 0.0 15.6 > sd02010 95 5.0 82 896 46.2 11.6 > sd02011 99 15.3 82 828 172.7 12.1 > sd02012 91 4.4 79 808 38.7 11.4 > sd02013 99 6.0 79 859 62.7 12.5 > sd02100 2 1.0 2 16 0.0 10.0 > sd02101 4 1.0 4 32 0.0 10.0 > sd02102 3 1.0 3 28 0.0 10.0 > sd02103 1 1.0 1 8 0.0 15.0 > sd02110 89 4.9 80 772 43.9 11.2 > sd02111 92 6.2 81 892 58.7 11.4 > sd02112 94 5.3 88 856 45.7 10.7 > sd02113 100 13.4 84 777 147.1 11.9