tag:blogger.com,1999:blog-7997313029981170997.post1364920102923350687..comments2009-05-21T20:32:25.636-04:00Jon Jensenhttp://www.blogger.com/profile/18273388885281263476noreply@blogger.comBlogger5125tag:blogger.com,1999:blog-7997313029981170997.post-50576041273512796642009-05-21T20:32:25.636-04:002009-05-21T20:32:25.636-04:00For reliability <B>and</B> performance, RAID 1 and RAID 10 are a good choice.Jon Jensenhttp://www.blogger.com/profile/18273388885281263476noreply@blogger.comtag:blogger.com,1999:blog-7997313029981170997.post-10569726521538390332009-05-21T19:42:40.044-04:002009-05-21T19:42:40.044-04:00Very well done! So what should I use for my pgsql dbs? I just started a new job and am new to PG in fact. We are using RAID5 right now which I see is not so great! But we like the checksum disk on RAID5. So what's the best configuration to give us that kind of reliability?bushidokahttp://www.blogger.com/profile/08181489805764291916noreply@blogger.comtag:blogger.com,1999:blog-7997313029981170997.post-35254629341433795332009-05-12T21:24:00.000-04:002009-05-12T21:24:00.000-04:00ZFS?qu1j0t3http://www.blogger.com/profile/16041515498065869604noreply@blogger.comtag:blogger.com,1999:blog-7997313029981170997.post-37285377699081917892008-10-27T18:07:00.000-04:002008-10-27T18:07:00.000-04:00Hi Jon,<BR/><BR/>We tested two disks in a striped LVM configuration. The relevant throughput results are here: <BR/><BR/>http://wiki.postgresql.org/wiki/HP_ProLiant_DL380_G5_Tuning_Guide#Two_Disks<BR/><BR/>At LPC, one developer noted that LVM automatically adjusts the read-ahead buffer, which may have accounted for a significant portion of the performance gain. This is something we probably won't dig into further (but would love for other people to test), other than to recommend to people that they try increasing their read-ahead buffer size to something like 8MB and test performance on their hardware.Selena Deckelmannhttp://www.blogger.com/profile/13787945278069006540noreply@blogger.comtag:blogger.com,1999:blog-7997313029981170997.post-16049122292400565822008-09-22T20:51:00.000-04:002008-09-22T20:51:00.000-04:00Very interesting, Selena. I'm curious about your LVM part of the investigation. What LVM configuration were you using? You wrote:<BR/><BR/><I>Our test showed that for sequential or random reads on RAID0, LVM doesn't incur much more overhead than hardware or software RAID.</I><BR/><BR/>Does that mean you were using LVM to concatenate several physical volumes into one volume group, and testing performance on a logical volume in that group?<BR/><BR/>Sorry to be pedantic, but specifically I'm curious if there's any measurable decrease in performance when using LVM on a single disk vs. no LVM (but no software RAID either).<BR/><BR/>LVM is still useful in such cases, among other things for making atomic volume snapshots. I have never been able to detect a performance hit, but I suppose there could be, just due to using device mapper if nothing else.Jon Jensenhttp://www.blogger.com/profile/18273388885281263476noreply@blogger.com