In <[🔎] 4D1F5543.3010108@hardwarefreak.com>, Stan Hoeppner wrote: >Atif CEYLAN put forth on 12/31/2010 4:58 PM: >> I have a large postgresql database system and I want to migrate to a new >> and fast storage system (10 Gbp/s FC network). But 150x3 ssd disk on my >> db server and I want to use ext4 file system (raid5) at the ssd disks as >> xlog storage or use zfs (raidz) as disk buffer cache. >> What is your idea? > >In as few words as possible? You're a nut job. The mere mention of >using FUSE ZFS in any production context on Linux proves it. Agreed. I wouldn't consider btrfs or ZFS for production work on Linux right now. >As does >mentioning running RAID 5 on 3 SSDs, Is your problem with RAID5 or the SSDs? Sudden disk failure can occur with SSDs, just like with magnetic media. If you are going to use them in a production environment they should be RAIDed like any disk. RAID 5 on SSDs is sort of odd though. RAID 5 is really a poor man's RAID; yet, SSDs cost quite a bit more than magnetic media for the same amount of storage. >or any SSDs for that matter, or SSDs intended as HD replacements support more read/write cycles per block than you will use for many decades, even if you were using all the disk I/O the entire time. SSDs intended as HD replacements are generally faster than magnetic media, though it varies based on manufacturer and workload. I see little to no problem using SSDs in a production environment. >running RAID 5 in a db context, for that matter. Some people just hate on RAID 5. It is fine for it's intended purpose, which is LOTS for storage with some redundancy on identical (or near-identical) drives. I've run (and recovered) it on 3-6 drives. However, RAID 1/0 is vastly superior in terms of reliability and speed. It costs a bit more for the same amount of usable space, but it is worth it. In a DB context in particular, you are probably going to be doing many small reads. RAID 5 does not speed up those operations significantly, whereas a good RAID 1/0 will reduce seek time by nearly 50%. I suggest you use RAID 1/0 on your SSDs, quite a few RAID 1/0 implementations will work with 3 drives. RAID 1/0 should be a little more performant and a little less CPU intensive than RAID 5 for transaction logs. As far as file system, I think ext3 would be fine for this workload, although it would probably be worth it to benchmark against ext4 to see if it gives any improvement. -- Boyd Stephen Smith Jr. ,= ,-_-. =. bss@iguanasuicide.net ((_/)o o(\_)) ICQ: 514984 YM/AIM: DaTwinkDaddy `-'(. .)`-' http://iguanasuicide.net/ \_/
Attachment:
signature.asc
Description: This is a digitally signed message part.