[HPADM] hfs vs vxfs

From: Rod Suter (rsuter@montefiore.org)
Date: Mon Aug 19 2002 - 10:24:02 EDT

• Next message: Yonghe Yan: "[HPADM] Summary -fuser"
• Previous message: Epstein, Kevin: "[HPADM] Host Security Testing"
• Next in thread: Anil Rajapure: "[HPADM] Difficult time with lpsched"
• Reply: Anil Rajapure: "[HPADM] Difficult time with lpsched"
• Messages sorted by: [ date ] [ thread ] [ subject ] [ author ] [ attachment ]

I have a 54 GB hfs filesystem for dumping sybase data. It is striped across 8 disks, with a greatly reduced number of inodes and 64K block size. Most files are 1.5 to 2 GB in size. It performs well.

I must recreate it on two new drives on the same FC10 (but a different volume group). The data is transient and overwritten daily. My concern is for optimizing the file system for fast read and write of large files. Would I be better off with hfs or vxfs? Is there a performance cost in maintaining the intent log in vxfs? Is there a performance benefit in dynamically allocated inodes?

--
             ---> Please post QUESTIONS and SUMMARIES only!! <---
        To subscribe/unsubscribe to this list, contact majordomo@dutchworks.nl
       Name: hpux-admin@dutchworks.nl     Owner: owner-hpux-admin@dutchworks.nl
 
 Archives:  ftp.dutchworks.nl:/pub/digests/hpux-admin       (FTP, browse only)
            http://www.dutchworks.nl/htbin/hpsysadmin   (Web, browse & search)

• Next message: Yonghe Yan: "[HPADM] Summary -fuser"
• Previous message: Epstein, Kevin: "[HPADM] Host Security Testing"
• Next in thread: Anil Rajapure: "[HPADM] Difficult time with lpsched"
• Reply: Anil Rajapure: "[HPADM] Difficult time with lpsched"
• Messages sorted by: [ date ] [ thread ] [ subject ] [ author ] [ attachment ]

This archive was generated by hypermail 2.1.7 : Sat Apr 12 2008 - 11:02:18 EDT