1

storage system in consideration from below h/w lying idle: 6 x 300GB 10K SAS; 2 X 146 GB 15K SAS; 12GB DDR2 RAM; Xeon CPU 2.5Ghz two 1GB NIC ports 1 - DLink 1GB ethernet switch (1000/100 MB) 8-port unmanaged

Software: nexentastor community 3.0.3 or Opensolaris

target usage: iSCSI for ESX 4.0

what are the general recommendations for ZFS cache: read, write? 1. SATA/SAS or SSD?; 2. minimum recommended size?

any ideas to tune network? thanks in adv.

JMS77
  • 1,275
  • 5
  • 27
  • 45
  • 1
    If you want a video series where they talk about how ZFS works and some tuning goto http://www.youtube.com/user/deirdresun and it is called "ZFS in the Trenches: Ben Rockwood at LISA 09" (7 in all). Ben talked about turning the cache and how to monitor ZFS. His blog is at http://www.cuddletech.com/blog/ I'm not sure that bug is still active, it isn't posted as fixed, but a workaround is posted in a related bug. When you go to that bug it was fixed in snv_56. Not sure if the second bug fix, fixed the first bug. I don't remember a reference to memory leakage in the video series. – Scott McClenning Oct 13 '10 at 03:10

1 Answers1

-2

You might not like this, but you might want to take a look at My OpenSolaris Server hangs when writing large files after upgrading zpool if you haven't already...

Community
  • 1
user48838
  • 7,431
  • 2
  • 18
  • 14
  • do you mean this bug still exists in ZFS and hence not recommended for any VM storage solution (large file writes)? – JMS77 Aug 03 '10 at 02:10
  • It's not just large writes, it's a memory leak, large writes just seems to speed up the leakage... – user48838 Aug 03 '10 at 02:43