Hello,
I couldn't find any answer to this at Google.
My FreeNAS box has 48GB of DDR3 ECC. I have noticed that there is always around 14GB of free RAM that could be used for ARC... 16GB module costs 100 Euro and it's a waste it`s not being used.
1. there are around 130 GB of stored data(NFS to mailserver), so there is plenty of data to store in ARC
2. the server is running two days, so the ARC should be populated.
Here is a result of: arc_summary.py | more
System Memory:
0.27% 128.42 MiB Active, 0.53% 253.16 MiB Inact
75.71% 35.19 GiB Wired, 0.00% 1.14 MiB Cache
23.49% 10.92 GiB Free, 0.00% 668.00 KiB Gap
Real Installed: 48.00 GiB
Real Available: 99.90% 47.95 GiB
Real Managed: 96.94% 46.49 GiB
Logical Total: 48.00 GiB
Logical Used: 76.74% 36.83 GiB
Logical Free: 23.26% 11.17 GiB
Kernel Memory: 34.37 GiB
Data: 99.94% 34.35 GiB
Text: 0.06% 22.71 MiB
Kernel Memory Map: 45.85 GiB
Size: 74.79% 34.29 GiB
Free: 25.21% 11.56 GiB
Page: 1
------------------------------------------------------------------------
ARC Summary: (HEALTHY)
Storage pool Version: 5000
Filesystem Version: 5
Memory Throttle Count: 0
ARC Misc:
Deleted: 389.45k
Recycle Misses: 555
Mutex Misses: 3.85k
Evict Skips: 3.85k
ARC Size: 75.44% 34.32 GiB
Target Size: (Adaptive) 75.45% 34.32 GiB
Min Size (Hard Limit): 12.50% 5.69 GiB
Max Size (High Water): 8:1 45.49 GiB
As you can see the target size is 75.45%... Why it is not 90% or more?
Should I run the Autotune?
Can somebody post his result of arc_summary.py | more ?? So we can compare and maybe tune a bit??
Thank you
I couldn't find any answer to this at Google.
My FreeNAS box has 48GB of DDR3 ECC. I have noticed that there is always around 14GB of free RAM that could be used for ARC... 16GB module costs 100 Euro and it's a waste it`s not being used.
1. there are around 130 GB of stored data(NFS to mailserver), so there is plenty of data to store in ARC
2. the server is running two days, so the ARC should be populated.
Here is a result of: arc_summary.py | more
System Memory:
0.27% 128.42 MiB Active, 0.53% 253.16 MiB Inact
75.71% 35.19 GiB Wired, 0.00% 1.14 MiB Cache
23.49% 10.92 GiB Free, 0.00% 668.00 KiB Gap
Real Installed: 48.00 GiB
Real Available: 99.90% 47.95 GiB
Real Managed: 96.94% 46.49 GiB
Logical Total: 48.00 GiB
Logical Used: 76.74% 36.83 GiB
Logical Free: 23.26% 11.17 GiB
Kernel Memory: 34.37 GiB
Data: 99.94% 34.35 GiB
Text: 0.06% 22.71 MiB
Kernel Memory Map: 45.85 GiB
Size: 74.79% 34.29 GiB
Free: 25.21% 11.56 GiB
Page: 1
------------------------------------------------------------------------
ARC Summary: (HEALTHY)
Storage pool Version: 5000
Filesystem Version: 5
Memory Throttle Count: 0
ARC Misc:
Deleted: 389.45k
Recycle Misses: 555
Mutex Misses: 3.85k
Evict Skips: 3.85k
ARC Size: 75.44% 34.32 GiB
Target Size: (Adaptive) 75.45% 34.32 GiB
Min Size (Hard Limit): 12.50% 5.69 GiB
Max Size (High Water): 8:1 45.49 GiB
As you can see the target size is 75.45%... Why it is not 90% or more?
Should I run the Autotune?
Can somebody post his result of arc_summary.py | more ?? So we can compare and maybe tune a bit??
Thank you