Reply
Topic Options
- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page
Realistic Performance Expectations?
- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
2014-06-16
12:05 PM
2014-06-16
12:05 PM
Realistic Performance Expectations?
Hello,
I am doing large file copies from NAS #1 to NAS #2. A typical copy job would be 8 x 60 GB files or about 500 GB. I have been performing this operation for a long time and it just seems to get slower and slower. I know there are a great number of variables but roughly, what network throughput should I expect?
Here are the details of my configuration...
NAS #1: ReadyNAS NV - 4 x 500 GB - 2 GB DIMM
NAS #2: ReadyNAS NV+ - 4 x 1 TB - 2 GB DIMM
Connectivity is provided by a NETGEAR GS116. The switch supports jumbo frames.
Both NAS #1 and #2 are directly connected to the switch at 1000/FULL. Jumbo Frames are enabled on NAS #1 and #2.
No computers are involved in the copy process.
I have a backup job set up in FrontView on NAS #2 that pulls from a "Remote NFS Server" (NAS #1) to a local folder (on NAS #2). I have reversed the backup job to where NAS #1 pushed to NAS #2 and it made little difference in performance.
I really appreciate any assistance/guidance.
-Steve
I am doing large file copies from NAS #1 to NAS #2. A typical copy job would be 8 x 60 GB files or about 500 GB. I have been performing this operation for a long time and it just seems to get slower and slower. I know there are a great number of variables but roughly, what network throughput should I expect?
Here are the details of my configuration...
NAS #1: ReadyNAS NV - 4 x 500 GB - 2 GB DIMM
NAS #2: ReadyNAS NV+ - 4 x 1 TB - 2 GB DIMM
Connectivity is provided by a NETGEAR GS116. The switch supports jumbo frames.
Both NAS #1 and #2 are directly connected to the switch at 1000/FULL. Jumbo Frames are enabled on NAS #1 and #2.
No computers are involved in the copy process.
I have a backup job set up in FrontView on NAS #2 that pulls from a "Remote NFS Server" (NAS #1) to a local folder (on NAS #2). I have reversed the backup job to where NAS #1 pushed to NAS #2 and it made little difference in performance.
I really appreciate any assistance/guidance.
-Steve
Message 1 of 7
Labels:
- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
2014-06-16
03:07 PM
2014-06-16
03:07 PM
Re: Realistic Performance Expectations?
I'd expect about 20 MB/s.
What speeds are you seeing?
What speeds are you seeing?
Message 2 of 7
- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
2014-06-16
07:09 PM
2014-06-16
07:09 PM
Re: Realistic Performance Expectations?
Wow...I'm getting about a third of that - around 7.8 MB/s.
Message 3 of 7
- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
2014-06-16
09:32 PM
2014-06-16
09:32 PM
Re: Realistic Performance Expectations?
The NV+ (v1) is very old now. Essentially the same performance wise as a product released back in February 2006.
What version of RAIDiator are you running?
What brand and model disks are you using?
If you download the logs, what is the "block size" in volume.log? Also, what does partition.log look like?
What version of RAIDiator are you running?
What brand and model disks are you using?
If you download the logs, what is the "block size" in volume.log? Also, what does partition.log look like?
Message 4 of 7
- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
2014-06-16
11:06 PM
2014-06-16
11:06 PM
Re: Realistic Performance Expectations?
Both are running RAIDiator 4.1.13 [1.00a043].
The NV (NAS #1) has 4 x Seagate Barracuda 7200.12 500 GB 7200RPM SATA 6Gb/s with NCQ 16MB Cache (ST3500413AS).
The NV+ (NAS #2) has 4 x Western Digital Red NAS Hard Drive 1 TB SATA 6.0Gb/s 64MB Cache (WD10EFRX).
Block Size on both is 16384.
Not sure exactly what I'm looking for in the partition.log files so I provided Dropbox links to each...
NAS #1 partition.log file.
NAS #2 partition.log file.
Do you think that 20 MB/s is unrealistic?
Thank you for your help.
The NV (NAS #1) has 4 x Seagate Barracuda 7200.12 500 GB 7200RPM SATA 6Gb/s with NCQ 16MB Cache (ST3500413AS).
The NV+ (NAS #2) has 4 x Western Digital Red NAS Hard Drive 1 TB SATA 6.0Gb/s 64MB Cache (WD10EFRX).
Block Size on both is 16384.
Not sure exactly what I'm looking for in the partition.log files so I provided Dropbox links to each...
NAS #1 partition.log file.
NAS #2 partition.log file.
Do you think that 20 MB/s is unrealistic?
Thank you for your help.
Message 5 of 7
- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
2014-06-17
03:07 AM
2014-06-17
03:07 AM
Re: Realistic Performance Expectations?
SJMarty:
How much free space is on the two NAS volumes?
Also, did you try a test with the jumbo frames turned off?
How much free space is on the two NAS volumes?
Also, did you try a test with the jumbo frames turned off?
Message 6 of 7
- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
2014-06-17
08:36 AM
2014-06-17
08:36 AM
Re: Realistic Performance Expectations?
NAS #1 is about 50% full.
NAS #2 is about 25% full.
It was a while ago so I don't remember the exact numbers but I did try the job with jumbo frames off and didn't see much of a difference.
Is there a way to monitor NAS performance? Even basic counters like CPU and memory would help.
NAS #2 is about 25% full.
It was a while ago so I don't remember the exact numbers but I did try the job with jumbo frames off and didn't see much of a difference.
Is there a way to monitor NAS performance? Even basic counters like CPU and memory would help.
Message 7 of 7