Post your performance results

[Helevitia]

I did some performance tests last night.

Specs:
ReadynasNV - 256MB w/ 2 Seagate ES 250GB drives
PC Asus A8V - AMD 3500+ with 2GB Memory
PC NIC - Yukon Marvell 10/100/1000 (supports jumbo frames)


With a Linksys WRT54G and everything connected at 100/full I get:

Read: 9.28MB/s
Write: 8.54MB/s


With my new Linksys SRW2008(8 port Gb switch w/ full 16Gb backplane non-blocking - supports jumbo frames) and everything connnected at 1000/full)

Read: 29.x MB/s
Write: 18.x MB/s

I tried to enable jumbo frames on my NIC, the NV and the switch bbut something went wrong so I have no results with jumbo frames enabled. I hope to have that issue resolved soon and I will post back here.

Added 10/12/2006:

I fnally got jumbo frames working and my write scores improved dramatically, but my read scores dropped a tad.

With Jumbo Frames enabled on my PC, switch and NV:

Read: 27.52
Write: 23.75

[zamboni]

ReasyNAS NV with single 750GB drive. UPS, journaling off, cache on, etc.
Read: 8.3 MB/sec

Write: 9.5 MB/sec

New SMC-GS5 gigabit (jumbo) switch. No jumbo frames.

Read: 15.32
Write: 16.02


NVIDIA motherboard based LAN to:
1) Optimize for throughput, not CPU utilization
2) Jumbo frames
3) Auto-negotiate to 1000-mbit full duplex.

Rebooted both NAS (enabled Jumbo) and PC. Ensured no apps or services running on the PC.

IO Meter Run #1
Read: 19.69 - CPU 27%
Write: 20.22 - CPU 10.32%

IO Meter Run #2 -- different CPU-switch cable (switch-NAS is Infrant cable)
Read: 18.88 - CPU 17.62%
Write: 22.01 - CPU 8.94%

[Helevitia]

ReasyNAS NV with single 750GB drive. UPS, journaling off, cache on, etc.
Read: 8.3 MB/sec

Write: 9.5 MB/sec

New SMC-GS5 gigabit (jumbo) switch. No jumbo frames.

Dreadful.

Read: 15.32
Write: 16.02

OK, so I increase my switch 10x, but my performance goes up a meagre 50%? I understand that jumbo frames will help write, but read is in the toilet... it is operating at a theoretical 122 MBit -- not 1000 MBit.

Note, this is after rebooting and disabling Antivirus, and every program and service running. Before this "clean reboot:"
Read: 14.68

(so, my NAV, with Outlook replicating every minute, my read was only 0.64 mbit worse)

Yeah, I may try a direct connection cable, but at this point, I am vastly disappointed; I expect better than 0.12 GBit performance out of a gigabit device... I may try a separate GBit NIC, but my "as-is" PC can natively do better with other GBit personal computers on a gbit network...

Definitely you should eliminate the switch first with direct connect. Most likely it is something like auto negotation failed. I highly recommend to manually set your speed/duplex on each device. This is a very common and overlooked problem.

[zamboni]

conversation moved to: http://www.infrant.com/forum/viewtopic.php?p=38101

[Helevitia]

Did you set the speed/duplex on the PC, NAS, and Switch? You must set it manually on all 3. Also, please list your specs of your PC. Do you see any errors on the Network/Ethernet screen when you click "show errors"? If so, post them here.

[Helevitia]

Well crap, I just realized the NV doesn't have the option to manually set 1000Mb. I have 10 or 100/half & 10 or 100/full and then auto negotiation. So forget what I said about manually setting speed/duplex on the NV. I just found out my nic card is the same way, yet my switch can do it.

[zamboni]

Conversation moved to: http://www.infrant.com/forum/viewtopic.php?p=38101

[yoh-dah]

Zamboni, you should create a new topic. This thread should be reserved just for posting user results so folks can easily skim to see if what they're seeing is the result of similar setups.

[zamboni]

This thread should be reserved just for posting user results so folks can easily skim to see if what they're seeing is the result of similar setups.

True - it started as just results, as I did not expect errors. I have now created a new thread with the relevant info from here. please delete my edited-empty posts and the replies to clean it up!

[sirsycho]

Adding my bit...

Using the recommended settings outlined in the performance post on this forum.

Write MBps: 19.452
Read MBps: 30.759

Here's my setup:

Stock NV
1 x 500GB (NORAID)
All journaling disabled
Fast writes on

AMD64 4800+
A8N32-SLI using the Marvell onboard NIC
2 gigs ram
2 x WD Raptors (RAID0+1)
Windows Vista x86 RC2

Netgear GS608 Gigabit switch (no jumbo frames)
Cat 5e cabling

[Daryl RL]

Original set-up:

ReadyNAS NV
256Mb memory
3 x Seagate ST3400832AS 400Gb drives
X-RAID
Jumbo frames off
Journaling disabled
Fast CIFS frames enabled

Dell 2.4Ghz P4 PC
Windows XP Home
512Mb Memory
Belkin Gigahertz NIC F5D5005 NIC
Jumbo frames off
Flow control enabled, not sure what the TCP offload option is (mentioned in Infrant's test set-up post - I don't see any option like that anywhere)

D-Link DGS-2205 switch (GigE, no jumbo frame support)

READ: 29.2
WRITE: 19.3


Made the following change to the system (ONLY change):

Replaced stock 256Mb memory with Patriot 1Gb memory card (PEP1G2700SLL) from NewEgg

READ: 32.2
WRITE: 19.8


Replaced D-Link DGS-2205 switch with SMCGS8 switch (from Infrant compat. list). NO change to jumbo frame settings (yet):

READ: 31.3
WRITE: 19.2


Ok - now with enabling jumbo frames on NIC (MTU=9014) and ReadyNAS NV (MTU=whatever is standard, 7936??):

READ: 28.4
WRITE: 23.9


So I gained in write performance but lost read performance.

NOTE: I had posted previously about some volume errors I was getting when re-booting the NV. It appears they were caused by or related to the USB drive I had attached to the NV, NOT the jumbo frames.

[jching]

Here's my info:

Stock NV
4 x Seagate ST3250823AS 250gb Hard Disk in X-RAID
All journaling disabled
Fast writes on


IO Meter Write: 19.321793 MBps
IO Meter Read: 26.803979 MBps

Do these performance numbers make sense? Correct me if I'm wrong, but aren't these numbers similar to regular IDE drives connected directly to an IDE interface? A SATA drive directly connected to the SATA interface should at least get twice this performance. A decent drive should get 3 times this performance.

Now take 4 of these drives and create a RAID5, it should be screaming above 100MB/s. I don't think gigabit ethernet is the bottle neck here, because I've done benchmarks with gigabit Ethernet and it's way higher than 30MB/s.

So, can someone explain why these numbers are so low? Where's the bottle neck?

--jc

[Helevitia]

Here's my info:

Stock NV
4 x Seagate ST3250823AS 250gb Hard Disk in X-RAID
All journaling disabled
Fast writes on


IO Meter Write: 19.321793 MBps
IO Meter Read: 26.803979 MBps

Do these performance numbers make sense? Correct me if I'm wrong, but aren't these numbers similar to regular IDE drives connected directly to an IDE interface? A SATA drive directly connected to the SATA interface should at least get twice this performance. A decent drive should get 3 times this performance.

Now take 4 of these drives and create a RAID5, it should be screaming above 100MB/s. I don't think gigabit ethernet is the bottle neck here, because I've done benchmarks with gigabit Ethernet and it's way higher than 30MB/s.

So, can someone explain why these numbers are so low? Where's the bottle neck?

--jc

The NV is definitely the bottleneck here. But if you compare the NV to the competition, you will see that not many are faster(plus these support forums are worlds better than the competition which is why I bought an NV). In time, as NAS devices become more popular, speed will become a bigger factor, but for now it's not to most people.

[jching]

The NV is definitely the bottleneck here. But if you compare the NV to the competition, you will see that not many are faster(plus these support forums are worlds better than the competition which is why I bought an NV). In time, as NAS devices become more popular, speed will become a bigger factor, but for now it's not to most people.

If you're refering to Buffalo or similar, than yes. I agree. But how about FC RAIDs, like Medea, Infortrend, Xyratec. Granted, these are fiber channel, so they get 280+MB/s with 6 disks. This is about 50MB/s per SATA drive. Which is what I would expect from a SATA RAID system.

But even if we're limited to gigabit Ethernet, I'd expect greater than 30MB/s. So why is the Buffalo/NV/Thecus/etc so slow in comparison? Why aren't they getting similar performance from the SATA drives? Exactly what in the NV is the bottle neck? Is the RAID operations done in software? Is the parity done by the CPU?

Aside from the fiber channel vs. gigabit ethernet, what is different between the Medea/Infortrend vs. Infrant/Buffalo?

--jc

[gfbarros]

Please list what protocol you are using when gathering these performance numbers. It is my understanding that there are some significant performance differences amongst the different supported protocols...