They look like standard HP DL server power supplies, blue label are 460W.
Enterprise SSD "small deals"
- Thread starter ca3y6
- Start date
Notice: Page may contain affiliate links for which we may earn a small commission through services like Amazon Affiliates or Skimlinks.
They are. And those are standard HP PDBs. Minor hacking on the control pins of the PDB and they act like regular ATX power supplies. The PDBs are from DL160 G6s I believe.
Ty, I got the toshibas, as theyre 512b formatted and should have the latest firmware applied.
OK a few 21 Days ago
. I must have forgotten about that one already because I couldn't buy any and I just bought some other Drives before .They are. I think I am using those. Though I'd probably go for some higher end supermicro ones if I was using PCIe 4 or 5.
Well Cheap, Good, Fast, pick 1 or 2 at most.
So Cheap it is, Good I don't know, Fast probably not
.
D
Deleted member 24947
Guest
No way. Worst case power draw is about 30 watts on startup. That’s only 360 watts for 12 drives. A 1000 watt PSU is absolutely not necessary.Of course, if the Backplate does NOT do sequential HDD Spinup, you don't really have a Choice. The Startup Current of 12 HDDs all at once will require a ~ 1kW PSU no Matter what. It would trip due to Overcurrent otherwise
Sorry to hear you've been having all that trouble with them. Disclaimer: I haven't bought SSDs from them yet, only 16-20TB Toshiba and Seagate Enterprise SATA drives so far. Around 20% arrived bad. From SMART details it appeared most somehow got damaged during shipment though they were well packed with no signs of damage. Mostly 200 Pressure_Limit. All were tested good (short offline) by the seller before shipment, except one that obviously failed before shipment. That one's on them, fell through the cracks somehow. I will say they were very responsive and processed full refunds quickly.
Based on your comments it sounds like they currently don't have a good handle on OEM vs vender formatting, firmware, and lock-in aspects for enterprise SSDs. Anyway I'd buy more enterprise HDDs from them, but I'd hesitate to buy enterprise SSDs off them, especially if i see more feedback like yours.
Last edited:
For a typical single socket 12LFF+2SFF 400-500w is what they normally have yeah, without using staggered spinup.
Here's the spec for the HGST He8 SAS drives (which are supposedly very power hungry).I'm surprised it's THAT low.
It's also not about Wattage but also about which Voltage Rail they are loading. You must also check that the 5V Rail can provide enough Current, although that goes also (and more importantly) for SSDs too. Startup Transient of HDDs should only be 12V.
I just remember that I had an Issue with a low Power (440W ? 560W ? cannot remember exactly) when I had 10 or 12 HDDs in that Chassis, but with the Move I didn't even retest since
If its a older split rail design those can be a bit more of a pain to slit the load correctly on.I just remember that I had an Issue with a low Power (440W ? 560W ? cannot remember exactly) when I had 10 or 12 HDDs in that Chassis, but with the Move I didn't even retest since
They would also trip easier than newer designs on the load spikes.
The price increase from going up in watts also used to be much lower, so going with a 1000w "just to be safe" did not come at the same premium as it does today.
Yup. Most Supermicro PSUs > ~700w are less than 70-75% efficient when you're idling in the two digits. Even power hungry CPUs like the Ivy Bridge era, idle at less than 40w with a single CPU. Even with dual CPUs they idle ~78-80w (I've done extensive measurements over the years).
The SM "platinum" PSUs are only efficient in the 30-90% range, and generally in a homely setting, we don't drive them that way.
Those are some incredible Prices
.If you have the Space for it and can give up the next PCIe Slot, sure. Or centrifugal Fan. Or Side Chassis fan depending on the Chassis Model.
Those are all of the reasons, the big guys (i.e. the hyperscalers and the likes of Oxide) don't even have individual PSUs in the systems. DC busbars are the name of the game. Way more efficient.
All 80+ rated power supplies need to meet their efficiency goal at 20%, except for titanium which needs to meet the goal at 10%.
See the chart at 80 PLUS certification specifications and ratings | CLEAResult
Platinum needs to be 90% efficient at 20% load.
Titanium needs to be 90% efficient at 10% load.
That is for 115v rated power supplies.
I don't have 1U or 2U servers, so I buy reasonably efficient ATX power supplies. My biggest power supply in use an a 550w platinum unit I use for my 64 core EPYC milan system.
Only for you @luckylinux ...Nice
Didn't you say you had to do a few Mods in order for it to fit ?
What about the "front" (left Side of your Picture), does it still fit the other "Part" of the Chassis ?
Everything fits. Wired up, tested successfully. So much space...
Those Motherboards (Sandy/Ivy Bridge Generation) are quite cheap at least:Those are the exact reasons, I'm redoing my SAN nodes. Needed more flash, but was out of slots. So...
10x pci-e 3.0 x8 slots...The chassis (Chenbro NR40700) will need a bit of surgery to fit this monster, but should give me enough I/O for years to come.
Supermicro X9DRX+-F Dual LGA 2011 DDR3 Proprietary All-Flash Storage Array | eBay
Open Box Supermicro X9DRX+-F Dual LGA 2011 DDR3 Proprietary Server Motherboard 2x LAN A ll-Flash Storage Array. Model: X9DRX+-F. Custom Label (SKU): 04162024- X9DRX+-F New. Socket: LGA 2011. Form Factor: Proprietary.
www.ebay.com
Supermicro X9DRX+-F-CS045 LGA 2011 Proprietary Server Motherboard E5-2600V2 | eBay
Model: X9DRX+-F-CS045. Custom Label (SKU): X9DRX+-F-CS045-NEW. Socket: 2x LGA 2011. UnixsurplusCom - Supermicro Systems. Form Factor: Proprietary. PlusBoards is a division of UNIXSurplus, a large Server dealer in Silicon Valley, California.
www.ebay.com
Well Flash is also SAS/SATA. I guess you WANTED (some at least) NVMe
.Of course we also need to remember that HBAs have a limited PCIe bandwidth, so if you are doing high IO Stuff you'll need several HBAs in Parallel anyways, even though 1 HBA might be able to handle all the Flash Disks Connection-wise.
For Instance the LSI 9306-24i for 24 Drives but can "only" do 64 gbps in one Direction or 128 gbps in both Directions, so above 64 gbps write / 6 gbps / drive ~ 10 SATA Drives or ~ 5 SAS Drives you will bottleneck - although I'd argue that in real Life it might NOT be such a big Problem in the End.
1PB of Spinning Rust
???EDIT 1: That Chembro Chassis seems to be super-expensive and difficult to find though (it's EOL apparently).
Officially it only supports 7xPCI Slots though, so I'm curious how you are going to make that work.
Even the Fractal Define 7 XL "only" has 9 PCI Slots (plus 3 transversal ones) and supports these "big" Motherboards, so I don't think it will work in this one either:
- E-ATX
- EE-ATX
- SSI-CEB
- SSI-EEB
EDIT 2: the Xeon E5 v3/v4 Model, the Supermicro X10DRX, has 11 PCIe Slots even
EDIT 3: also the Motherboard you mentioned and the Picture shows 11 PCIe Slots. Why did you say 10x Slots, is one of them not working ?
Last edited:
Yeah, zero rating from china, I pasted that quickly, wouldn’t buy it myself
Probably better the X10DRX at that Point, 300-350 USD instead of the 50 USD for the X9DRX, but potentially at least double the RAM and CPU Power. You'll need the GPUs anyways but I mean budget wise the increase in Motherboard Cost isn't that much when looking at the Total Cost of the System at that Point.
But ... I Googled for half an Hour but couldn't find any reasonable SSI-MEB or HPTX nowadays, there are a few Threads around, but it's about Cases that were built over a decade ago and were quite a Niche Market (i.e. low availability nowadays):
This is interesting to me, I have 2x PWS-1K28P-SQ in my SuperMicro CSE 847 36 bay that idles roughly at 350 watts.
I should have been more specific. 5 SAS SSDs or 10 SATA SSDs
Definitively NOT spinning Rust, those I can see wiring 24 Spinning Rusts on a single HBA without sacrificing Performance.
Holy ****. They must have costed a Fortune !
Fair enough, but is there "free Space" when there are no more exposed PCIe Slots ?
Nah, 300-350 USD right now, probably down to 200-250 USD or so with some Negotiation.
The Paradox is that Supermicro keeps using this bad Habit also in the X10 E5 v3/v4 Generation. DMI x4 2.0 when even the X11 E3 v5/v6 have DMI x4 3.0
...I have a g292-z20 (which is a power hog), removing one of the two power supplies lets me idle at around 270W instead of 290W.
I'm quite sure that most of it is the CPU frequency/voltage being lowered by the system (I have the P-state managed by Linux, but removing the PSU changes the frequency a bit), but probably also some efficiency gain by using a single PSU.
If you have accurate power metering at the wall (IPMI might be close enough, mine matches my meter, others don't trust theirs much) you can quickly test pulling one PSU to see how much the idle power drops from pushing the load over 20% on the remaining PSU. I personally run my 826 with one PSU pulled out a half inch so I can manually swap to it in the rare case that the primary PSU dies.