INTL 3:770/1 3:770/3
REPLYADDR theom+news@chiark.greenend.org.uk
REPLYTO 3:770/3.0 UUCP
MSGID:  af1f8460
REPLY:  d10ddf8a
PID: SoupGate-Win32 v1.05
Pancho  wrote:
> On 10/30/24 08:50, Andy Burns wrote:
> > Pancho wrote:
> >
> >> The official NVMe Pi Hat has been out for months,
> >
> > Oh, I don't have a Pi5, and though I kept hearing about 3rd party NVMe
> > HATs and lack of official one
> >
>
> OK, I see there is a story about rPi launching actual NVMe M.2 SSDs. As
> opposed to a hat. I've no idea why they would do that. The obvious
> suspicion is cashing in on a brand name.
>
> 

It may be they are doing it because supply of small-capacity 2230 NVMe is a
bit of a minefield.  eg I checked scan.co.uk and the smallest 2230 they have
is 512GB.  There are some 256GB sold by Amazon.co.uk which are more
expensive (and a few more dispatched by other sellers, of variable
trustworthiness).  At least with the RPi brand you know they're compatible,
and they seem to be decent value.

> It's hard to know what is going on with the Raspberry Pi guys, the
> RK3588 devices are clearly faster, lower energy, albeit with shit
> software support. Who knows what will happen with the next generation
> Arm SoCs. I guess maybe Raspberry Pi have a clue, and hence decided to
> monetise the brand now, before a new product wipes the floor with them.

It'll depend on what fab slots they can get.  Not everyone can fab on the
latest process, especially with a budget.  Also how much cache they can
afford to put on the die.

RK3588: (64+64+512)*4+(32+32+128)*4+3072 = 6400KiB
RPi5  : 512*4+2048 = 4096KiB

RK3588 also has 4 extra A55 cores which RPi doesn't have, but is more
expensive ($100+ for the Banana Pi).

> >> I guess I should get one, or maybe an alternative. I just bought a
> >> NVMe USB enclosure which has appalling performance
> >
> > Anyway, is it likely the write speeds are faster than the  read speeds?
> > I know some enterprise SSDs come in "read mostly" or "write mostly"
> > flavours, but for a Pi?

> Dunno, IOPS doesn't mean a lot to me. As TNP says, maybe a write
> operation is to cache, and a read is from main memory.
>
> On many solid state persistence devices you see a very fast initial
> write (presumably to cache) before quickly settling down to a much lower
> rate for big files.

Any decent benchmarking tool should get past the cache to exercise the real
storage.

I think they've got them around the wrong way.  Their ODM Biwin's 2230 has
more read than write IOPS:
https://droix.co.uk/product/biwin-2230/

Theo

--- SoupGate-Win32 v1.05
 * Origin: Agency HUB, Dunedin - New Zealand | Fido<>Usenet Gateway (3:770/3)
SEEN-BY: 10/0 1 90/1 103/705 105/81 106/201 124/5016 128/187 129/305
SEEN-BY: 153/757 7715 218/0 1 601 700 840 870 930 220/70 221/1 6 360
SEEN-BY: 226/17 30 100 227/114 229/110 111 114 200 206 300 317 400
SEEN-BY: 229/426 428 470 550 616 664 700 240/1120 266/512 267/800
SEEN-BY: 282/1038 291/111 292/854 301/1 113 812 310/31 320/219 322/757
SEEN-BY: 335/364 341/66 342/200 396/45 460/58 633/280 712/848 770/1
SEEN-BY: 770/3 100 330 340 772/210 220 230 5020/400 1042 5075/35
PATH: 770/3 1 218/840 221/6 301/1 218/700 229/426