* Posts by Nate Amsden

1055 posts • joined 19 Jun 2007

Page:

FUMBLE! NFL app drops privacy ball just before Super Bowl Sunday

Nate Amsden
Bronze badge

really

what is the purpose for this app needing such info (other than obvious selling that data to advertisers)

so many mobile apps are rendered useless immediately when I see what sort of stuff they want, I don't even bother to install on my phone (though on a tablet maybe I'd try one since it has no personal data on it). I don't lose any sleep over it though.

1
0

Linux chaps want to recycle your mobe as a supercomputer

Nate Amsden
Bronze badge

Re: What an amazing idea...

this makes about as much sense as people who used to want to collect a bunch of old computers to build a beowulf cluster or something. It's a cute idea, but beyond being cute it is quite pointless. (same goes for folks that like building clusters out of Rasberry Pis, cute for about 30 seconds).

1
2

SimpliVity claims fivefold sales boost, hugs Cisco tightly

Nate Amsden
Bronze badge

Re: I smell bullshit...

any idea what a license covers? (I sure don't have a clue) I would think they would advertise whichever number is biggest, so would not expect them to say 1,500 licenses if that covered 4,000 deployments or something.

0
0

Samsung's 850 EVO 1TB SSD appears live ... in 3D

Nate Amsden
Bronze badge

Re: Let's hope

Curious what is heavy load for you? I've been running 850 pro on my 4 year old laptop(SATA 2 only) since September and no issues. 99% of the time in linux, though I have booted to windows a few times. I wouldn't consider my workload heavy though I did notice that I was writing about 1TB/mo to the drive according to the samsung tools. Haven't checked in a month or so.

1
0

Want an Internet of Stuff? Not so 4K-ing fast ... yet – Akamai

Nate Amsden
Bronze badge

sounds like a solution

to cut down on the attacks just block those ips, unless you need traffic from China but I imagine most smaller websites and companies don't need anything to do with them. Certainly none of the companies I have worked for has ever sought sales or coverage etc in China

0
0

Yep, we'll judge WHOLE DARN storage config. Problem with that?

Nate Amsden
Bronze badge

Re: Big Data

using big data analytics to work out storage array requirements? How high are you? I'd say give me whatever you are on but I'll hold off on drugs until the superbowl (go hawks)

0
0

Microsoft Azure was most FAIL-FILLED cloud of 2014

Nate Amsden
Bronze badge

meanwhile in the real world

storage uptime

System is up and running from 2011-12-19 16:15:58 EST

(that was when that particular system was installed, before that my company was hosted in one of the public cloud providers), through software upgrades, hardware failures etc.. of course probably no big surprise to anyone in the industry to have 3 years of 100% uptime on storage.

What pissed me off most about being in a cloud an reliability was not the full big outages but the small fails that occurred seemingly constantly. Since moving out we haven't had to "rebuild" a VM even once in over 3 years. That was a semi regular occurrence when we were in "the cloud".

We've had one sudden physical host failure in 3 years, I was in bed watching tv, phone went nuts, got up to walk 10 feet to my desk and by that time vmware had moved the VMs to another host and was starting back up, and the underlying HP server detected the failure and automatically restarted(first time I had personally experienced that since being a ESX customer since 2006, I didn't even know HP servers had a feature called Automatic Server Recovery). There was some additional manual recovery steps for some apps but wasn't too bad. HP diagnosed the problem as a system board issue, forget what exactly and they replaced the board the next day(4 hour support on everything but I wasn't in a big rush).

4
0

SAN upstart Coraid AXING staff, struggling to survive – sources

Nate Amsden
Bronze badge

became a niche player?

When were they anything but niche? ATA over ethernet itself I'm not even sure I'd say that is niche, it's something below niche..if such a thing exists I don't know.

I knew someone who worked there a few years ago, the concept sounded a bit interesting but the product wasn't something I could find myself using at any of the companies I have worked at. I'm sure it has it's use cases, just not in my network.

1
1

VMware finds new post-paranoia RAM-saving tricks

Nate Amsden
Bronze badge

tps doesn't work for me anyway

one such example

PMEM /MB: 393179 total: 800 cos, 3167 vmk, 212022 other, 177190 free

[..]

PSHARE/MB: 4775 shared, 1758 common: 3017 saving

ooh, saving 3GB out of ~200GB that is in use (386GB total memory)

another system

PMEM /MB: 393163 total: 800 cos, 2992 vmk, 215446 other, 173924 free

[..]

PSHARE/MB: 2920 shared, 426 common: 2494 saving

2.5G!

that is mostly linux, I have noticed TPS seems quite effective with windows VMs for whatever reason. I've never seen it work with linux VMs though.

0
0

DDN chap throws in towel, taps on Accenture’s door

Nate Amsden
Bronze badge

wouldn't want to work there

one of my friends who was a "Global VP" at DDN left recently to start his own gig, DDN is not a place I would ever want to work myself...ugh. Have one friend there left last I checked anyway.

0
0

DANGER: Is that 'hot babe' on Skype a sextortionist?

Nate Amsden
Bronze badge

Re: For the love of all that's precious!

I'm on skype 24/7 ita what my work uses for communication

My profile must be set to private or

something as I almost NEVER get requests to connect from strangers.

My experience goes back 4 years. 99.99% of my skype usage is work related or with people I used to work with.

0
0

Cash-burning Box makes yet ANOTHER IPO promise

Nate Amsden
Bronze badge

Re: Investing in data centers

I'd bet those professional services add up fast too. One company I worked at flew people on site to their customers to hold their hands while they used the app. They saw they were spending more on that then the customers were paying. So they stopped the practice, and usage of the app nosedived, the company closed a couple years later.

0
0

Disk areal density: Not a constant, consistent platter

Nate Amsden
Bronze badge

Re: Doesn't everyone who works in storage know this?

Maybe I'm missing something here but one revolution of a platter on the outside tracks will pass over a ton more bits than the inside tracks(more surface area), I don't think it has much to do with how dense it is, I suppose density could play a role if the inner tracks were much more dense than outer but the gist from the article I get is they don't have that much control over it, some tracks are dense others are not sounds kind of random.

I lay my 3PAR storage out the opposite way, new data goes to the inner tracks and work their way out, to sort of ease the burden of a system as it fills up, or something.

0
0

Are we ready to let software run the data centre?

Nate Amsden
Bronze badge

Blah

Ive been on the server AND network team for over 10 years and have gotten by just fine without SDN, which is far overhyped. It has its limited use cases in very large orgs but for the rest it is a waste of breath

2
1

This week it rained in San Francisco and the power immediately blew out. Your tech utopia

Nate Amsden
Bronze badge

Hate sf

SF sucks. Well I guess all big cities suck to me anyway. I live near SF airport and have been to SF 3 times this year (two of which were to meet people from out of country). I hate every aspect of the city. Though SF is not alone same goes for Seattle(lived near there for a decade). Theres two places I like in seattle, hate the rest.

I cant think of a single place worth visiting in SF that would make up for the otherwise horrible experience being there.

I drove to orange county this mornin just missed the rain. My UPS said I had a 21 min outage this mornin but the batteries held up.

8
6

Net neutrality: Cisco, Intel, IBM warn FCC NOT to crack down on ISPs

Nate Amsden
Bronze badge

just look at the DSL market

for an example of the title 2 stuff right.. Lots of folks seem to want title 2 applied to cable companies, when they already have title 2 providers in their area in the form of DSL. But DSL is "too slow" so they don't want to use it.

I suspect the same will happen to cable(over time) if they go that route.

I don't care too much either way myself my internet usage is pretty minimal these days.

0
18

NGINX scores $20 MEELLLION to remind people it sells stuff

Nate Amsden
Bronze badge

Apache works fine

For most websites the webserver is not the bottleneck but rather crappy apps that run on top of them.

http://www.eschrade.com/page/why-is-fastcgi-w-nginx-so-much-faster-than-apache-w-mod_php/

(The title is misleading)

3
0

Furious GTA V gamers seek similar ban on violent, misogynistic title: the Holy Bible

Nate Amsden
Bronze badge

GTA V is a blast

I haven't been much into games in nearly 15 years, but GTA V caught my eye last year (had never really played any GTA before), I really liked the open world it seemed to portray. When I saw that an enhanced version was coming for the next gen consoles it was enough for me to buy a GTA V+PS4 bundle a couple weeks ago. It's been quite fun to play. The flexibility is pretty amazing to me anyway, the visuals are stunning.

I still suck badly at the game, but have had a lot of fun exploring and causing mayhem.

Also got the PS4 for that game demo P.T. which I heard was pretty good. though when I tried it I got a headache pretty quick and had to stop, maybe the motion wasn't smooth enough, and/or I'm old. Tried playing my old FPS games like original Unreal Tournament a couple years ago and had to stop after a few minutes because of headaches, used to be able to play them for hours on end w/o issue.

3
0

Another lick of Lollipop: Google updates latest Android to 5.0.1

Nate Amsden
Bronze badge

eh

I've kept wifi off on my note 3 to prevent it from getting the latest kitkat update from AT&T. I'm too afraid it's going to break shit(especially since restoring from backup or rolling the update back seems non trivial if not impossible unless the device is rooted etc which mine is not). for 5.0 I see absolutely nothing remotely interesting to me.

OS updates on mobile seem so hit and miss. Really there was nothing worthwhile in the android 4.3->4.4 update for me anyway on Note 3. Maybe I'm just getting old.

0
0

Huawei and Inspur Electronics challenge Q3 server status quo

Nate Amsden
Bronze badge

Re: Supermicro?

I think they fall under "other", with so many resellers selling servers with their parts(which I would expect would each be counted separately)..I doubt supermicro sells too many servers (direct) enough to show up on a chart of even the top 10.

0
0

If the COMMISH says block that email account, BLOCK IT!

Nate Amsden
Bronze badge

Re: Finally a use for POP3.

POP3 can be configured to leave mail on a server, likewise IMAP4 I believe can be configured to delete mail from a server too(though this use case is probably really rare).

Seems like all the more reason to run your own email server, don't use a service provider whom can snoop on you (likely) without you knowing about it (I have hosted my own email for about 18 years now)

4
0

Feds dig up law from 1789 to demand Apple, Google decrypt smartphones, slabs

Nate Amsden
Bronze badge

still have a backdoor though right?

for IOS anyways from what I've read it seems the contents on the phone are encrypted, but contents stored in icloud are not encrypted in the same manor so if the data happens to be in icloud (or in google equivalent) then perhaps apple/google could provide *that* data, just not the data on the handset itself..

me, I don't plan to encrypt, hell I'm still pissed off I have to assign a pass code to unlock my phone in order to install a SSL CA for one of my personal services. Have never lost or had a phone stolen, and worst case there really isn't too much of value/secrets on my phone. Oh maybe you can use my corporate email, big whoop! I could have IT change my password pretty quick.

Much more important to me is more the work it would take to get a new phone, put my data back on it, customize it etc....

6
16

Wikipedia won't stop BEGGING for cash - despite sitting on $60m

Nate Amsden
Bronze badge

they are emailing too

got this a short time ago (after I read el reg story)

Dear (me),

Thank you for helping keep Wikipedia online and ad-free. I’m sure you’re busy, so I’ll get right to it. We need your help again this year. Please help us forget about fundraising and get back to improving Wikipedia.

[..]

If all our past donors simply gave again today, we wouldn't have to worry about fundraising for the rest of the year.

[..]

To protect our independence, we'll never run ads. We take no government funds. We survive on donations from our readers. Now is the time we ask.

If Wikipedia is useful to you, please take one minute to keep it online and ad-free another year.

[..]

Thanks,

Jimmy Wales

Wikipedia Founder

0
0

Docker: Sorry, you're just going to have to learn about it. Today we begin

Nate Amsden
Bronze badge

Re: Differences from virtualisation?

one major one in my experience is networking. In my experience deploying LXC it seemed not practical to have multiple network segments (and thus routing tables) existing on a host that has LXC. So for example we have our nonproduction VMs on one VLAN and production on another, both have different default gateways(IPs on the switches). In my testing I was not able to have both co-exist on a single LXC host. I read that it *might* be possible at the time(6 months ago on Ubuntu 12.04) but highly experimental and complex, so I decided to not even bother as those two things are not something I am interested in trying to support.

Another difference is fully abstracted isolation in a VM vs container which gives you things like VM mobility between storage and servers w/o downtime - at least I haven't seen this happen with containers of any type.

We have deployed 6 containers(across 3 LXC hosts) for a very specific production workload (all are load balanced running the same application stack). I could see us expanding container support in very specific production workloads in the future to better leverage the hardware, though I don't see a point in using it for non production stuff as it is not flexible enough(routing tables) and our non production stuff isn't redundant since it is non prod, so a failure would be more of a pain to deal with if it can't be transparently recovered, also scheduled downtime(e.g. kernel update since there is only 1 kernel across all containers on a given host) would be a pain as well for the same reason.

I also do not like how I cannot query CPU/memory usage on a per container basis using regular linux tools they are not container aware (there may be tools that can get this info I haven't seen them myself). Same goes for network traffic - if I query SNMP on a linux container for network data I get 0 data. Also do not like how the LXC "parent" host shows all of the PIDs from all of the containers, makes it very difficult to sort through things. For us it is manageable since the workloads are very specific but I wouldn't want to deploy a dozen different random containers on a host that weren't tightly controlled for this reason too.

Since deploying containers, aside from the annoying things from a management perspective they have been flawless and have served their original purpose - unlock a massive amount of CPU(24 cores (48 threads) x Xeon E5-2695v2 per host) for our main e-commerce platform in production that comes with a $15k/server/year license. Average CPU went from ~40% to about 3%(new systems have much more horsepower than previous VMs). Peak CPU hasn't gone above about 25%, so these have a good 2 or 3 years of growth for them I bet, which was the plan. Massively under subscribed most of the time but that's fine - the cost of the license alone justifies that easily, as does knowing we'll not run out of capacity on that application for a VERY long time under any circumstances.

Unlike some orgs we are not one of the ones that likes to destroy and re-create resources on a regular basis. These containers will have a life span measured in years, like our VMs, ideally anyway.

3
0

That sub-$100 Android slab you got on Black Friday? RIDDLED with holes, say infosec bods

Nate Amsden
Bronze badge

don't trust mobile period

I don't do any online banking, any e-commerce transactions (outside of google play store for a few apps, no movies/music/whatever else they have) on my mobile devices (all Android Samsung Note 3 and Toshiba tablet though I wouldn't do it on IOS either).

I am very very cautious not to install any privacy invading applications either.

anything that needs security gets done on my linux laptop.

exception is I do occasionally login to work VPN from my phone.

in general I think the risk is quite low for me, but I don't do it anyway. There's never been a time where I felt "I have to do this *now* (and can't wait till I get to my own computer)"

also maybe goes without saying I don't use public wifi hotspots (except the very occasional hotel but that is rare I prefer to use my phone's mifi which I pay $50/mo for already).

6
2

Samsung Galaxy Note 4: Spawn of Galaxy Alpha and a Note 3 unveiled

Nate Amsden
Bronze badge

Re: Won't upgrade

what is "the vpn bug" ? does it impact note 3? I occasionally use Dell Sonicwall VPN on my note 3 without any issues (with their app).

0
0
Nate Amsden
Bronze badge

Re: Why so late?

I can drive my note 3 battery down by 50% in about 45mins with intensive usage. Light usage gets me through a day. I think I've lost 20% of the battery capacity over the past 11 months, it goes from 100->80% pretty quick.

to me anyways looping a video isn't a good indicator of battery life, since most of the work is done by the GPU. Drive the CPU hard and tap the screen a bunch, and see what you get.

going to buy a new battery soon.

3
0

Amazon: DROP DATABASE Oracle; INSERT our new fast cheap MySQL clone

Nate Amsden
Bronze badge

Trading one lock in for another

Title says it all

1
3

729 teraflops, 71,000-core Super cost just US$5,500 to build

Nate Amsden
Bronze badge

absolutely, nail on the head there.

this "super computer" didn't cost $5,500 to build, it cost $5,500 to rent. big difference(duh). Obviously 99.9%+ of the workloads out there aren't suited to one off runs of a few hours never to be needed again..

You've been able to "rent" super computer time for a long time, no news here.

This is one of the very very few good use cases of public cloud computing (IaaS anyway - SaaS is a good model, PaaS not sold on either).

20
0

Juniper boss exits after board probes his 'leadership and conduct'

Nate Amsden
Bronze badge

Re: Could it be some stupid and simple?

maybe he pulled a SAVVIS and spent tens of $ at a good strip club then refused to pay the bill.

1
0

Russian internet traffic detours through China's Frankfurt outpost

Nate Amsden
Bronze badge

Re: Not that uncommon

this is my own personal favorite traceroute - from just over 10 years ago, ISPs claimed a fiber broke in the eastern US which caused routes to fail over and opened a hole in which russian ISP(s) were able to advertise for our IP space(no idea if intentional or not), resulting in some ISPs routing to russia before getting to us resulting in excess of 95% packet loss. Sometimes the routes would bounce back to normal.

Took AT&T (our ISP) and friends a good 8-9 hours to get it fixed(I assume by installing route filters or something). Due to the packet loss we had to shut our website down for several hours.

As soon as the packets hit Russian routers the packet loss went from around 0 to more than 40% and higher from there.

http://elreg.nateamsden.com/funkyroute.txt

That is a traceroute that in theory only should go about 30 miles from source to destination(my apartment to my company's colo), instead - 32 hops, 200ms+ and 98% packet loss.

2
0

Wipro uses Nexenta to blast its way out of the hardware prison

Nate Amsden
Bronze badge

purchase price is not the full cost

Of course, having used Nexenta for the past couple of years in a very limited role I would never ever deploy it to true mission critical, wouldn't even consider it.

Big IT firms buy things lightly all the time, they have the budget to do so, they can buy something, have it work or not work,toss it out and go to something else.

As for data integrity on ZFS - it probably works great when there are no issues, once you get data corruption(as I had several times with Nexenta - due to their clustering software messing up) you are SOL. The diagnostic/repair tools for zfs for such a situation are basically useless. Even something as simple as say "zero out the corrupt data and fsck the file system so at least it mounts cleanly without panicing the Opensolaris kernel resulting in an automatic reboot" (something I've done with linux on one or two occasions w/ease) wasn't possible at the time (about 1.5 years ago). Support said "restore from backup". I didn't care too much about the data that was lost I just didn't want to have to rebuild the entire file systems, there didn't seem to be a way around it though. I spent hours with the zfs repair tools to no avail (at some points it seemed like it would work then after some time it would panic again).

Nexenta also tries to do too much for a small company, too many features makes me nervous in general. For us we were using only a few of the most basic ones(mainly I was using it as a NFS platform(for under 1TB of data) because it supported snapshots and high availability -- until we turned the HA off to stabilize the system). Oh and don't try to click on the snapshots in the GUI, it will spin for about 75 minutes before timing out because it is iterating through each and every snapshot on the system in serial to get info on it (yes the Nexenta software we have is old, I refuse to update it until we are migrated off out of fear it will break more, at least the issues we have now are known and I can fix them if they come up - support was useless)

Nexenta is not much more than a toy for white box system builders to be able to say "hey we do storage cheaper than the big guys!". For that they do it well, not a solution I'm in the market for anyway.

I'm sure it can work for some folks, I feel sorry for anyone being forced into using it for an important project though - you get what you (don't) pay for. Storage is complicated, storage is generally pretty fragile (unlike networking which is generally stateless), it's hard to get right, it's not cheap to get right. Cutting corners will likely cost you more in the end (or maybe you'll be lucky and not be impacted).

0
0

HP gives StoreServ a speed boost with flashy cachey spit'n'polish

Nate Amsden
Bronze badge

Re: Avoid at all costs

I just got my 7450 installed last week and upgraded to 3.2.1 MU1 (as far as I can tell that is the first release that supports dedupe and it is *brand* new (the ISO on HP's ftp site is dated Oct 30).

http://h20565.www2.hp.com/portal/site/hpsc/template.BINARYPORTLET/public/kb/docDisplay/resource.process/?spf_p.tpst=kbDocDisplay_ws_BI&spf_p.rid_kbDocDisplay=docDisplayResURL&javax.portlet.begCacheTok=com.vignette.cachetoken&spf_p.rst_kbDocDisplay=wsrp-resourceState%3DdocId%253Demr_na-c04491766-1%257CdocLocale%253Den_US&javax.portlet.endCacheTok=com.vignette.cachetoken

from the PDF

"After upgrading to HP 3PAR OS 3.2.1 MU1, customers with an SSD CPG can provision TDVVs(Thinly Deduped Virtual Volume)."

the 3.2.1 release notes don't mention dedupe, only 3.2.1 MU1 (above link has release notes for both versions in one PDF)

So find it kind of hard to believe you've had much time to test dedupe at this point. Dedupe would obviously get it's best value on something like VDI (never used VDI myself and don't foresee that changing anytime soon).

As a customer since 2006 I have been very happy, even more so to have such a mature platform offering all flash and dedupe etc.. The initial footprint of our 7450 (4-node) can fit almost 200TB of raw flash alone (that is assuming they don't release larger drives in the future which I'm sure they will have larger drives). Cost was really good too. Even if there is no dedupe it will pay for itself quite easily in performance and scalability.

I exchanged a couple emails with a friend of mine who works at Pure Storage (who used to work at 3PAR) and he said they do get beaten by 3PAR on price (not on data reduction - 3PAR doesn't support compression yet). Just hearing 3PAR beating someone (esp a smaller player) on price is just foreign to me. Most of it comes down to the very large SSDs and how they can get much lower $/GB as a result.

I don't have anything yet connected to my 7450, been busy configuring new vmware servers and other things -- but in the next few days will be storage vmotioning 1-200 VMs over to it. I don't expect much savings from dedupe until we move some databases over. Short term it's just playing around with it, see how it runs, probably won't have time to move much production stuff on it until our holiday "freeze" starts at the end of next week.

I have never used AO -- never really liked the concept of sub LUN tiering(on any platform was never sold on it), I always wanted to see a real array-based flash cache(that can cache writes), and it seems now after 5+ years of me pleading for it they are getting closer.. caching reads on a 90% write workload isn't going to do shit for me.

3
0

Forget Paris: OpenStack is not a cheap alternative to VMware

Nate Amsden
Bronze badge

sadly

that's not going to stop a lot of idiotic management types from trying......fortunately I don't work for those types at the moment. Having worked with such in the past though, so frustrating..

0
0

Down in the Dell, Compellent and EqualLogic are stirring

Nate Amsden
Bronze badge

Re: New partner?

seems like a fairly typical article. I don't see any opinion in it saying "oh go buy this it is better than the rest". They are just reporting on what the vendor is announcing, El reg has been doing that for as long as I can remember (been a reader for about 14 years now though my memory doesn't go that far back).

El reg does seem to favor sponsors though I suppose is understandable. One vendor I use for networking doesn't get mentioned much here in articles, after speaking with the vendor's PR folks (who do send info out to network oriented sites) speculated it is because they do not advertise on el reg.

1
0

Fujitsu's ETERNUS CD10000: Better Ceph than sorry?

Nate Amsden
Bronze badge

why

why would you want to risk storage by running workloads on a storage system? It's not like your going to benefit from ultra low latency on such a system it's distributed object storage. Even if you did benefit, spend the extra $ and get dedicated compute hardware, keep them separate.

my VAR has latched onto the idea of Cleversafe back end + Avere front end(NAS + tiering/caching) which seems to be an interesting combination. I have warned him against Ceph, not mature enough for most customers out there. (Not sure how much better Cleversafe is but they do seem to be the market leader so that says something at least). I believe Ceph has NAS as well but that's another thing I wouldn't put much trust in at this stage of their game.

I'm not in the market for such a system and don't imagine that changing in the next 2-3 years anyway.

1
1

EFF: VPNs will crumble Verizon's creepy supercookie stalkers

Nate Amsden
Bronze badge

might it be easy

to make a firefox (or other browser plugin) to get rid of this header? or perhaps just bake it directly into the browser. Enough users would benefit from it anyway.

1
0

New Dell FX2 chassis mixes 'n' matches server innards

Nate Amsden
Bronze badge

would it kill ya

to include some pics.

was curious so ended up going to zdnet to see pics

0
0

Pay-by-bonk 'glitch' means cards can go kaching-for-crims

Nate Amsden
Bronze badge

I'd expect..

that this is limited to the credit line of the card? If I have a $30k credit line there's no way the card/system could approve a $999,999 transfer?

0
0

Windows XP market share FELL OFF A CLIFF in October

Nate Amsden
Bronze badge

I don't get out much

but I was kind of surprised to see an official Delta airlines computer running XP (had the XP screensaver at least) a couple of weeks ago at the gate I was at. Or maybe it is a generic computer managed by the airport and just used by whatever airline is at the gate I am not sure.

0
0

Facebook OCP crowd to ogle MICROSOFT'S server-room SECRETS

Nate Amsden
Bronze badge

20 milliseconds?

What kind of generators spin up in 20 milliseconds? Maybe 20 seconds..but even then for me that is way too low, want at least 5 minutes in case something goes wrong with the transfer (same reason I won't put gear in a data center that uses flywheel UPS)

0
0

Keep up with the fast-moving world of flash array storage

Nate Amsden
Bronze badge

hybrid not tiering

IMO anyways more traditional folks that have SSD+HD in the same system and do sub LUN tiering aren't hybrid. I would call that tiering. I would call hybrid more transparently integrated like Nimble, or a few others that I forget the names now because I'm really tired.

I got my 7450 installed on monday though so I'm pretty happy. maybe next week will have time to play with it

0
0

Microsoft discovers long-lost phone division down back of sofa

Nate Amsden
Bronze badge

dropping Lumia too?

the headline says Lumia, but the article says Nokia.

Of course we knew MS had a limited time frame to use the Nokia name, though I don't recall seeing any restrictions on Lumia.

Not that it matters to me, it is interesting if they brand it Microsoft given the extent they went to in the early days of trying to hide the Microsoft brand from Xbox.

12
1

Upstart brags about cheaper-than-Amazon private cold data cloud

Nate Amsden
Bronze badge

should be easy

to beat public cloud object storage when your talking PB or more of data, that's quite a bit of (initial) volume.

object storage players have been doing this for years, not sure why this might be news. I was thinking maybe it was news because it was going to be a small scale or something but a PB of data is significant to all but the largest orgs in the world.

0
0

Amazon's AWS opens data center in Germany – just as we said

Nate Amsden
Bronze badge

Re: US will still get your data

Even if they do win, the threat of having future rulings overturned etc will probably always be there. So if your concerned about such a thing, no point in even considering such a cloud company. You can encrypt a lot of your data, but obviously most active data has to be in a decrypted state in some form to be read(I suppose one exception is if your doing nothing but storing and retrieving encrypted data and decrypting it off of the cloud for reading -- in which case this new data center buys you nothing new from a security standpoint)

2
0

Xen says its security policies might be buggier than its software

Nate Amsden
Bronze badge

Re: VM Migration

I remember about 4 years ago I met with the head of EC2 and their chief scientist (the head of EC2 was the brother of the CEO of the company I was at at the time). We vented our frustrations with their platform (it wasn't the first time my boss met with them to say how unhappy he was as a customer). And they acknowledged the problems (but never fixed most of them likely to this day).

ANYWAY the topic of vmotion came up in the discussion and they said "oh well when you move a VM you get a spike in latency for a few seconds, we don't want our customers to endure that so we don't have it" (I think that was more of a cheap excuse because they probably weren't technically able to do it due to the outdated and hacked Xen that they had(and probably still have).

As a customer I'd be more than happy to endure some latency during a VM migration if it means avoiding hard downtime of that VM, easy choice to make.

Moved my company out of ec2 cloud about 3 years ago, I couldn't help but laugh when about a year afterwards a developer was doing something and I asked them why (I forget what they were doing) and they said they were doing that in case we had to rebuild a server (not too uncommon in public cloud). I laughed, to this day 3 years later we have not had to rebuild a server for any reason.

lots of apps have single points of failure, not everything is a stateless web server. One of my big arguments against such cloud providers is just that -- most developers don't build for that, even dozens of ones I have worked with who built their apps from the ground up in cloud environments. It's simply not a priority. It makes sense to me anyway, you have to choose building features for the users or making the app really robust, I'd wager greater than 95% of orgs choose the former(in all of the "web" startups I've worked at the past 15 years that number is 100%). Only when the latter becomes really really painful do most orgs invest in that(yet to work for a company that did this) because it's quite complicated to get right, and in many cases it is simpler/more cost effective to provide higher levels of availability in the infrastructure than it is in the app (that usually flips around when you get to really large scale (systems numbering in the thousands at least) -- but most orgs aren't at that scale and never will be).

most management types see cloud and think of it as a utility that it'll never go down, some magical thing that just works.... there's a ton of work that has to be done to leverage such cloud providers properly and most folks never get around to doing it. Certainly was never, and is not worth the effort for my org, or any company I have worked for in the past, the return on the effort is simply not worth it with all the other compromises (both in cost and tech) that must be made to make things work.

2
0

You get what you pay for: Kingston's SSDNow V310 960GB whopper

Nate Amsden
Bronze badge

Re: Where are the 2TB SSD's?

There are 1.6TB SSDs in the enterprise space (seem to be starting in the $2-3k range)

I imagine 2TB SSDs will come when they are more cost effective for the consumer space. Right now it seems a 1TB runs well north of $500 it seems like, so perhaps when 2TB can be sold in that price band it will come.

2
0
Nate Amsden
Bronze badge

for one supply and demand, if flash was so cheap people would be buying flash and not disk, and there is not enough capacity in the world to come close to being able to satisfy anything remotely resembling that demand.

two, the cost of spinning rust has always been going down and continues to do so. I don't understand the logic behind flash is getting cheaper so it should be cheaper than spinning rust(which is getting cheaper too).

Flash has a lot of precision involved as well, just look to the massive quality issues on many of the lesser brands over recent years. Just ask Samsung how much it cost them to develop their 3D NAND technology, probably wasn't cheap (my laptop has a 850 Pro in it, so far averaging 1TB/writes/month over the first two months of usage).

2
0

Violin: Don't weep for Tier 1 storage... it'll soon be flashtastic

Nate Amsden
Bronze badge

The best solution will vary of course. For me higher priority goes to high reliabilty, proven systems. Server side san sounds nice on paper but to me too complex to build a solid system yet anyway in a few years maybe itll get there.

Forgive typos am on my phone

0
0
Nate Amsden
Bronze badge

Re: Sustained writes flash sucks

How does 8PB of writes for an SSD sound? That's whats behind HP's 5 year unconditional warranty on 3par SSDs.

Deploying my 7450 in about a week or two.

Violin is 2 years too little too late

0
0

Page:

Forums