Posts by Nate Amsden

Google: We look forward to running non-Intel processors in our cloud

IBM doesn't have dividend shareholders? Or are there 3rd party POWER chips available now that el reg hasn't covered?

Re: Plus ca change

With youtube I assume they solved it eons ago

Re: Blast from the past

Can't edit posts on mobile. I had vpn too of course :)

Re: Blast from the past

Because it's a pain in most cases? VGA over IP has been good for a decade. Serial works alright but still often painful to use. I remember the last time i had serious serial console use a decade ago, in servers with 3ware raid cards. Everything worked fine outside of the 3ware raid bios.

HP servers automatically detect serial and switch to CLI (or they did last time I ran serial on them years ago). But setting options via CLI took much longer than using the ANSI GUI. Last I tried again yeara ago installing esxi interactively via serial not possible either.

So nice option to have but will take HP iLO advanced over serial in a heatbeat. I've even just for shits and giggles installed esxi 5

5.5 via ISO from my phone at a bar using xenapp, iLO advanced and remote desktop.

Re: Blast from the past

Because it works fine and is a standard? Because most server systems don't need more than 1024x768 16bit? Because many servers are using 20 year old graphics chips like matrox g200? These are used for management not for workstations.

Re: AMD?

Amd hasn't refreshed their server chips in years. I still have a bunch of opteron 6xxx i like the chips and hope their new shit is good, gave up hope for them since they abandoned their high end chips and I assume lost a lot of the engineering talent behind them. HP has gone 2 generations of servers with no AMD.

My latest servers are 18 to 22 core intel though. If AMD comes out with lotsa cores for vmware even if the per core performance is lower I'll buy some for vmware servers for sure. As is core for core the intel chips are 2x faster than my AMD. I don't think I'd accept a 50% performance hit for new AMD chips unless there is perhaps double the number of cores.

More curious to me is it sounds like they have no ARM either. Which given google's scale surprises me that they wouldn't have some in there. Guess ARM on servers sucks more than I thought.

Galaxy Note 7 US flight ban

Re: wonder if they check

To answer my own Q flying out of san francisco airport last night no extra checks just a message on the TVs (every now and then) saying note 7 is not allowed. No mention of criminal charges just you would be denied boarding.

Note 3 with android 4.4.x is about as perfect a phone as i could hope for.

wonder if they check

Boarding a flight with 2 galaxy note 3s in a few hrs. Wonder if they will have pictures of the phone posted to try to catch them or something.

How a chunk of the web disappeared this week: GlobalSign's global HTTPS snafu explained

living in a bomb shelter

Didn't notice any issues on any of the maybe dozen sites I regularly visit. Company I work for uses go daddy (where tf are the godaddy girls), so no issues there either over the 150 or so certs we have. (Same goes for CDN which uses another provider I forget who)

Native OpenBSD hypervisor

Re: It will be interesting to compare

As an openbsd user since 3.5, sounds cool but don't need it.

Vmware works fine(even with openbsd as a guest i use this config personally to insert a firewall inbetween my personal linux and windows VMs and the internet on my co located server, also use openbsd at home as internet gateway. )

Haven't used it at a company in a professional manor in a decade. For some reason i have to reboot the openbsd firewall in a VM every year or so, network performance tanks and is magically fixed by reboot.

Openbsd pf is awesome though.

The exploding Note 7 is no surprise – leaked Samsung doc highlights toxic internal culture

when I read this

reminds me of one of the robo cop movies where the OCP corporation (japanese owned I think in the movie) was harsh on employees, and towards the end of one of the movies several people in company suits are seen jumping from their offices 20-30 floors up.

Oracle DB admins urged to swap their gas guzzler for an electric car

Re: And...

Of course it will work. You're developing your app for the db so you develop it for mysql. Converting an existing app can be more difficult depending on how the app was written but many apps already support multiple DBs.

Re: And...

And oracle might just say here is mysql enterprise edition for a lower cost than oracle db. There are many times more users of mysql than postgres, look ma we do open source too.

Hey, you know what Samsung is also burning after the Galaxy Note 7 fiasco? $2.3bn

Somwhere deep inside samsung

is a lone engineer, or perhaps a team of engineers saying "I/WE FUCKING TOLD YOU SO!!"

Much smaller scale obviously but reminds me of another company I worked at years ago, 3-4 years after I left someone told me a story that went something like this

1) company deploys new version of code across QA environments (many of them)

2) code causes non stop problems and crashes for a month

3) company has a "go, no-go" decision for production

4) EVERYONE on the tech team said something like are you fucking crazy this is shit, NO GO

5) management decided to go anyway because of contractual obligations

6) Company ends up taking 12 to 14 hours of hard downtime in production(for their customers including the biggest mobile carriers the world) in order to roll back the bad code.

Big Mickey Dell is wrong: Cloud ain't going to eat all of IT

cars and phones terrible analogies

My last company years ago was a startup all in on amazon (CEOs brother heads amazon cloud). Bills were over 500k a month at peak.

That company is long dead

Current company was well on the way to 200k a month before we moved out 4 years ago. Absolute cost savings was just a small part of the savings. That was IaaS cloud. We still use many many SaaS cloud solutions. IaaS is a load of shit, SaaS makes sense in a lot of cases.

Companies spending such high dollars on cloud because they don't know any better is quite common. Here is a story i found a couple years ago about a very extreme case where a startup was spending 25% of REVENUE on cloud. They moved out, CEO was pissed they got fucked out of millions per year because they didn't know any better

http://www.techopsguys.com/2014/01/30/more-cloud-fail/

Some executives don't know any better on the costs. Some are smart enough to realize they are getting fucked by the service provider though.

If you can really do it right cloud can make sense. Getting it right is hard. MANY developers still struggle with things like single points of failure and multithreading.

If cloud were the magical thing it's marketed as(to many execs it sounds like 100% uptime and low cost) then it would be great. But it's not. Cloud companies like to blame the customer for their own outages (google may be an exception).

Biggest challenge I see to avoiding getting fucked by the cloud companies is adequate staffing to run shit internally. Companies seem more comfortable paying millions in extra cost to a cloud because they don't know any better but paying the salaries required to attract and retain talent to do it yourself (even if it means saving millions ) doesn't compute in their heads. Sad.

First look at Windows Server 2016: 'Cloud for the masses'? We'll be the judge of that

Re: Licensing

Oracle does that too. Interesting

Like it or not, here are ALL your October Microsoft patches

so do these new patch bundles

really include everything ? I mean if I did a clean install of windows 7 and got this month's update it would have every update since windows 7 came out ? Or if for example I am current today and run updates in 1 year does it install one round of updates or is it 12 rounds of updates or somewhere in between?

I'm no windows guy, but I did have an interesting(if you can call it that) experience installing a fresh win2008 R2 last week, the ISO image was 3 years old I think, it installed a bunch of patches, then got to SP1 (why SP1 didn't include all of those other patches I don't know). SP1 wouldn't install, strange error, and the help said nothing. Fortunately I was able to manually download a 2GB ISO file which contained SP1 and that installed flawlessly, allowing windows update to continue on it's patch frenzy, I counted roughly 330 patch IDs installed after it was all done. Took all day but it was working in the end.

Maybe someday MS will be able to download all of the patches in one go, I do kind of miss the NT4 days where at least I believed at the time the service packs were in fact rollups of all other patches(up to that point), and there was of course multiple SPs (at least 4 in the case of NT4 I think). Though overall stability of NT4 is really part of what drove me to linux on the desktop in the end.

It's really rare a MS patch causes issues for stuff I do(can't remember last time that happened), though my windows use cases are very limited.

Skype for Linux users can crash-test video calls in v1.10 Alpha

yeah pretty sad huh. Still have skype for linux 4.3 on my system though my skype usage has gone down about 99% since the company I work for changed to slack about a year ago. At the time 90% of my usage was text chat, probably 8% voice chat and 2% video chat. Had been using Skype on linux since about 2010 with very few issues.

With all of the resources MS has, to go around killing native clients for skype(even native clients on some windows versions!!) and breaking compatibility with so many installed systems out there is just unbelievably stupid. Almost up there with their attempts to try to force so many people to upgrade to windows 10.

fortunately I don't feel much pain anymore as I don't use skype much, when the native 4.3.x app stops connecting to their service maybe that will be the time I just delete it and forget about it.

slack for linux sucks too, memory usage wise anyway. Have to restart it at least once a week it can easily grow to 4GB of memory(larger than any other process on my laptop including vmware and firefox), skype was able to run for weeks or months at a time and be stable for me anyway.

Oh should clarify a bit, I am told the slack for linux is not a native client either but rather a bullshit wrapper around chrome and a webapp on top. wtf.

Cloudera tells bright Sparks: Go teach yourselves Hadoop

the trouble with hadoop

Is once you get good at it most likely you can jump jobs to another company that will pay more.

The other trouble with hadoop is people wanting to use it for the wrong reasons, and not being able to utilize it effectively (e.g. writing batch jobs that are so poor they can only be processed by a single node, or an organization that wants to use hadoop so badly they just start using it even though they only have a GIGABYTE or two of data).

I had one clueless VP years ago tell me with a straight face he wanted to use HDFS to host VMware VMs.

National Australia Bank starts week with TITSUP*

this is why

Developers aren't allowed to touch production.

Leap second scheduled for New Year's Eve 2016

wtf

What value does this have? Really none everyone is already in sync even if it is off by a second or two or three. Keeping time in sync with aliens from another planet provides no value.(if there are people that it does cause an issue for then change your clocks don't fuck with the rest of the world's)

(Someone who was burned by the 2012 fuckup, least I didn't run the airline that went down, and of course NTP did nothing to address the issue)

Secure cloud doesn’t always mean your stuff in it is secure too

Re: LOL

say what AC ?

If it helps as recently as last year I know a guy who has a highly technical background and was playing with elastic search in amazon cloud, he got hacked multiple times(elastic search bugs or something).

Which goes back to my original point of everything being on a public IPv4 address by default is generally a bad thing.

I do not believe the security group situation has changed. Don't know about azure or google cloud or other public clouds but amazon was absolutely terrible in pretty much every respect(and yeah I met the head of amazon cloud years ago along with his chief scientist where they tried to justify the issues would be fixed in the future, they never were).

Re: LOL

Generally it is far easier to deploy insecure shit in a IaaS public cloud especially amazon when the defaults are to give every VM a public IP address, and their security groups stuff isn't the most intuitive in the world if you are getting beyond even a very basic level of usage(maybe it's better in past 5 years been that long since I had to use it).

We've seen many articles about how things like unsecured S3 or mongo databases in amazon have been raided for data in recent years.

vs on prem where it is far more likely most services are deployed behind a firewall with VPN, if for no other reason than limitations in public IPv4 availability.

Breaking compression, one year at a time

Re: Windows Server 2008 R2

In large part why all of my new windows VMs are 2008R2. I don't have many windows VMs couple dozen vs 900 linux. I have win2012+classic shell too and it's not enough. Fortunately I don't need windows for much and 2008r2 is more than capable of doing everything we need except for one custom app that requires 2012R2.

Oh and windows storage server on 2012 sucks sooo bad. I have used that too in the form of HP StoreEasy with windows clustering for HA. I thought for 1 or 2TB of data that would be more than enough. But it was not. Too many bugs that were not going to get fixed. I did get MS to fix one bug but decided to retire the platform before installing the fix. Just couldn't trust it with the data.

Last straw was an error occurring on one data volume with dedupe on (dedupe error thought volume out of space when there were tons of space) caused entire cluster to fail on both nodes. Half a dozen other volumes went down because of a fault on one volume. Killed the cluster after that. Migrated to freenas in short term hope to jump to isilon early mext year. Finding a suitable NAS for a reasonable price for such a small amount of data that supports real high availability has been much harder than I expected (originally used nexenta that was a disaster too).

Fortunately 98% of our data is block and 3par provides a rock solid foundation for that.

hp pretty good about extended support

I have a 3PAR F series array going end of support this month. Array is 5 years old (array originally launched 7 years ago). Support prices were consistent throughout the life of the array. Going to 3rd party support now from a company called sherlock services. Their price matches HPs price for support only thing they can't do is software support. Which isn't a big deal haven't had a software issue on that array in 2 or 3 years. Hope to retire it soon since it uses 2 or 3x the power of our 3par AFA. Adding. 30TB to our AFA today to get us further down that path.

I have a bunch of DL385G7s that are entering year 6 wasn't expecting HP to support them still but just renewed about a month ago. Price went up but not much.

Anyway am glad I left internal IT 13 years ago so have not and do not live in a post refresh world. Everything gets 24x7 4 hour onsite support where available (for some reason load balancers like F5 and Citrix do not offer that last I checked)

Part of the reason for on site support is both datacenters we have are 3000 miles or more away from me and I'm the only one qualified to do the datacenter work at my company still.

The shoemaker, the array refresh and the VMworld smackdown

seems like a bad config

I mean an array that can only deliver 33k iops at 300ms? Must've been doing something very wrong. Never used VMAX myself but that number seems just bad.

Also 177k iops from cache on infinidat? Also seems bad, would expect at least 3 to 4 times that. Should be able to get more than that with just ssds pretty easily.

Maybe these folks have some really strange workloads but those numbers make little sense to me.

Without more details this is not a case study I would trust.

Is Apple's software getting worse or what?

little to do with apple

The fail fast fix fast mentality of software development is insane. (Have worked with software dev teams for 16 years now). Sounds fine if you are working on some new thing. But should not be used on core products. Whether it is apple (not a customer so can't say from personal experience ), Microsoft struggling with their updates, MANY others as well.

The focus has been shifting towards faster delivery of lower quality stuff because they believe they can just fix it later. Though in many cases later never comes because they move onto something else new and shiny.

It is possible of course to release things often but it requires more care than just doing it.

Too often agile is used as an excuse to ship faster and not need quality control.

Windows 10 seems to be turning into the largest scale agile fail in the history of software.

Companies like apple and MS have absolutely no excuses each having 10s of billions of dollars in the bank.

Yahoo! tries!, fails! to! shoot! down! email! backdoor! claim!

Re: BT customers locked into BTYahoo email service

But are you really locked in? I mean you can probably just stop using the email service.

I haven't used an ISP-provided email account since 1999, and even then it was pretty light usage.

Google melts 78 Android security holes, two of which were critical

Re: @sabroni

I've been using a Note 3 since a couple months after it came out (the one and only Android smart phone I have owned). I have two now, my main one running 4.4.4 and a backup running 5.0 (wish there was an easy way to get it to 4.4.4, tried once got too close to bricking it and haven't tried since). No real complaints, only issue I have on 4.4.4 is I can no longer make a phone call in multi window mode with the calendar up at the same time, phone app goes full screen, didn't used to do that. Annoying when I am calling into a conference bridge and trying to read the conference code from the calendar.

Android 5 on note 3 (AT&T note 3 in both cases) is worse, I read some of the isues are fixed in newer android 5 but those are not available. I really don't like the "recently used apps" feature in android 5 that drives me crazy. Also am not fond of the newer UI in 5.0.

I'm happy with 4.4.4 though, as happy as I think I could be anyway. Before that I was a WebOS user for a few years, and long before that Blackberry.

For the most part I stopped updating my apps too unless I really need to, too many things change that make them worse and there's no way to roll back to earlier version. Weather.com app I like, at least the version on my android 4 device, on the android 5 it worksok but not as good. I did roll back the Samsung health app on my note 3 after an upgrade prevented it from going to landscape mode, though I lost all of the data in the process.

So many issues could be fixed I think if there was just an easy way to roll back, whether it is apps, or full phone OS. Too much risk of shit breaking or not acting the way I am used to with upgrading, so not worth the risk.

I am very careful as to what I do on my phone of course, obviously no banking, or online purchases of really any kind. Am careful in other ways too. Security wise I think the risk is low. Risk much higher for a frustrating user experience though.

Which is what makes me like Linux Mate so much, Ubuntu 10.04 LTS UI was the best UI of any linux I have used(20 years now), and was very afraid to jump to Gnome 3, then MATE came out and saved the day.

Windows 2016 just came out too right ? and here I am deploying fresh Windows 2008 R2 servers because I prefer the UI on those too over 2012(have a few of those with classic shell) and up. Though 98% of my systems are linux.

Infinidat's big iron array gets data scrunching, no-footprint iSCSI

sure it's faster

but at what cost?

A few years ago I was joking with my then manager about how EMC likes to come in and "buy" business by engaging at the executive level, one of the reasons I have not bought from EMC (though it seems recently they are working to change that image and I see positive results - may be an Isilon customer soon).

Anyway, maybe it was barely a WEEK later and I am in a meeting with some people along with our then-CIO, and someone comes in with two boxes. In them were two dozen premium cupcakes from EMC. They wanted to meet. My boss joked "why didn't they just buy him(CIO) a @# car" (we were/are a 3PAR customer). Maybe 2 years later had a more direct conversation with the person at EMC that sent the cupcakes. Seemed like nice people, and really appreciated their new approach, their attitude was they weren't going to try to end run around me, if their solution isn't a good fit and we are happy with what we have, that's great. Let them know if that changes. No high pressure shit, none of the "old EMC" that so many people are familiar with, and it is that "old EMC" that these and other newer EMC staffers have told me they are trying so hard to wipe that image because almost every customer they go to feels the same way.

CIO asked if we need storage I said no not really, but said I am fine to meet with them. I expected EMC themselves to show up but a reseller did instead.

They weren't prepared to deal with me. It was funny. In the end they actually shifted to try to sell us Hitachi storage instead of EMC which got me confused as until that point I thought they were EMC. They said they could sell us an array that had 1 TERABYTE of cache in it(i.e. Hitachi VSP), so much faster than our tiny little 3PAR array. I laughed, they said this with straight faces too, we obviously don't have the budget for that kind of system. They later walked out with their tail between their legs and haven't heard from them since. It was a somewhat enjoyable conversation though as I rarely get to talk about storage to someone in person who even has a vague idea of what I am talking about. Maybe a couple times a year (yeah I don't get out much). Same goes for networking.

But I thought of that experience when I read the comment on how Infinidat's storage is faster than all SSD platforms. Don't doubt that for a minute for many workloads especially ones that fit in the cache.

I have no doubt their storage platform is a really good platform for the target market (tells you a lot if they are supporting mainframe connectivity), and I'm sure really good for many other workloads though also confident the price premium is hefty too, given the high availability probably well deserved premium for the niche of apps that really need that.

'Too big to fail' cloud giants like AWS threaten civilization as we know it

Re: Absolutely

core networking protocols? tcp/ip ? Shit I had a developer come to me recently with a straight face, and said he had a new app he needed deployed and he needed some back end storage for it. Sure, so I asked him a few Qs, and he answered, all sounded reasonable. So I asked them then what is his timeframe, and he said "they want it today........." (he added the dots..) Fortunately this was over online chat and I burst into laughter. I asked if the code was even written yet, he said the front end part was, the back end was not(part that stores the images and stuff). He asked if there was an API to code to, I said he should ask the development team, but I am very sure the answer is no, and the lead time to get a new API is probably a few weeks assuming they even agree to do it.

I have worked with developers who don't even understand the basic concept of reading log files, its depressing. I mean they wrote the damn thing can't you at least look at the logs ? They often just throw up their hands and say it doesn't work I don't know what to do. I have a new saying for many developers, saying may not be the right word but it goes something like "XX is broken, I don't know why, I don't want to understand why I just want someone else to fix it for me". Often times it is in the code. I can understand non technical people behaving this way but not "developers". Certainly not all developers are like this. BUT I see it as a disturbing trend that is only increasing as the layer of abstractions increase between the underlying hardware and the software they are writing.

How many developers even know how to look at a core dump ? (e.g. php/apache core dump). I don't think I've even worked with more than 2 that can do that in the past 8 years. They know php, but go one inch outside their comfort zone and it's like deer in headlights.

Another favorite is I give a developer a specific SQL query that is causing problems and ask them if they can fix it -- they have no idea where that query came from (other than their code) because it's so abstracted, all they know is they called some object and the magic sauce underneath generated the SQL.

This kind of thing is really what gave rise to things like docker. Instead of fixing broken systems like node or ruby(another depressing thing they haven't fixed ruby on some core things since the first time I had to operate it 9 years ago, now I understand it is by design and they won't fix it, anymore than Linus will fix constantly breaking Linux driver ABI). So instead of fixing the actual problem they come up with something like docker, to hide the monstrosity of dependencies and crap in a container to make it more deployable and manageable. Oh my god the first time I tried to build node I think it took me 3 days and it ended up being a version that was too old for the developer. (yes I try to build things properly I won't download some random shell script and pipe it to bash as root to do everything magic). Worst inter dependency mess I have ever seen, even put ruby to shame. One recent node upgrade I recall we had to upgrade GCC, and other core libraries which were not compatible with our OS standard, just to compile the damn thing. I mean I haven't had to go out of my way to upgrade gcc for something I want to say in 15 YEARS (I remember using 'egcs' way back when).

Then another development team comes around and says they need something else, some other version, but that version breaks the code from the first development team..it goes on and on what a mess.

The worst part about it is more people are using it, and more NEW people are using it not knowing how unstable it really is because that's all they know. I see developers constantly having trouble with mismatched node shit.

Getting developers to know low level protocols, shit I'd be happy if they just knew their own damn application stack.

biggest DDoS threat

is collateral damage. Not being directly targeted but being on a shared service that has someone else that is targeted.

Lots of random people and orgs use public clouds, which just means they have bigger targets painted on their backs.

I recall in the earlier days of amazon cloud credit card fraud was one of their biggest issues, not sure how it stacks up now.

Snoop! stooge! Yahoo! handed! all! your! email! to! Uncle! Sam! – and! any! passing! hacker!

FBI contacted me one time

Not sure why I remember this but for some reason it triggered this memory. A few years ago I was asleep in a hotel room and I got a phone call.. some guy was trying to get in touch with my former employer, after some discussion he revealed he was with the FBI and wanted to see if this company had some data they were tracking down someone(s). He asked whether or not the company had web access logs. I assume they were looking for something child porn related this company had a lot of user generated content and no controls whatsoever (said company has been out of business for some time now). I joked to my friends at the company at the time since they were hosted in amazon cloud hell just give them a splunk account, there is nothing useful in those logs anyway!

But I did find it funny that even the FBI investigator could not figure out how to get in touch with someone at the company, so they resorted to the WHOIS information on the domain, which more than a year after I left for some reason still pointed to me. There was no phone number or general email address(or physical address) to contact on the website etc, the whole time I worked there it sort of felt like they could decide to close up shop on a friday afternoon and have the place be emptied in a matter of hours and it would look like they were never there.

I could say the CEO of said company went over to Yahoo at one point but that's purely coincidence !

Anyways I got this guy in touch with people at the company and they took it over from there. Only such request I've ever dealt with.

Software-defined traditional arrays could be left stranded by HCI

as a non HCI customer

I have no interest in HCI and prefer best of breed solutions which for me are proliant, 3par(fibre channel) and vmware. I also do LXC too on bare metal proliant systems. The uptime on some of my storage is longer than some HCI vendors have been shipping products.

HCI sounds great for edge and branch office (internal)IT. Though I've been on the SaaS datacenter production side for more than a decade. HCI has no value for me in this space.

Dell-EMC's dual server supply problem... is not a problem, it reckons

what choice?

I just searched the whitepaper for the word "choice" and it seems the only choices you get are a few different CPUs and the ability to control bandwidth. Seems choice wise HP is far far better(so much more flexibility with HP it's not even a comparison) though it would be pretty stupid for Dell/EMC to not offer a choice of using Dell blades, I have no doubt like others that this is coming. No reason to throw UCS away, show the price points of each and let the customer decide what they want.

(currently running HP servers+storage+vmware but NOTHING is converged)

Colour us shocked: Dell EMC rules converged systems like a boss

next obvious question for me

Is how does revenue of all of these "converged" systems compare to non converged ? For the business I work for we do use HP DL servers and storage and vmware, though none of it would be considered "converged".

Wow, still using disk and PCIe storage? You look like a flash-on victim, darling – it isn't 2014

tiny niche

The stuff that needs this kind of tech is a tiny niche. Been supporting ops/dev type shit for 15 years now and at really no time has something faster than SSD been even thought as a "nice to have". Current org is a typical online e-commerce business doing well over $200M/year in revenue running standard web stacks (with mysql as the DB of choice). In excess of 90% of all I/O for OLTP occurs within mysql's buffer cache. Disk I/O to the LUNs mysql lives on is tiny, really only happens for very infrequent big expensive stupid queries but far more often for log writing (binary logs, relay logs etc). Storage array I/O workload is over 90% write under 10% read. We probably peak at 15-20% of the array's I/O capacity (meaning it will never be a bottleneck in lifetime we will be using it for).

I was at another company several years ago who, many years before that wrote a proprietary in memory database for behavioral ad targeting. We had dozens of servers with massive amounts of memory(for the time) and clunky processes for loading data into these in memory instances. While I was there they eventually decided that in memory was too expensive so they re-wrote the stack so it did some layer of caching in memory(reducing memory usage probably by 80-90%) and the rest of the data sat on a NAS platform connected to a 3PAR storage array(with SATA disks no less). So they went from in memory to NAS on SATA, and the performance went UP, not down.

I still believed it was a flawed architecture I would of preferred them use local SSD storage (at the time I wanted them to use Fusion IO). But they architected it so it HAD to reside on a shared storage NAS pool it wasn't going to work on local storage. Too bad, missed opportunity.

So I've seen and managed traditional mysql (and Oracle) and vmware etc as well as in memory systems across now thousands of linux systems primarily across many companies over the past 15 years, and solutions like those presented in the article I believe are very very niche(relative to the size of the market as a whole). I could see things changing if the costs get down low enough that it makes no difference in cost/complexity if you are using DIMM SSD or SAS SSD(or even PCIe SSD), but I don't see that happening anytime soon.

I do believe there is a market for this kind of stuff just much smaller one than articles like this seem to portray.

Windows Server 2016 will cost more on big servers, but discounts can be found

Re: Wasn't it VMware

Can't edit post on mobile. Also wanted to say my standard vmware server spec uses dual 18 core cpus(older gen servers have less either have 12 or 16 cores per socket). I have some new LXC container servers coming (fuck docker) that have dual socket 22 core (88 threads) soon too.

Re: Wasn't it VMware

Mainly vmware wanted to charge for memory. People called it the vRAM tax at the time.

As a loyal vmware customer for 17 years I was not happy(my standard was and remains 384GB/server with 2 sockets). In the end it had no effect on my stuff since i stuck to esx 4.1 until past end of support (on accident). The vRAM tax only impacted one or 2 versions of the 5.x product line.

By the time I upgraded to 5.5 the issue had been resolved for a year or more. Also no plans to upgrade past 5.5 until end of support again it does everything I need and is stable as a rock. I hear bad things about v6 so perhaps a couple more years and it too will be rock solid stable.

I imagine win2012 has many years of support left in it(2023 looks like?). If folks want to postpone the license hit just don't upgrade.

I'm going to deploy a few new windows servers myself soon (in vmware). I think I will stick to 2008R2 I prefer that UI(I have some 2012 too dislike UI even with classic shell). That and their roles match other systems that I have that do the same and I like consistency though technically those others are 2008 not R2).

I have roughly 900 other systems that run linux (~98% on top of vmware enterprise +)

Mozilla tells Firefox OS devs to fork off if they want to chase open web apps vision

so they want to continue gecko..

but last I heard anyway the future of firefox browser is the engine that runs on chrome ??

(firefox user since phoenix 0.3 and like many others increasingly upset with the direction mozilla has taken firefox in recent years, if I wanted chrome I'd switch to chrome).

IO, IO, it's profiling we do: Nimble architect talks flash storage tests

3par has been saying this for close to 15 years

And built their architecture around it

Picture describing this aspect

http://www.techopsguys.com/wp-content/uploads/2013/05/3par-mixed-workload.png

Scale-out sister? Unreliable disks are better for your storage

3par does this too

Working with SSD vendors to reduce space allocated for bad cells and give it to the array (20% I think). Since 3par operates with chunklets if some flash goes bad it just stops using it. Too many chunklets go bad and the drive is proactively failed. HP calls this "adaptive sparing".

My org's oldest 3par flash is about 22 months old and as far as media life the SSDs have 98% of their life left (if you were to source these SSDs direct from SanDisk they would be read intensive SSDs though HP doesn't limit their workload under the 5 year warranty).

Google could do what XIO did just partner with the HDD makers. Or go buy XIO(and stick to seagate drives last I read XIOs tech was specific to that). XIO can't be too much to buy.

Cisco preps the P45s for 500 unlucky UK staffers

Not that I entirely disagree but it seems kind of funny so many of the "hot big and sometimes new" companies are the ones that constantly lose money, meanwhile the old boring ones that keep laying people off often make tons of money(and have even more in the bank). Sure some of their businesses may be in decline to some extent but if I were a betting person I would think that in many cases these old big companies will run out of cash long after the newer companies that seem to live paycheck to paycheck.

Video service Binge On 'broke the internet' but 99pc of users love it

best of both worlds

People get to watch more video. Those that hate the concept can opt out.

As an ATT subscriber with a 5G data plan who streams maybe 10 minutes of video a month across both wired(200meg comcast with 1TB) and wireless it doesn't impact me either way but sounds like they had a good idea(i think i said that before here)

Samsung intros super-speedy consumer SSDs, 'fastest M.2s ever'

Re: Viable as SAN replacement?

SANs are all about high availability and data services. A lot of which is very sophisticated software and hardware architecture.

You can certainly have a very fast disk array with this kind of storage but it wouldn't really be in the same space as a traditional SAN product. And no the open source storage stacks don't come close to being adequate either unless you are very committed and have significant internal resources for support. Support will of course matter most when shit hits the fan.

Re: Laptops with dual M.2 slots?

My lenovo p50 has dual 512GB 950 pro(pci e 4x 10gig) and a 1TB 850 pro sata. With this config and 3 year on site support about 3500.

I expect to be using it for at least 5 years(previous laptop was a toshiba and was primary computer for 5 years gets light usage still).

I see no difference in performance between 850 pro and 950 pro outside of benchmark scores. Everything is plenty fast.

My normal operating system is linux mint though have windows 7 dual boot in the rare chance i want it for gaming.

Oracle's cloud strategy is simple – woo and win the latecomers

IaaS sucks

but Oracle probably has a decent chance to do some level of SaaS with all of the apps that they have, maybe some PaaS with something like weblogic and oracle db etc..

More value in the higher level services anyway.

IaaS sucks which is why almost everyone is failing at it or those that are not still do a shitty job like amazon (I assume Azure too but can't speak with personal experience).

Seventeen hopefuls fight for the NVMe Fabric array crown

Re: NVMe right, but block fabrics less relevant in the new stack

And those legacy type systems will be around for a very long time yet - even today such systems are still being built as new. The last time I spoke with DBAs about MySQL compression for example the basic suggestion was don't use it. The last time we attempted to use it in a test environment it blew up badly.

You may like new funky DBs that have weird names and are optimized for special edge cases, but the bulk of the world will continue working off of things like Oracle, MySQL, MS SQL and other "legacy" platforms with apps that won't support things like you are talking about for the next decade or more (in many cases they will get along fine without them).

Been working closely with devs on "new" web apps over the past 13 years(across several companies all sort of in SaaS in one way or another) and they still have problems grasping basic things like "single points of failure", or "take the whole app/site down while we make a small schema change". Or let's have microservices, where in many cases there is so many inter dependencies that you are just increasing your points of failure rather than reducing them. Or how about "HEY there are two cpus in this server let's run with more threads to better utilize them, but no the code is too highly serialized and doesn't scale like that..".

I saw one recent app update to a 3rd party component deliver literally an 82% drop in performance(worst case). Can't get the CPU usage above 30% (10 CPUs), vs before could get to 93%. Vendor who makes the software doesn't seem too bothered by the results, or at least not enough to even prioritize a simple investigation into the cause when it's so easy to reproduce.

I remember another time, at another company, in house app - new version comes out - 66% drop in performance due to new serialization in the code. They squeezed an extra 15-20% out of it again(eventually) but admitted that was as fast as it was going to get.

The more I do stuff(and talk with others that do it) the more I realize this is more the norm rather than the exception.

Half! a! billion! Yahoo! email! accounts! raided! by! 'state! hackers!'

why would people sue

This is an email account, not like they swiped credit cards or social security numbers or something like that(I would expect Yahoo would not need that information for signing up for an account anyway).

(been hosting my own email for roughly 20 years now)

Intel XPoint over-selling criticism surges as Chipzilla hits back

kind of funny

or sad to see some folks here on el reg (in the forums) touting how great Xpoint will be every so often yet expectations keep getting lowered.

For me I'm really not paying attention until the product starts shipping and people see what the real thing is. Until then what's the point of getting excited ? SSDs and NVMe flash are already so damn fast, and durable.

My own org has been using a 3PAR 7450 for nearly 24 months now with what Sandisk would call "Read intensive" SSDs (though HP has no limits as to workloads for their 5 year warranties). After nearly 24 months of usage across hundreds of VMs and MySQL servers the oldest SSDs in the array have 98% of their life left in them according to their internal metrics anyway.

There may be a few extreme edge cases where something like Xpoint will really make a big difference but customers already have a lot of choices for very fast storage. I didn't get the impression that Xpoint will be dramatically cheaper either, which really would be more of something to get excited about I think.

I have a pair of Samsung 950 Pros (NVMe) in my Lenovo P50 laptop(which the Samsung windows tool says has PCIe 4x with 10Gig interface w/ i7-6820HQ CPU), I see absolutely ZERO difference in real world performance between those and the Samsung 850 Pro (2.5" SATA) SSD. Feels kind of crazy to have 3 SSDs in one laptop but I figured what the hell it has the space so I put them in.

I would wager if I replaced all of my SAS SSDs in my 3PAR arrays with NVMe I would see no difference either, because well the individual apps just don't drive that much I/O (much of it is handled in memory caching). Sub millisecond response time is more than good enough for any of the VMs or databases I have worked with over the past 15 years.