Any file regardless of size which is unchanged for several months will be subject to this issue. This is not isolated to "pro" stuff like databases and virtual servers, but also includes locally stored video files, games, photos, etc.
Out of curiosity I contacted them and asked about the benchmark. Turns out they simulated 5 high-load servers running concurrently by started the bechmark tool on 5 different virtual servers on the SAN and running them at the same time, taking the average values for about 7 minutes of benchmarks. Each server reported around 192.000 IOS at a QD of 16, for a total of approx 960.000 IOPS.
There was no other activity on the SAN an the servers were small so it's a pretty fair bet that 100% of the load was on the SSD tier, which contained 48 SSDs in two separate enclosures.
The bug does not affect your data for at least a couple of months. And running the Samsung tool fixes it completely - as does moving the data to new blocks (though OS files are somewhat harder to move around if they're not in a virtual disk file).
Not sure if you're trolling or just being contrary out of principle. But yeah, I'll take the EVO in your drawer if you insist it is unusable. Hell, I'll even make a donation to the EFF worth the drives second-hand value when I receive it. Let me know if you want my address for shipping.
For the 840 series, the EVO is almost as fast as the Pro. The difference is about 3-5% depending on sources. The price of the pro is almost double that of the EVO. So no, I'd say the Pro only makes sense if you want the added reliability and extended warranty.
The difference was bigger for the previous series, and I haven't checked the new 850 drives. But if you're in the 840 series then the Pro actually makes very little sense unless you get it at a bargain price.
No, that hasn't been true for quite a while. At least not on workstation or gaming-grade motherboards. They all come with an Intel controller and Rapid Storage Technology which performs quite well for simple raid volumes like 0 and 1. Probably because there is much less work for these volumes than for the complex ones, like RAID 5, 6, 50 and 60.
Generally speaking most "Enterprise" VMs on slow SANs suck. Really - seriously - suck!
And no, it does not represent real business workloads unless the company in question is either being cheap, or their infrastructure team has no clue what they're doing.
Don't get me wrong; VMs on a SAN can be fine if the SAN is any good. The best SAN I have seen to date was at one of our clients where it was used for the primary servers running a complex ERP solution. It provided almost a full million IOPS when benchmarked at its installation date (they bought it new when we started our project with them). I can't say for sure if the massive performance threw the benchmarking software off so it was actually lower, but it was fast as hell to work with as well.
My laptop gives me around 14.000 IOPS at random reads with a Que Depth of 1, and around 120.000 IOPS with a Que Depth of 16, for Random Reads. Data transfer for sequential reads is around 900 MB/s which is pretty fair for a laptop. Its based on an Intel RST RAID0 aray and to Plextor M5 Pro drives.
My previous array with 840 EVO's had slightly better random reads and somewhat worse sequential read performance. And the bug mentioned in TFA was very noticeable for large VM's... like a bloated 120 GB Windows server with a lot of concurrent services.
Really? I haven't heard that, and none of the drives used at our small company have failed in that way (I believe we have a total of around 40-45 EVO drives in various sizes). I also haven*t seen reputable sources criticize their reliability?
Feel free to share your source for this; if it's any good I'll certainly pass it on to our infrastructure guys.
Actually they perform as advertised when they're new, or when the data is refreshed. So your claim is wrong.
The degraded performance occurred when blocks of data remained unchanged for many months. And the fix was somewhat easy: Run the Samsung optimizer tool or alter the data.
You can criticize them for the degradation-bug, sure. But to claim they shipped drives that did not live up to claimed performance is wrong.
Hey, why the attitude man? Did it somehow offend you that I decided to replace the drives? Are you so emotionally attached to your own identity as an EVO customer that you must attack people who choose differently?
I used the EVO 840 from virtually the same week they became available. Performance was great, but it slowly degraded with time passed. The decrease was very visible for large blocks of data which were read often but not refreshed or updated. Not just on synthetic benchmarks. My usage pattern fits that bill because I use several virtual machines that are 40 - 120 GB large, and only a small portion of their virtual disk files are changed (SQL database files). Moving the virtual machine to an external drive and back on to the SSD's solved the problem, but shuffling around 120 GB virtual servers in order to "keep the memory cells happy" is a chore I'd rather be without.
Perhaps the issue was more visible to me because I run 2 drives in RAiD0 which means I get hit by the degradation twice - once for each drive. Never the less, the issue was very real to me. YMMV off course, but please accept that your own perception of this issue is not the universal truth.
In regards to your snarky comment about me being a "savvy consumer": Yes, I believe I am a reasonably savvy consumer when it comes to SSD drives. I am a Business Intelligence specialist and I am quite confident in my ability to understand and evaluate disk read performance. It is part of my job. When analyzing large amounts of data or operating virtual servers (booting or resuming), sustained data transfer is very important. The slightly lower random read performance of my Plextor Pro drives is a very good trade-off for the added sustained transfer rate. In addition the Plextor pro drives use a server-grade controller chip with a GC routine that works very well without TRIM. Since I operate in RAID mode that is also a concern when I buy drives. My Laptop does not support TRIM in RAID mode (desktop/gaming rig does though).
Not everybody on the planet uses their computer in exactly the same way as you do.
Not quite. The specs on the EVO 840's are actually very good... if only they lived up to them!
If this new fix actually works, the EVO's will be a very good buy. Pretty reliable too according to tests. I just couldn't wait (and had no idea if/when a fix was ever going to surface).
Six months is not an acceptable time to wait for a performance fix for an SSD drive. The very essence of an SSD is "speed".
I offloaded the EVO's on eBay (being honest about the reason) and got myself a couple of Plextor Pro drives. Running in RAID0 they are a bit slower at random reads than the EVOs, but faster at sustained transfer rates.
An SSD with slow/degraded performance is like a burger without the beef... something is missing...!
Not trying to troll or anything... but this news leaves me with mixed feelings.
Should I simply forget that Occulus has been assimilated by the privacy-nightmare-that-is-facebook? You know... "You will be assimilated"... and "Privacy is irrelevant"... and all that stuff?
Or do I simply cheer about the technological achievement and hope for a competitor to set up camp soon?
I don't want a Zuckerberg product in my household unless the Slashdot community approves of it!
I don't know where you went to school, but you should ask for a refund. Or read up on basic percentage calculations.
Microsoft claims that 93% of the malware traffic is traced to No-IP. But that says nothing about the total amount of traffic for No-IP, nor does it say anything about the total volume of legitimate domains. Malware traffic could be as little as 1% on No-IP's infrastructure while still accounting for 93% of malware DDNS traffic.
It is completely wrong to state that 93% of No-IP domains are hosting malware. A large number of legitimate customers are being affected by this, and Microsoft is not resolving their DDNS domains correctly (as promised). The actual percentage of legitimate vs malicious domains is unknown, as is the distribution of legit/malicious traffic.
Also, Microsofts claims are disputed by No-IP, so we should not take them at face value. No real evidence of malice has been proven (yet), which makes it extremely questionable that this was conducted ex parte.
Finally, the fact that No-IP was a favorite for malware is not (or should not be) in itself sufficient to take control of the domains like this. I sincerely hope Microsoft can prove No-IP did not respond properly to requests. Or that they can document that an extremely large portion of total traffic on No-IP was malware (which we know nothing about at this point).
Simply quoting the 93% number is a pile of BS. I can't stand by itself. I can say with certainty that at least 93% of the Nigerian scam mail I have received the last year has used a hotmail.com or outlook.com account. But surely this does not prove that Microsoft is willingly aiding Nigerian scammers and that their domains should be seized?
The world + dog is already trying to cut their funding?
And no, I will not compare the situation to the civil wars in Lybia and Syria. Regimes their were as bad as Saddam, and their atrocities are much greater than the moderate/secular freedom forces. Granted, there are religious fanatics fighting as well (and fortunately among them selves too) but that is to be expected in ANY civil war zone, and they are certainly not being funded by western governments.
Yes that seemed an interesting read. Completely unbiased, with no specific agenda but the truth. Right?
Too bad there isn't a "livingunderterroristimposrdsharia.org" website, but there is nobody to make it since the population living under such conditions are robbed of their resources, denied education, denied free speech, and routinely abused.;-)
I am not saying drones are great, but stop fighting terrorist fanatics is not a solution either. Not by a long shot.
Provide some examples of realistic alternatives. Then we'll talk!
There is no evidence to support the notion that collateral damage (while unfortunate and very problematic in many areas) causes significant rise in terrorists abilities to recruit new subjects. They are able to do that "perfectly fine" anyway. Losing a child or a nephew does not make a peasant suddenly long for harsh Sharia-rule.
The argument is mostly put forth by critics who have no more than Hollywood movies as "evidence" to back it up.
I will take the word of a military intelligence analyst over that... any day and twice on Sunday.
Are you aware that civilian populations in areas controlled by these groups wish for more western intervention - not less? Their girls are being raped and kept from getting an education. Their boys are killed or recruited into armies of fanatics. They are forced into a rule of Sharia for which they have no desire. They are forced into paying tribute to the groups for "protection"; while being systematically abused by them.
The civilian population does not see these groups as any kind of "salvation" and no, they are not flocking to the local terrorist recruitment center when their nephew is killed by a drone strike. They curse these religious fanatics as much as we do, the recognize that the nephew died because of the fanatics presence, and they prey the US will continue to fight, because for them the alternative (ie. permanently being under the control of religious fanatics) is so far far worse for them.
It seems to me that while you claim I am not thinking as "a religious/political/get-out-of-our-country fanatic" you are at the same time trying to apply common sense to their way of thinking. And I believe you have a thoroughly misguided understanding of their rationale for being as fanatic as they are.
See, they don't believe that America is "the Great Satan" because their leaders are killed. No, the US is "the Great Satan" because girls can go to school and get an education, girls can marry whom they please, rape is illegal, stoning is illegal, and alcohol is served in public places.
Even if nobody killed their leaders they would still see the US as "the Great Satan" and continue their holy war - now better organized and with better leaders. Not because of Drone Strikes, but because their twisted minds honestly believe we should all die for sending our girls to school and allowing them to choose their husband for themselves.
Seriously. They are so far beyond any kind of rational thinking that the only alternative to fighting them is winning once and for all!
This is an interesting philosophical dilemma discussed for thousands of years.
If you ask a true consequentialist then the answer might be n-1; where n is the number of people saved.
If you ask a parent then the answer will often be n - [own_children] .
If you ask a pacifist the answer will be 0... hence the scarcity of pacifists.
Your question cannot be answered without establishing further parameters for he discussion. Such as "is the preservation of society worth paying lives for".
It is not only done to protect Americans in the US. It is also done to increase the chance that the affected countries can build and grow a healthier population and economy. The best way to do that is through education - which incidentally the extremists groups oppose.
So yes, things could be way worse. If you stop fighting these groups, so they no longer has the US as their enemy, they will turn their attention back to the local population in a bid to impose Sharia upon them. They will force children out of school and establish rules and a society which will over time will significantly decrease the life quality of millions. And it will get worse and grow more terrorists, because a rule of Sharia governed by fanatics only has one outcome: An army of fanatics large enough to wipe out the "unbelievers".
There is no alternative to fighting them; except perhaps winning once and for all.
Slashdot Mirror
Exactly.
Besides, lets be fair here. This is not something you can't fix with a $27.49 ChromeCast key ...
Politely: "State regulation" =! "socialism" ...
I think your 99,9% assertion is flat out wrong.
Any file regardless of size which is unchanged for several months will be subject to this issue. This is not isolated to "pro" stuff like databases and virtual servers, but also includes locally stored video files, games, photos, etc.
Out of curiosity I contacted them and asked about the benchmark. Turns out they simulated 5 high-load servers running concurrently by started the bechmark tool on 5 different virtual servers on the SAN and running them at the same time, taking the average values for about 7 minutes of benchmarks. Each server reported around 192.000 IOS at a QD of 16, for a total of approx 960.000 IOPS.
There was no other activity on the SAN an the servers were small so it's a pretty fair bet that 100% of the load was on the SSD tier, which contained 48 SSDs in two separate enclosures.
The bug does not affect your data for at least a couple of months. And running the Samsung tool fixes it completely - as does moving the data to new blocks (though OS files are somewhat harder to move around if they're not in a virtual disk file).
Not sure if you're trolling or just being contrary out of principle. But yeah, I'll take the EVO in your drawer if you insist it is unusable. Hell, I'll even make a donation to the EFF worth the drives second-hand value when I receive it. Let me know if you want my address for shipping.
For the 840 series, the EVO is almost as fast as the Pro. The difference is about 3-5% depending on sources. The price of the pro is almost double that of the EVO. So no, I'd say the Pro only makes sense if you want the added reliability and extended warranty.
The difference was bigger for the previous series, and I haven't checked the new 850 drives. But if you're in the 840 series then the Pro actually makes very little sense unless you get it at a bargain price.
No, that hasn't been true for quite a while. At least not on workstation or gaming-grade motherboards. They all come with an Intel controller and Rapid Storage Technology which performs quite well for simple raid volumes like 0 and 1. Probably because there is much less work for these volumes than for the complex ones, like RAID 5, 6, 50 and 60.
Generally speaking most "Enterprise" VMs on slow SANs suck. Really - seriously - suck!
And no, it does not represent real business workloads unless the company in question is either being cheap, or their infrastructure team has no clue what they're doing.
Don't get me wrong; VMs on a SAN can be fine if the SAN is any good. The best SAN I have seen to date was at one of our clients where it was used for the primary servers running a complex ERP solution. It provided almost a full million IOPS when benchmarked at its installation date (they bought it new when we started our project with them). I can't say for sure if the massive performance threw the benchmarking software off so it was actually lower, but it was fast as hell to work with as well.
My laptop gives me around 14.000 IOPS at random reads with a Que Depth of 1, and around 120.000 IOPS with a Que Depth of 16, for Random Reads. Data transfer for sequential reads is around 900 MB/s which is pretty fair for a laptop. Its based on an Intel RST RAID0 aray and to Plextor M5 Pro drives.
My previous array with 840 EVO's had slightly better random reads and somewhat worse sequential read performance. And the bug mentioned in TFA was very noticeable for large VM's... like a bloated 120 GB Windows server with a lot of concurrent services.
Really? I haven't heard that, and none of the drives used at our small company have failed in that way (I believe we have a total of around 40-45 EVO drives in various sizes). I also haven*t seen reputable sources criticize their reliability?
Feel free to share your source for this; if it's any good I'll certainly pass it on to our infrastructure guys.
Actually they perform as advertised when they're new, or when the data is refreshed. So your claim is wrong.
The degraded performance occurred when blocks of data remained unchanged for many months. And the fix was somewhat easy: Run the Samsung optimizer tool or alter the data.
You can criticize them for the degradation-bug, sure. But to claim they shipped drives that did not live up to claimed performance is wrong.
Hey, why the attitude man? Did it somehow offend you that I decided to replace the drives? Are you so emotionally attached to your own identity as an EVO customer that you must attack people who choose differently?
I used the EVO 840 from virtually the same week they became available. Performance was great, but it slowly degraded with time passed. The decrease was very visible for large blocks of data which were read often but not refreshed or updated. Not just on synthetic benchmarks. My usage pattern fits that bill because I use several virtual machines that are 40 - 120 GB large, and only a small portion of their virtual disk files are changed (SQL database files). Moving the virtual machine to an external drive and back on to the SSD's solved the problem, but shuffling around 120 GB virtual servers in order to "keep the memory cells happy" is a chore I'd rather be without.
Perhaps the issue was more visible to me because I run 2 drives in RAiD0 which means I get hit by the degradation twice - once for each drive. Never the less, the issue was very real to me. YMMV off course, but please accept that your own perception of this issue is not the universal truth.
In regards to your snarky comment about me being a "savvy consumer": Yes, I believe I am a reasonably savvy consumer when it comes to SSD drives. I am a Business Intelligence specialist and I am quite confident in my ability to understand and evaluate disk read performance. It is part of my job. When analyzing large amounts of data or operating virtual servers (booting or resuming), sustained data transfer is very important. The slightly lower random read performance of my Plextor Pro drives is a very good trade-off for the added sustained transfer rate. In addition the Plextor pro drives use a server-grade controller chip with a GC routine that works very well without TRIM. Since I operate in RAID mode that is also a concern when I buy drives. My Laptop does not support TRIM in RAID mode (desktop/gaming rig does though).
Not everybody on the planet uses their computer in exactly the same way as you do.
Why?
SSDs are pretty reliable. I also have daily automated backup of my entire drive, and all important documents are synced with a SkyDrive account.
And ... I need the extra performance for virtual machines. :-)
I think you can fully expect Samsung to apply the firmware fix to all subsequent EVO series if applicable.
Not quite. The specs on the EVO 840's are actually very good ... if only they lived up to them!
If this new fix actually works, the EVO's will be a very good buy. Pretty reliable too according to tests. I just couldn't wait (and had no idea if/when a fix was ever going to surface).
Six months is not an acceptable time to wait for a performance fix for an SSD drive. The very essence of an SSD is "speed".
I offloaded the EVO's on eBay (being honest about the reason) and got myself a couple of Plextor Pro drives. Running in RAID0 they are a bit slower at random reads than the EVOs, but faster at sustained transfer rates.
An SSD with slow/degraded performance is like a burger without the beef... something is missing...!
Not trying to troll or anything ... but this news leaves me with mixed feelings.
Should I simply forget that Occulus has been assimilated by the privacy-nightmare-that-is-facebook? You know ... "You will be assimilated" ... and "Privacy is irrelevant" ... and all that stuff?
Or do I simply cheer about the technological achievement and hope for a competitor to set up camp soon?
I don't want a Zuckerberg product in my household unless the Slashdot community approves of it!
There is no Taurine in bananas or coffee.
If people want to pay for beverages with extract from animal tissue or synthetics produced from cyclic ether who are we to argue? ;-)
I don't know where you went to school, but you should ask for a refund. Or read up on basic percentage calculations.
Microsoft claims that 93% of the malware traffic is traced to No-IP. But that says nothing about the total amount of traffic for No-IP, nor does it say anything about the total volume of legitimate domains. Malware traffic could be as little as 1% on No-IP's infrastructure while still accounting for 93% of malware DDNS traffic.
It is completely wrong to state that 93% of No-IP domains are hosting malware. A large number of legitimate customers are being affected by this, and Microsoft is not resolving their DDNS domains correctly (as promised). The actual percentage of legitimate vs malicious domains is unknown, as is the distribution of legit/malicious traffic.
Also, Microsofts claims are disputed by No-IP, so we should not take them at face value. No real evidence of malice has been proven (yet), which makes it extremely questionable that this was conducted ex parte.
Finally, the fact that No-IP was a favorite for malware is not (or should not be) in itself sufficient to take control of the domains like this. I sincerely hope Microsoft can prove No-IP did not respond properly to requests. Or that they can document that an extremely large portion of total traffic on No-IP was malware (which we know nothing about at this point).
Simply quoting the 93% number is a pile of BS. I can't stand by itself. I can say with certainty that at least 93% of the Nigerian scam mail I have received the last year has used a hotmail.com or outlook.com account. But surely this does not prove that Microsoft is willingly aiding Nigerian scammers and that their domains should be seized?
The world + dog is already trying to cut their funding?
And no, I will not compare the situation to the civil wars in Lybia and Syria. Regimes their were as bad as Saddam, and their atrocities are much greater than the moderate/secular freedom forces. Granted, there are religious fanatics fighting as well (and fortunately among them selves too) but that is to be expected in ANY civil war zone, and they are certainly not being funded by western governments.
Yes that seemed an interesting read. Completely unbiased, with no specific agenda but the truth. Right?
Too bad there isn't a "livingunderterroristimposrdsharia.org" website, but there is nobody to make it since the population living under such conditions are robbed of their resources, denied education, denied free speech, and routinely abused. ;-)
I am not saying drones are great, but stop fighting terrorist fanatics is not a solution either. Not by a long shot.
Provide some examples of realistic alternatives. Then we'll talk!
Why wouldn't I be real?
There is no evidence to support the notion that collateral damage (while unfortunate and very problematic in many areas) causes significant rise in terrorists abilities to recruit new subjects. They are able to do that "perfectly fine" anyway. Losing a child or a nephew does not make a peasant suddenly long for harsh Sharia-rule.
The argument is mostly put forth by critics who have no more than Hollywood movies as "evidence" to back it up.
I will take the word of a military intelligence analyst over that ... any day and twice on Sunday.
Unlimited manpower?
Are you aware that civilian populations in areas controlled by these groups wish for more western intervention - not less? Their girls are being raped and kept from getting an education. Their boys are killed or recruited into armies of fanatics. They are forced into a rule of Sharia for which they have no desire. They are forced into paying tribute to the groups for "protection"; while being systematically abused by them.
The civilian population does not see these groups as any kind of "salvation" and no, they are not flocking to the local terrorist recruitment center when their nephew is killed by a drone strike. They curse these religious fanatics as much as we do, the recognize that the nephew died because of the fanatics presence, and they prey the US will continue to fight, because for them the alternative (ie. permanently being under the control of religious fanatics) is so far far worse for them.
It seems to me that while you claim I am not thinking as "a religious/political/get-out-of-our-country fanatic" you are at the same time trying to apply common sense to their way of thinking. And I believe you have a thoroughly misguided understanding of their rationale for being as fanatic as they are.
See, they don't believe that America is "the Great Satan" because their leaders are killed. No, the US is "the Great Satan" because girls can go to school and get an education, girls can marry whom they please, rape is illegal, stoning is illegal, and alcohol is served in public places.
Even if nobody killed their leaders they would still see the US as "the Great Satan" and continue their holy war - now better organized and with better leaders. Not because of Drone Strikes, but because their twisted minds honestly believe we should all die for sending our girls to school and allowing them to choose their husband for themselves.
Seriously. They are so far beyond any kind of rational thinking that the only alternative to fighting them is winning once and for all!
This is an interesting philosophical dilemma discussed for thousands of years.
If you ask a true consequentialist then the answer might be n-1; where n is the number of people saved.
If you ask a parent then the answer will often be n - [own_children] .
If you ask a pacifist the answer will be 0 ... hence the scarcity of pacifists.
Your question cannot be answered without establishing further parameters for he discussion. Such as "is the preservation of society worth paying lives for".
It is not only done to protect Americans in the US. It is also done to increase the chance that the affected countries can build and grow a healthier population and economy. The best way to do that is through education - which incidentally the extremists groups oppose.
So yes, things could be way worse. If you stop fighting these groups, so they no longer has the US as their enemy, they will turn their attention back to the local population in a bid to impose Sharia upon them. They will force children out of school and establish rules and a society which will over time will significantly decrease the life quality of millions. And it will get worse and grow more terrorists, because a rule of Sharia governed by fanatics only has one outcome: An army of fanatics large enough to wipe out the "unbelievers".
There is no alternative to fighting them; except perhaps winning once and for all.