About the appearance of 8 and 10TB hard drives
News: deliveries of 8TB hard drives began, 10TB hard drives with a “ shingled magnetic recording ” system were announced, which promises an increase in volumes by reducing the speed of random access ( details ).
SSD almost completely devoured everything in the range of tens / hundreds of gigabytes. HDD is used only as an ultra-cheap plug, and I don’t understand why no smart Chinese has ever thought of making an SD card reader with an mSATA interface. For a low-end (just to boot), this is enough for the eyes and the ears, and it will cost less. If a person is "slow", then it is obvious that the SSD will save him. As you move beyond 300-400GB, the picture becomes economically unattractive for many segments (1Tb costs € 50 for HDD versus € 350 for the cheapest SSD). But everyone understands that access to a budget terabyte for SSD is a matter of time. Although the demand for space is growing (games / movies of all larger resolutions), at the same time the area of needs is decreasing (why download, when you can watch online), that is, the desktop market can be considered lost.
But besides him there are other markets.
')
HDD, except for the low-end, continue to live:
This last factor defines a unique niche for HDD - they are better suited for linear recording. The SSD has a lot worse with this - if you constantly write to the SSD in large blocks, then housekeeep'ing stops coping (especially if the record is cyclic within the file, such as video surveillance servers), the cache gets clogged, and the SSD degrades to WD Green or even worse . At the same time they are more expensive, the wear on recording multiplies for them to write amplification (when the disk is full of data, the SSD has to be moved a few blocks to record one), the cheaper the SSD, the usually worse resource (and unlike , my SSD'ka wears out "potential wear SSD on the server of video surveillance - quite objective question).
If the client does not care about seek time for reading (which is also linear), then we get a net loss of SSD. Note that SSDs are very complex in the analysis and design of things, with an extremely uneven curve. If you run an IO test on HDD, then its schedule (in time) will look like a perfect straight line, even if not high, which barely trembles. In SSD, this is always a shake from “very bad” to “awesome” - and this complicates the math or gives “strange sticking” at high loads.
Thus, the target audience of expensive disks are customers who need very cheap storage (in terms of $ / Tb) mostly linear writing. Logs, intermediate backup systems, video, archives, lower tier for multi-tier storage. The key place for market success here is a combination of a low terabyte price along with a high copy price. Note that shingled magnetic recording finally removes the issue of performance in random access. But, in the light of the target audience, this is not a particular problem (as long as random access can be done in a reasonable time - file systems still want to read from strange places sometimes).
And this market has quite bright calm prospects. There will be more and more data, you will not save all of them on SSD - the need for archival storage with random access will grow. Industrial standards are well developed, the infrastructure is ready and generally accepted, there is backward compatibility. Current trends show that the HDD still manages to grow in size, and after a strange “slowdown” in the region of 1-2Tb, Moore’s debts are quite good. Skeptics may say that HDD will soon rest on quantum problems and this will stop everything, but not everything is so good with SSD - the more levels there are in SSD cells, the larger the block size for rewriting, that is, the smaller the resource. But the capacity grows as log 2 (N) then the number of levels ... And there are also quantum effects there (perhaps, we must begin to introduce the concept of “bits per mole”, or even “atoms per bit”). In other words, the race is going on with obstacles on both sides.
In light of this, it is possible to roughly describe the thorny future: Hard disks from the “essential part” for the entire computer industry turn into a completely niche product. Which is not going to disappear anywhere. As streamers do not disappear (how many streamers do you have at home?), So does the life of hard drives do not threaten until SSDs can offer such capacity for such money with such performance indicators.
Comment
SSD almost completely devoured everything in the range of tens / hundreds of gigabytes. HDD is used only as an ultra-cheap plug, and I don’t understand why no smart Chinese has ever thought of making an SD card reader with an mSATA interface. For a low-end (just to boot), this is enough for the eyes and the ears, and it will cost less. If a person is "slow", then it is obvious that the SSD will save him. As you move beyond 300-400GB, the picture becomes economically unattractive for many segments (1Tb costs € 50 for HDD versus € 350 for the cheapest SSD). But everyone understands that access to a budget terabyte for SSD is a matter of time. Although the demand for space is growing (games / movies of all larger resolutions), at the same time the area of needs is decreasing (why download, when you can watch online), that is, the desktop market can be considered lost.
But besides him there are other markets.
')
HDD, except for the low-end, continue to live:
- Because of a completely crazy park of servers that live a lot more than drives. Disks need to be changed.
- Because of huge volumes for reasonable money
- Because of the best performance on the well-established linear recording.
This last factor defines a unique niche for HDD - they are better suited for linear recording. The SSD has a lot worse with this - if you constantly write to the SSD in large blocks, then housekeeep'ing stops coping (especially if the record is cyclic within the file, such as video surveillance servers), the cache gets clogged, and the SSD degrades to WD Green or even worse . At the same time they are more expensive, the wear on recording multiplies for them to write amplification (when the disk is full of data, the SSD has to be moved a few blocks to record one), the cheaper the SSD, the usually worse resource (and unlike , my SSD'ka wears out "potential wear SSD on the server of video surveillance - quite objective question).
If the client does not care about seek time for reading (which is also linear), then we get a net loss of SSD. Note that SSDs are very complex in the analysis and design of things, with an extremely uneven curve. If you run an IO test on HDD, then its schedule (in time) will look like a perfect straight line, even if not high, which barely trembles. In SSD, this is always a shake from “very bad” to “awesome” - and this complicates the math or gives “strange sticking” at high loads.
Thus, the target audience of expensive disks are customers who need very cheap storage (in terms of $ / Tb) mostly linear writing. Logs, intermediate backup systems, video, archives, lower tier for multi-tier storage. The key place for market success here is a combination of a low terabyte price along with a high copy price. Note that shingled magnetic recording finally removes the issue of performance in random access. But, in the light of the target audience, this is not a particular problem (as long as random access can be done in a reasonable time - file systems still want to read from strange places sometimes).
And this market has quite bright calm prospects. There will be more and more data, you will not save all of them on SSD - the need for archival storage with random access will grow. Industrial standards are well developed, the infrastructure is ready and generally accepted, there is backward compatibility. Current trends show that the HDD still manages to grow in size, and after a strange “slowdown” in the region of 1-2Tb, Moore’s debts are quite good. Skeptics may say that HDD will soon rest on quantum problems and this will stop everything, but not everything is so good with SSD - the more levels there are in SSD cells, the larger the block size for rewriting, that is, the smaller the resource. But the capacity grows as log 2 (N) then the number of levels ... And there are also quantum effects there (perhaps, we must begin to introduce the concept of “bits per mole”, or even “atoms per bit”). In other words, the race is going on with obstacles on both sides.
In light of this, it is possible to roughly describe the thorny future: Hard disks from the “essential part” for the entire computer industry turn into a completely niche product. Which is not going to disappear anywhere. As streamers do not disappear (how many streamers do you have at home?), So does the life of hard drives do not threaten until SSDs can offer such capacity for such money with such performance indicators.
Source: https://habr.com/ru/post/236429/
All Articles