https://www.opencompute.org/documents/datacenter-nvme-ssd-sp...

Fewer servers means fewer cpus, less RAM, fewer fans, and maybe fewer switches.

Most of our green cabinets were spotlite green. Seafoam green was rare. Both paint colors were prepared by our local sherwin Williams. The colors looked pretty much the same to me.

https://mitsloan.mit.edu/ideas-made-to-matter/working-defini...

In Navy boot camp the person reviewing my security clearance application (which was filled out weeks before) was very helpful in the way he asked the critical question. “It says here you tried marijuana once. Is that true?”

Microsoft has the KEK or passphrase that can be used to derive the KEK. The KEK protects the DEK which is used to encrypt the data. Rotating the KEK (or KEKs if multiple slots are used) will overwrite the encrypted DEK, rendering the old KEK useless.

Or does BitLocker work differently than typical data at rest encryption?

It is easy to switch between Verizon, AT&T, and T-Mobile as well. This was helpful for me as all three of the networks normally have one bar or less at my house. T-mobile WiFi calling works more reliably than Verizon.

I expect this becomes most interesting with l2arc and cache (zil) devices to hold the working set and hide write latency. Maybe would require tuning or changes to allow 1m writes to use the cache device.

        extern fin;

        if(getpw(0, pwbuf))
                goto badpw;
        (&fin)[1] = 0;

A specific somewhat dated example: Samsung 980 Pro (consumer client), PM9A1 (OEM client), and PM9A3 (datacenter) are very similar drives that have the same PCI ID and are all available as M.2. PM9A3 drives have power loss protection and the others don’t. It has very consistent write latency (on the order of 20 - 50 μs when not exceptionally busy) and very consistent throughput (up to 1.5 GB/s) regardless of how full it is. The same cannot be said of the client drives without PLP but with tricks like TurboWrite (aka pseudo-SLC). When more than 30% of the NAND is erased, the client drives can take writes at 5 GB/s but that rate falls off a cliff and gets wobbly when the pseudo-SLC cache fills.

> 6.8 Flush command

> …

> If a volatile write cache is not present or not enabled, then Flush commands shall complete successfully and have no effect.

And:

> 5.21.1.6 Volatile Write Cache

> …

> Note: If the controller is able to guarantee that data present in a write cache is written to non-volatile media on loss of power, then that write cache is considered non-volatile and this feature does not apply to that write cache.

Solaris 11 made boot environments a mandatory part of the OS, which was an obvious choice with the transition from UFS to ZFS for the root fs. This came into Solaris development a bit before Solaris 11, so it was present in OpenSolaris and lives on in many forms of illumos.

https://www.yesigiveafig.com/p/part-1-my-life-is-a-lie

With SSDs, the write pattern is very important to read performance.

Datacenter and enterprise class drives tend to have a maximum transfer size of 128k, which is seemingly the NAND block size. A block is the thing that needs to be erased before rewriting.

Most drives seem to have an indirection unit size of 4k. If a write is not a multiple of the IU size or not aligned, the drive will have to do a read-modify-write. It is the IU size that is most relevant to filesystem block size.

If a small write happens atop a block that was fully written with one write, a read of that LBA range will lead to at least two NAND reads until garbage collection fixes it.

If all writes are done such that they are 128k aligned, sequential reads will be optimal and with sufficient queue depth random 128k reads may match sequential read speed. Depending on the drive, sequential reads may retain an edge due to the drive’s read ahead. My own benchmarks of gen4 U.2 drives generally backs up these statements.

At these speeds, the OS or app performing buffered reads may lead to reduced speed because cache management becomes relatively expensive. Testing should be done with direct IO using libaio or similar.

> Native NVMe is now generally available (GA) with an opt-in model (disabled by default as of October’s latest cumulative update for WS2025).

https://www.elevenforum.com/t/announcing-native-nvme-in-wind...