<html><head></head><body>I'm spoiled on sas. It's actually much closer to saturating speeds that sata. But read and write. Write helped by much larger buffer cache. Read by multiple heads and dual channel to not interrupt read upload with next block request.<br><br>The speeds do matter with ssd. <br><br><div class="gmail_quote">On August 3, 2020 8:35:42 AM EDT, DJ-Pfulio via Ale <ale@ale.org> wrote:<blockquote class="gmail_quote" style="margin: 0pt 0pt 0pt 0.8ex; border-left: 1px solid rgb(204, 204, 204); padding-left: 1ex;">
<pre class="k9mail">On 8/3/20 6:58 AM, Bob via Ale wrote:<br><br><blockquote class="gmail_quote" style="margin: 0pt 0pt 1ex 0.8ex; border-left: 1px solid #729fcf; padding-left: 1ex;">The specifications say that it is backwards compatible with earlier <br>versions of SATA and supports speeds of 6.0 gbs, 3.0 gbs, and 1.5 <br>gbs.<br></blockquote><br>Bus speeds often have ZERO to do with actual read-write speeds. Think of them as speed limits, not speed in traffic. That applies to all things bandwidth.<br>USB, SATA, Networking ... there's the theory and then there's reality.<br><br>My SATA-III connected disks are lucky to get 180 MBps. There are 8 bits in a byte, so 1440 Mbps ... which is nowhere near 6000 Mbps, right? So a SATA-I controller with 1.5Gbps is fine for almost all spinning HDDs.<br><br>A few years ago, I tested USB2 (480Mbps) and USB3 (5Gbps) HDD throughput. It was really sad, though a USB3 controller did slightly help USB2 storage. Did move a bunch of data through a USB2 connector and USB3 controller a few days ago - got 38-40 Mbps (320 MBps) for the thousands of larger files. The device also supports eSATA, which explains why it was able to get much better throughput than a typical USB2 storage connection. The internals are better than a typical USB2-only device which gets about 20 MBps. Eventually, I noticed the bad throughput and pulled the storage from that USB "dock" and put it into an empty SATA-III bay on the system. I was just trying to fill it up with data before running a long SMART test and using it as a replacement disk on a RAID1 system in a different box.<br><br>Wired ethernet is the closest, then NVMe SATA storage.<br><br>Powerline and wifi networking real-world speeds are usually 25-50% of that the box claims in theory. I have a 600 Mbps powerline setup that bridges floors of the mansion. From the networking room downstairs gets a solid 60 Mbps which is more than sufficient for video or internet stuff. I tested the powerline bandwidth between 2 outlets on the same wall - one inside a room and the other in the hallway outside. Got 220 Mbps. A small hole in the wall with a 2ft CAT5e would have been better. Just sayin'.<br><br>Marketing likes to claim the highest possible speeds. Most of the time, it is only marketing and has little connection to the real-world.<hr>Ale mailing list<br>Ale@ale.org<br><a href="https://mail.ale.org/mailman/listinfo/ale">https://mail.ale.org/mailman/listinfo/ale</a><br>See JOBS, ANNOUNCE and SCHOOLS lists at<br><a href="http://mail.ale.org/mailman/listinfo">http://mail.ale.org/mailman/listinfo</a><br></pre></blockquote></div><br>-- <br>"no government by experts in which the masses do not have the chance to inform the experts as to their needs can be anything but an oligarchy managed in the interests of the few.” - John Dewey</body></html>