On Tue, 30 Jun 2020, Ming Lei wrote: > On Wed, Jun 24, 2020 at 5:01 AM Henrique de Moraes Holschuh > <hmh@xxxxxxxxxx> wrote: > > Cache flushes do not matter that much when SSDs and sudden power cuts > > are involved. Power cuts at the wrong time harm the FLASH itself, it is > > not about still-in-flight data. > > > > Keep in mind that SSDs do a _lot_ of background writing, and power cuts > > What is the __lot__ of SSD's BG writing? GC? GC, and scrubbing. > > during a FLASH write or erase can cause from weakened cells, to much > > larger damage. It is possible to harden the chip or the design against > > this, but it is *expensive*. And even if warded off by hardening and no > > FLASH damage happens, an erase/program cycle must be done on the whole > > erase block to clean up the incomplete program cycle. > > It should have been SSD's(including FW) responsibility to avoid data loss when > the SSD is doing its own BG writing, because power cut can happen any time > from SSD's viewpoint. Oh, I fully agree. And yet, we had devices from several large vendors complaining about unclean shutdowns. So, "it should have been", as usual, amounts to very little in the end. > > When you do not follow these rules, well, excellent datacenter-class > > SSDs have super-capacitor power banks that actually work. Most SSDs do > > not, although they hopefully came a long way and hopefully modern SSDs > > are not as easily to brick as they were reported to be three or four > > years ago. > > I remember that DC SSDs often don't support BG GC. And have proper supercap local power banks, etc. I'd say they're not really relevant to this thread. -- Henrique Holschuh
