Recent content by llowrey

I received 4 and they all survived my 3-day torture test. My experience has mirrored that of the others on this thread. These are good drives at a great price. Here's a the output from smartctl: === START OF INFORMATION SECTION === Vendor: HGST Product...

Anyone get the QXL video driver to install and function properly for QEMU/KVM? I found a virtio iso with signed drivers and all of the other virtio drivers I tried worked just fine. The QXL driver install seemed successful and did indicate that it was signed by Red Hat but after reboot device...

I have a mixture of CX-3 (non-pro) and CX-4 and have observed a couple of differences in behavior. For some strange reason, Network Manager (at least RHEL/CentOS/Fedora) has a hard time with linking at 56GbE with the CX-3 cards. On boot, it'll link up, almost immediately go down, and will come...

I have a 20 bay and a 24 bay Norco chassis with mixed SAS and SATA devices and an Adaptec 72405 (24 port) and a 71605 (16 port). I have not experienced any issues mixing SAS and SATA. On the power management front, the Adaptec firmware seems to try to keep the drives spinning at all times...

There has been a lot of discussion over the years about Ryzen ECC support, function and reporting. I managed to see an ECC corrected error reported in the wild. [Hardware Error]: Corrected error, no action required. [Hardware Error]: CPU:0 (19:21:0)...

I have had this same issue. In my case, it's always the PCIe3 x2 slot. It's intermittent... sometimes it's detected... and sometimes it's not. This machine is my backup server and powers up once a day to run backups then shuts down. So, I was rolling the dice every day. The slot in question is...

This is in my X470D4U board: 2c:00.0 Serial Attached SCSI controller: Broadcom / LSI SAS3008 PCI-Express Fusion-MPT SAS-3 (rev 02) Subsystem: Broadcom / LSI SAS9300-8i Control: I/O+ Mem+ BusMaster+ SpecCycle- MemWINV- VGASnoop- ParErr- Stepping- SERR- FastB2B- DisINTx+...

Dang... I misread your post I thought you specified the X470D4U. Sorry for adding confusion. I do have an X570D4U waiting for a CPU so can't test this just yet. I still recommend checking if bifurcation is x8x8 and not x8x4x4

I have a similar config with the same board and CPU. PCIE6 is an x8 Mellanox card PCIE5 is an x8 SAS 3008 running at x4 since the slot is only x4 PCIE4 is an x8 SAS 3008 running at x8 My guess is you might have bifurcation set up incorrectly. It should be x8x8 but if you have it set to x8x4x4...

I just received a number of Samsung PM1633 1.92TB SSDs. They initially showed up as 1.6TB, presumably due to over-provisioning. They were also 512e/4096. I used sg_format to format to 4096 and ended up with the full 1.92TB. The Samsung brochure lists sequential read as "up to" 1,400MB/s and...

Indeed. I suppose I should have said "failure cost" and not "failure risk". In my case the downtime cost is relatively low, backups are frequent and tested and restores are quick. I would rather replace a $200 drive (or two) than a $1,600 drive.

Interesting. So, after some investigation I came to understand that I had assumed that devices had low sequential rates due to being single port but in fact they were slow... because they were slow. So, I am now considering: 8x 1.92TB Samsung PM1633(a) - slow but cheapest 4x 3.84TB Samsung...

I would like to build an aprox. 16TB raid0 array of SSDs. My backplane has plenty of dual port SAS3 12Gb/s capacity but I lack PCIe lanes for enough m.2 or u.2 NVMe devices. Usage is ~90/10 reads/writes and almost entirely small random iops (lots of 4k). DWPD would be around 10%. The data is...

Bridge mode is definitely what you want. That allows, as you said, for the ISP's all-in-one device to look and act just like a dumb modem. IPv6 is a different beast in that NAT, as a practical matter, is not a thing. DCHP6 will issue a /128 address for use by the WAN interface and Prefix...

I had this problem, but with an Epyc. This is, apparently, an uncommon use case since I didn't get any replies to my post linked below. https://forums.servethehome.com/index.php?threads/epyc-rome-unable-to-pass-through-sata-ports-to-vm-flr-bug.28592/ AMD seems to have buggy Function Level...