Search results

An update for the Windows 8/2012 (64-bit) driver snuck out 11/01/2013; 6.20.00.25. Love the patch notes: "Bug fix low performance issue in storport". Also it appears the latest bios for Supermicro X9SCM-F 2.0b and the areca 1882i bios 1.51 201209 (it was updated after release without a...

The hilarious part is that scheduled "defragmentor" will actually deliberately fragement files. The defragmentor or optimizer as it gets called in later versions cooperates with superfetch which monitors application startup process to re-order file fragements so it can transform random reads...

It looks like the ARC-1882i has a firmware regression for dealing with the older 7k2000 Deskstars (well it's either that or my 1882i is damaged), on the upside the beta firmware shows they are at least working to support 4k physical sector drives. The new options for how the card reacts to SMART...

I got around todo'ing this. Each drive in passthrough mode worked correctly and on-par with a drive handing off the motherboard with which is the same type & firmware. On 4 disks, I created some RAID6/RAID5 slices which even at 4-10gb took ages to init. and when I tried to delete the...

According to hitachi's spec spreadsheet, the 7k3000 deskstar is rated for 24x7 avaliability.

This isn't 100% correct. According to the paper here, it is "is more than 8% of DIMM affected by errors per year" and these are correctable errors Looking into the paper: An important take away from this is most DIMMs don't have any errors but without ECC you are going to have a hell of...

Yup. I've got 16 2TB 7200rpm Hitachis, in two raid 6 sets of 8 drives each. Both sets have the same massive performance issues regardless if it's a single set attached directly to the controller or both sets via the sas expander (or just 1 set via the sas expander). Even after migrating...

Wierd, is how turning on the disk write cache improves read speeds; . I'm probably going to have to RMA the controller, as something is borked with it. I'm planning on see how an Intel G2 SSD performs on each port in pass-through (or a 1 disk raid0) and see if one of the ports is doing...

Would anyone have an idea why an Arc-1882i + intel sas expander would be having shockingly slow read speeds off an 8 disk RAID6 2tb Hitachi 7200rpm? ARC-1680lp (v.149 firmware, aka latest firmware): ARC-1882i (latest v1.50 firmware, originally shipped with an earlier version of v1.50)...

Make sure the SCSI Ch/Id/Lun for each volumn is different? Areca cards will not present it as an error if there are multipule volumes with the same Ch/Id/Lun, but Windows will only see 1.

This is fundementally impossible with sata over sas. A sata drive simply doesn't have the unique ID which is identifiable over the disk subsystem that a sas drive has, and no amount of smarts with how ZFS/Solaris deals with this can solve it. The only solution is to write that unique ID onto the...

They using stripping as thier mirrored set is actually a RAID10 setup which is smart enough to work on two drives. As you add more drives, Windows 8 is apparently smart enough to only use the least used drive which has a copy of the data you need. There are good solid reasons todo that, and...

On-disk post-processing dedupe is baked into the core OS now, it functions on ReFS & NTFS. Of course the question then becomes at what edition point does it become enabled.

If you are willing to get dirty with powershell commands, there appear to be a bunch documented here. Calling Optimize-Volume should do the trimming & moving to free up space. Something like: Optimize-Volume -DriveLetter H -ReTrim -SlabConsolidate -Verbose Where "H" is whatever the...

How does this conflict show up? Stuff not working or just degraded performance?

No. It's a new thin provisioned volumn format which natively does striping. The difference is mirrored spaces have at least 2 copies of a strip somewhere, and parity spaces have a random parity chunk somewhere.

There is no one "parity" drive. The chunk of data protected by a parity block can span 8 members(which is then 7 slices of data + 1 slice of parity), so if you have enough drives it is then posible to have different sets of data+parity being on distinctly different drives. In that case you...

Be aware, that having Windows installed on your raid volume will cause a lot of random reads & writes to hit the disks. Depending on what the OS does could also dramatically impact performance as the low RPM drives generally have much worse seek speeds. Also, Windows 8 Server disk-based...

Yes, it's somewhere on the Microsoft blogs but they have truely baked both TRIM & UNMAP into the storage layers this time around. This includes issuing a Trim command on the contents of a VHD and having it propagating to the underlying storage whatever it is. It's actually how Storage spaces...

Yup, from the MSDN blog. If you look for "integrity streams", you'll find a lot of info. It may be the fact that it is journelling the changes before writing them to the parity spaces data store to guard against the RAID5 write hole. You can apparently define an arbitary drive for where this...

ReFS does have file-level checksumming and COW where it never directly overwrites filedata, but you need to set an attribute on the pool to get it. I'm not sure if the GUI exposes this. The only problem is the parity spaces (aka raid5) doesn't have the fancy intelligent autocorrection based...

So my 1882i is going quite nicely with 8x 4tb hitachi 7200rpm (aka the Deskstar 7k4000), I did enable disk write cache during the array build and it does have dual links from the 1882i to the RES2SV240 intel sas expander. The 4tb hitachis do appear to run hotter but the Norco RPC-4224 w/...

ReFS has checksumming on metadata and files. The problem is it can only actually correct these reliably when using Mirrors (aka Raid1), It would be great to be proven wrong, but the initial release can not reliably correct soft errors on Parity Spaces (aka raid5) despite having checksums...

ReFS does look interesting, but it is missing a number of features which is why it isn't a bootable filesystem yet. Storage spaces's Parity Spaces is software raid5 on a thin provisioned volumn, great that it doesn't need to rebuild empty space and uses 'trim' commands to free diskspace back to...

After determining that a bad sata power termination on some custom cables was causing my resume from spin-down issues, a few months later I've now encountered something else. On my arc-1680lp; I'm getting the following error and the external sas expander just not showing up; > Enc#1 Time...

HP's website describes it as supporting 6gbps sas and 3gbps sata. But exactly how in-sync the website is with the actual firmware capabilities is another matter.

Nope. Running stock, and most of the time slower than stock due to powersaving features. I'm got it running fine with two arrays with spin-down disabled. Once I get some free time I'll breakout a multimeter and look at what is coming out of each power run on the end of the chain. If it's a...

I think I've just been bitten by a floating reset signal or not enough psu. The hardware is; A q6600 in a GA EP45 DQ6, 8gb of ram (mostly generic stuff), areca 1680lp(SES2 disabled, latest firmware), hp sas expander(2.02) and a hd5450 for video signal. 17x2tb hitachi deskstar 7k2000's (8x3EA...

The issue with the HP Sas Expander only syncing drives at SATA150 instead of SATA300 is wierd. It appears dependant on the port you are using. For example I have the following drives; Drives E#2PHY#32 ->E#2PHY#35 have SATA300, but the rest are SATA150. I'll need to move cables around and...

The double beep is probably from the motherboard sending the PCIe reset signal twice on boot. It should be completely harmless, if somewhat anoying.

The out-of-band mangement webpage on the 1880/1680's also uses SES2 when listing various drive information under the "Hardware Monitor" tab. Probably the most important information it lists is the drive temperature. Disabling SES2 disables the ability to see all the drive temperatures at once...

The 1880 only supports multi-link on the latest firmware. One thing I want clarified is if SES2 support is fixed as well.

I've got 8x2tb hitachi's on my hp sas expander & 1680lp (rev2) which used to work at SATA-300 but have all dropped to SATA-150. I've just added another 8 hitachi's which also sync at SATA-150. However, I know the mini-sas to sata fanout cables I'm using are shit. They are very thin wires, and...

By the wording the the initial post and the follow post, it strongly looks like Microsoft bowed to OEM/ISV wanting to "value add" something like the DE without it being part of the core OS. This isn't the first time Microsoft has been willing to cripple Windows functionality (hello working...

It was unnerving to discover it is posible to log into an Areca controller via out-of-band management and have it, falsely, list all the attached drives as "FAILED" because the controller hasn't finished booting. Infact the "HTTP log in" message managed to get logged a good 8 seconds before...

Yes, I've sucessfully replaced the battery for a PERC5/i with an ebay battery. The battery /controller is not hotswap compatabile and you need to leave it charging for some time and then reboot the controller(and thus the server) for it to recognise the, partially, charged battery. This...

Did you remember to let the battery charge for half an hour before after installing the new battery? After that you need to reboot to let the controller redetect the battery as it will not detect the battery if it has no charge on boot and charges after boot. This procedure is actually in...

As long as it will show up as a NTFS formated drive or via SMB Hyper-V can use it(or whatever Windows uses for clustering).

Technically, superfetch does do page-in's ahead of time :p Hence apps hanging when a lot of page-in's are required. The SATA standard is half-duplex and spinning drives generally can only do a single IO at once. This is why an SSD is such a massive upgrade for most people, even the crap SSDs...

Windows will select whatever pagefile is the least busy to queue a page-out request on. And since Windows can dispatch parallel IO operations, those page-outs can run simultaneously.