similar to: NCQ performance

fun example that shows NCQ lowers wait and %w, but doesn''t have much impact on final speed. [scrubbing, devs reordered for clarity] extended device statistics device r/s w/s kr/s kw/s wait actv svc_t %w %b sd2 454.7 0.0 47168.0 0.0 0.0 5.7 12.6 0 74 sd4 440.7 0.0 45825.9 0.0 0.0 5.5 12.4 0 78 sd6 445.7 0.0

I was trying to simply test bandwidth that Solaris/ZFS (Nevada b63) can deliver from a drive, and doing this: dd if=(raw disk) of=/dev/null gives me around 80MB/s, while dd if=(file on ZFS) of=/dev/null gives me only 35MB/s!?. I am getting basically the same result whether it is single zfs drive, mirror or a stripe (I am testing with two Seagate 7200.10 320G drives hanging off the same interface

First Post! Sorry, I had to get that out of the way to break the ice... I was wondering if it makes sense to zone ZFS pools by disk slice, and if it makes a difference with RAIDZ. As I''m sure we''re all aware, the end of a drive is half as fast as the beginning ([i]where the zoning stipulates that the physical outside is the beginning and going towards the spindle increases hex

Hi. Just migrated to zfs on opensolaris. I copied data to the server using rsync and got this message: Oct 10 17:24:04 zetta ^Mpanic[cpu1]/thread=ffffff0007f1bc80: Oct 10 17:24:04 zetta genunix: [ID 683410 kern.notice] BAD TRAP: type=e (#pf Page fault) rp=ffffff0007f1b640 addr=fffffffecd873000 Oct 10 17:24:04 zetta unix: [ID 100000 kern.notice] Oct 10 17:24:04 zetta unix: [ID 839527 kern.notice]

I have two identical servers. The only difference is that the first one has Maxtor 250G drives and the second one has Seagate 320G drives. OS: CentOS-4.4 (fully patched) CPU: dual Opteron 280 Memory: 16GB Raid card: 3ware 9550Sx-8LP Raid volume: 4-disk Raid 5 with NCQ and Write Cache enabled On the first server I have decent performance. Nothing spectacular, but good enough. The second one

I have two identical servers. The only difference is that the first one has Maxtor 250G drives and the second one has Seagate 320G drives. OS: CentOS-4.4 (fully patched) CPU: dual Opteron 280 Memory: 16GB Raid card: 3ware 9550Sx-8LP Raid volume: 4-disk Raid 5 with NCQ and Write Cache enabled On the first server I have decent performance. Nothing spectacular, but good enough. The second one

Currently I''m trying to figure out the best zfs layout for a thumper wrt. to read AND write performance. I did some simple mkfile 512G tests and found out, that per average ~ 500 MB/s seems to be the maximum on can reach (tried initial default setup, all 46 HDDs as R0, etc.). According to http://www.amd.com/us-en/assets/content_type/DownloadableAssets/ArchitectureWP_062806.pdf I would

Does SATA Native Command Queueing and Linux software RAID1 play well together or is it better to turn off NCQ when doing software RAID?

All, I have a problem with a new Seagate hard disk. The problem occurs when i go to install CentOS, i insert the cd and start the boot up process, when it gets to the section where it detects the hard disks, the driver is seems crashes, the message it produces complains about no one caring about a interrupt on IRQ11. The hard disk is a Seagate 200GB 8MB SATA150 NCQ drive, on a SilliconImage

Hi, I've got a new server with a 3ware 9550SXU with the Battery. I am using FreeBSD 7.0-Release (tried both 4BSD and ULE) using AMD64 and the 3ware performance for writes is just plain horrible. Something is obviously wrong but I'm not sure what. I've got a 4 disk RAID 10 array. According to 3dm2 the cache is on. I even tried setting The StorSave preference to

After applying 125205-07 on two X4500 machines running Sol10U4 and removing "set sata:sata_func_enable = 0x5" from /etc/system to re-enable NCQ, I am again observing drive disconnect error messages. This in spite of the patch description which claims multiple fixes in this area: 6587133 repeated DMA command timeouts and device resets on x4500 6538627 x4500 message logs contain multiple

Running an mmap-intensive workload on ZFS on a X4500, Solaris 10 11/06 (update 3). All file IO is mmap(file), read memory segment, unmap, close. Tweaked the arc size down via mdb to 1GB. I used that value because c_min was also 1GB, and I was not sure if c_max could be larger than c_min....Anyway, I set c_max to 1GB. After a workload run....: > arc::print -tad { . . . ffffffffc02e29e8

I?d like to report the ZFS related crash/bug described below. How do I go about reporting the crash and what additional information is needed? I?m using my own very simple test app that creates numerous directories and files of randomly generated data. I have run the test app on two machines, both 64 bit. OpenSolaris crashes a few minutes after starting my test app. The crash has occurred on

Currently, some new storage devices have the ability to do performance optimizations according to the type of data payload - say, file system metadata, time-stamps, sequential write in some granularity, random write and so on. For example, the latest eMMC 4.5 device can support the so-called ''Context Management'' and ''Data Tag Mechanism'' features. By receiving

Hi all,? I have a CentOS 4.5 server running on a workstation mainboard (PCI Slots only).? We have now one 200 Gigs IDE disk dedicated for e-mail server storage.? We use Communigate Pro and the server has 45 Outlook clients with the MAPI connector (All mailboxes on the server).? When a user opens Outlook, a refresh of the local cache is performed for his data.? There is a big "Public"

I know there are a few 3Ware fans here and I was hoping to find some help. I just built a new server using a 3Ware 9550SX-4LP with four disks in raid 5. The array is fully initialized but I'm not getting the write performance I was hoping for -- only 40 to 45MB/Sec. 3Ware's site advertises 300MB/Sec writes using 8 disks on the PCI Express version of this card (the 9580 I think.)

I''m looking for an example of how one could write a dtrace probe that could follow something like a NULL terminated linked list. For example: struct list { struct list *next; void *data; }; struct list *list_root; Assuming I had "list_root" available, but I wanted to know how long the linked list is, how can I do this in a dtrace probe? If I had looping

I''m running OpenSolaris 2008.05 in VirtualBox on a Windows XP host. Playing around with various probes, I found that trying to load any probe associated with bdev_strategy dumps core. I can think of one or two likely and reasonable causes for this, but am assuming it''s undesirable behavior. Anyone know what''s happening here? -- This message posted from

Hi All, Newbie here! I was wondering if anyone has succeeded in getting NCQ enabled with the ServerWorks chipset in the 2.6.18 kernel. I am running a Dell 1435/CentOS 5.0-x86_64 with dual 250GB Western Digital NCQ supported drives, when I load up the OS I get these messages: ata1: SATA link up 1.5 Gbps (SStatus 113 SControl 300) ata1.00: ATA-7, max UDMA/133, 488281250 sectors: LBA48

Hi all, I'm sure this eventually will be resolved with a BIOS or kernel update, but in case someone experiences this on this or a similar motherboard, I thought I'd post a problem-and-workaround report. Platform CentOS5, x86_64 kernel-2.6.18-53.1.21.el5 Motherboard Asus M3a78-EMH HDMI SATA-controller configured as AHCI Experienced symptom; Periodic, ~20s lockups/freezes, several a