Seb Mouren

  • Content Count

  • Joined

  • Last visited

Community Reputation

0 Neutral

About Seb Mouren

  • Rank
  1. Seb Mouren

    Intel SSD 750 Review Discusison

    Hello, A question comes. What stack software-driver and its version- was used for testing? Regards.
  2. Seb Mouren

    Is eSATA really slower than USB 2.0?

    eSATA is a more efficient hard drive interface than USB2.0. But there are other things to consider: USB2.0 could deliver limited power to your drive (max one drive if 2,5', not enough for some 3,5'), eSATA cannot and requires an external power source; there use scenario are not the same, eSATA is more oriented toward connecting more than one drive with a port multiplier in a static configuration, USB is oriented toward a mobile and simple connection solution. Your perceived performance depends on many other factor: -what's your PCMCIA controller and what chipset is it hooked on? -what is the eSATA controller on the PCMCIA card? -what SATA drive is in the enclosure, which SATA spec does it support? -what OS are you using?
  3. Seb Mouren

    Are WD Raptors AHCI Compliant?

    Don't replace anything now. Test with new cable following strictly SATA 2.5 or 2.6 spec. Try to limit the SATA speed in the BIOS if available to 1,5GT/S. Test your hard drive using PowerMax or similar tools Update your drive firmware.
  4. Seb Mouren

    SCSIport vs. Storport white paper

    STORport is supported under W2K3(prefereably SP1) 32 bits and 64 bits, WinXP 64 bits, Vista 32 bit and Vista 64 bit. STORport requires facilities that were introduced by W2k3 OS and that are only present in its children.
  5. Seb Mouren

    SCSIport vs. Storport white paper

    You could read the driver supplied inf file to see if it supports SCSIPort or StorPort or ATAport under the class line. Promise, HighPoint, VIA, Marvell, Silicon Image and many others have STORport drivers.
  6. Hello, I wanted to share with you -and start a discussion about- some industry views, papers and specifications about storage. About the growing problem of reliability of har disk drive: Before terabytes fail: disk reliability in Windows Vista and beyond (1.47 MB) About a hardware/software solution to enhance drive responsiveness: Windows Vista Storage I/O Prioritization (806 KB) About hybrid disk drive: Hybrid Hard Disk & ReadyDriveâ„¢ Technology: Improving Performance and Power for Windows Vista Mobile PCs (968 KB) See the respective specification of the proposed solution here (for large sector drive, PCRS, NV-cache Command, NCQ priority etc...):
  7. Seb Mouren

    Unlocking a HDD password (Toshiba HD)

    You have to know what is password locked. If it is the hard drive using the official ATA password locking scheme you could unlock it through the original BIOS that locked it (no specific tools). If it is more proprietary it depends on what and how it locks it. Another option you've got is to let it in its original computer and boot using a bootable CD or external drive (if supported by your BIOS) using another OS (WinPE, BartPE, Linux etc...) to read the data from your drive and save it to another disk.
  8. Seb Mouren

    Raptor 150 NCQ

    This is completely true: these settings are adapter default user controls of Windows SCSIport drivers. They have been introduced since SCSIport driver stack creation (I think it was in NT3.51) to map user adjustable settings to driver parameters. But drivers could implement them or not and implemented them in many different ways. So as Eugene mentionned in another subthread it is recommended to employ driver's utilities to read and adjust your adapter settings.
  9. Seb Mouren

    Anyone Else Tempted by SiL3132?

    I highly disagree. And I fear that my post wasn't clear or that you misunderstood it. AHCI (read the spec and the license agreement) define a common approach for a controller interface and doesn't add or modify any details regarding the SATA specification. It is considered as the main target component for OS driver support (Linux, Vista, an even MacOS X, I heard); so software compatibility -in number of peripherals supported and in time they are supported- COULD be better than relying on Silicon Image alone for a product that MAY NOT exists in a few month -because of the economical non-sense of doing it. Regarding SATA: Interoperability, features and extensions supports testing are currently done by industry participant internally and in plugfest from which no results are published. Serial ATA standards, extensions are really fragmented and this situation is a total mess for the consumer. The current state of interoperability between SATA devices is good in numbers of peripherals that COULD work but quite poor in features supported between them (see firmware updates of numerous drives notably the latest Maxtor/nFORCE history) . For example there are no standard or label validation tests that say Sil3132 supports 3Gbits/s rate (Serial ATA 2.5 tries partly to correct that). It doesn't mean that Silicon Image doesn't do its maximum to make it work reliably at this rate and that Sil3132 doesn’t work at his rate with some drives Nonetheless it clearly doesn't work (or so say the driver inf file) with NCQ with some drive that say to support it too because of incompatibilities. For a few bucks, all these things don’t really matter for my personnal use. At work the situation is different: I buy only AHCI compliant controller and carefully qualify the references of my hard-disk drive.
  10. Seb Mouren

    Anyone Else Tempted by SiL3132?

    This chip is not actually AHCI compliant - I recommend you read the introduction of the spec if you don't understand objectives and roles from this spec. It doesn't imply anything relative to performance or reliability. It means that support by future OS (Linux, Vista and OSX) and interoperability with other Serial ATA components (drives, other chips) COULD be of lesser quality - this depends more on Silicon Image support evolution in time and the maturation of their product interoperability tests. On a feature-set basis, the chip doesn't implement all the required extensions to cover Serial ATA 2.5 but cover the most important Serial ATA II extensions - currently only high-end chips or integrated-chipset cover more. Regarding the driver/BIOS issue, as this is a low cost product, I didn't see any company investing in specific development with this product. So as long as they are recent and logo'ed stick with software from Silicon Image. Check the driver inf file to see incompatibilities and workarounds with specific combo of firmware/drive. Hope it helps. P.S: I don't actually own a chip or a board and I didn't play with one.
  11. Seb Mouren

    Western Digital Raptor WD1500

    Hi, I'm pleased to see SR keeping up with reviews of recent drives. Don't you think it would be interesting to test this drive and eventually other SATA or SATA 2.5 drive with the LSI SAS1068 adapter? It would offer us a first glimpse of current state of interoperability between SAS and SATA, and allow us to evaluate performance and stability of this solution as well as the current HBA driver implementation. Regards, Sébastien Mouren
  12. Hello, 1/ Most web sites I saw, report single-user performance as a pattern of hard disk drive IO. They try to reproduce common tasks of a single user, whether there are one or many drive in the benchmarked system, and measure the elapsed time spend in IO retrieving. This pattern typically consists of hard drive access with good data proximity and a short queue of user requests to the IO subsystem; it makes drive sustained transfer rate shine. It is often opposed to a multi-user pattern where data proximity is variable and queues of user requests are deep. This multi-user pattern is often associated to a "server pattern". 2/ NCQ is not only about drive performance: it allows, if supported by the OS, the hard drive interface controller, and the drive itself, to deliver IO commands some quality of service (a tag) and fast, drive-controlled and initiated data to memory transfer. To my knowledge today, Windows doesn't offer a NCQ enabled driver stack (it will in Vista, ATA-port, but I don't have any info about the envisaged implementation), and Linux offer some test driver to play with. Currently under Windows it could be implemented as a SCSI-port or STOR-port driver for the hard drive controller in which general CQ are wrapped around NCQ functionalities. In the hard disk controller interface (the chipset or discrete SATA controller chip), prior to the AHCI specification, NCQ implementation was ambiguous and often not interoperable between drives/controllers. In the drive, NCQ is implemented as support for the command set. Part of this implementation could employ a reordering command algorithm to maximize the drive throughput at the expense of latency of some commands. But NCQ in itself doesn’t necessitate the use of this algorithm. What the current crop of benchmark tries to measure is this part of NCQ: the ability for a drive to reorder effectively commands to maximize throughput. And in effect, for a particular command, this algorithm, when implemented, could be slower than using no reordering algorithm: imagine retrieving two pieces of data on the disk, the reordering algorithm objective is to make sure retrieving these two is faster but the time to retrieve the first of the two could be longer. That’s why NCQ enabled drive today shine more on multi-user benchmark. The full benefits of NCQ regarding performance and other aspects would only be unleashed by a good software implementation, a good controller implementation and a good drive implementation and as stated, it isn’t the case actually. 3/ WD implement in some Raptor (some models firmware have it others not) a command queuing algorithm said to mimics TCQ (Tagged Command Queuing, an SCSI command queuing scheme) but there's not much information about what part of it is in the box and it will suffer similarly from the problem explained above.