jrv

Patron
  • Content Count

    88
  • Joined

  • Last visited

Community Reputation

0 Neutral

About jrv

  • Rank
    <a href='/patron.html'><b>StorageReview Patron</b></a>

Contact Methods

  • Website URL
    http://
  • ICQ
    0
  1. I just discovered a drive that might have the infamous Seagate death-by-firmware bug. The printed drive label says it is a Barracuda 7200.11, ST31500341AS, Part # 9JU138-300, Firmware SD17, Date Code 09145, Site Code TK That's definitely a match for what Seagate says needs an upgrade. But when I run the upgrade program, it refuses to touch the drive. It says Model ST31500341AS SN 9VS09JBV FW SD17on Generic PCI ATA Bus 0 Device 0 NO MATCH! WILL NOT DOWNLOAD FIRMWARE! Error: Specific model not found. ST31500341AS expected. Of course, it *is* an ST31500341AS as expected. Has anyone run into this? I guess I'll have to put this drive on the shelf, along with 13 others just like it, until Seagate provides a new installer WD's big drives begin shipping...
  2. jrv

    Expresscard and SATA II?

    In theory what you want to do is reasonable and should work fine. But, you're on the bleeding-edge of things here... Two things to watch for: 1. There are two different ExpressCard form factors, ExpressCard/34 an ExpressCard/54. The numeric suffix refers to width. A completely bone-headed things for them to have done, since /54 cards won't fit into /34 sockets, and the notebook manufacturers are of course only going to want to use /34 and the card manufacturers are generally going to want /54 for connector space... For example I think Apple's MacBook Pro has a /34 socket and the two SATA cards I have heard of are /54 ... a completely predictable result when you can't agree on one form factor in committee! Firmtek will presumably solve this when they release, and might even be able to boot off the ExpressCard, or at least mount an external SATA disk as the root filesystem. 2. "Port Multiplier" support. If the ExpressCard host controller supports SATA II Port Multipliers then a single external SATA cable can connect to several devices: Addonics and Cooldrives sell chassis that can have five devices that talk to the system over a single external SATA cable. If the ExpressCard only has one connector due to space limitations then Port Multiplied support still allows several external drives to be supported. Addonics see ST5X1PM http://www.addonics.com/products/raid_system/ast4.asp Note that you can have four hard disks and a CD/DVD drive (either SATA CD/DVD or ATA with tailgate).
  3. Where can I find the cable needed to go from the controller activity connector to the motherboard? I've got on my to-do list hooking this up for a client. I'm told this is a standard connector and that these motherboards and controllers have it. But I haven't seen these cables listed for sale on any web sites?
  4. Your English is fine. That chart looks almost exactly like my MAU3073NP. I think your drive is working normally. A 32-bit 33 MHz PCI card has a theoretical maximum speed of 125 MB/sec or so. You are very close to the limit but mine gets the same on much faster 100 MHz PCI-x, so I think you are (just barely) OK. The Raptor is a very fast disk drive for non-server work. It is not surprising that two Raptors in RAID 0 is faster. The Fujitsu is designed for server work. The only thing faster for workstation work is likely to be a new 150GB Raptor, or maybe a pair in RAID 0 (RAID 0 doesn't always win but it looks like it does in HD Tach on your system).
  5. jrv

    NCQ only good for servers?

    They appear to ignore the reliability issue: without NCQ these drives scramble the write ordering that the OS depends on to avoid data loss around power loss. With NCQ one hopes the drives won't lie and that the various filesystem hardening techniques in the OS will work as intended.
  6. jrv

    Firefox disappointment :(

    Any examples that aren't Flash issues? I've only found a few sites that didn't look right, but all had bad HTML. I don't use IE any more at all after spending too many hours scrubbing IE-targeted spyware from systems.
  7. jrv

    7-Zip

    Their compression ratios SUCK by today's standards. 7z archives are often less than HALF the size of gzip archives of the same files. And even creating zip archives it does about 4% smaller than gzip. It's not just the dictionary size. Compression ratio isn't everything. Also important is the reliability - do you get back the original file after decompression? The DEFLATE code in gzip was very stable ten years ago; I don't know if they've seen a single bug in either the compressor or decompressor in that interval. The code is well understood (at least by some people; it resists casual reading by me quite well). It has been enshrined in an RFC 1950. Sometimes a 7-zip is much smaller than a gzip but often the difference is not enough to overcome the reliability question for me, even for home use. For job use - where data loss might cost me my job - I would not even consider 7-zip unless each compress cycle could be tested and recovery done; I would be willing to trust gzip after some testing to show that the compiler hadn't mangled it (assuming patents aren't an issue). There are people trying to fix the 7-zip source code and if they succeed it might be worth giving it a hard look and test. For now 7-zip is too risky for me.
  8. Don't get too fixated on raw I/O performance. If the drive and OS driver both work right then both TCQ and NCQ should make the system much less likely to corrupt the hard disk than ordinary ATA. Getting TCQ/NCQ to the desktop is about data integrity (hardening the filesystem against data loss) and not performance.
  9. Don't SCSI drives do the same if the Force Unit Access bit is off? I think you can force this behavior but there is no reason to do so if SCSI TCQ is used, and nobody in their right mind would do such a thing in a production environment.
  10. Eugene: is there evidence, or has WDC said, as to whether the drive returns an early SUCCESS for NCQ writes? I think it is important that the drive not return SUCCESS until an NCQ write has, in fact, successfully committed to media. Existing ATA drives return a false SUCCESS and re-order writes to media without the OS’s knowledge. This can cause disk corruption that filesytem hardening strategies normally prevent. MS has published KB articles on the problem. I think the log-based nature of NTFS can help reduce the problem but more-modern filesystems that use no log are at even greater risk of damage from false SUCCESS result. The usual reason for this sad state of affairs is performance: internal write reordering wins significantly, enough to outweigh data loss (for drive manufacturers anyway). But with NCQ this is no longer necessary: the drive may continue to accept writes and reorder them at will, suffering no performance hit from only completing the transaction (returning a result code) after data has been committed to media. The OS simply withholds ordered writes until previous activity completes when ordering is important. This data loss issue is what really sets SCSI apart from IDE in my mind. I would promptly switch to sATA / NCQ in the drive vendors promised not to report false SUCCESS for NCQ writes with the intended benefit being crash resistance. The data loss problem probably deserved more attention in your paper; if nothing else it is a significant reason NCQ would be desirable even for a single-user workstation. PS. Non-NCQ writes will probably continue to return false SUCCESS as before for performance reasons. It’s the NCQ write commands, which won’t benefit from cheating, that I’m hoping to see work right.
  11. Considering that the driver comes with the controller, I think this is a rather silly point, no offence. Why bother splitting this hair? In all practicality you have to buy a controller that supports TCQ. FreeBSD has (had) a driver that supported ATA TCQ on all correctly-functioning drives. “All†meant “one†(1). Moreover, ATA TCQ has been removed from FreeBSD so I suspect “all†turned out to be “noneâ€. But no card driver is needed unless to base OS driver is missing TCQ support, and the card driver’s TCQ support would work equally well with any ATA controller is not otherwise blocked. (in all reality it might be better to say you have to buy a drive that supports TCQ, and in the ATA world there are none) PS. I've read the TCQ specs in the ATA document and it's pretty straightforward as long as there is only one device on the channel. I suppose it’s time to find the sATA spec and see how NCQ works. Has anyone here really dug into NCQ yet?
  12. See http://news.yahoo.com/news?tmpl=story&u=/s...espn25shardsell. Anyone still think the NBA doesn't rig the tournament?
  13. jrv

    Directory File Limit?

    The filenames all fit in 8.3 format so no hit in creation from that. Also, it wasn't just the first time (when you MFT was growing). It's possible that some of the XP bug fixes dealt with this.
  14. jrv

    Directory File Limit?

    This is probably true since NTFS performance just falls through the floor and exhibits other anomalies. I did a proof-of-concept test to demonstrate a ZIP file with one million (1,000,000) entries. The point was to prove the tools. I happened to use NT (2.0 GHz Xeon, 2 GB RAM) at first and it was incredibly slow, taking over a day to create the files (it was CPU bound not disk bound). However, an NTFS directory did hold a million files. Another group did some experiments and found that for file reads – no creation and rebalancing – it was faster to manually place the files into a subdirectory structure (i.e. aardvark.zip in a/a/aardvark.zip etc) than to place everything in one directory. That’s shocking – it says their B-tree implementation is so bad that it is cheaper for the filesystem to descend into subdirectories than search within a directory. I think this group was dealing with the 20,000 to 50,000 files case. The point of the million file case was not that we wanted to do it, but rather to prove that the plan using ZIPs worked with existing cases, foreseeable growth, unreasonable growth, and truly absurd outlier cases (a million files in a ZIP). I had to defend it and wanted to show that the tools and plan would not break even far past the point at which the rest of the process would be expected to fall over.
  15. This is one of the keys to Reagan: his moral compass was almost always predictable. It wasn't necessary to wait for a public opinion poll or to see who had donated the most campaign money to see what position he would take on an issue: anyone, friend or foe, knew where he stood on any issue because they knew what his principles were, and it was principles, right or wrong, that guided him.