Filesystem performance - btrfs, zfs, xfs, ntfs

I was somewhat curious about filesystem performance for video streaming purposes. So I set up a test system. The test system was:

• 12-disk Supermicro chassis with SAS1/SATA2 backplane, scrap (has motherboard issues with the sensors and a broken backplane connector and was rescued from the scrap heap)
• SuperMicro X8DTU-F motherboard with two 2.4Ghz Xeon processors (Nehalem architecture) and 20Gb of memory (the odd amount of memory is due to being populated from the contents of my junk bin)
• Six 2Tb 7200 RPM drives (all the SATA-2 drives that I could scrounge up from my junk bin)
• One LSI 9211-4I SAS2 HBA controller (purchased for this purpose)
• One Intel 160Gb SATA-2 SSD (replaced with a larger SSD in my laptop)

There was also another 64Gb SSD used as the boot drive for Fedora 18, the OS used for this test. Fedora 18 was chosen because it has a recent BTRFS with RAID10 support and because ZFS On Linux will compile easily on it. The following configurations were tested:

1. BTRFS with 6 drives configured as RAID10
2. ZFS with 6 drives set up as three 2 disk mirror pairs, striped. I experimented with the 160Gb SSD as logging device, and without it as logging device.
3. XFS on top of a Linux MD RAID10
4. A Windows 7 virtual machine running in KVM virtualization environment with the MD RAID10 exported as a physical device to the virtual machine.

I did not test ext4 because I know from experience that its performance on large filesystems with large files is horrific.

Note that XFS on top of RAID10 is subject to data loss, unlike BTRFS and ZFS which include integrity guarantees. Windows 7 in a virtual machine on top of MD RAID10 is subject to even more data loss plus has approximately 5% I/O performance overhead in my experience (the host system chews up a huge amount of CPU, but CPU was not in short supply for this test). The purpose was not to propose them as serious solutions to this problem (though for security camera data loss of a few seconds of data in the event of a power failure may be acceptable) but, rather, to compare BTRFS and ZFS performance with the "old" standards in the area.

The test itself was simple. I set up a small script that set up 8 dd processes with large block sizes running in parallel streaming /dev/zero data to the filesystem, similar to what might occur if eight extremly high definition cameras were simultaneously streaming data to the filesystem. Compression was off because that would have turned it into a CPU test, heh. At intervals I would killall -USR1 dd and harvest the resulting performance numbers.

My experience with these hard drives as singletons is that they are fundamentally capable of streaming approximately 110Mb/sec to the platters. Because ZFS and BTRFS are both COW filesystems, they should have been utilizing the full streaming capability of the drives if they properly optimized their disk writes and had zero overhead. In practice, of course, that doesn't happen.

First I tried BTRFS. After some time it settled down to approximately 298Mb/sec throughput to the RAID10 test volume. This infers approximately 10% overhead (note that since RAID10 is striped mirrors, multiply by two to get total bandwidth, then divide by six to get per-drive bandwidth). The drive lights stayed almost constantly lit.

Next I tried ZFS with the log on the SSD. I immediately noticed that my hard drive lights were "loping" -- they were brightly lit then there were occasional burps or pauses. The final result was somewhat disappointing -- approximately 275Mb/sec throughput, or roughly 17% penalty compared to raw drive performance.

But wait. That's an older Intel SSD that had been used in a laptop computer for some time before I replaced it with a larger SSD. Perhaps the common ZFS wisdom to put the log file onto an SSD is not really that good? So the next thing I tried was to destroy the testpool and re-create it from scratch without the log device, and see whether that made a performance difference. The result was no performance difference. Again I was averaging 275Mb/sec throughput. To say that I'm surprised is an understatement -- "common knowledge" says putting the ZFS log on a SSD is a huge improvement. Doesn't appear to be true, at least not for streaming workloads with relatively few but large transactions.

In other words, don't use ZFS for performance. Its performance appears to have... issues... on Linux, likely due to the SEL (Solaris Emulation Layer), though it is quite acceptable for many purposes (a 17% I/O performance penalty sucks, but let's face it, most people don't max out their I/O subsystems anyhow). It's the same licensing issues that have held up ZFS adoption elsewhere, Sun created their license for their own purposes, which are not the same as the Open Source community's purposes, and Oracle appears to agree with Sun. On the other hand ZFS is *really* handy for a backup appliance, due to the ability to snapshot backups and replicate them off-site, thereby providing all three of the functions of backups (versioning, replication, and offsite disaster recovery). For limited purposes ZFS's deduplication can be handy also (I use it on virtual machine backups since virtual machine files get rsync'ed to the backup appliance every time but most of the blocks are the same as the last time it was rsync'ed -- ZFS merely links those blocks to the previously-existing blocks rather than use up all my disk). That's a purpose that I've put it to, and am having excellent results with it. Note that the latest BTRFS code in the very latest Linux kernel has RAIDZ-like functionality so that's no longer an advantage of ZFS over BTRFS.

Finally I went to the hoary old md RAID10 driver. This caused some havoc because md RAID10 insists upon scanning and possibly rebuilding every block on the RAID array before you get full-performance access to it. I changed the max rebuild speed to well above the physical capability of the hardware and MD10 reported that it was rebuilding at 315Mb/sec. This means approximately a 4% performance overhead from MD10 compared to the raw physical hard drive speed. The kernel thread md10_raid10 was using 66% of one core, and the kernel thread md10_resync was using 15% of another core. This tends to indicate that if I had a full 12-disk RAID10 array, I'd be maxing out a core and get lower performance -- fairly disappointing. Intransa's code has similar bottlenecks (probably caused by the bio callbacks to the RAID layer from the driver layer), but I'd expected the native code to perform better than 10 year old code that wasn't even originally designed for modern kernels and was not originally designed to talk to local storage and can do so only via a shim layer that I am, alas, intimately familiar with (Intransa's RAID layer was originally designed to talk to IP-connected RAID cabinets for scale-out storage). So it goes.

So now the RAID is rebuilding. I'll come back tomorrow with a new post after it's rebuilt and look at what xfs and ntfs on top of that RAID layer do. In the meantime, don't attach too much importance to these numbers. Remember, this is being done on scrap hardware as basically a "I wonder" as to how good (or how bad) the new filesystems are compared to the oldies for my particular purpose (streaming a lot of video data to the drives). YMMV and all that. And testing it on modern hardware -- SATA3 drives and backplanes, Sandy/Ivy motherboard and processors, etc. -- likely would result in much faster numbers. Still, for my purposes, this random scrap assemblage gives me enough information. So it goes.

- Eric Lee Green

* Disclaimer - I am currently chief storage appliance engineer at Intransa, Inc., a maker of iSCSI storage appliances for video surveillance. This blog post was not, however, conducted using Intransa-owned equipment or on company time, and is my own opinion and my own opinion only.

How to upgrade to a bigger SSD

Okay, on a 17" HP Envy, here's how to upgrade from a small SSD to a new SSD:

1. Make a Windows system repair disk via the control panel's Backup/Restore item.
2. Put the new SSD into an external USB case
3. Boot into a Linux live CD that supports your hardware, and dd the internal drive to the external drive.
4. Unplug the external drive, reboot back into Windows.
5. Now to extend the partitions on the new drive so you have your new C:. Plug in the external drive, run Easus Partition Master and move your rescue and tools partitions to the end of the drive and resize your C: partition on the new drive.
6. Shutdown the system
7. Remove the old SSD from the computer, replace it with the new SSD.
8. Boot into the repair disk. It'll then whine that your boot needs repairing. Let it.
9. Boot into the system, and then go to the control panel's 'System' item. Select "System Protection", then scroll down to the end of the list and you'll see something that says "C: (Unavailable)" that says System Protection is enabled. Click on it, then click "Configure", then "Disable".
10. Click your new "C:" partition, select 'Enable', then whatever percentage you want to enable for System Restore snapshots.

There you go. All done.

UDP or TCP for lossy networks?

So I was discussing video streams today and how typical video streaming protocols like RTP react to loss on the network -- i.e, by dropping frames -- and someone made the statement, "TCP would be better for lossy networks." He was wrong, of course. But I hear you saying, "but... but... TCP recovers from data loss!" Well, yes... if you don't care about timing or throughput, only about reliability. But if you're talking video streaming, TCP could result in loss of not only a few frames, but could result in loss of seconds worth of frames, or even cause video cameras, switches, or servers to crash.

At which point you're saying, "say wha?!" But here's the deal. If you lose a video packet with UDP, you lose a frame. RTP handles reassembling the packets into frames, if the next frame has come in and there's no packet to fill in slot X in the previous frame, RTP just throws the frame away. If you're getting 28 frames per second, you lose one frame out of that, big deal. Just replay the previous frame on replay, nobody will notice.

Now let's say you're using TCP. A missing packet occurs. TCP is expecting packet N... and doesn't get it. The TCP window goes SLAM at that point -- 4 megabytes of data backs up behind the missing packet as TCP tries to build its window and has a missing piece that it is waiting for, then TCP flow control assures that no more data is accepted until after the 1.5 second timeout causes a retransmit on the sender side. What this does is add 1.5 seconds worth of delay. You have a 1.5 seconds of delay, 4 megabyte window, and a gigabit Ethernet line, and what that means is that one lost packet every 1.5 seconds basically causes your gigabit Ethernet line to become a 21 megabit/sec Ethernet line. Congratulations, you just returned to 1985. And if you have 200 megabits/sec of incoming data, all that data is piled up in the network stack somewhere between you and the cameras, and you're in big trouble.

For streaming data, UDP thus handles a lossy network much more gracefully than TCP does. At least, that's true if you don't care about data loss due to redundancy in the data stream. I.e., frame 1000 in a video stream is very similar to frame 999 and frame 1001, so if frame 1000 goes missing it can be recontructed as simply the duplicate of the preceding or following frame. So what if you *do* care about data loss?

The reality is that if you *do* care about data loss, you're much more likely to get good results when streaming data if you use out-of-band data recovery. That is, if you've tried filling your frame, you already have packets for a couple more frames incoming, and you're missing a couple of packets, request packet retransmission directly via a NAK rather than wait for the sender to timeout waiting for an ACK. Thus *one* reason why most reliable multicast protocols rely on recipients proactively sending a NAK rather than time out waiting for an ACK before sending a packet. You can combine the two if you wish -- in this case, ACK would let the sender know that all packets in the frame were received thus it doesn't need to retain the frame in order to potentially service a NAK -- if you're really wanting both reliability and performance. But TCP doesn't do that. Which is why, on a lossy network, TCP is probably the worst protocol you could use for streaming data, and why the person who said "TCP is best for lossy networks" was wrong, at least for this application.

-ELG

The importance of strong product management

There's a lot of folks who whine about Windows 8, "Why did Microsoft have to change the UI? I like the old one!" The thing is, the old one simply isn't working well for a lot of people anymore. Hard drives have gotten so big, and people have installed so many programs on their systems, that the Start menu has achieved a depth that nuclear submarines would envy. Because the population is aging and eye-hand coordination is declining, both seeing all the tiny print on that Start menu and navigating it through several levels of sub-menus has become increasingly hard for a large percentage of the population. And finally, the Start menu paradigm simply doesn't work for tablets. If eye-hand coordination diving through the menu is an issue with a mouse, with a tablet touchscreen it would simply be impossible.

In other words, the notion that the Windows 8 UI change is all about "marketing" is pretty much nonsense. It's been well known that the Cairo user interface introduced with Windows 95 has reached its logical limits for quite some time, and ideas for changing the UI to meet the new challenges of the 21st Century have been floating around inside Microsoft for years, if a look at the Microsoft Research web site is any guide. I'm sure that Marketing told engineering, "we need a UI that will be usable on a tablet! And oh, make it usable on a desktop too!", but at worst Marketing merely hurried what was already in progress, rather than being a direct cause of the changes in Windows 8. The writing was on the wall for the Cairo UI, and sooner or later it would have been consigned to the dustbin of history regardless of Marketing's frantic panic about tablets.

So unlike a lot of people, I'm not surprised at all that Windows 8 has a significant shift in UI functionality. What I *am* surprised at is that it was done so badly. Microsoft has a lot of good people, and Windows 8 has all the raw tools in it to be a great operating system. Yet there's some needless complexities in its operation that shouldn't be there, and some important missing functionality that should be, such as IOS or Android style icon folders (without that, you're in endless sideways-scrolling territory to get all your most-used programs onto the start screen). So what gives?

In my opinion, the biggest issue with Windows 8 is caused by a clear failure of product management. Good product managers are hard to find because the job requires an understanding of customers at an intuitive level such that you can devise workable requirements to meet their needs, yet sufficient technical chops to understand what is doable and guide engineering toward producing the product that is going to meet those requirements. It also requires taste -- the ability to look at a product and say, "yes, that is tasteful and will please our customers" or look at a product and say "that is a pile of garbage, get it out of my sight until you do X, Y, and Z to it." Furthermore, product managers have to be empowered to be able to make those sort of judgements and have them stick. For better or for worse, Steve Jobs provides the template for what a strong product manager looks like -- opinionated, tasteful, with an intuitive understanding of the customer, with enough technical chops to understand what can be done, and power to make it stick.

Thing is, it's hard to find product managers like that because the geeks and nerds who typically run engineering departments wouldn't know good taste if it bit them on their bum, while the sales flunkees who typically run marketing departments wouldn't know technical chops if said chops bit off their ear. You almost need a Steve Jobs to do it. Unfortunately Microsoft doesn't appear to have a Steve Jobs to find good product managers, or if they do have good product managers, haven't empowered said product managers to make critical decisions about the product. Which is a shame. Because Windows 8 has a lot of good ideas, and the underlying technology is good. It just fails because of a lack of good taste (and courage, but see my prior blog on that), not because of a lack of technical chops.

Which just goes to show that putting out a great product isn't a matter of having great technology. It has to be a team effort, and if you don't have that, what you'll get is either a product that doesn't meet the needs of the marketplace, or a product that's far less great than it should be. Something to think about, if you're thinking about forming or joining a new startup. Do you have the kind of team that it will take? Does the company you are thinking of joining have such a team? Important questions, yet pretty much every startup I've encountered is all about the technology, and the rest of what it takes to have a great product is completely ignored. Which is probably why so many startups fail. So it goes.

-ELG

Adding certificates for Windows 8 Mail

I run my own email server and of course SSL-encrypt both imap and smtp, but have a self-signed certificate, not a certification authority signed certificate. Outlook has no problem with that -- it whines about the certificate, but then gives me a dialog where I can import it. Once I import it, fine. But I don't have Outlook installed on my Windows 8 evaluation for a variety of reasons. So I tried Windows 8 Mail and rather than offer to import the certificates, I got a message that I needed to contact my system administrator to import some certificates. Erm, I *am* my system administrator! Hrm. So...

My email server is running Debian "squeeze" Linux with Exim4 as the smtp server and dovecot as the imap server. The first thing I needed to do was verify on the mail server that there were valid (self-signed) certificates for both exim4 and dovecot. This can be done with:

• openssl x509 -in some.crt -text -noout

This will give you a bunch of information about the certificate, so you may wish to pipe it to 'less'.

The exim4 certificate was expired so I regenerated it with:

• /usr/share/doc/exim4-base/examples/exim-gencert --force

So then I located the two certificates:

• Dovecot - /etc/ssl/certs/dovecot.pem
• Exim4 - /etc/exim4/exim.crt

I downloaded the two certificates to my Windows 8 system via sftp and renamed the dovecot certificate from dovecot.pem to dovecot.crt . The next thing I did was open the Microsoft Management Console by pressing Windows-R and typing 'mmc'. I then selected Add/Manage Snapons, and selected to add the Certificates snapon.

Next, open up the Certificates tree until you see "Trusted Root Certification Authorities" and open it up to see "Certificates" underneath it. Right-click on Certificates and click "All Tasks" then "Import". Import your two certificates and there you are -- now all your self-signed certificates coming from your email server look as valid as any certificates, and are accepted by Windows 8 Mail just fine.

So, uhm... why does Microsoft make this so hard? I dunno, they're Microsoft, I guess. But the "ask your system administrator" is just BS, because Windows 8 Mail will *never* be used by anybody who actually has a system administrator other than themselves -- all businesses will be using Outlook Mail as their email client for a number of reasons. Oh well, just another example of how Windows 8 is half-baked and characterized by an utter lack of understanding of, well, actual customers.

-ELG

BTRFS vs ZFSonLinux: How do they compare?

• Integration with Linux
  • ZFS: Not integrated. Has its own configuration database (not /etc/fstab), has its own boot order for mounting filesystems (not definable by you), cannot be told to bring a filesystem up after iSCSI comes up or down before iSCSI goes down.
  • BTRFS: It's just another Linux filesystem as far as the system is concerned. You bring a pool up by mounting it (preferably by label) in /etc/fstab and can define the mount order so it comes up after iSCSI.
• Snapshots
  • ZFS: Full snapshot creation and removal capabilities, well exploited by the FreeBSD port 'zfs-periodic'. Snapshots appear in a special "dot" directory rather than cluttering up the main filesystem. This script is relatively easy to port to Linux.
  • BTRFS: Snapshots are created as "clones" of subvolumes, and destroyed as if they were subvolumes. They can be created either read-write or read-only.
• RAID: Both of these use filesystem-level RAID where filesystem objects are stored redundantly, either as entire clones (RAID1) or, in the case of ZFS, via RAID
  • ZFS: Raid1 (mirroring) and RaidZ (similar to RAID5, except that it never does partial-stripe writes because it does variable stripe size -- the size of an object is the size of a stripe). Note that due to ZFS's COW implementation, an update to a RAID stripe cannot be corrupted by a power loss halfway through the write (see: RAID5 write hole)-- the old copy of the data (prior to the start of the write) is instead accessed when power comes back on.
  • BTRFS: Raid1 (mirroring). BTRFS currently has nothing like RaidZ. Note that putting a BTRFS filesystem on top of a software mdadm RAID5 will not give you the same reliability and performance as RaidZ, since you will still have the random write hit of partial-stripe writes and will still have the RAID5 write hole where if a stripe update fails due to power loss halfway thru the stripe write, the entire stripe is corrupted.
• Portability
  • ZFS: A ZFS filesystem can be read / written on: Linux (via either ZFS/Fuse or ZFSonLinux), FreeBSD, OpenIndiana, and MacOS (via Zevo). Requires extra 3rd party software to be installed on Linux and MacOS, comes standard with FreeBSD and OpenIndiana.
  • Linux: Any recent Linux distribution (one with a 3.x vintage kernel) has BTRFS built in. Your BTRFS pools will be immediately available when you upgrade to a newer kernel or a newer Linux distribution, with no need to install any additional software. However, BTRFS doesn't run on any other OS.
• Stability
  • On Linux, both BTRFS and ZFS are listed as "experimental". ZFSonLinux uses SEL (the Solaris Emulation Layer) as a "shim" between ZFS proper and Linux. Unfortunately this is sort of like nailing jello to a tree, while the underlying Linux block layer API hasn't changed in years, locking inside that block layer API has been in constant turmoil ever since the 2.6.30 timeframe as the last vestiges of the Big Kernel Lock were ferreted out and sent to the great bit bucket in the sky. The end result is that code that *used* to work may or may not cause deadlocks or strange races that cause an oops with current Linux kernels -- *UNLESS* it was developed as part of that current Linux kernel, as BTRFS is, in which case the person who changes the locks is responsible to make sure that all other kernel modules that are part of the next kernel release change their locks to match.
  • Summary: On Linux, this is a tie. BTRFS is under rapid development. ZFS is attempting to nail jello to a tree from outside the Linux kernel. Use for production data of either system on Linux is not recommended. If you want a production server running a production-quality modern snapshotting filesystem, use ZFS on FreeBSD.

Final summary:

If you must use Linux, and you must have a modern snapshotting filesystem, and you can live with a RAID1 limitation on data redundancy, I would strongly recommend going with BTRFS. The reason for this is that BTRFS is only going to get better on Linux, while ZFS is always going to be fighting the nail-jello-to-a-tree issue where Linux keeps changing underneath it and breaking things in weird ways. Unless ZFS is included as part of the Linux kernel -- and Oracle's lawyers will never allow changing the license to GPL in order to allow that -- there simply is no way ZFS will ever achieve stability except with specific kernel versions shipped with specific distributions. And even there I'm dubious.

If you need the stability of ZFS, I strongly recommend using FreeBSD and not using Linux. I have personal experience dealing with the issues that come with supporting an emulation layer on top of the Linux block layer, including dealing with some deadlocks and races caused by locking changes inside recent kernels that caused a six-week delay in the release of an important product, and I honestly cannot say that any current ZFSonLinux implementation will continue to work with the next kernel revision. I can reliably say that BTRFS will work with the next kernel revision. While production servers don't change kernel revisions often, only once every three or four years, if the next version of the server OS doesn't happen to be one that is well supported by ZFSonLinux's then-current SEL implementation, you have problems.

So: Linux -- BTRFS. If you need the functionality of ZFS -- FreeBSD. Enough said on that.

Crack-smoking Linux zealots

It seems that every year, like the swallows flocking back to Capistrano, you get yet another burst of Linux zealots claiming that this is the year for the Linux desktop. As you know, I've said good things about Gnome 3 and its usability by mere mortals. Linux geeks whine about how they can't customize it blah de blah blah, but mere mortals don't customize their window manager -- other than setting the desktop background to a photo of their kids or grandkids, all they care about is whatever applications they're wanting to run. And from that perspective, Gnome 3 works just fine. But: An operating system is more than a window manager. And that is where Linux still is Utter Fail on the desktop.

Okay, let me tell you a story. I installed Fedora 17 on a 64GB SSD to manage my RAID arrays that serve data to my home network. For grins and giggles I installed Thunderbird and told it about a couple of my email accounts. I clicked through on a link in one of those email accounts that went to a page that had a video embedded. Well, that *would* have a video embedded, on Windows or MacOS. On Linux? Just a blank box and a message about a plugin that simply doesn't exist for Linux that needs to be installed, probably a Quicktime plugin. Now I'm sure you're saying, "but that's not Linux's fault, that's Apple's fault for patenting the algorithm used for that plugin!" But see, the deal is, end users don't care whose fault it is. All they know is that they can't see that embedded video with Linux, and they can see it with Windows or MacOS. BTW, same applies to playing MP3 files -- they simply won't play. Again, a patent issue, but Joe Sixpack doesn't care why his music files won't play on his Linux system -- all he cares about is that they don't play on his Linux system. End of game.

Now let's look at another issue, one where the excuse of patents does not hold. The SSD came out of an old Asus Aspire One netbook, which I'd put it in as part of an attempt to build a mobile GPS system, one of a couple of failed attempts that eventually ended up successful with the iPad, thus rendering the need for an SSD in the Aspire One obsolete. So I grabbed an old 160GB hard drive to put into the Aspire One to take the place of the SSD, and imaged it using the rescue disks that I'd purchased to put an image onto the SSD in the first place. Except it didn't boot. Okay, no big deal, I'll just haul a Windows XP rescue disk over there ... err... I don't happen to have one burned? No biggie, I'll just burn one. And since I have my beautiful Linux desktop sitting here, I'll just use that to do so.

So I pop the blank CD/RW disk into the Asus SATA CD/DVD writer, and attempt to burn it using the stock Brasero disk burner... and it's utter fail. Won't do it. In fact, locks up the system for 30 seconds because it locks up the SATA bus while not doing it. What the BLEEP?! So I go check Google, and it looks like Brasero has been broken on Fedora FOR YEARS, it'll write DVD's (sometimes) but CD's? No way! So I try a couple of other programs, and have similar results. Then I go down to the underlying 'wodim' program and again the same results. At that point I'm, like, "okay, maybe it's broken CD recorder hardware". So I pull out an external USB CD recorder drive -- one that I recently used on another system that doesn't have an internal DVD-RW drive -- and attempt to use that. Same result.

So maybe it's a bad disk? So I sling the disk into my MacBook Pro, erase it, and record it. It Just Works. As would have been the case, I'm 99% certain, if I had been trying to do this under Windows 7 -- it would have Just Worked.

And lest you think this is just my physical chunk of hardware and the particular version of Linux here at home, I have similar (lack of) success recording CD-R's at work on my Centos 6.3 desktop system. There, again, I have to record CD's on my MacBook Pro because Linux simply refuses to do it. Which infuriates me, because I could write CD's for *years* under Linux, but it's broken now, and nobody seems to care (at least, it's been broken in every release of Fedora since Fedora 10, which was, what, four years ago? Five years ago?), so ...

So let's recap: I can't view videos, I can't play music, and I can't burn CD-R's. I *can* do all of those things on Windows or MacOS. What Linux does well is serving data to networks. It does that very well, my Linux box serves as the Time Machine backup for my MacBook Pro as well as being the central data repository for the various Windows laptops I have hanging around. But the desktop? When it can't do simple desktop tasks that Windows and MacOS have done for literally years? Crack. That's my only explanation for why anybody would ever make a ludicrous statement like "this is the year of desktop Linux!" given the current state of Linux.

-ELG

This is the droid you're looking for

I have a new toy now. I ditched my aging iPhone 4 upon completion of its contract (and ported its number into Google Voice), and now have a brand new Samsung Galaxy S3.

So far it's mostly all good. Battery life is bad, but we already knew that. I tried several different home screen programs but I'm sticking with TouchWiz for now because the updated one for the Galaxy S3 works as well as anything else I tried, even the backported Jellybean launcher. It has lousy reception inside company HQ but so did the iPhone 4, just an AT&T thing I guess (my Verizon iPad has great reception inside company HQ). I'm still looking for a clean solution for automatically syncing my photos into iPhoto, but iSyncr is doing a reasonably good job of getting them onto my Macbook so I'm not too displeased.

Thus far I've found substitutes for everything I did on my iPhone except one: There is no good offline GPS program like the Magellan program that I used on the iPhone. Supposedly TomTom is going to be remedying that soon. We'll see.

So anyhow, I have found one bug in the Galaxy S3's ICS Android version: It does not handle exFAT very well. I found this out the hard way when my 64GB microSD card quit working and reported, "Damaged SD Card". Indeed, checking the Internet, it appears that random exFAT corruption is an epidemic on the Galaxy S3. This afflicts any microSD over 32GB, since Microsoft officially says FAT32 won't go over 32GB. This is, of course, a lie -- FAT32 is quite capable of handling terabyte-sized filesystems -- but because Microsoft enforces this limit in all their filesystem tools, nobody knew it was a lie until they actually looked at FAT32 and realized hey, this will work with bigger filesystems! (Though there is still that nasty 4GB limit on file size to contend with).

So how did I resolve this problem? First, I put the flash into a Windows 7 laptop and ran chkdisk on it. This found and fixed some problems. But when I put it back into the Galaxy S3 it *still* said "Damaged SD Card" despite the fact that Windows 7 said it was clean. So I resolved to reformat as FAT32. I copied the data off, and then had to go find a tool that would actually format a 64GB microSD card as FAT32 since the Windows disk manager won't do so: EaseUS Partition Master.

At that point it was just a matter of copying the data back on, which was very... very... slow since Windows operates SD cards in sync mode. As in, an hour slow. I know where the async flag lives in Windows and could have flipped it, but it was trash night so I did chores around the house instead. At the end of the process I inserted the microSD into the Sammy and... no more "Damaged SD Card".

Executive summary: If you buy a microSD card with greater than 32GB capacity, it is likely that it is formatted with Microsoft's proprietary exFAT filesystem and will not work well Android unless you reformat it, even if it appears to work correctly at first. exFAT support is not supported well because it is patented by Microsoft and thus does not have the magic of dozens of eyes of Open Source developers noticing and fixing bugs in it. So reformat it using the EaseUS tool above (NOT the internal Samsung formatter, it'll put the buggy exFAT filesystem back onto it) *before* you put stuff on it. Otherwise you'll be going through this whole time-consuming dance yourself sooner or later. Fun, it was not.

-ELG

Windows 8 and taste

One thing about most geeks that I've noticed: They have horrible taste. You can look at their homes, their clothes, their cars, the trinkets scattered about their cubicles, it's all a horrible mishmash of ugly. The way that Apple addressed this was via the Stalinesque concept of the Chief Designer. You may laugh at that description, but the Soviet-era Soyuz rocket and space capsule, designed under the supervision of Chief Designer Sergei Korolev, are still flying today fifty years after their design process began because he had exactly the same kind of qualifications as Apple's Chief Designer -- good engineering taste that balanced simplicity, cost, performance, and capability into a pleasing whole.

What brings this to mind is Windows 8, which I'm using to type this while eval'ing the RTM product. I'm not disclosing any NDA stuff here, it's pretty much the same product you downloaded earlier as the "Consumer Preview" with a few pieces of missing functionality filled in (and undoubtedly many bugs fixed). Windows 8 is Microsoft's attempt to re-invent the user interface, but fails primarily because of two reasons: A lack of courage, and a lack of that chief designer.

The lack of courage part is where Microsoft flinched at the notion of completely re-inventing the desktop. As a result, they have the "classic" desktop available by hitting a button on the "Modern" desktop. The end result is a bizarre mishmash of two different desktop environments in one, twice the amount of stuff to learn if you're a user because the "Classic" desktop environment doesn't *exactly* work the same as the well-known Windows 7 desktop environment, while the "Modern" desktop... well, it's entirely different, period. Twice the amount for end users to learn is user environment fail, period.

The lack of that chief designer, however, shows even more in the design of the "Modern" desktop. A good design is clean, looks simple (even if it isn't), everything's laid out in an obvious manner, there's a limited number of things for end users to learn in order to be productive, and, for lack of a better word, it is tasteful. It doesn't look like a mishmash of unrelated ideas from multiple independent teams all smashed together into one product.

That, however, doesn't describe the "Modern" desktop at all. One of the things I noted about Gnome 3 was that you had to basically know one gesture -- how to move your mouse pointer to the top left of the screen (or touch the top left of the screen on a touchscreen) -- to make it useful to you. Everything else is pretty obvious touch an icon or touch and drag an icon (or the click-on and click-on-and-drag with a mouse) or scroll up and down using the mouse wheel or two fingers. With the "Modern" desktop, every single corner of the screen does something -- and does something *different* (with the exception of the right-hand corners, which does something the *same*). Furthermore, moving to a corner, waiting for the hover timeout, then moving your mouse up and down does something even *different*. And right-clicking does something even *more* different. The confusing number of things you can do, indeed, need to know how to do to make the environment useful, are well past the three things you need to know how to do to use Gnome 3.

In essence, it's as if a bunch of geeks got together and decided to take every idea from every touchscreen environment ever created anywhere, and put them all into the same user interface. It's as if every geek critic of Gnome 3's tasteful design got together and designed their perfect touchscreen environment with every feature they could think of. It's as if Larry Wall designed the thing. Folks, Perl is many things, but clean and easy to use are not among those things -- it's an ugly, nasty, piece of work that will spit you in the eye if you look at it wrong just like the camel on the cover of the definitive book on the language. Like said camel it also happens to be very useful (thus why I wrote the virtualization management infrastructure for our virtualized product line in Perl, because it was the most reasonable way to parse the output of all the low-level virtualization-related utilities that the various virtualization systems use for their low-level management), but nobody has ever suggested that end users be given Perl as their user interface to their computers.

So the question is, will Windows 8 succeed? Well, define "success". The majority of personal computers in the world next year will ship with Windows 8 pre-installed. And because everything in post-Gates Microsoft is an API and Microsoft is quite open with their API's (Apple, not Microsoft, is the "Do Evil" company in the post-Gates era), sooner or later someone is going to come up with a means to tame this mess. But I have to say that Windows 8 is, in the end, a disappointment to me. Microsoft had an opportunity to re-define how personal computers worked, and they have all the pieces needed in Windows 8 to do so. They just needed a tasteful Chief Designer with the power to impose order and taste upon this mess -- and, alas, it appears they have no Jon Ives or Sergei Korolev to do so.

-ELG

Linux block layer, BTRFS, and ZFS On Linux

Long time no blog. Lately I've been stuck way down in the 2.6.32 kernel block device midlayer, both initiating I/O to block devices via the submit_bio interface, and also setting up a midlayer driver.

What I'm finding is that things are a bit of a mess in the 2.6.32 kernel when it comes to device pulls and device removals. When I chug down into the scsi midlayer I see that it's supposed to be completing all bios with -EIO, but there's still situations where when I yank a drive out of the chassis, I don't get all of my endios back with errors because of races in the kernel between device removal and device teardown. The net result is I have no idea what actually made it to disk or not. Note that you will NOT see this racy behavior on a normal system where the completion (almost) always wins the race, I was generating thousands of I/O's per second to 48 disks with CPU usage pretty much maxed out as part of load testing to see how things worked at the limits.

Now, that's no problem for my particular application, which is somewhat RAID-like, or for the Linux MD layer, or for single standalone block device filesystems for that matter. What's on the disk is on the disk, and when the standalone filesystem is remounted it'll know its state at that point by looking at the log. For the RAID type stacking drivers, when it comes back the RAID layer will note that its RAID superblock is out of data and rebuild the disk via mirror or ECC recovery, a somewhat slow process but the end result is a disk in known state. So when I get the disk removal event I mark the device as failed, quit accepting I/O for it, and mark all the work pending for that device that hasn't already endio'ed as errored, and if an endio sneaks in afterwards and tries to mark that work item again as errored, no big deal (although I put a check in the endio so that it simply noops if the work already was completed by the disk removal event). This means I have to keep a work pool around, but that's a good idea anyhow since otherwise I'd be thrashing kalloc/kfree, and if the drive comes back I'll re-use that pool again.

So traditional RAID and standalone devices don't have a problem here. Where a problem exists is with filesystems like btrfs and zfs that do replication on a per-file-block level rather than on a per-block-device-block level. If they can't log whether a block made it or not because they never got an endio, they can get confused. btrfs appears to err on the side of caution (i.e., assumes it didn't get replicated, and replicate it elsewhere if possible) but when the missing volume comes back and has that additional replica on it, strange things may happen. ZFSonLinux is even worse, since its SEL (Solaris Emulation Layer) appears to assume that bios always complete, and deadlocks waiting for bio's to complete rather than properly handle disk remove events. (Note that I haven't really gone digging into SEL, I'm basing this solely on observed behavior).

The good news: The popularity of btrfs among kernel developers appears to be motivating the Linux kernel team to fix this situation in newer kernels. I was chugging through the block subsystem in 3.5 to see if there was something that could be backported to make 2.6.32 behave a bit better here, and noticed some significant new functionality to make the block subsystem more flexible and robust. I didn't backport any of it because it was easier to just modify my kernel module to behave well with the default 2.6.32 behavior (I'm talking *extensive* changes in the block layer in recent kernels), but it appears that the end result is that btrfs on the 3.5 kernel should be *significantly* more reliable than the backported version of btrfs that Red Hat has put into their 2.6.32 kernel on RHEL 6.3.

So that's my recommendation: If you want to run btrfs right now, go with the latest kernel, whether it's on RHEL 6.3 or Fedora 17 or whatever. And you know the reason for my recommendation now. Red Hat has *not* backported any of those block layer changes back to RHEL 6.3, so what you have with btrfs on their stock 2.6.32 kernel is the equivalent of having a knight in shining armor that's missing the breast-plate. Sort of renders the whole exercise useless, in the end.

-ELG