thinking sysadmin

Since Sun and Amazon removed the limit on the number of OpenSolaris 2008.05 instances able to run on EC2, I’ve been curious – and a little bothered – by the fact that the 2008.05 AMI is 32-bit only. Curious because OpenSolaris shouldn’t have any issues running on a 64-bit EC2 instance (there are other 64-bit OpenSolaris AMIs available on EC2, after all), and a little bothered because there have been long-standing reports of trouble running Solaris on 32-bit architectures, which makes me hesitant to invest much effort in a 32-bit OpenSolaris EC2 environment.

Well, perhaps a 64-bit AMI is forthcoming – I think this is still a beta program – and perhaps Sun’s just trying to save us a buck or two, since the cheapest 64-bit EC2 instance is four times as expensive per hour as the cheapest 32-bit instance.

• Less known Solaris Features: CacheFS – Joerg Moellenkamp at c0t0d0s0.org offers another installment of his excellent Less known Solaris Features series. Of note: “In the recent days there was some discussion about the declaration of the End-of-Feature status for CacheFS which will lead to the announcement of the removal of CacheFS. After a few days of discussion the ARC decided in favour of the removal.” While I’ve never personally used CacheFS – and see no use case for it on the horizon – I’m not thrilled to see it slated for removal as it does sound like it serves an important role. Perhaps ADM or SAM-QFS will become more general to support this style of HSM as well in the future.

• Prediction: Citrix will drop the open source Xen hypervisor for Hyper-V. The rest of the open source world drops Xen for KVM. – Lengthy speculation about the future of Xen now that Hyper-V is out. If this turns out to be correct, I think it leaves Sun in a particularly awkward spot, given that the work they’ve done on integrating Xen with Solaris. (Seen at virtualization.info and vinternals.)

Chuck’s got another, uh, thought-provoking blog post up, More Examples Of Why Server Vendors Just Don’t Get Storage, surely intended to ruffle a few feathers. And he does raise some really good points: Most server vendors need more of an SSD strategy than just making a flash drive an option (it’s how you use it, not that you have it!). And as big a fan as I am of ZFS and Sun’s storage options in general, to win in the “enterprise” (and not just, say, HPC) Sun needs to pull everything together into Solaris (from OpenSolaris) and make it less of a DIY operation.
Read the rest of this entry »

There’s been a lot of noise from the storage industry about flash recently – in particular, noise from EMC and Sun, both of whom recently announced storage products using flash, EMC in January and Sun earlier this month. Below are my thoughts on what EMC and Sun are doing, as well as what NetApp might do. Since I see a fair amount of visitors from all three companies here, if I’ve got something about your employer wrong, please correct me in the comments.
Read the rest of this entry »

• Adam Leventhal’s Weblog: Flash, Hybrid Pools, and Future Storage – Excerpts from a forthcoming ACM article on hybrid (flash-disk) storage pools, including: “Flash should be viewed not as a replacement for existing storage, but rather as a means to enhance it. [...] By combining the use of flash as an intent-log to reduce write latency with flash as a cache to reduce read latency, we can create a system that performs far better and consumes less power than other system of similar cost.” Which perhaps could be thought of as a dig at EMC’s flash implementation, although I doubt that’s how the author intended it. (Seen at c0t0d0s0.)

• Jonathan’s Blog: Anything But a Flash in the Pan – Jonathan Schwartz on Sun’s soon-to-be-released (late this year) flash drives. Quote: “ZFS will transparently incorporate Flash into the storage hierarchy of a running system, using the microprocessor cache for the most performance sensitive tasks, DRAM for the next, then Flash, then disk (then ultimately tape).” Speaking of tiered storage, I wonder how flash drives would work within a SAM-QFS implementation – and if SAM-QFS is destined to wither in the shadow of ZFS: Sure it’s open source now, but where is it going these days?

• Performance Isolation of a Misbehaving Virtual Machine with Xen, VMware and Solaris Containers – A paper comparing the ability of VMware (Workstation), Xen and Solaris Containers to isolate virtual machines from each other with regards to performance. Quick summary: VMware and Xen go one-two in protecting one virtual machine from another, and Solaris Zones lag far behind, a definite trade-off to consider if you’re inclined to use zones for their higher density. I would expect similar results to what was reported with Solaris if the authors had also looked at OpenVZ and FreeBSD Jails – in fact, (anecdotally) I’ve seen generally the same behavior with OpenVZ and Jails, although OpenVZ does give you a lot of knobs to adjust (if performance isolation is a concern for you with OpenVZ, you may want to look at all the options it gives you before making decisions about its suitability). It would have been nice to see more details about the Solaris configuration used in the paper, and to have had the work repeated with a recent OpenSolaris build – substantial work appears to be being done in this area (for example, Improved Resource Management and Zones Integration). Seen at blog.scottlowe.org.

Generally, I’m a fan of Sun Microsystems. For the most part, I like their hardware and their software – and their best products show real innovation and willingness to take risks. I’m also a fan of Amazon’s EC2 product, so the announcement that Sun would be officially bundling OpenSolaris for EC2 was great news. Unfortunately, it seems that after all the hullabaloo, Sun doesn’t really want to make it that easy for you to actually use OpenSolaris on EC2, by managing access to it like a control freak would.
Read the rest of this entry »