c0t0d0s0.org

27 und der Rest von heute ....

Interesting benchmark between GCC and GCCfss. GCCffs is a GCC compatible frontend with Sun Studio backend. Up to 65% more floating point performance gives you a nice boost in your applications. You should give it a try.

One of the hurting annoyances of ZFS was the problem, that Samba wasn´t able to set and get ZFS access control lists. This even led to a lost project in one of my accounts. But the end of the suffering is near: 2149388 - Samba ACL interaction with NFSv4 and ZFS does not work - fix delivered or 6576479 - Handling of the special ace's in samba vfs module vfs_zfsacl need fix - fix delivered

Nice presentation of the usage of mirror mounts and referals in upcoming releases of NFSv4 in Opensolaris.

Today is System Administrator Appreciation Day. Without them there would be only black on all the screens around you.

The Register reports (speculates) about the upcoming releases of Niagara II and later Rock:Sun preps 2048-thread monster. It´s hard to keep thinks secret, when you write and open-source the code to support your new gear. I won´t comment the speculations of the new systems. But they will be available on time

Ich habe heute eine Einladung zu einem Abi-Treffen nach 15 Jahren bekommen. Interessant zu sehe, welche Geschichten die einzelnen Mailaddressen erzählen, oder die einzelnen Mailaddressen kommen, das viele anscheinend immer noch im Dunstkreis der Heimat sind, das sich bei den meisten Frauen des Jahrgangs der Nachname dem Anscheine nach nicht geändert hat (passt zu meiner Beobachtung im Freundeskreis, das die Namenänderung mittlerweile unüblicher wird, hab das schon für eine Anomalie gehalten) leider wenige Firmenaddressen dabei (bin ja so garnicht neugierig). Ich überlege noch, ob ich hinfahre ... mal gucken ....

I´ve reported about the separated ZIL a few days ago. The problem of the described NVRAM PCI card is, that you can´t do a clusterfailover with such a device. How do you want to failover the seperate log, when the log is on a card in the failed server? Sun had a product called Prestoserve, that was used to accelerate NFS and DB. It was static RAM with a battery. It was great for benchmarks, but suffered by the cluster problem.

Thus you should use some external device, that can failover with the rest of your storage. The obvious choice would be a RAM-based Solid State Disk(SSD). But these are quite expensive: You need the RAM, you need a harddisk to keep the data persistent when power fails, and you need a rechargeable battery or an capacitor that´s able to power the SSD until all data is written to the hard disk.

A Flash-Based SSD would be a more sensible choice, as Flash is a non-volatile memory by nature. Such a disk costs you approximatly 400$. But most people think "Oh no, wear will destroy it within a few days". Experiences with el-cheapo CF-cards underline this assumption.

But let´s calculate with the specifications of a leading brand flash disk. Let´s assume: A 32 GB flash-based SSD is specified for 2.000.000 write cycles. We have a sustained stream of 40 MB per second (conservative assumption). The wear leveling is perfect (perhaps supported by a seperate ZIL algorithm, that looks at the flash SSD as a cyclic buffer). Okay, a little math:


So this flash SSD wouldn´t fail by wear within the usable live of the storage and the server, even when you write 40 MB every second to it. I´m sure, that a flash disk doesn´t run such a long time, but this is not a wear problem, it´s the problem, that modern electronic hasn´t the build quality of former times.

Based on this considerations, a flash SSD would be an interesting choice for the separated ZIL. Or at least: Wear isn´t a reason for not using Flash SSD

PS: There is one point, i´m not perfectly sure, but i interpret the 2 million write cycles as the ability to erase and write the full disk 2 million times.

Since a few month i synced teasers for the articles in my main blog automatically to my blog at blogs.sun.com. I decided to make a full sync. You can read the complete articles in the b.s.c-log now

Ich habe gerade über das Vielfliegerblog eine interessante Pressemitteilung gefunden: Introducing the Qantas A380. Ich frag mich da insbesondere bei der First Class, ob das Teil ein Flugzeug oder ein fliegendess Hotel wird:

The design of our First cabin has evolved over five years to culminate in a layout of 14 private suites, each featuring a 17 inch LCD wide screen video monitor, an array of personal stowage options, a unique touch screen control unit and a seat - manufactured by B/E Aerospaces's VIP jet group - that swivels into a comfortable armchair and a fully flat, extra long and very wide bed.

From time to time the products of your own company are can surprise you a little bit. Rolf Kersten published on his systems hero portal a photo of an sight to behold. But a sight, nobody wants to see. A sight to get a stroke and a cardiac arrest at the same time.

The fascinating fact: All systems worked without problems. The administrator wasn´t able to find out, when this "catastrophic raised floor malfunction" occured, as there wasn´t even a reboot. At the end there was only one victim at this event: a single, unfortunate hard disk. Sun Server - build to last!

Was macht Darth Vader in seiner Freizeit? Ja, genau !