Entries by Joerg Moellenkamp

There is a new version of the Logical Domains available. The version 1.2 of the LDOMs gives you some new interesting features. You can download it here. The Release Notes for 1.2 are available at docs.sun.com. To give you a short overview to the new features, i´ve extracted the relevant passages out of the documentation:

• Support for CPU power management.
• Support for jumbo frames. The Logical Domains virtual switch (vsw) and virtual network (vnet) devices can now support Ethernet frames with payload sizes larger than 1500 bytes. This change results in these drivers being able to increase network throughput.
• Restriction of delayed reconfiguration operations to the control domain. The Logical Domains Manager 1.2 software restricts delayed reconfiguration operations to the control domain. For all other domains, you must stop the domain to modify the configuration unless the resource can be dynamically reconfigured.
• Support for configuring domain dependencies. You can use the Logical Domains Manager to establish dependency relationships between domains. A domain that has one or more domains that depend on it is called a master domain. A domain that depends on another domain is called a slave domain. Each master domain can specify what happens to its slave domains in the event that the master domain fails. For instance, if a master domain fails, it might require its slave domains to panic. If a slave domain has more than one master domain, the first master domain to fail triggers its defined failure policy on all of its slave domains.
• Support for autorecovery of configurations. Starting with the Logical Domains 1.2 release, a copy of the current configuration is automatically saved on the control domain whenever the Logical Domains configuration is changed. This autosave operation enables you to recover a configuration when the configurations that are saved on the SP are lost. This operation also enables you to recover a configuration when the current configuration was not explicitly saved to the SP when the system powercycled.
• Support for export of same backend multiple times. A virtual disk backend can be exported multiple times either through the same or different virtual disk servers. Each exported instance of the virtual disk backend can then be assigned to either the same or different guest domains. When you mount such devices read/write on two different paths, the applications have to enforce the consistency. Without such means mounting r/w from different locations is a sure way to the tapes
• API to support LDMD discovery. Logical Domains Managers can be discovered on a subnet by using multicast messages. The ldmd daemon is able to listen on a network for a specific multicast packet. If that multicast message is of a certain type, ldmd replies to the caller. This enables ldmd to be discovered on systems that are running Logical Domains.
• Support for physical-to-virtual migration tool. The Logical Domains P2V Migration Tool automatically converts an existing physical system to a virtual system that runs in a logical domain on a chip multithreading (CMT) system. The source system can be any of the following:
  • Any sun4u SPARC system that runs at least the Solaris 8 Operating System
  • Any sun4v system that runs the Solaris 10 OS, but does not run in a logical domain
  
  


• Support for configuration assistant tools.
  The Logical Domains Configuration Assistant leads you through the configuration of a logical domain by setting basic properties.



• Bug Fixes

The integrated memory controller of the Intel Xeon 5500 series has some limitations: It runs at 1333 MHz with one DIMM per channel, it runs at 1033 MHz with two DIMMS per channels and with 800 MHz with 3 banks per channel. With Nehalem you can have either speed or memory size but not both. The limits are enforced by the system as soon as you put the DIMMS into the system.

But the Sun X2270, x4170, x4270 x4275 and x6270 have a special capability. The systems were designed to enable a stable operation at 1333 MHz with 2 DIMMS per channel. The newest versions of the BIOS gives you the option to enable this mode of operation. You will find more informations about this in John´s blog article "Update to: Configuring and Optimizing Intel® Xeon Processor 5500 & 3500 Series (Nehalem-EP) Systems Memory". The BIOS updates are available at www.sun.com (Sun Fire X4170/X4270/X4275 Software 2.0, Sun Blade X6270 Software 2.0 and Sun Fire X2270 2.0.0)

There are two upcoming public presentations in the next time: Both are in german language. At first i will hold a "Insights to Solaris" presentation at the 10 years UURGN event at July, 4th on Saturday.

The other one is my webinar about "Less known Solaris Features" on July, 8th. You can still register for this event at the Sun website.

Glenn published the first public version of the OpenSolaris Immutable Service Containers. This is an really interesting concept. This concept use containers to isolate application. This isn´t something new, but the way it´s done here, is really cool:

In an ISC configuration, the global zone is treated as a system controller and exposed services are deployed (only) into their own non-global zones. From a networking perspective, however, the entire environment is viewed as a single entity (one IP address) where the global zone acts as a security monitoring and arbitration point for all of the services running in non-global zones.

PS: Glenn, i didn´t found the time to check ISC as promised by twitter out of the same reason there aren´t many blog postings at the moment, sorry. But´s still on my ToDo-list.

Soviel zum Thema Kompetenz zum Thema Computersicherheit: Herr Schünemann sitzt vor einem Rechner des LKA. Achtet mal auf den Monitor. Ich vermute das ist ein DemoPC, aber trotzdem: Sowas macht man nicht ...

Jeff Savit wrote an interesting article about theVirtual SMP functionality of VirtualBox 3:

This is a really big step. Now you can host guests with up to 32 virtual CPUs on machines with VT-X or AMD-V. Think of all the work that had to be done to provide architecturally consistent CPU and memory in the virtual machine while dispatching virtual CPUs. This affects locking and atomic memory semantics, CPU scheduling to prevent starvation - a lot of things to think about and implement. I may wind up eating my words, but 32 virtual CPUs ought to be enough to handle most people for a very long time.

After getting some comments at Facebook, Twitter and ICQ, i have to give you a pledge: I will never, never title an article in my blog just with the line "Farewell". Especially not in this times.

Yesterday Sun released Virtualbox 3.0.0. You can download at the usual location. A changelog is available at the website as well.

Just saw the honour guard for the last flight of an Airbus A300 departing in Hamburg. The Lufthansa stops to use this type of aircraft after several years of service on July, 1st. This A300 is the last one in active service. It will depart the last time with passengers tomorrow from Rome.

Just arrived at the airport in Stuttgart. I have a presentation at the Solaris Day 09 this afternoon: It´s a renewed version of an presentation about the "Less known Features of Solaris" again. I´m just taking a fast coffee and i´m looking for the travel directions at the website at the moment.

Manchmal finde ich es dann doch erstaunlich, wie wenig Ahnung manche Leute der Blogosphäre ausserhalb ihres Fachgebietes von der praktischen Seite der IT haben: Schönes Beispiel ist hier Fefe:

Die RAM-Hersteller (wahrscheinlich nur die chinesischen, nehme ich mal an) lassen ihre RAMs durch die Qualitätsprüfung fahren, und die RAMs, die das überstehen, die gehen in den Export nach Amerika und Europa, und die anderen verscheuern sie dann billig in den Schwellenländern, wo die Leute sich die Export Grade RAMs nicht leisten könnten.

Und wenn ihr das hört, dann denkt mal darüber nach, dass RAMs ja auch in embedded Computern drin ist, wie sie aus China kommen. Man muß da gar nicht über medizinische Geräte oder Reaktorsteuerungen nachdenken, um ein schlechtes Gefühl zu kriegen.

Also, Fefe ... das nennt sich Yield Management und das macht jeder. Nicht nur der Chinese. Oder meinst Du, irgendjemand wirft 90% des Wafers weg, weil die Dies nicht perfekt sind?

Schönes Beispiel ... Prozessoren. Es werden da eigentlich nur die Topprozessoren gefertigt. Das Dumme ist nur: Chipfertigung dauert lange (mehrere Wochen von Waferstart bis Ende), es gibt Fertigungstoleranzen, unterschiedliche Kontaminationen in der Umgebung und das heisst soviel wie. Alle Dies haben eine leicht unterschiedliche Qualität. Alles was den Topqualität nicht besteht, wird einfach dann eingestuft in eine andere Qualitätsstufe. Wird im Volksmund auch Taktung genannt. Wo nen Core kaputt ist ... wird ein TripleCore draus. Für die Leute auch in den Industrieländern, die sich keinen Topprozessore leisten können. Das schöne ist: So kann man mehr vom Wafer verkaufen und hat ein abgestuftes Preismodell. Die nicht ganz so guten Cores zahlen den Wafer, die guten Cores den Gewinn.

Interessanterweise gilt: Je ausgereifter ein Prozess wird, desto weniger Schraddel produziert man. So passiert es oft, das man nicht genügend Schraddel hat, um den Markt zu decken. Was macht man also, man stuft eigentlich bessere Komponenten herunter, um den Bedarf zu bedienen. Bei CPUs und Speicher wird das dann oft als Übertaktungspotenzial genannt, ist aber aber eine Konsequenz aus dem Yield Management. Es ist also wahrscheinlich, bessere Qualität zu erhalten, als eigentlich gekauft.

Im Speicherbereich ist es das selbe: Man bekommt Speicher in "extrem gut, kaum Alterungserscheinungen,nahezu perfekt" über "haelt für normalen Haushaltsgebrauch im PC" bis hin zu "Läuft stabil bei halbiertem Takt". Letzteres verkauft man dann in Anwendungen wie Embedded, wo die hohen Anforderungen von PC-Speicher nicht gestellt werden und Speicher weit unterhalb von seiner Spezifikation läuft.

Klar gibt es da dann immer wieder Leute die noch mal nen Euro oder Yuan sparen wollen, und sich dann über ultrabilligen PC-Speicher freuen, auf dessen Platinen dann irgendeine Hinterhofwerkstatt den Niedrigqualitätsspeicher geloetet hat.

Und mal ganz ehrlich: Das was wir üblicherweise in PC hier in Europa als Speicher stecken, ist auch nur der Mittelqualitätsschraddel.

Wirkliche Spitzenqualität kostet mehr ... sehr viel mehr. Nur das passt nicht mehr ins Preisgefüge eines x86 und oftmals auch nicht in das Preisgefüge eines x86 Servers. Das ist dann eher für Leute, die sich Gedanken darüber machen müssen, das man in einigen Jahren noch Speicher austauschen kann, und der benutzte Speicher nicht soweit aus der Toleranz gelaufen ist, das er mit neuem Speicher nicht mehr laufen kann.

Ich denke nicht, das man da verwundert tun muss. Das ist Business-as-usual.

The nice thing about Perl is the point, that there is always someone who has solved the problem you have at the moment. Yesterday i had the idea to put all articles in an addtional category based on their language as this is an bilingual blog. With a article count heading towards 6000, a manual process to do so, was out of question. Thus i´ve searched for an automatic way to do this. After googling for the problem i found the Lingua::Identify module. The usage of the module made the rest easy. The following script puts articles in a Serendipity-based blog in a category based on the English. 41 is the category ID for English articles, 42 is the category for articles in German. Interestingly articles with many HTML tags are frequently identified as written in Danish.


#!/usr/bin/perl

use Lingua::Identify qw(:language_identification);
use DBI;

my $dbh = DBI->connect( "DBI:mysql:databasename","username","password") || die "Database connection not made: $DBI::errstr";

my $sql = qq{SELECT id,body FROM serendipity_entries};
my $sth = $dbh->prepare($sql);
$sth->execute();
while(@ergebnis=$sth->fetchrow_array)
{
$id=$ergebnis[0];
$body =$ergebnis[1];
$lang =langof($body);
if (($lang ne "en") and ($lang ne "de")) {
next;
}
$cat=41 if $lang eq "en";
$cat=42 if $lang eq "de";
print "INSERT INTO serendipity_entrycat(entryid,categoryid) values($id,$cat);\n";
}

$sth->finish();
$dbh->disconnect();


Neben Kinderpornographie, Raubkopieren wird das Internet jetzt auch noch für den Zusammenbruch der Demokratie verantwortlich gemacht. Denn jetzt wird gemutmasst, das die Veröffentlichung von Nachrichten auf Twitter zur Ungültigkeit einer Wahl führen könnte. Naja ... nach der Zensursula-Nummer könnte ich mir jetzt auch lebhaft vorstellen, das man auch Wahlnachrichten der Netzsperre unterwirft.

... you don´t need enemies. Sun has a good working relationship with Intel. Thus i would expect better articles like this one at the Server Room Blog. While i understand that a Intel guy wants to pitch the processors of his employer, i don´t understand why he talks about Solaris and AIX, when he really wants to say SPARC and Power. Okay, Power and AIX are dependent from each other.

But you can run Solaris at x86 as well and it runs especially well on Nehalem based systems. Ken Lloyd does the mistake of many people by thinking about Solaris: Thinking about SPARC when thinking about Solaris and connecting Linux with x86. When your cost structure mandates x86 your could easily use Solaris as well.

It´s the same RedHat tries to tell you: Obviously Linux on a brand new Xeon is cheaper when you compare with Solaris on an old E250 Server.

Ken writes:

It is reasonable to say Xeon can deliver better performance, better value, and equal or better reliability

I would like to answer to this quote with a quote of Jonathan Heiliger, the vice president of technical operations for Facebook:

The biggest thing ? was less-than-anticipated performance gains from new microarchitectures, so new CPUs from guys like Intel and AMD. The performance gains they're touting in the press, we're not seeing in our applications," Heiliger told the audience.

As the GHz race has ceased and the Intel/AMD fraction goes into multicores as well, they run in pretty much the same problem as Sun since 2005. Not every customers application is multicore friendly. And by the way:The Nehalem just got in the same range of per socket performance like the UltraSPARC T2 processor, a processor that hit the market in 2007. Does Ken really thinks that we don´t develop a successor to UltraSPARC T2? When you look at performance of SPARC just look at the SPARC64 VIIIfx.

10 GBit/s or crypto acceleration on die has to be seen on Intel procs ... so much to the "value" moniker. And Xeon is nowhere near to UltraSPARC T or even SPARC64 VII in term of reliability.

By the way: I find this reliability discussion on CPU basis really funny. Reliability is a systemic property, not a component property. Even the best CPU is helpless, when the system around it doesn´t hold to the standards of the CPU. A CPU can´t work in a reliable way, when you just put the cheapest memory from the spot market into the system.

The mentioned Machine Check Architecture architecture mentioned in the blog entry is just a reporting system of errors (something SPARC, Power and all the other RISC architectures do since the last century). It needs the OS to react on the error. So the dismissal of Solaris is really strange,too: Linux doesn´t have something like the Fault Management Architecture of Solaris, but you need exactly something like the FMA to take advantage of MCA.

Ken, the managers you mention as those negelecting the business aren´t idiots. They just don´t believe everything Intel, the Linux business and the media tries to implant in their mind without questioning everything. At last your article is just a good example for marketing piece trying to pitch the products of your employer by repeating the same stuff again and again. But that doesn´t make it true.