Tag Archive for Oracle Corporation

Sun SPARC T3 Servers

Oracle announced their new line of Sun SPARC T3 powered servers at Oracle Openworld 2010. The SPARC T3 processor includes several improvements on T2 and T2+ processors including:

T2 / T2+T3
65 nm manufacturing process40 nm manufacturing process
4MB L2 Cache6MB L2 Cache
8 Cores (8 threads/core)16 Cores (8 threads/core)
8 Crypto Accelerators (1/core)16 Crypto Accelerators (1/core)
1 On Board PCIe x8 v1 Port2 On Board PCIe x8 v2 Ports

It is interesting to note that the T2 processor was only used in single socket systems. The T2+ processor removed the T2’s on board 10 GbE ports and other components to make room for the SMP glue. With the T3 processors, the 10 GbE ports have returned and the chip has built in glueless support for 4 way servers.

All in all they have packed more T-Series goodness in a smaller package but I’m not making goo-goo eyes yet.

For one, the smallest T3 based server, the T3-1, has the same number of threads as the T5140 but takes twice as many rack units. Although the T3-1 supports more PCIe cards and more internal hard disks, I would rather have a 1RU server or else have it support twice as much RAM.

The T3-2 server supports 256 threads. Compared to the T5440, it is actually smaller at 3RU and uses less power which sounds like a step in the right direction. Unfortunately, the T3-2 is also light on RAM supporting a maximum of 256GB compared to the T5440’s 512GB.

In short, The T3 series is a little off course for me at the moment. As a platform for consolidating tens of smaller applications, the thread to RAM ratio is too low making it hard to get 100% utilization out of these servers. With the T3-4 servers loading even more processing power into a single machine, the thread to machine ratio high as well. This is good if you are running a few really huge applications but if you are consolidating many smaller applications, you will not want to put this many eggs in one basket.

Vendor Lock-In or One Stop Shop

I was recently discussing load balancers with someone. I said I was much happier with F5 than I was with Cisco and he countered that although he preferred F5 head to head, going with Cisco for all the network was better for them in the long run.

The situation with storage is similar. EMC makes a great SAN but a pretty bad NAS. Is it worth getting EMC”s NAS for the One Stop Shop factor?

Since Oracle’s acquisition of Sun, I’ve been looking forward to the success of their “One Stop Shop” philosophy. Successfully bringing all their offerings under one roof promises better and faster support all around.

Unfortunately, it has been almost a year and Oracle is still not sure how they are to unify the customer support systems. New support contracts don’t work in either system.  To make things a little less clear, Oracle recently announced that everything will be migrated to “My Oracle Support” but they don’t know when- very reassuring.

A simple pattern emerges. One Stop Shop is a dream for IT people. Support is hard enough to get when you’ve isolated a problem to a specific vendor. It is even harder when your problems are between two vendors and each points the finger at the other.

When does the One Stop Shop strategy become a rationalization for Vendor Lock-In? It is a delicate balance around how much better your IT could be with Best of Breed vs. how much worse they will be integrating all the different pieces of the puzzle.

Regarding Cisco vs. F5, I’m also pretty happy letting Cisco handle everything Layer 3 and under and I don’t worry too much about the integration. I’m also optimistic regarding Sun and Oracle. I think they’ll have the wrinkles ironed out by the second half of 2011. If they don’t, it will be a serious let down.

EMC Fully Automated Storage Tiering

Storage Tiering is nothing new. We use fast 15K RPM disks for high performance applications, slower 10K RPM disks for less demanding applications, and 7.2K RPM SATA disks for archive storage. Recently, solid state disks (SSDs) have also become more common for really high performance needs. The trick is managing it all.

Two or three years ago, if you wanted to implement automatic storage tiering, I would have pointed you in the direction of Sun’s Storage and Archive Manager- SAM and QFS, Sun’s tightly integrated shared file system. SAM-QFS automatically moves files from one storage tier to another based on the SAM policy and transparently retrieves the files when requested. With tape still the least expensive storage available, this is still a great solution for archiving petabytes of documents/files.

Unfortunately, SAM works at the file level so it will not help our databases run faster. What will help us is ZFS. ZFS is still making some fairly big waves in the storage community with it’s Hybrid Storage Pool feature. In a standard configuration, ZFS uses RAM for a Layer 1 read cache (ARC).  In advanced configurations, the zpool can be configured to use a Layer 2 cache (L2ARC) on faster disks ie. SSDs compared to SAS compared to SATA , etc. The zpool can also be configured to use separate, possibly faster disks for the ZFS Intent Log (ZIL) which is basically a write cache (without getting into why it is more than a write cache). Even without faster disks, the ability to store the read/write cache on a separate device can increase performance just by dedicating more IOPS to the cause.

Oracle/Sun’s 7000 series storage builds on the success of the ZFS Hybrid Storage Pool, using Logzilla devices for the ZIL and Readzilla devices for the L2ARC. With the powerful flash acceleration in the storage pool, even 7.2K RPM disks can give performance equal to that of higher speed 15K RPM disks.

Although ZFS does great things for performance by utilizing multiple tiers of storage devices, all the data is still physically stored on the same tier of storage in addition to having the hot data stored again in the caches. This is arguably a waste of capacity but can also lead to performance issues in some cases. For example, a cold L2ARC cache after reboot could give slower performance until fully warmed up. Oracle will probably fix this at some point by allowing the L2ARC to persist if stored on a non-volatile device (bug_id=6662467).

In the meantime, EMC recently announced an interesting new feature called FAST, short for Fully Automated Storage Tiering. FAST is available from FLARE version FAST allows you to define a pool in the array composed of multiple RAID Groups, and then define a LUN on the pool as opposed to defining a LUN on the RAID Groups themselves. Once the LUN begins filling with data, the EMC will transparently begin transparently migrating data between the tiers of the pool in 1GB chunks, storing hot data on the fastest tiers and coldest data on the slowest tier.

FAST sounds like a dream come true. No more complicated storage configurations for the database. No more packages and processes to move historical data to slower disk groups. On the other hand, I am skeptical as to whether or not this technology is really mature. Do all EMC products treat the FAST LUNS the same as traditional LUNS (SnapView, Replication Manager, etc.) Also, are the ramifications of disk failures for a FAST LUN the same or does failure of a Tier 1 disk in a FAST pool mean alot more high performance eggs in one basket? Time will tell.

Sun Oracle Webcast Wrap Up

Last night I watched almost the entire 5 hour live webcast announcing Oracle’s strategies regarding the Sun Microsystems acquisition. As a near-evangelist for Sun and Solaris, I’m very happy with the deal finally going through and even happier that most of what Oracle said makes sense to me as a customer.

What I liked:

  • The clear commitment to the SPARC roadmap especially the T series. I honestly don’t know what I would have done if the T series servers disappeared. I’m very happy that they put raising the clock speed into the roadmap because some applications just can’t be deployed on these servers.
  • The clear commitment to making waves in Enterprise Storage. NetApp was specifically mentioned and obviously the 7000 series arrays are best suited to compete with the NetApp arrays but I hope they will draw some EMC blood as well. I like the plans for integrating backup capabilities.
  • The plans to integrate really great Solaris tech into Oracle applications like DTrace, and RBAC
  • The plans to offer direct support. Honestly this was one of the most annoying parts of working with Sun was having to work with different support providers in every location.
  • The plans to change the supply chain and ship direct- no more out of stock excuses.
  • The plans to integrate Ops Center with Oracle Enterprise Manager.
  • Larry Ellison’s stand up comedy
  • And completely unrelated- the flashing disk lights on the Exadata V2 🙂

I didn’t like:

  • The obvious cut planned for the x64 line of hardware. While they are keeping x64 where convenient (storage appliances, database machines, various other “clusters”) it looks like Oracle has no plans for dealing in x64 server business as a server business. I’m not a big user of the x64 stuff for servers but Sun doesn’t really offer anything reasonable for entry level anymore except the x64 line. This brings me to my next point-
  • The SPARC roadmap is slightly sucky as in how much processing power do you really want inside a single box.  According to the roadmap, their next plan is to double the amount of cores in a T3 processor so you’ll have one cpu with 16 cores and 128 threads. Their going to put two in a machine? four?  Here is how I see the servers they have today:
    • T1000- useless poorly designed server
    • T2000- ok server but a waste of rack space at 2RU
    • T5120- ok server but a waste of rack space considering I could put a T5140 in the same space
    • T5220- worse than the T5120 at 2RU
    • T5140- The best server ever built with exactly the right amount of everything
    • T5240- 2RU again???
    • T5440- I could serve ~8.64 billion web requests per day from one of these but I’d need a 1.6Gbit uplink and two servers for redundancy = 8RU, or else use 4 T5140 machines, deliver the same performance, and use 4RU?- maybe 5RU including n+1 redundancy.
    • NONEXISTANT – little SPARC machine for backup/monitoring/insert your SPARC only app that doesn’t deserve a minimum of 32 threads and 2RU  here.

    At some point, you just want more smaller machines for less points of failure. I really have uses for low end SPARC machines and they don’t make them any more.

  • I don’t really like the “server phone home” idea.
  • No mention of OpenSolaris- I’m not really a user but I didn’t like that it wasn’t mentioned- What does that mean??
  • No mention of Webstack. I really like Sun Webstack as an idea. I’m not sure what is happening to it now?
  • No mention of how Oracle will be combining the knowledge bases? Sunsolve? Bigadmin? docs.sun.com? forums.sun.com (looks like this already had an Oracle makeover :?)

One thing I’m not sure about is the integration of Sun virtualization technologies into Oracle VM. On one hand it sounds good, on the other hand, I think this was the only part of the presentation where I noticed there were no due dates. Virtualization is super important to me so I really want to know where things stand.

Obviously, it is easy to  get up and say everything will integrate but doing it is much harder. Just getting past the internal politics of this will be a major issue. Now we can only wait and see if Oracle can pull it off.

I used to get upset with “Oracle people” for always thinking that Oracle was the solution to every problem. If they pull off this acquisition, I much just become an “Oracle person” myself.

Real Time Reporting Databases

Reporting projects are the kind of projects which never seem to end. After a couple iterations I’ve come to the following conclusions:

  1. Absolutely no reports should run on a production database.
  2. Moving/aggregating data from a production database to a reporting database using ETL tools prone to synchronization issues and pretty unreliable.
  3. The best option is to set up real time replication of the data and build additional views on that.

Unfortunately, if you need to get data from heterogeneous databases, ie. Oracle, MySQL, SQL Server, etc. into a single reporting database, replication is not a simple solution. If you are running expensive database software in production, it may not be cost effective to run the same database for reporting.

Of course there are cross database replication solutions like Golden Gate or SharePlex but they are very expensive. I had already given up on getting data from Oracle into MySQL for reports when I stumbled across Tungsten Replicator.

According to the website, Tungsten Replicator provides open source database-neutral master/slave replication. Master/slave replication is a highly flexible technology that can solve a wide variety of problems including Cross DBMS Integration, ie. replication from Oracle to MySQL.

I’m looking forward to testing this product in the near future and I’d be happy to get anyone’s input if they’ve used it.