Search Results

Search found 13151 results on 527 pages for 'performance counters'.

Page 241/527 | < Previous Page | 237 238 239 240 241 242 243 244 245 246 247 248  | Next Page >

• How do I send traffic from my Mac's wifi to my VPN client?

  - by Heath Borders

  I need to connect my Android to a Juniper VPN. Unfortunately, Juniper doesn't support Android on our VPN version. We've already put in a feature request for it, but we have no idea how long it will take to be complete. Right now, I connect to the Juniper VPN with a Juniper Mac OSX VPN client that uses Java to install kernel extensions to start and stop the VPN. Thus, I can't use the Network panel in System Preferences to create a VPN device, which means it won't show up in the 'Sharing' panel's Internet Sharing Share your connection from: menu, as suggested here. I used newproc.d to see what /usr/libexec/InternetSharing did when it ran, and it runs the following processes: 2013 Nov 1 00:26:54 5565 <1> 64b /usr/libexec/launchdadd 2013 Nov 1 00:26:55 5566 <1> 64b /usr/libexec/InternetSharing 2013 Nov 1 00:26:56 5568 <5566> 64b natpmpd -d -y bridge100 en0 2013 Nov 1 00:26:56 5569 <1> 64b /usr/libexec/pfd -d 2013 Nov 1 00:26:56 5567 <5566> 64b bootpd -d -P My Juniper VPN client creates the following devices (output of ifconfig): jnc0: flags=841<UP,RUNNING,SIMPLEX> mtu 1400 inet 10.61.9.61 netmask 0xffffffff open (pid 920) jnc1: flags=841<UP,RUNNING,SIMPLEX> mtu 1450 closed So, it seems like I should just be able to do this and have everything work: sudo killall -9 natpmpd sudo /usr/libexec/natpmpd -y bridge100 jnc0 My android connected fine and could hit public internet sites, but it couldn't hit private VPN sites. I assume this is because I need to change the routes that /usr/libexec/InternetSharing sets up. This is the output from sudo pfctl -s all before starting Internet Sharing: No ALTQ support in kernel ALTQ related functions disabled TRANSLATION RULES: nat-anchor "com.apple/*" all rdr-anchor "com.apple/*" all FILTER RULES: scrub-anchor "com.apple/*" all fragment reassemble anchor "com.apple/*" all DUMMYNET RULES: dummynet-anchor "com.apple/*" all INFO: Status: Disabled for 0 days 00:11:02 Debug: Urgent State Table Total Rate current entries 0 searches 22875 34.6/s inserts 1558 2.4/s removals 1558 2.4/s Counters match 2005 3.0/s bad-offset 0 0.0/s fragment 0 0.0/s short 0 0.0/s normalize 0 0.0/s memory 0 0.0/s bad-timestamp 0 0.0/s congestion 0 0.0/s ip-option 12 0.0/s proto-cksum 0 0.0/s state-mismatch 1 0.0/s state-insert 0 0.0/s state-limit 0 0.0/s src-limit 0 0.0/s synproxy 0 0.0/s dummynet 0 0.0/s TIMEOUTS: tcp.first 120s tcp.opening 30s tcp.established 86400s tcp.closing 900s tcp.finwait 45s tcp.closed 90s tcp.tsdiff 60s udp.first 60s udp.single 30s udp.multiple 120s icmp.first 20s icmp.error 10s grev1.first 120s grev1.initiating 30s grev1.estblished 1800s esp.first 120s esp.estblished 900s other.first 60s other.single 30s other.multiple 120s frag 30s interval 10s adaptive.start 6000 states adaptive.end 12000 states src.track 0s LIMITS: states hard limit 10000 app-states hard limit 10000 src-nodes hard limit 10000 frags hard limit 5000 tables hard limit 1000 table-entries hard limit 200000 OS FINGERPRINTS: 696 fingerprints loaded This is the output from sudo pfctl -s all after starting Internet Sharing: No ALTQ support in kernel ALTQ related functions disabled TRANSLATION RULES: nat-anchor "com.apple/*" all nat-anchor "com.apple.internet-sharing" all rdr-anchor "com.apple/*" all rdr-anchor "com.apple.internet-sharing" all FILTER RULES: scrub-anchor "com.apple/*" all fragment reassemble scrub-anchor "com.apple.internet-sharing" all fragment reassemble anchor "com.apple/*" all anchor "com.apple.internet-sharing" all DUMMYNET RULES: dummynet-anchor "com.apple/*" all STATES: ALL tcp 10.0.1.32:50593 -> 74.125.225.113:443 SYN_SENT:CLOSED ALL udp 10.0.1.32:61534 -> 10.0.1.1:53 SINGLE:NO_TRAFFIC ALL udp 10.0.1.32:55433 -> 10.0.1.1:53 SINGLE:NO_TRAFFIC ALL udp 10.0.1.32:64041 -> 10.0.1.1:53 SINGLE:NO_TRAFFIC ALL tcp 10.0.1.32:50619 -> 74.125.225.131:443 SYN_SENT:CLOSED INFO: Status: Enabled for 0 days 00:00:01 Debug: Urgent State Table Total Rate current entries 5 searches 22886 22886.0/s inserts 1563 1563.0/s removals 1558 1558.0/s Counters match 2010 2010.0/s bad-offset 0 0.0/s fragment 0 0.0/s short 0 0.0/s normalize 0 0.0/s memory 0 0.0/s bad-timestamp 0 0.0/s congestion 0 0.0/s ip-option 12 12.0/s proto-cksum 0 0.0/s state-mismatch 1 1.0/s state-insert 0 0.0/s state-limit 0 0.0/s src-limit 0 0.0/s synproxy 0 0.0/s dummynet 0 0.0/s TIMEOUTS: tcp.first 120s tcp.opening 30s tcp.established 86400s tcp.closing 900s tcp.finwait 45s tcp.closed 90s tcp.tsdiff 60s udp.first 60s udp.single 30s udp.multiple 120s icmp.first 20s icmp.error 10s grev1.first 120s grev1.initiating 30s grev1.estblished 1800s esp.first 120s esp.estblished 900s other.first 60s other.single 30s other.multiple 120s frag 30s interval 10s adaptive.start 6000 states adaptive.end 12000 states src.track 0s LIMITS: states hard limit 10000 app-states hard limit 10000 src-nodes hard limit 10000 frags hard limit 5000 tables hard limit 1000 table-entries hard limit 200000 TABLES: OS FINGERPRINTS: 696 fingerprints loaded It looks like I need to change the pf settings that /usr/libexec/InternetSharing set up, but I have no idea how to do that.

  Read the article

• Difference in Ubuntu One sync-speed between Natty and other versions?

  - by bisi

  I was wondering if anyone had had the chance to compare performance between Ubuntu One upload speeds on Natty Narwhal and any other version of Ubuntu? Also, any difference on how well it connects? [don't shoot me for asking ;)] I am hesitant about upgrading on my regular workstation, but if it improves my user-experience with U1, I might be willing to risk it... Thanks for all informed opinions :) bisi

  Read the article

• Python Forgiveness vs. Permission and Duck Typing

  - by darkfeline

  In Python, I often hear that it is better to "beg forgiveness" (exception catching) instead of "ask permission" (type/condition checking). In regards to enforcing duck typing in Python, is this try: x = foo.bar except AttributeError: pass else: do(x) better or worse than if hasattr(foo, "bar"): do(foo.bar) else: pass in terms of performance, readability, "pythonic", or some other important factor?

  Read the article

• Alachisoft’s new version of NCache announced at TechEd !

  - by Latest Microsoft Blogs

  Before coming to Microsoft I owned a consulting company that specialized in solving performance and scalability problems in web applications. It always amazed me how many seeming huge problems could be solved with a little strategic caching implementation Read More......(read more)

  Read the article

• TSAM 11gR1

  - by todd.little

  The Tuxedo System and Application Monitor (TSAM) 11gR1 release provides powerful new application monitoring capabilities, as well as significant improvements in ease of use. The first thing users will notice is the completely redesigned user interface in the TSAM console. Based on Oracle ADF, the console is much easier to navigate, provides a Web 2.0 style interface with dynamically updating panels, and a look and feel familiar to those that have used Oracle Enterprise Manager. Monitoring data can be viewed in both tabular and graphical form and exported to Excel for further analysis. A number of new metrics are collected and displayed in this release. Call path monitoring now displays CPU time, message size, total transport time, and client address giving even more end-to-end information about a specific Tuxedo request. As well the call path display has been completely revamped to make it much easier to see the branches of the call path. The call pattern display now provides statistics on successful vs failed calls, system and application failures, and end-to-end average elapsed time. Service monitoring now displays minimum and maximum message size, CPU usage, and client address. System server monitoring now includes monitoring the SALT gateway servers to provide detailed performance metrics about those servers. Perhaps the most significant new feature is the consolidation of alert definitions and policy management. In previous versions of TSAM, some alerts were defined and checked on the monitored systems while others were defined and checked in the console. Policy management could be performed on both the monitored node via environment variable or command, as well as from the console. Now all alert definitions and policy definitions are only made using the console. For alerts this means that regardless of where the alert is evaluated it is defined in one and only one place. Thus the plug-in alert mechanism of previous releases can now be managed using the TSAM console, making SLA alert definition much easier and cleaner. Finally there is support in TSAM for monitoring rehosted mainframe applications. The newly announced Oracle Tuxedo Application Runtime for CICS and Batch can be monitored in the TSAM console using traditional mainframe views of the application such as regions. Look for a future blog entry with more details on this as well as some entries providing a glimpse of the console. TSAM gives users a single point for monitoring the performance of all of their Tuxedo applications.

  Read the article

• Make the Web Fast: Google Web Fonts - making pretty, fast!

  Make the Web Fast: Google Web Fonts - making pretty, fast! Join us for a technical deep-dive on Web Fonts: how they work, the data formats, performance optimizations, and tips and tricks for making your site both fast and pretty at the same time - turns out, these two goals are not mutually exclusive! From: GoogleDevelopers Views: 468 69 ratings Time: 01:11:43 More in Science & Technology

  Read the article

• Http 400 'Bad Request' and win32status 1450 when larger messages are sended to a WCF service

  - by Tim Mahy

  Hi all, we sometimes receive Http 400 bad request resultcodes when posting a large file (10mb) to a WCF service hosted in IIS 6. We can reproduce this using SOAP UI and it seems that it is unpredictable when this happens. In our WCF log the call is not received, so we believe that the request does not reach the ASP.NET nor WCF runtime. This happens on multiple websites on the same machine each having their own application pool. All IIS settings are default, only in ASP.NET and WCF we allow bigger readerQuota's etc.... The win32status that is logged in the IIS log is 1450 which we think means "error no system resources". So now the question: a) how can we solve this b) (when a is not applicable :) ) which performance counters or logs are usefull to learn more about this problem? greetings, Tim

  Read the article

• Don’t Miss The Top Exastack ISV Headlines – Week Of May 26

  - by Roxana Babiciu

  Calypso Technology announced that Calypso version 14 has achieved Oracle Exadata Optimized status through OPN. In simulations of data-intensive straight through-processing tasks, Calypso achieved performance gains of up to 500% using Exadata hardware – Read more Infosys achieves Oracle SuperCluster Optimized status with Finacle, a core banking solution. Finacle can process 6x the volume of transactions currently processed by the entire US banking system – Read more

  Read the article

• Paper on Linux memory access techniques sought

  - by James

  Over on stackoverflow someone posted a link to a paper written by a Linux kernel engineer about how to use computers and RAM. He started off by explaining how RAM works (right down to the flip-flops) and then went on to discuss performance problems associated with operations on matrices (column vs row accesses), offered solutions and then dealt with some stuff MMX instructions can do. Sorry it's a bit vague but I can't find it anywhere. I think the guy had a Scandinavian name, possibly Anders

  Read the article

• Ceph: open-source petabyte scale distributed storage

  - by Gregory Burd

  You might want to read this interesting research paper titled "Object Storage on Berkeley DB". The Ceph project is a distributed network file system designed to provide excellent performance, reliability, and scalability... and it uses Oracle Berkeley DB for storage.

  Read the article

• Digital Storage for Airline Entertainment

  - by Bill Evjen

  by Thomas Coughlin Common flash memory cards The most common flash memory products currently in use are SD cards and derivative products (e.g. mini and micro-SD cards) Some compact flash used for professional applications (such as DSLR cameras) Evolution of leading flash formats Standardization –> market expansion Market expansion –> volume iNAND –> focus is on enabling embedded X3 iSSD –> ideal for thin form factor devices Flash memory applications Phones are the #1 user of flash memory Flash memory is used as embedded and removable storage in many mobile applications Flash memory is being used in computers as USB sticks and SSDs Possible use of flash memory in computer combined with HDDs (hybrid HDDs and paired or dual storage computers) It can be a removable card or an embedded card These devices can only handle a specific number of writes Flash memory reads considerably quicker than hard drives Hybrid and dual storage in computers SSDs can provide fast performance but they are expensive HDDs can provide cheap storage but they are relatively slow Combining some flash memory with a HDD can provide costs close to those of HDDs and performance close to flash memory Seagate Momentus XT hybrid HDD Various dual storage offerings putting flash memory with HDDs Other common flash memory devices USB sticks All forms and colors Used for moving files around Some sold with content on them (Sony Movies on USB sticks) Solid State Drives (SSDs) Floating Gate Flash Memory Cell When a bit is programmed, electrons are stored upon the floating gate This has the effect of offsetting the charge on the control gate of the transistor If there is no charge upon the floating gate, then the control gate’s charge determines whether or not a current flows through the channel A strong charge on the control gate assumes that no current flows. A weak charge will allow a strong current to flow through. Similar to HDDs, flash memory must provide: Bit error correction Bad block management NAND and NOR memories are treated differently when it comes to managing wear In many NOR-based systems no management is used at all, since the NOR is simply used to store code, and data is stored in other devices. In this case, it would take a near-infinite amount of time for wear to become an issue since the only time the chip would see an erase/write cycle is when the code in the system is being upgraded, which rarely if ever happens over the life of a typical system. NAND is usually found in very different application than is NOR Flash memory wears out This is expected to get worse over time Retention: Disappearing data Bits fade away Retention decreases with increasing read/writes Bits may change when adjacent bits are read Time and traffic are concerns Controllers typically groom read disturb errors Like DRAM refresh Increases erase/write frequency Application characteristics Music – reads high / writes very low Video – r high / writes very low Internet Cache – r high / writes low On airplanes Many consumers now have their own content viewing devices – do they need the airlines? Is there a way to offer more to consumers, especially with their own viewers Additional special content tie into airplane network access to electrical power, internet Should there be fixed embedded or removable storage for on-board airline entertainment? Is there a way to leverage personal and airline viewers and content in new and entertaining ways?

  Read the article

• Understanding Column Properties for a SQL Server Table

  Designing a table can be a little complicated if you don’t have the correct knowledge of data types, relationships, and even column properties. In this tip, Brady Upton goes over the column properties and provides examples. "It really helped us isolate where we were experiencing a bottleneck"- John Q Martin, SQL Server DBA. Get started with SQL Monitor today to solve tricky performance problems - download a free trial

  Read the article

• BI&EPM in Focus June 2013

  - by Mike.Hallett(at)Oracle-BI&EPM

  Analyst Report from Ovum: BI bites into a bigger slice of Oracle’s Red Stack Customers INC Research Ensures 24/7 Enterprise Application Availability and Supports Rapid Expansion in Asia with Managed Cloud Services – Hyperion Planning, PeopleSoft, E-Business Suite, SOA Suite PL Developments Improves Quality and Demand Planning Accuracy, Streamlines Compliance as It Moves into Manufacturing – Hyperion Planning, OBIEE, E-Business Suite Release 12.1, Agile, Demantra Kiabi Provides Store Managers with Monthly Earnings Statements in Four Business Days to Support Continued Retail Growth – Hyperion Planning, Hyperion Financial Reporting, Hyperion Smart View for Office Speedy Cash Improves Global Financial Budgeting and Forecasting to Support Continued Company Growth - Hyperion Planning, Essbase, Hyperion Smart View for Office, Hyperion Financial Management Grupo Sports World Automates and Reduces Budget Consolidation Time by 33% for 30 Fitness Centers – Hyperion Planning Jupiter Shop Channel Automates Budgeting Processes, Enhances Visibility of Project Investments to Support Strategic Decision-Making – Hyperion Planning GENBAND Saves US$1.25 Million Annually with Automated Global Trade Management, Gains Compliance Assurance – Hyperion Financial Management, E-Business Suite Aldar Properties Consolidates and Simplifies Group Planning and Reporting for Business and Finance Structures with Integrated ERP and Business Intelligence – Hyperion Planning, Essbase, Data Integrator, OBIEE, E-Business Suite, SUN Link to Complete Archive Enterprise Performance Management Hyperion EPM 11.1.2.3 Webcast Tutorials EPM Blog: Three Technologies CFOs Need to Know About The CFO as Catalyst for Change - Part 1 The CFO as Catalyst for Change - Part 2 Actions Speak Louder in Scorecards Unlocking Business Potential with Enterprise Performance Management Business Intelligence Oracle Database 12c is launched Analysis: How to Take Big Data Advantage of Oracle Database 12c by Data-informed.com Normal 0 false false false EN-GB X-NONE X-NONE /* Style Definitions */ table.MsoNormalTable {mso-style-name:"Table Normal"; mso-tstyle-rowband-size:0; mso-tstyle-colband-size:0; mso-style-noshow:yes; mso-style-priority:99; mso-style-qformat:yes; mso-style-parent:""; mso-padding-alt:0cm 5.4pt 0cm 5.4pt; mso-para-margin-top:0cm; mso-para-margin-right:0cm; mso-para-margin-bottom:10.0pt; mso-para-margin-left:0cm; line-height:115%; mso-pagination:widow-orphan; font-size:11.0pt; font-family:"Calibri","sans-serif"; mso-ascii-font-family:Calibri; mso-ascii-theme-font:minor-latin; mso-hansi-font-family:Calibri; mso-hansi-theme-font:minor-latin; mso-bidi-font-family:"Times New Roman"; mso-bidi-theme-font:minor-bidi; mso-fareast-language:EN-US;}

  Read the article

• Working with Sub-Optimal Disk Configurations (Making the best of what you’ve got)

  - by Jonathan Kehayias

  This is the first post in a what will be a series of posts on working with a sub-optimal disk configuration to squeeze as much performance out of it as possible.  You might ask what a Sub-Optimal Disk Configuration?  In this case it is a Dell Powervault MD3000 with 15 Seagate Barracuda ES.2 SAS 1 TB 7.2K RPM disks (Model Number ST31000640SS).  This equates to just under 14TB of raw storage that can configured into a number of RAID configurations.  In this case, the disk array...(read more)

  Read the article

• Technical differences between square and hexagon for a grid?

  - by Marlon Dias

  I'm developing a 2D city-building game and trying to decide on the type of grid. There will be vehicles, so the unit movement is important too. I know there are visual differences for using Squares or Hexagons, what I want know is: What are the issues for programming each type of grid regarding implementation and performance? Is there a tradeoff or specific benefit for using one of them in a game context?

  Read the article

• Announcing SO-Aware Test Workbench

  - by gsusx

  Yesterday was a big day for Tellago Studios . After a few months hands down working, we announced the release of the SO-Aware Test Workbench tool which brings sophisticated performance testing and test visualization capabilities to theWCF world. This work has been the result of the feedback received by many of our SO-Aware and Tellago customers in terms of how to improve the WCF testing. More importantly, with the SO-Aware Test Workbench we are trying to address what has been one of the biggest challenges...(read more)

  Read the article

• Apple met à jour son Mac Mini : un nouveau design, et un démontage plus aisé, mais un prix salé

  Apple vient de dévoilé son nouveau MacMini : Citation: Apple Unveils All New Mac mini CUPERTINO, California?June 15, 2010?Apple® today unveiled a completely redesigned Mac® mini, featuring up to twice the graphics performance, a new HDMI port and a new SD card slot, all in an amazingly compact aluminum enclosure. Mac mini is the world's most energy efficient desktop and starting at $699, is the most affordable way to enjoy Mac OS® X, iLife® or Mac OS X Snow Leopard® Server. ?The sleek, aluminum Mac mini packs gre...

  Read the article

• Printer Review: HP LaserJet Pro 1606dn

  Looking for a black-and-white laser printer for your small office or workgroup? HP's $199 entry offers Ethernet, duplex printing, and fast performance -- and can install itself with no CD to insert or driver to download.

  Read the article

• Printer Review: HP LaserJet Pro 1606dn

  Looking for a black-and-white laser printer for your small office or workgroup? HP's $199 entry offers Ethernet, duplex printing, and fast performance -- and can install itself with no CD to insert or driver to download.

  Read the article

• Thread placement policies on NUMA systems - update

  - by Dave

  In a prior blog entry I noted that Solaris used a "maximum dispersal" placement policy to assign nascent threads to their initial processors. The general idea is that threads should be placed as far away from each other as possible in the resource topology in order to reduce resource contention between concurrently running threads. This policy assumes that resource contention -- pipelines, memory channel contention, destructive interference in the shared caches, etc -- will likely outweigh (a) any potential communication benefits we might achieve by packing our threads more densely onto a subset of the NUMA nodes, and (b) benefits of NUMA affinity between memory allocated by one thread and accessed by other threads. We want our threads spread widely over the system and not packed together. Conceptually, when placing a new thread, the kernel picks the least loaded node NUMA node (the node with lowest aggregate load average), and then the least loaded core on that node, etc. Furthermore, the kernel places threads onto resources -- sockets, cores, pipelines, etc -- without regard to the thread's process membership. That is, initial placement is process-agnostic. Keep reading, though. This description is incorrect. On Solaris 10 on a SPARC T5440 with 4 x T2+ NUMA nodes, if the system is otherwise unloaded and we launch a process that creates 20 compute-bound concurrent threads, then typically we'll see a perfect balance with 5 threads on each node. We see similar behavior on an 8-node x86 x4800 system, where each node has 8 cores and each core is 2-way hyperthreaded. So far so good; this behavior seems in agreement with the policy I described in the 1st paragraph. I recently tried the same experiment on a 4-node T4-4 running Solaris 11. Both the T5440 and T4-4 are 4-node systems that expose 256 logical thread contexts. To my surprise, all 20 threads were placed onto just one NUMA node while the other 3 nodes remained completely idle. I checked the usual suspects such as processor sets inadvertently left around by colleagues, processors left offline, and power management policies, but the system was configured normally. I then launched multiple concurrent instances of the process, and, interestingly, all the threads from the 1st process landed on one node, all the threads from the 2nd process landed on another node, and so on. This happened even if I interleaved thread creating between the processes, so I was relatively sure the effect didn't related to thread creation time, but rather that placement was a function of process membership. I this point I consulted the Solaris sources and talked with folks in the Solaris group. The new Solaris 11 behavior is intentional. The kernel is no longer using a simple maximum dispersal policy, and thread placement is process membership-aware. Now, even if other nodes are completely unloaded, the kernel will still try to pack new threads onto the home lgroup (socket) of the primordial thread until the load average of that node reaches 50%, after which it will pick the next least loaded node as the process's new favorite node for placement. On the T4-4 we have 64 logical thread contexts (strands) per socket (lgroup), so if we launch 48 concurrent threads we will find 32 placed on one node and 16 on some other node. If we launch 64 threads we'll find 32 and 32. That means we can end up with our threads clustered on a small subset of the nodes in a way that's quite different that what we've seen on Solaris 10. So we have a policy that allows process-aware packing but reverts to spreading threads onto other nodes if a node becomes too saturated. It turns out this policy was enabled in Solaris 10, but certain bugs suppressed the mixed packing/spreading behavior. There are configuration variables in /etc/system that allow us to dial the affinity between nascent threads and their primordial thread up and down: see lgrp_expand_proc_thresh, specifically. In the OpenSolaris source code the key routine is mpo_update_tunables(). This method reads the /etc/system variables and sets up some global variables that will subsequently be used by the dispatcher, which calls lgrp_choose() in lgrp.c to place nascent threads. Lgrp_expand_proc_thresh controls how loaded an lgroup must be before we'll consider homing a process's threads to another lgroup. Tune this value lower to have it spread your process's threads out more. To recap, the 'new' policy is as follows. Threads from the same process are packed onto a subset of the strands of a socket (50% for T-series). Once that socket reaches the 50% threshold the kernel then picks another preferred socket for that process. Threads from unrelated processes are spread across sockets. More precisely, different processes may have different preferred sockets (lgroups). Beware that I've simplified and elided details for the purposes of explication. The truth is in the code. Remarks: It's worth noting that initial thread placement is just that. If there's a gross imbalance between the load on different nodes then the kernel will migrate threads to achieve a better and more even distribution over the set of available nodes. Once a thread runs and gains some affinity for a node, however, it becomes "stickier" under the assumption that the thread has residual cache residency on that node, and that memory allocated by that thread resides on that node given the default "first-touch" page-level NUMA allocation policy. Exactly how the various policies interact and which have precedence under what circumstances could the topic of a future blog entry. The scheduler is work-conserving. The x4800 mentioned above is an interesting system. Each of the 8 sockets houses an Intel 7500-series processor. Each processor has 3 coherent QPI links and the system is arranged as a glueless 8-socket twisted ladder "mobius" topology. Nodes are either 1 or 2 hops distant over the QPI links. As an aside the mapping of logical CPUIDs to physical resources is rather interesting on Solaris/x4800. On SPARC/Solaris the CPUID layout is strictly geographic, with the highest order bits identifying the socket, the next lower bits identifying the core within that socket, following by the pipeline (if present) and finally the logical thread context ("strand") on the core. But on Solaris on the x4800 the CPUID layout is as follows. [6:6] identifies the hyperthread on a core; bits [5:3] identify the socket, or package in Intel terminology; bits [2:0] identify the core within a socket. Such low-level details should be of interest only if you're binding threads -- a bad idea, the kernel typically handles placement best -- or if you're writing NUMA-aware code that's aware of the ambient placement and makes decisions accordingly. Solaris introduced the so-called critical-threads mechanism, which is expressed by putting a thread into the FX scheduling class at priority 60. The critical-threads mechanism applies to placement on cores, not on sockets, however. That is, it's an intra-socket policy, not an inter-socket policy. Solaris 11 introduces the Power Aware Dispatcher (PAD) which packs threads instead of spreading them out in an attempt to be able to keep sockets or cores at lower power levels. Maximum dispersal may be good for performance but is anathema to power management. PAD is off by default, but power management polices constitute yet another confounding factor with respect to scheduling and dispatching. If your threads communicate heavily -- one thread reads cache lines last written by some other thread -- then the new dense packing policy may improve performance by reducing traffic on the coherent interconnect. On the other hand if your threads in your process communicate rarely, then it's possible the new packing policy might result on contention on shared computing resources. Unfortunately there's no simple litmus test that says whether packing or spreading is optimal in a given situation. The answer varies by system load, application, number of threads, and platform hardware characteristics. Currently we don't have the necessary tools and sensoria to decide at runtime, so we're reduced to an empirical approach where we run trials and try to decide on a placement policy. The situation is quite frustrating. Relatedly, it's often hard to determine just the right level of concurrency to optimize throughput. (Understanding constructive vs destructive interference in the shared caches would be a good start. We could augment the lines with a small tag field indicating which strand last installed or accessed a line. Given that, we could augment the CPU with performance counters for misses where a thread evicts a line it installed vs misses where a thread displaces a line installed by some other thread.)

  Read the article

• ASP.NET 4.0- Menu control enhancement.

  - by Jalpesh P. Vadgama

  Till asp.net 3.5 asp.net menu control was rendered through table. And we all know that it is very hard to have CSS applied to table. For a professional look of our website a CSS is must required thing. But in asp.net 4.0 Menu control is table less it will loaded with UL and LI tags which is easier to manage through CSS. Another problem with table is it will create a large html which will increase your asp.net page KB and decrease your performance. While with UL and LI Tags its very easy very short. So You page KB Size will also be down. Let’s take a simple example. Let’s Create a menu control in asp.net with four menu item like following. <asp:Menu ID="myCustomMenu" runat="server" > <Items> <asp:MenuItem Text="Menu1" Value="Menu1"></asp:MenuItem> <asp:MenuItem Text="Menu2" Value="Menu2"></asp:MenuItem> <asp:MenuItem Text="Menu3" Value="Menu3"></asp:MenuItem> <asp:MenuItem Text="Menu4" Value="Menu4"></asp:MenuItem> </Items></asp:Menu> It will render menu in browser like following. Now If we render this menu control with tables then HTML as you can see via view page source like following.   Now If in asp.net 4.0 It will be loaded with UL and LI tags and if you now see page source then it will look like following. Which will have must lesser HTML then it was earlier like following. So isn’t that great performance enhancement?.. It’s very cool. If you still like old way doing with tables then in asp.net 4.0 there is property called ‘RenderingMode’ is given. So you can set RenderingMode=Table then it will load menu control with table otherwise it will load menu control with UL and LI Tags. That’s it..Stay tuned for more..Happy programming.. Technorati Tags: Menu,Asp.NET 4.0

  Read the article

• .NET 4 Web Application Startup Time

  - by Latest Microsoft Blogs

  I was chatting with Jonathan Hawkins and some of the folks on the ASP.NET team about performance and Jonathan mentioned the startup time for large ASP.NET applications is improved on .NET 4. There are some improvements in the CLR and in ASP.NET itself Read More......(read more)

  Read the article

• Small Business and Organic SEO - A Win Win Situation

  Small business owners have to run on tiny budgets and that becomes constraint for effective publicity. The online marketing performance also suffers due to this crucial factor. The remedy lies in organic SEO, which efficiently works for the website of small business and supports the placement in higher rankings in search results. It is a win win situation for small business owners.

  Read the article

• Mind the gap, the latest version number for SQL Server 2008 R2 is....

  - by ssqa.net

  Since the news about SQL Server 2008 R2 RTM is publicised I have downloaded and installed the Evaluation edition and R2 Express edition. You can also download SQL Server 2008 R2 RTM - Management Studio Express (with pre-registration) The Microsoft® SQL Server® 2008 R2 RTM - Express is a powerful and reliable data management system that delivers a rich set of features, data protection, and performance for embedded applications, lightweight Web applications, and local data stores. Designed for easy...(read more)

  Read the article

• Update of SAE Benchmark Presentation to M6/T5/ZFS

  - by uwes

  Strategic Applications Engineering (SAE) published in March an updated Benchmark presentation showing the performance of Oracle systems, software and Virtualization. SPARC M6/T5/ZFS Benchmarks March 2014 The presentation is available via our eSTEP portal.  You will need to provide your email address and the pin below to access the downloads. Link to the portal is shown below. URL: http://launch.oracle.com/ PIN: eSTEP_2011 The material can be found under tab eSTEP Download Located under: Recent Updates and Miscellaneous

  Read the article

< Previous Page | 237 238 239 240 241 242 243 244 245 246 247 248  | Next Page >