Au Aix7networkoptimize1 PDF

Copyright IBM Corporation 2010 TrademarksOptimizing AIX 7 network performance: Part 1, Network overview- Monitoring the hardware

Page 1 of 17

Optimizing AIX 7 network performance: Part 1,Network overview - Monitoring the hardwareMartin Brown ([email protected])Professional writerFreelance

Ken MilbergWriter/site expertFuture Tech

23 November 2010

This three-part series on AIX 7 networking focuses on the challenges of optimizing networkperformance. With AIX 7 and the new POWER7 architecture, you have to think about theperformance of your system, and also the effects of your network performance on both LPARand WPAR environments. In the first installment, you'll review some best practices for networkconfiguration and utilize those practices for efficient monitoring of your hardware by takingadvantage of network tools such as netstat, netpmon, entstat, and nmon. You'll alsoexamine certain tools used to look at your interfaces to see how to configure them.

View more content in this series

About this seriesPart 1 of this three-part series on AIX networking provides a networking overview and discussesthe tools that help you monitor your hardware. Part 2 covers tuning the Network File System(NFS) with monitoring utilities, such as nfsstat and nmon, and it also goes over how to tune withnfso. Part 3 shows you how to monitor network packets and how to use netstat for this purpose.You'll learn how to tune your network subsystem using the no utility. This series also expounds onvarious best practices of network I/O performance tuning.

IntroductionThe first thing that usually comes to mind when a system administrator hears that there mightbe some network contention issues is to run netstat. netstat, the equivalent of using vmstator iostat for your memory reports, is a quick way to get an overview of how your network isconfigured. Unlike vmstat or iostat, the defaults usually do not give you as much information asyou probably would like. You need to understand the correct usage of netstat and how best toutilize it when monitoring your system.

developerWorks ibm.com/developerWorks/

Optimizing AIX 7 network performance: Part 1, Network overview- Monitoring the hardware

Page 2 of 17

netstat is really not a monitoring tool in the sense of vmstat and iostat. You can use other toolsmore suitable (discussed later in the article) to help monitor your network subsystem. At the sametime, you can't really start to monitor unless you have a thorough understanding of the variouscomponents related to network performance. These components include your network adapters,your switches and routers, and how you are using virtualization on your host logical partitions.If you determine you are indeed having a network bottleneck, fixing the problem might actuallylay outside of your immediate host machine. There is little you can do if the network switch isimproperly configured on the other end. Of course, you might be able to point the network team inthe right direction. You should also spend time gathering overall information about your network.How are you going to be able to understand how to troubleshoot your network devices unless youreally understand your network? In this article, you'll look at specific AIX network tracing tools,such as netpmon, and how they can help you isolate your bottlenecks.

Finally, no matter which subsystem you are looking to tune, you must think of systems tuning asan ongoing process. As stated before, the best time to start monitoring your systems is at thebeginning, before you have any problems and users aren't screaming. You must have a baselineof network performance so that you know what the system looks like when it is behaving normally.Finally, when making changes, be careful to make changes only one at a time so that you canreally assess the impact of your change.

Network I/O overview

This section provides an overview of the network as it relates to AIX 7 and covers the physicalaspects of the network (device drives and adapters), the AIX networking stack, and how to makesome changes to your adapter.

Understanding the network subsystem, as it relates to AIX, is not an easy undertaking. Whenexamining the CPU and memory bottlenecks, there are far fewer areas that you need to examinefrom a hardware and software aspect. Disk I/O tuning is more complex, as there are many moreissues that impact performance, particularly during the architectural and build-out of your systems.In this respect, tuning your network is probably most like tuning your disk I/O, which is actually nottoo surprising, as they both relate to I/O. Let's start.

Figure 1 illustrates the AIX Transmission Control Protocol/Internet Protocol (TCP/IP) layers.

ibm.com/developerWorks/ developerWorks


Page 3 of 17

Figure 1. The AIX TCP/IP layers

Figure 1 illustrates that there is more to network monitoring than running netstat and looking forcollisions. From the application layer through the media layer, there are areas that need to beconfigured, monitored, and tuned. At this point, you should notice some similarities between thisillustration and the Open Systems Interconnection Basic Reference Model (OSI Model). The OSIModel has seven layers (bottom to top):

Physical Data-link Network Transport Session Presentation Application

Perhaps the most important concept to understand is that on the host machine each layercommunicates with its corresponding layer on the remote machine. The actual applicationprograms transmit data using either User Datagram Protocol (UDP) or Transmission ControlProtocol (TCP) transport layer protocols. They receive the data from whatever application youare using and divide them into packets. The packets themselves differ, depending on whether itis a UDP or TCP packet. Generally speaking, UDP is faster, while TCP is more secure. There aremany tunable parameters to look atyou'll get to these parameters during subsequent phasesof the series. You might want to start to familiarize yourself with the no command, which is theutility designed to make the majority of your network changes. From a hardware perspective, it iscritical that you understand the components that need to be configured appropriately to optimize



Page 4 of 17

performance. Though you might work together with the network teams that manage your switchesand routers, it is unlikely that you will be configuring them (unless you are a small shop or a one-person IT department). The most important component you will be working with is your networkadapter. Gigabit Ethernet is now the standard network interface, although 10Gbit network cardsand infrastructure is becoming more accessible.

Maximum Transfer Unit

Maximum Transfer Unit (MTU) is defined as the largest packet that can be sent over a network.The size depends on the type of network. For example, 16-bit token ring has a default MTU sizeof 17914, while Fiber Distributed Data Interface (FDDI) has a default size of 4352. Ethernet hasa default size of 1500 (9000 with jumbo frames enabled). Larger packets require less packettransfers, which result in higher bandwidth utilization on your system. In particular, using jumboframes allows for an entire 8KB NFS block to be exchanged in a single packet, which cansignificantly improve performance. An exception to this is if your application prefers smallerpackets, and this includes web applications on the Internet, since most Internet connections do notsupport jumbo frames. If you are using a Gigabit Ethernet, you can use a jumbo frames option. Tosupport the use of jumbo frames, it's important to note that your switch must also be configured,accordingly.

To change to jumbo frames, use this fastpath: # smit devices.

Then go to Communication>Ethernet>Adapter>Change/show characteristics of an Ethernetadapter. Try to change the transmit jumbo frames option from "No" to "Yes" (see Listing 1).

Listing 1. Characteristics of an Ethernet adapter screen Change / show characteristics of an Ethernet adapter Change / Show Characteristics of an Ethernet AdapterType or select values in entry fields.Press Enter AFTER making all desired changes.

[Entry Fields] Ethernet Adapter ent0 Description Virtual I/O Ethernet Adapter (l-lan) Status Available Location Enable ALTERNATE ETHERNET address no + ALTERNATE ETHERNET address [0x000000000000] + Minimum Tiny Buffers [512] +# Maximum Tiny Buffers [2048] +# Minimum Small Buffers [512] +# Maximum Small Buffers [2048] +# Maximum Medium Buffers [128] +# Maximum Medium Buffers [256] +# Minimum Large Buffers [24] +# Maximum Large Buffers [64] +# Minimum Huge Buffers [24] +# Maximum Huge Buffers [64] +# Transmit Copy Buffers [32] +# Transmit Copy Buffer Size [65536] +# Trace Debug Enable no + Checksum Offload Enable yes + I/O memory entitlement reserved for device 0 Apply change to DATABASE only no +



Page 5 of 17

Where is the jumbo frames option? In this case, you cannot make the change. The reason for thisis because you are only using the Virtual I/O Ethernet on this systemthis topic is discussed inmore detail later.

On a system where you have direct access to the network hardware, check the system usingListing 2.

Listing 2. Checking the system

Change / show characteristics of an Ethernet adapter

Type or select values in entry fields.Press Enter AFTER making all desired changes.

[Entry Fields] Ethernet Adapter ent1 Description 10/100/1000 Base-TX P> Status Available Location 1j-08 RX descriptor queue size [1024] +# TX descriptor queue size [1024] +# Software transmit queue size [8192] +# Transmit jumbo frames yes + Enable hardware TX TCP resegmentation yes + Enable hardware transmit and receive checksum yes + Media speed Auto_Negotiation + Enable ALTERNATE ETHERNET address no + ALTERNATE ETHERNET address [0x000000000000] + Apply change to DATABASE only no +

F1=Help F2=Refresh F3=Cancel F4=ListF5=Reset F6=Command F7=Edit F8=ImageF9=Shell F10=Exit Enter=Do

You have now changed the field to support jumbo frames.

Media speed

Most modern network switches and environments can take advantage of auto-negotiation toprovide the best speed, especially as full-duplex network switches have become the standard.However, you force a particular configuration if the auto-negotiation fails to configure a speed thatyou know your network switch is capable of supporting.

The lsattr command gives you the information that you need. The en prefix displays your driverparameters, while the ent prefix displays your hardware parameters. Let's display your hardwareparameters (see Listing 3).



Page 6 of 17

Listing 3. Displaying the hardware parameterstestsys:/home/test>lsattr -El ent0alt_addr 0x000000000000 Alternate Ethernet AddressTruechksum_offload yes Checksum Offload Enable Truecopy_buffs 32 Transmit Copy Buffers Truecopy_bytes 65536 Transmit Copy Buffer Size Truedesired_mapmem 0 I/O memory entitlement reserved for device Falsemax_buf_huge 64 Maximum Huge Buffers Truemax_buf_large 64 Maximum Large Buffers Truemax_buf_medium 256 Maximum Medium Buffers Truemax_buf_small 2048 Maximum Small Buffers Truemax_buf_tiny 2048 Maximum Tiny Buffers Truemin_buf_huge 24 Minimum Huge Buffers Truemin_buf_large 24 Minimum Large Buffers Truemin_buf_medium 128 Minimum Medium Buffers Truemin_buf_small 512 Minimum Small Buffers Truemin_buf_tiny 512 Minimum Tiny Buffers Truetrace_debug no Trace Debug Enable Trueuse_alt_addr no Enable Alternate Ethernet Address True

In this case, your interface is set as auto-negotiate.

You should also check your firmware levels to make sure they are up to date. We've seen manynetwork problems fixed when updating to the latest levels of firmware. The lscfg command givesyou the firmware information (see Listing 4).

Listing 4. Using the lscfg command for firmware informationtestsys:/home/test >lscfg -vp | grep -p ETHERNET 4 X 1GB ETHERNET: Record Name.................VINI Flag Field..................XXET Hardware Location Code......U78C0.001.DBJ3229-P2-C8 Customer Card ID Number.....2BC4 Serial Number...............YL10D9360034 CCIN Extender...............1 Product Specific.(VZ).......04 FRU Number..................46K5965 Part Number.................46K6484 Product Specific.(HE).......0001 Product Specific.(CT).......30910008 Product Specific.(HW).......0001 Product Specific.(B3).......000000000001 Product Specific.(B4).......00 Product Specific.(B7).......000000000000000000000000 Product Specific.(B1).......00215EEB40C0002000215EEB40E00020 Version.....................ipzSeries Physical Location: U78C0.001.DBJ3229-P2-C8

4 X 1GB ETHERNET: Record Name.................VINI Flag Field..................XXET Hardware Location Code......U78C0.001.DBJ3226-P2-C8 Customer Card ID Number.....2BC4 Serial Number...............YL10D9360085 CCIN Extender...............1 Product Specific.(VZ).......04 FRU Number..................46K5965 Part Number.................46K6484 Product Specific.(HE).......0001 Product Specific.(CT).......30910008 Product Specific.(HW).......0001 Product Specific.(B3).......000000000001 Product Specific.(B4).......00



Page 7 of 17

Product Specific.(B7).......000000000000000000000000 Product Specific.(B1).......00215EEB4680002000215EEB46A00020 Version.....................ipzSeries Physical Location: U78C0.001.DBJ3226-P2-C8

4 X 1GB ETHERNET: Record Name.................VINI Flag Field..................XXET Hardware Location Code......U78C0.001.DBJ3227-P2-C8 Customer Card ID Number.....2BC4 Serial Number...............YL10D9360028 CCIN Extender...............1 Product Specific.(VZ).......04 FRU Number..................46K5965 Part Number.................46K6484 Product Specific.(HE).......0001 Product Specific.(CT).......30910008 Product Specific.(HW).......0001 Product Specific.(B3).......000000000001 Product Specific.(B4).......00 Product Specific.(B7).......000000000000000000000000 Product Specific.(B1).......00215EEB4140002000215EEB41600020 Version.....................ipzSeries Physical Location: U78C0.001.DBJ3227-P2-C8

See the Resources section at the end of the article for a link to the most current releaseinformation for your adapter.

Though the series focuses on tuning in subsequent parts, you might want to start to familiarizeyourself with the memory management facility of network subsystems. What you need to knowat this point is that it relates to data structures called mbufs. These are used to store kernel datafor incoming and outbound traffic. The buffer sizes themselves can range from 32 to 16384 bytes.They are created by making allocation requests to the Virtual Memory Manager (VMM). In an SMPbox, each memory pool is split evenly for every processor. The monitoring section below showsyou how to view mbufs. An important concept to note is that processors cannot borrow from thememory pool outside of its own processor.

Two other concepts you should be familiar with are virtual Ethernet and shared Ethernet.

Virtual Ethernet: Virtual Ethernet allows for inter-partition- and IP-based communicationsbetween logical partitions on the same frame. This is done by the use of a virtual I/O switch.The Ethernet adapters themselves are created and configured using the HMC. If you recall,you tried to change an adapter earlier that was configured with virtual Ethernet.

Shared Ethernet: Shared Ethernet allows for the use of Virtual I/O servers (VIOs), whereseveral host machines can actually share one physical network adapter. Typically, this is usedin environments that do not require substantial network bandwidth.

While the scope of this series is not on virtualization, you should understand that if you are usingvirtualization, there might be other reasons for your bottleneck outside of what you are doing onyour host machine. While virtualization is a wonderful thing, be careful not to share too manyadapters from your VIO server, or you might pay a large network I/O penalty. Keep in mind as wellthat with workload partitions (WPAR), the network configuration of the host environment is usedand shared by each partition; you cannot configure WPAR network performance individually. Usingappropriate monitoring tools should inform you if you have a problem.



Page 8 of 17

In addition, application performance can be affected fundamental services, such as domain nameservice (DNS) used to resolve hostnames and Internet addresses.

MonitoringThis section provides an overview of general network monitoring commands and specific AIX 7tools available to you. Some of the tools allow you to troubleshoot a performance problem quicklywhile others capture data for historical trending and analysis.

Let's get back to the old standby, netstat, which displays overall network statistics. Probably oneof the most common commands you type in is netstat -in (see Listing 5).

Listing 5. Using netstat with the -in optionl488pp065_pub[/tmp] > netstat -inName Mtu Network Address Ipkts Ierrs Opkts Oerrs Collen1 1500 link#2 66.da.93.d1.6b.18 70136750 0 336237 0 0en1 1500 10.153 10.153.20.65 70136750 0 336237 0 0en0 1500 link#3 66.da.93.d1.6b.17 202571785 0 79277 0 0en0 1500 172.29.128 172.29.148.225 202571785 0 79277 0 0lo0 16896 link#1 778719 0 778718 0 0lo0 16896 127 127.0.0.1 778719 0 778718 0 0lo0 16896 ::1%1 778719 0 778718 0 0

Here is what it means:

Name: Interface name. MTU: Interface Maximum Transfer Unit size. Network: The actual network address that the interface connects to. Address: Mac and IP address. Ipkts: The total amount of packets received by the interface. Ierrs: The amount of errors reported back from the interface. Opkts: The amount of packets transmitted from the interface. Oerrs: The amount of error packets transmitted from the interface. Coll: The amount of collisions on the adapter. If you are using Ethernet, you won't see

anything here.

Another handy netstat flag is the -m option. This flag allows you to view the Kernel mallocstatistics; the mbuf memory requests, including the size of the buffers, the amount in use and thefailures by CPU (see Listing 6).

Listing 6. netstat with -m optionl488pp065_pub[/tmp] > netstat -mKernel malloc statistics:

******* CPU 0 *******By size inuse calls failed delayed free hiwat freed64 566 2015884 0 7 266 5240 0128 5890 1830085 0 175 158 2620 0256 5781 651987 0 295 2875 5240 500512 8000 181192188 0 972 56 6550 01024 3165 1889042 0 792 35 2620 02048 1071 3387085 0 520 23 3930 04096 2056 2775 0 83 5 1310 0



Page 9 of 17

8192 6 260 0 3 163 327 016384 256 413 0 62 0 163 032768 55 274 0 23 4 81 065536 117 175 0 76 0 81 0131072 4 5 0 0 102 204 0

******* CPU 1 *******By size inuse calls failed delayed free hiwat freed64 46 226765 0 0 146 5240 0128 58 152657 0 2 134 2620 0256 51 70035 0 2 301 5240 0512 78 46458768 0 4 66 6550 01024 62 171426 0 12 30 2620 02048 23 3669503 0 5 25 3930 04096 1 891 0 4 9 1310 08192 1 567 0 3 306 327 016384 0 12 0 5 2 163 032768 2 17 0 3 7 81 065536 0 11 0 6 0 81 0131072 0 1 0 0 20 40 0

******* CPU 2 *******By size inuse calls failed delayed free hiwat freed64 21 1295 0 1 43 5240 0128 9 781 0 0 23 2620 0256 9 1226 0 0 39 5240 0512 81 36991563 0 10 55 6550 01024 27 1241 0 15 33 2620 02048 5 3286 0 0 23 3930 04096 0 52 0 1 5 1310 08192 0 1 0 1 0 327 032768 0 1 0 1 1 81 0131072 0 0 0 0 16 32 0

******* CPU 3 *******By size inuse calls failed delayed free hiwat freed64 42 1224 0 2 86 5240 0128 15 1195 0 13 401 2620 0256 12 2607 0 82 1316 5240 0512 83 36405229 0 222 1733 6550 01024 32 1220 0 14 32 2620 02048 23 4549 0 260 507 3930 04096 1 42 0 3 3 1310 08192 0 58 0 7 21 327 016384 0 128 0 19 121 163 032768 2 29 0 7 22 81 065536 0 47 0 24 47 81 0131072 0 0 0 0 102 204 0

The -m option is particularly useful because it shows the network performance statistics in relationto individual CPUs. When monitoring and managing the performance with LPAR and WPARenvironments, the ability to correlate your CPU resources and the network resources can give youvaluable information about the correct allocation and distribution of network resources.

For Ethernet, you can use the entstat command to display device-driver statistics. This provides aplethora of information (see Listing 7).

Listing 7. Using the entstat command to display device driver statisticsl488pp065_pub[/tmp] > entstat -d ent0



Page 10 of 17

-------------------------------------------------------------ETHERNET STATISTICS (ent0) :Device Type: Virtual I/O Ethernet Adapter (l-lan)Hardware Address: 66:da:93:d1:6b:17Elapsed Time: 16 days 1 hours 48 minutes 7 seconds

Transmit Statistics: Receive Statistics:-------------------- -------------------Packets: 79636 Packets: 203054741Bytes: 15868037 Bytes: 30905882351Interrupts: 0 Interrupts: 201058047Transmit Errors: 0 Receive Errors: 0Packets Dropped: 0 Packets Dropped: 0 Bad Packets: 0Max Packets on S/W Transmit Queue: 0S/W Transmit Queue Overflow: 0Current S/W+H/W Transmit Queue Length: 0

Broadcast Packets: 5 Broadcast Packets: 203036730Multicast Packets: 6171 Multicast Packets: 215No Carrier Sense: 0 CRC Errors: 0DMA Underrun: 0 DMA Overrun: 0Lost CTS Errors: 0 Alignment Errors: 0Max Collision Errors: 0 No Resource Errors: 0Late Collision Errors: 0 Receive Collision Errors: 0Deferred: 0 Packet Too Short Errors: 0SQE Test: 0 Packet Too Long Errors: 0Timeout Errors: 0 Packets Discarded by Adapter: 0Single Collision Count: 0 Receiver Start Count: 0Multiple Collision Count: 0Current HW Transmit Queue Length: 0

General Statistics:-------------------No mbuf Errors: 0Adapter Reset Count: 0Adapter Data Rate: 20000Driver Flags: Up Broadcast Running Simplex 64BitSupport ChecksumOffload DataRateSet

Virtual I/O Ethernet Adapter (l-lan) Specific Statistics:---------------------------------------------------------RQ Length: 4481Trunk Adapter: FalseFilter MCast Mode: FalseFilters: 255 Enabled: 1 Queued: 0 Overflow: 0LAN State: Operational

Hypervisor Send Failures: 0 Receiver Failures: 0 Send Errors: 0Hypervisor Receive Failures: 0

Invalid VLAN ID Packets: 0

ILLAN Attributes: 0000000000003002 [0000000000003002]

Port VLAN ID: 2VLAN Tag IDs: None

Switch ID: ETHERNET0

Hypervisor Information Virtual Memory



Page 11 of 17

Total (KB) 79 I/O Memory VRM Minimum (KB) 100 VRM Desired (KB) 100 DMA Max Min (KB) 128

Transmit Information Transmit Buffers Buffer Size 65536 Buffers 32 History No Buffers 0 Virtual Memory

Collisions are largely a thing of the past with modern network switches, but look for transmit errorsand make sure they are not increasing too fast. You need to learn to troubleshoot collision anderror problems before you even begin to think about tuning. Alternatively, you can use netstat -v,which provides similar information.

Let's look at netpmon. netpmon provides information on CPU usage as it relates to the network,and it also includes data about the network device driver I/O, Internet socket calls, and othervarious statistics. Similar to its other trace brethren, tprof and filemon, it starts a trace and runsin the background until you stop it with the trcstop command. We like netpmon because it reallygives you a detailed overview of network activity and also captures data for trending and analysis(though it is not as useful as nmon for this purpose). Here you'll use a trace buffer size of two millionbytes (see Listing 8).

Listing 8. netpmom with -T optionl488pp065_pub[/tmp] > netpmon -T 2000000 -o /tmp/net.outRun trcstop command to signal end of trace.Sun Aug 15 04:58:06 2010System: AIX 7.1 Node: l488pp065_pub Machine: 00F604884C00

Now you'll stop it (see Listing 9).

Listing 9. Stopping netpmoml488pp065_pub[/tmp] > trcstop[netpmon: Reporting started]23675650 Missed Entries found

[netpmon: Reporting completed][ 4 traced cpus ][ 0.091 secs total preempt time ]

[netpmon: 43.388 secs in measured interval]

Let's look at the data. Here is just a small sampling of the output (see Listing 10).

Listing 10. Sample outputSun Aug 15 04:58:06 2010System: AIX 7.1 Node: l488pp065_pub Machine: 00F604884C00

========================================================================

Process CPU Usage Statistics:-----------------------------



Page 12 of 17

NetworkProcess (top 20) PID CPU Time CPU % CPU %----------------------------------------------------------netpmon 12976354 41.7559 24.072 0.000netpmon 14155800 32.1352 18.526 0.000inetd 14155804 29.3093 16.897 0.000xmtopas 14155834 29.2385 16.856 0.000xmtopas 14155830 29.2381 16.856 0.000xmtopas 14155822 28.9899 16.713 0.000xmtopas 14155816 28.9433 16.686 0.000xmtopas 14155826 28.9390 16.683 0.000xmtopas 14155828 28.9308 16.679 0.000inetd 14155824 28.9287 16.677 0.000xmtopas 14155820 28.9227 16.674 0.000xmtopas 14155814 28.9158 16.670 0.000inetd 14155866 23.7606 13.698 0.000inetd 14155864 23.7131 13.671 0.000xmtopas 14155846 19.0223 10.966 0.000inetd 14155848 19.0083 10.958 0.000inetd 9371742 18.8547 10.870 0.000inetd 9371658 16.5665 9.551 0.000inetd 9371886 16.4571 9.488 0.000xmtopas 9371888 16.4094 9.460 0.000----------------------------------------------------------Total (all processes) 838.3315 483.300 0.000Idle time 78.8376 45.450

========================================================================

First Level Interrupt Handler CPU Usage Statistics:--------------------------------------------------- NetworkFLIH CPU Time CPU % CPU %----------------------------------------------------------data page fault 255.0988 147.065 0.000UNKNOWN 17.9673 10.358 0.000PPC decrementer 2.7282 1.573 0.000external device 0.0081 0.005 0.000instruction page fault 0.0002 0.000 0.000queued interrupt 0.0000 0.000 0.000----------------------------------------------------------Total (all FLIHs) 275.8026 159.001 0.000

========================================================================

TCP Socket Call Statistics (by Process):---------------------------------------- ------ Read ----- ----- Write -----Process (top 20) PID Calls/s Bytes/s Calls/s Bytes/s------------------------------------------------------------------------sshd: 5636334 0.12 1888 0.53 37nonstop_aix 3539136 0.05 9 0.05 0java 4260046 0.05 9 0.05 0------------------------------------------------------------------------Total (all processes) 0.21 1907 0.62 37

========================================================================

Detailed TCP Socket Call Statistics (by Process):-------------------------------------------------

PROCESS: sshd: PID: 5636334reads: 5

As you can see, there is little overall network I/O activity going on during this time. The top sectionis most important, as it really helps you get an understanding of what processes are consuming



Page 13 of 17

network I/O time, and you can use the more detailed per-process output to obtain more specificinformation. lsattr (used earlier to view the hardware parameters) is another command you willbe using frequently to display statistics on your interfaces. The attributes that you see here areconfigured using either the chdev or no commands. Let's display your driver parameters (seeListing 11).

Listing 11. Displaying the driver parameters using lsattr

l488pp065_pub[/tmp] > lsattr -El en0alias4IPv4 Alias including Subnet Mask Truealias6 IPv6 Alias including Prefix Length Truearp on Address Resolution Protocol (ARP) Trueauthority Authorized Users Truebroadcast Broadcast Address Truemtu 1500 Maximum IP Packet Size for This Device Truenetaddr 172.29.148.225 Internet Address Truenetaddr6 IPv6 Internet Address Truenetmask 255.255.192.0 Subnet Mask Trueprefixlen Prefix Length for IPv6 Internet Address Trueremmtu 576 Maximum IP Packet Size for REMOTE Networks Truerfc1323 Enable/Disable TCP RFC 1323 Window Scaling Truesecurity none Security Level Truestate up Current Interface Status Truetcp_mssdflt Set TCP Maximum Segment Size Truetcp_nodelay Enable/Disable TCP_NODELAY Option Truetcp_recvspace Set Socket Buffer Space for Receiving Truetcp_sendspace Set Socket Buffer Space for Sending True

Finally, let's look at Figure 2.

Figure 2. nmon statistics

If you've been following the other series on AIX 7 (see Resources), you know we love nmon andyou should also, once you start using it. With nmon (type in n after startup), you have a quicksnapshot of everything going on in your network, including adapter details, MTU, error countersand collisions, and megabit rating.

Further, you also have the ability to capture data with nmon. Using the nmon analyzer, you can printout graphical reports directly from Microsoft Excel spreadsheets. See Resources for a link to anIBM Wiki for the nmon manual or for downloads.



Page 14 of 17

Summary

This article covered the relative importance of the network I/O subsystem, and defined the AIX7 network I/O layers and how it relates to the OSI Model. You learned some best practices fornetwork configuration, changed your Ethernet settings to support jumbo frame, and viewedinterface hardware and driver data. You even examined the monitoring tools available to you andcaptured data using netpmon and nmon. In the next part of the series, you'll tune NFS, find out moreabout monitoring utilities, such as nfsstat and nmon, and discover how to tune with nfso.



Page 15 of 17

ResourcesLearn

AIX Wiki: Get the nmon manual or downloads here. Improving database performance with AIX concurrent I/O: Read this white paper for more

information on how to improve database performance. Power Architecture: High-Performance Architecture with a History: Read this white paper. "Power to the People; A history of chip making at IBM" (developerWorks, December 2005):

This article covers the IBM power architecture. "CPU Monitoring and Tuning" (March, 2002): Learn how standard AIX tools can help you

determine CPU bottlenecks. nmon analyser -- A free tool to produce AIX performance reports (Steven Atkins,

developerWorks, April 2006): You can download nmon analyser from here. nmon performance: A free tool to analyze AIX and Linux performance (Nigel Griffiths,

developerWorks, February 2006): Read this article for information on nmon. Operating System and Device Management from IBM provides users and system

administrators with complete information that can affect your selection of options whenperforming such tasks as backing up and restoring the system, managing physical and logicalstorage, and sizing appropriate paging space.

The AIX 7.1 Information Center is your source for technical information about the AIXoperating system.

The IBM AIX Version 6.1 Differences Guide can be a useful resource for understandingchanges in AIX 6.1.

The IBM AIX Version 7.1 Differences Guide can be a useful resource for understandingchanges in AIX 7.1.

Popular content: See what AIX and UNIX content your peers find interesting. AIX and UNIX: The AIX and UNIX developerWorks zone provides a wealth of information

relating to all aspects of AIX systems administration and expanding your UNIX skills. New to AIX and UNIX?: Visit the New to AIX and UNIX page to learn more about AIX and

UNIX. AIX Wiki: Discover a collaborative environment for technical information related to AIX. Safari bookstore: Visit this e-reference library to find specific technical resources. developerWorks technical events and webcasts: Stay current with developerWorks technical

events and webcasts. Podcasts: Tune in and catch up with IBM technical experts. Future Tech: Visit Future Tech's site to learn more about their latest offerings.

Get products and technologies

IBM trial software: Build your next development project with software for download directlyfrom developerWorks.

Discuss

Follow developerWorks on Twitter.



Page 16 of 17

Participate in developerWorks blogs and get involved in the developerWorks community. Get involved in the My developerWorks community. Participate in the AIX and UNIX forums:

AIX Forum AIX Forum for developers Cluster Systems Management Performance Tools Forum Virtualization Forum More AIX and UNIX Forums



Page 17 of 17

About the authors

Martin Brown

Martin Brown has been a professional writer for over eight years. He is the author ofnumerous books and articles across a range of topics. His expertise spans myriaddevelopment languages and platforms - Perl, Python, Java, JavaScript, Basic,Pascal, Modula-2, C, C++, Rebol, Gawk, Shellscript, Windows, Solaris, Linux, BeOS,Mac OS/X and more - as well as web programming, systems management andintegration. Martin is a regular contributor to ServerWatch.com, LinuxToday.com, IBMdeveloperWorks and a regular blogger at Computerworld, The Apple Blog, and othersites. He is also a Subject Matter Expert (SME) for Microsoft. He can be contactedthrough his website at http://www.mcslp.com.

Ken Milberg

Ken Milberg is a technology writer and site expert for techtarget.com and providesLinux technical information and support at searchopensource.com. He is also awriter and technical editor for IBM Systems Magazine, Open Edition. Ken holds abachelor's degree in computer and information science and a master's degree intechnology management from the University of Maryland. He is the founder andgroup leader of the NY Metro POWER-AIX/Linux Users Group. Through the years,he has worked for both large and small organizations and has held diverse positionsfrom CIO to Senior AIX Engineer. Today, he works for Future Tech, a Long Island-based IBM Business Partner. Ken is a PMI certified Project Management Professional(PMP), an IBM Certified Advanced Technical Expert (CATE, IBM System p5 2006),and a Solaris Certified Network Administrator (SCNA). You can contact him [email protected].

Copyright IBM Corporation 2010(www.ibm.com/legal/copytrade.shtml)Trademarks(www.ibm.com/developerworks/ibm/trademarks/)

Table of ContentsAbout this seriesIntroductionNetwork I/O overviewMaximum Transfer UnitMedia speed

MonitoringSummaryResourcesAbout the authorsTrademarks

Au Aix7networkoptimize1 PDF

Documents

network performance

network overview

network subsystem

network adapters

network team

network bottleneck

network switch

network packets