Skip to main content

Reason for getting less Network performance In Linux-2.6.20.9

By

Packets can be sent out immediately with out a delay if it falls under below reasons and without violation of Nagle’s rules

Ø It is full sized.

Ø Or it contains FIN. (Already checked by caller)

Ø Or TCP_NODELAY was set.

Ø Or TCP_CORK is not set, and all sent packets are ACKed. With Minshall's modification: all sent small packets are ACKed.

The reason for getting less Network performance In Linux-2.6.20.9 is as follows.

If we have TSO enabled and if we an 8KB of data to be transmitted, In this case what the TCP/IP stack does is as follows.

STEP1: 8KB of data will be copied from Application to the Kernel Buffer

STEP2: Before forming the TCP segment Nagle’s test will be done, this will be done only if TSO_SEGS is equal to 1. This variable tells the HW to how many chunks this 8kB has to be divided while sending it out on the wire. For Example: IF 8KB of data is to be transmitted and if your MSS is 1448 then your tso_segs will be 6 (i.e. 8192 /1448 ~= 6).

STEP3: TCP/IP stack will only give data of length which is multiple of MSS, i.e., if you have 8KB of data and your max segment size is 1448 then in this case the amount of data that has sent out will be calculated as follows

Amount of data to be sent out = 8192 – (8192 mod 1448)

= 8192 – 952

= 7240

As a result of this only 7240 out of 8192 will be sent out, the remaining amount of data that is 952 will be sent out later as new TCP/IP segment. That is it as fall through again from step2.

STEP4: TCP/IP header will formed successfully for the data of length 7240 and it will be given to the Network driver for sending it out on the wire.

This remaining amount of data 952 bytes will be tried to send out, it will start from step2 again; in this case the tso_segs value will be 1, as a result of this it has to go for Nagel’s test. Since it is not a full sized packet nagle’s test will be failed and the packet will be delayed in sending out. As a result of this we were getting less performance in 2.6.20.9.

This can be avoided by committing the Trimming of data in step3 as our H/W as the feature of handling the entire 8k even if the last chunk is less than MSS or this can also be avoided by disabling Nagle’s algorithm.

Nagle’s algorithm can be disabled by using setsockopt

Labels:

Comments

Post a Comment

Popular posts from this blog

Dotnet, .Net 3.5, 2.0, C# Interview Questions

By
Few questions on dotnet, C# 2.0, 3.5 On Object oriented concepts 1)What is inheritance with e.g 2)What is polymorphism -function overloading -Function overriding -virtual keyword use -Static keyword and use -Abstract classes -Interface -Object 3)What is threading and how do we use in realtime application(cognizant) 4)What is threadpooling, lock, monitor(write code sample) 5)Architecture of current project 6)Session state, diffrent types of state management. 7)What is Application_Start, how it works. 8)Type of authentication in asp.net 9)How to configure ASP.NET application. 10) What is Impersonation. 11) What is WebService, WSDL, UDDI, Discovery, asmx files. 12) How to implement WebService and use it. 13) When to use WebServices. 14) WPF, how to implement(BOA) 15) Testing concvepts. 16) Test attributes 17) Flow of Automation Test Method execution 18) Features of dotnet 3.5 19) CLR, garbage collection 20) Finally block 21) Manifest, Metadata, MSIL 22) Assemblies, Type of assemblies, str...
2 comments
Read more

Linux SMB write performance With Simple Tips

By
SMB write performance can be increased by Tuning the buffer cache. The secret to good performance is to keep as much of the data in memory for as long as is possible. Writing to the disk is the slowest part of any filesystem. If you know that the filesystem will be heavily used, then you can tune this process for Linux Samba. writing out dirty blocks to the disk until the filesystem buffer cache is 80 percent full (80). default is 40%, source = http://tldp.org/LDP/solrhe/Securing-Optimizing-Linux-RH-Edition-v1.3/chap29sec287.html by writing echo 80 > /proc/sys/vm/dirty_ratio I am getting around 2MB increase while write operation, tested in Xp. I have tried with this single option, as the ref source is for linux 2.2 and we are using 2.6 kernel. we can try out Linux General Optimization suggested at http://tldp.org/LDP/solrhe/Securing-Optimizing-Linux-RH-Edition-v1.3/gen-optim.html Tried with smb.conf, I am getting around 1MB gain while read and write. socket options = TCP_NODELAY I...
Post a Comment
Read more

The Linux Foundation Free Training Program at linuxfoundation

By
The Linux Foundation Training Program is: * For the Community, by the Community. The Linux Foundation is building the program with its Technical Advisory Board to ensure the content, instructors and classes are the top quality available. * Technically the most advanced. Since the Linux Foundation works directly with community developers, it can cover features and advances in Linux before commercial companies. * Connected. The Linux Foundation has unfettered access to the leading developers and companies in the Linux ecosystem and will use these connections to best position attendees for success. For example, attendees can attend the exclusive, invite-only Collaboration Summit where they can forge connections beneficial to their career. * Real World. The Linux Foundation training courses all have hands on components and a highly rigorous curriculum of programming or administration exercises. Graduates will be well equipped to master Linux programming and system administr...
Post a Comment
Read more