Skip to main content

Sticky Session




Sticky session means that when a request comes into a site from a client all further requests go to the same server initial client request accessed. I believe that session affinity is a synonym for sticky session.

Both mean that when coming in to the load balancer, the request will be directed to the server that served the first request (and has the session).

The problem is "sticky session" where each user is assigned to a single server and his/her state data is contained on that server exclusively throughout the duration of the session.

Pros
  • it's easy-- no app changes required.
  • better utilizes local RAM caches (e.g. look up user profile once, cache it, and can re-use it on subsequent visits from same user)
Cons
·  if the server goes down, session is lost. (note that this is a con of storing session info locally on the web server-- not of sticky sessions per se). if what's in the session is really important to the user (e.g. a draft email) or to the site (e.g. a shopping cart) then losing one of your servers can be very painful.
·  depending on "sticky" implementation in your load balancer, may direct unequal load to some servers vs. others
·  bringing a new server online doesn't immediately give the new server lots of load-- if you have a dynamic load-balancing system to deal with spikes, stickiness may slow your ability to respond quickly to a spike. That said, this is somewhat of a corner case and really only applies to very large and sophisticated sites.
Labels:

Comments

Post a Comment

Popular posts from this blog

Error: could not find function "read.xlsx" while reading .xlsx file in R

Got this during the execution of following command in R > dat Error: could not find function "read.xlsx" Tried following command > install.packages("xlsx", dependencies = TRUE) Installing package into ‘C:/Users/amajumde/Documents/R/win-library/3.2’ (as ‘lib’ is unspecified) also installing the dependencies ‘rJava’, ‘xlsxjars’ trying URL 'https://cran.rstudio.com/bin/windows/contrib/3.2/rJava_0.9-8.zip' Content type 'application/zip' length 766972 bytes (748 KB) downloaded 748 KB trying URL 'https://cran.rstudio.com/bin/windows/contrib/3.2/xlsxjars_0.6.1.zip' Content type 'application/zip' length 9485170 bytes (9.0 MB) downloaded 9.0 MB trying URL 'https://cran.rstudio.com/bin/windows/contrib/3.2/xlsx_0.5.7.zip' Content type 'application/zip' length 400968 bytes (391 KB) downloaded 391 KB package ‘rJava’ successfully unpacked and MD5 sums checked package ‘xlsxjars’ successfully unpacked ...
Post a Comment
Read more

Training LLM model requires more GPU RAM than storing same LLM

Storing an LLM model and training the same model both require memory, but the memory requirements for training are typically higher than just storing the model. Let's dive into the details: Memory Requirement for Storing the Model: When you store an LLM model, you need to save the weights of the model parameters. Each parameter is typically represented by a 32-bit float (4 bytes). The memory requirement for storing the model weights is calculated by multiplying the number of parameters by 4 bytes. For example, if you have a model with 1 billion parameters, the memory requirement for storing the model weights alone would be 4 GB (4 bytes * 1 billion parameters). Memory Requirement for Training: During the training process, additional components use GPU memory in addition to the model weights. These components include optimizer states, gradients, activations, and temporary variables needed by the training process. These components can require additional memory beyond just storing th...
Post a Comment
Read more

What is the benefit of using Quantization in LLM

Quantization is a technique used in LLMs (Large Language Models) to reduce the memory requirements for storing and training the model parameters. It involves reducing the precision of the model weights from 32-bit floating-point numbers (FP32) to lower precision formats, such as 16-bit floating-point numbers (FP16) or 8-bit integers (INT8). Bottomline: You can use Quantization to reduce the memory footprint off the model during the training. The usage of quantization in LLMs offers several benefits: Memory Reduction: By reducing the precision of the model weights, quantization significantly reduces the memory footprint required to store the parameters. This is particularly important for LLMs, which can have billions or even trillions of parameters. Quantization allows these models to fit within the memory constraints of GPUs or other hardware accelerators. Training Efficiency: Quantization can also improve the training efficiency of LLMs. Lower precision formats require fewer computati...
Post a Comment
Read more