• Home
• com.twitter
• finagle-netty4_2.11
• 6.39.0
• source code
• poolReceiveBuffers.scala

×

Project download

Many resources are needed to download a project. Please understand that we have to compensate our server costs. Thank you in advance.
Project price only 1 $

You can buy this project and download/modify it how often you want.

com.twitter.finagle.netty4.poolReceiveBuffers.scala Maven / Gradle / Ivy

package com.twitter.finagle.netty4

import com.twitter.app.GlobalFlag

/**
 * An experimental option that enables pooling for receive buffers.
 *
 * Since we always copy onto the heap (see `DirectToHeapInboundHandler`), the receive
 * buffers never leave the pipeline hence can safely be pooled.
 * In its current form, this will preallocate at least N * 2 mb (chunk size) of
 * direct memory at the application startup, where N is the number of worker threads
 * Finagle uses.
 *
 * Example:
 *
 * On a 16 core machine, the lower bound for the pool size will be 16 * 2 * 2mb = 64mb.
 *
 * @note This will likely be a default for finagle-netty4.
 */
object poolReceiveBuffers extends GlobalFlag(false, "enables/disables pooling of receive buffers")