Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]


Groups > comp.programming.threads > #4665

Transactional Memory Everywhere: I/O Operations

From Horizon68 <horizon@horizon.com>
Newsgroups comp.programming.threads
Subject Transactional Memory Everywhere: I/O Operations
Date 2018-10-03 12:16 -0700
Organization A noiseless patient Spider
Message-ID <pp34hm$dsa$1@dont-email.me> (permalink)

Show all headers | View raw


Hello,


Transactional Memory Everywhere: I/O Operations

One can execute I/O operations within a lock-based critical section, 
and, at least in principle, from within an RCU read-side critical 
section.  What happens when you attempt to execute an I/O operation from 
within a transaction?

The underlying problem is that transactions may be rolled back, for 
example, due to conflicts.  Roughly speaking, this requires that all 
operations within any given transaction be idempotent, so that executing 
the operation twice has the same effect as executing it once. 
Unfortunately, I/O is in general the prototypical non-idempotent 
operation, making it difficult to include general I/O operations in 
transactions.

Read more here:

https://mirrors.edge.kernel.org/pub/linux/kernel/people/paulmck/Answers/TransactionalMemoryEverywhere/IO.html


Thank you,
Amine Moulay Ramdane.

Back to comp.programming.threads | Previous | Next | Find similar | Unroll thread


Thread

Transactional Memory Everywhere: I/O Operations Horizon68 <horizon@horizon.com> - 2018-10-03 12:16 -0700

csiph-web