Improve disk read performance (multiple files) with threading

Posted by pablo on Stack Overflow See other posts from Stack Overflow or by pablo
Published on 2010-04-24T10:00:08Z Indexed on 2010/04/24 10:03 UTC
Read the original article Hit count: 170

Filed under:

c#

|

Performance

|

Windows

I need to find a method to read a big number of small files (about 300k files) as fast as possible.

Reading them sequentially using FileStream and reading the entire file in a single call takes between 170 and 208 seconds (you know, you re-run, disk cache plays its role and time varies).

Then I tried using PInvoke with CreateFile/ReadFile and using FILE_FLAG_SEQUENTIAL_SCAN, but I didn't appreciate any changes.

I tried with several threads (divide the big set in chunks and have every thread reading its part) and this way I was able to improve speed just a little bit (not even a 5% with every new thread up to 4).

Any ideas on how to find the most effective way to do this?

© Stack Overflow or respective owner

Related posts about c#

.NET WebRequest.PreAuthenticate not quite what it sounds like

as seen on West-Wind - Search for 'West-Wind'
I’ve run into the problem a few times now: How to pre-authenticate .NET WebRequest calls doing an HTTP call to the server – essentially send authentication credentials on the very first request instead of waiting for a server challenge first? At first glance this sound like it should be easy:… >>> More
HttpWebRequest and Ignoring SSL Certificate Errors

as seen on West-Wind - Search for 'West-Wind'
Man I can't believe this. I'm still mucking around with OFX servers and it drives me absolutely crazy how some these servers are just so unbelievably misconfigured. I've recently hit three different 3 major brokerages which fail HTTP validation with bad or corrupt certificates at least according to… >>> More
The dynamic Type in C# Simplifies COM Member Access from Visual FoxPro

as seen on West-Wind - Search for 'West-Wind'
I’ve written quite a bit about Visual FoxPro interoperating with .NET in the past both for ASP.NET interacting with Visual FoxPro COM objects as well as Visual FoxPro calling into .NET code via COM Interop. COM Interop with Visual FoxPro has a number of problems but one of them at least got a lot… >>> More
Dynamic Type to do away with Reflection

as seen on West-Wind - Search for 'West-Wind'
The dynamic type in C# 4.0 is a welcome addition to the language. One thing I’ve been doing a lot with it is to remove explicit Reflection code that’s often necessary when you ‘dynamically’ need to walk and object hierarchy. In the past I’ve had a number of ReflectionUtils that used string based expressions… >>> More
Finding a Relative Path in .NET

as seen on West-Wind - Search for 'West-Wind'
Here’s a nice and simple path utility that I’ve needed in a number of applications: I need to find a relative path based on a base path. So if I’m working in a folder called c:\temp\templates\ and I want to find a relative path for c:\temp\templates\subdir\test.txt I want to receive back subdir\test… >>> More

Related posts about Performance

Improving VPN performance - stronger encryption = more performance?

as seen on Server Fault - Search for 'Server Fault'
I have a site-to-site VPN set up with two SonicWall's (a TZ170 and a Pro1260). It was suggested to me that turning off encryption (so the VPN is tunneling only) would improve performance. (I'm not concerned with security, because the VPN is running over a trusted line.) Using FTP and HTTP transfers… >>> More
Inaccurate performance counter timer values in Windows Performance Monitor

as seen on Stack Overflow - Search for 'Stack Overflow'
I am implementing instrumentation within an application and have encountered an issue where the value that is displayed in Windows Performance Monitor from a PerformanceCounter is incongruent with the value that is recorded. I am using a Stopwatch to record the duration of a method execution, then… >>> More
Excel-based Performance Reviews transformed into Web Application for Performance Management

as seen on Geeks with Blogs - Search for 'Geeks with Blogs'
HR TMS provides enterprise talent management solutions for healthcare, retail and corporate customers, focusing on performance management, compensation management and succession planning. As the competency of nurses and other healthcare workers is critical, the government, via the Joint Commission… >>> More
How to save a perfmon Performance Counter as a textfile (Reliability and Performance Monitor Version

as seen on Server Fault - Search for 'Server Fault'
Now the file gets saved as blg, but I would like a txt versin to import in Excel. >>> More
SQLAuthority News – A Successful Performance Tuning Seminar at Pune – Dec 4-5, 2010

as seen on SQL Authority - Search for 'SQL Authority'
This is report to my third of very successful seminar event on SQL Server Performance Tuning. SQL Server Performance Tuning Seminar in Colombo was oversubscribed with total of 35 attendees. You can read the details over here SQLAuthority News – SQL Server Performance Optimizations Seminar – Grand… >>> More