Hi, Running a splice benchmark on a 4-way IPF box, I decided to give the lockless page cache patches from Nick a spin. I've attached the results as a png, it pretty much speaks for itself. The test in question splices a 1GiB file to a pipe and then splices that to some output. Normally that output would be something interesting, in this case it's simply /dev/null. So it tests the input side of things only, which is what I wanted to do here. To get adequate runtime, the operation is repeated a number of times (120 in this example). The benchmark does that number of loops with 1, 2, 3, and 4 clients each pinned to a private CPU. The pinning is mainly done for more stable results. -- Jens Axboe
Attachment:
lockless.png
Description: PNG image
- Follow-Ups:
- Re: Lockless page cache test results
- From: Pavel Machek <[email protected]>
- Re: Lockless page cache test results
- From: Nick Piggin <[email protected]>
- Re: Lockless page cache test results
- From: Andrew Morton <[email protected]>
- Re: Lockless page cache test results
- Prev by Date: [PATCH] i386: apic= command line option should always be honored
- Next by Date: [PATCH] adjust outputmakefile rule
- Previous by thread: [PATCH] i386: apic= command line option should always be honored
- Next by thread: Re: Lockless page cache test results
- Index(es):
 |