lkml.org 
[lkml]   [2015]   [Nov]   [25]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
SubjectRe: [PATCH] vmscan: do not throttle kthreads due to too_many_isolated
From
Date
On 11/25/2015 04:36 PM, Vladimir Davydov wrote:
> Block device drivers often hand off io request processing to kernel
> threads (example: device mapper). If such a thread calls kmalloc, it can
> dive into direct reclaim path and end up waiting for too_many_isolated
> to return false, blocking writeback. This can lead to a dead lock if the

Shouldn't such allocation lack __GFP_IO to prevent this and other kinds of
deadlocks? And/or have mempools? PF_KTHREAD looks like a big hammer to me that
will solve only one potential problem...



\
 
 \ /
  Last update: 2015-11-25 17:01    [W:0.285 / U:0.572 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site