[dpdk-dev] [PATCH v3 4/7] hash: add memory ordering to avoid race conditions

Honnappa Nagarahalli Honnappa.Nagarahalli at arm.com
Wed Oct 17 01:28:53 CEST 2018


> When I applied this commit:
> fatal: sha1 information is lacking or useless
> (lib/librte_hash/rte_cuckoo_hash.c).
> Please double check.
I will verify the patches when I send out the next version.

> 
> >-----Original Message-----
> >From: Honnappa Nagarahalli [mailto:honnappa.nagarahalli at arm.com]
> >Sent: Thursday, October 11, 2018 11:32 PM
> >To: Richardson, Bruce <bruce.richardson at intel.com>; De Lara Guarch,
> >Pablo <pablo.de.lara.guarch at intel.com>
> >Cc: dev at dpdk.org; Wang, Yipeng1 <yipeng1.wang at intel.com>;
> >honnappa.nagarahalli at arm.com; dharmik.thakkar at arm.com;
> >gavin.hu at arm.com; nd at arm.com
> >Subject: [PATCH v3 4/7] hash: add memory ordering to avoid race
> >conditions
> >
> >Only race condition that can occur is -  using the key store element
> >before the key write is completed. Hence, while inserting the element
> >the release memory order is used. Any other race condition is caught by
> >the key comparison. Memory orderings are added only where needed.
> >For ex: reads in the writer's context do not need memory ordering as
> >there is a single writer.
> [Wang, Yipeng]
> I remember we discussed that this commit itself does not fix any bug/issue, or
> enabling feature, it is supposed to work with the following patches to enable
> lock-free read-write concurrency. You separated the commits for easier
> review.
> 
> If you plan to merge these commits and change the commit message it would
> be fine. Otherwise the current message title and content Is misleading. It
> sounds like a bug fix but actually not.
I think it is time to merge this commit. I will do it in the next version.


More information about the dev mailing list