[dpdk-dev] [PATCH v4 0/8] Add read-write concurrency to rte_hash library

[Wang, Yipeng1]

Hi, Honnappa,

Thanks for the comment.

RCU can handle one of the currency issue (key deletion while lookup) that has been discussed before, but we think it is not easy for RCU-alone to
protect reader from cuckoo path displacement. Also, RCU solution requires user interaction.

We agree that the current rwlock does not support preemptable writer. But a more advanced rwlock with priority could be
implemented in the future into the rwlock library.

Thanks
Yipeng

>-----Original Message-----
>From: Honnappa Nagarahalli [mailto:Honnappa.Nagarahalli at arm.com]
>Sent: Tuesday, July 10, 2018 11:00 AM
>To: Wang, Yipeng1 <yipeng1.wang at intel.com>; De Lara Guarch, Pablo <pablo.de.lara.guarch at intel.com>
>Cc: dev at dpdk.org; Richardson, Bruce <bruce.richardson at intel.com>; vguvva at caviumnetworks.com; brijesh.s.singh at gmail.com; nd
><nd at arm.com>
>Subject: RE: [PATCH v4 0/8] Add read-write concurrency to rte_hash library
>
>Hi Yipeng/Pablo,
>	Apologies for my delayed comments
>
>-----Original Message-----
>From: Yipeng Wang <yipeng1.wang at intel.com>
>Sent: Monday, July 9, 2018 5:45 AM
>To: pablo.de.lara.guarch at intel.com
>Cc: dev at dpdk.org; yipeng1.wang at intel.com; bruce.richardson at intel.com; Honnappa Nagarahalli <Honnappa.Nagarahalli at arm.com>;
>vguvva at caviumnetworks.com; brijesh.s.singh at gmail.com
>Subject: [PATCH v4 0/8] Add read-write concurrency to rte_hash library
>
>This patch set adds the read-write concurrency support in rte_hash.
>A new flag value is added to indicate if read-write concurrency is needed during creation time. Test cases are implemented to do
>functional and performance tests.
>
>The new concurrency model is based on rte_rwlock. When Intel TSX is available and the users indicate to use it, the TM version of the
>rte_rwlock will be called. Both multi-writer and read-write concurrency are protected by the rte_rwlock instead of the x86 specific
>RTM instructions, so the x86 specific header rte_cuckoo_hash_x86.h is removed and the code is infused into the main .c file.
>
>IMO, at a high-level, there are two use cases for the rte_hash library:
>1) Writers are on control plane and data plane are readers
>2) Writers and readers are on data plane
>
>This distinction is required as in the case of 1) writers are pre-emptible. If I consider platforms without TSX (I do not know how Intel
>TSX works), the rte_rwlock implementation is blocking. A writer on the control plane can take the lock and get pre-empted. Since
>rte_rwlock is used for read-write concurrency, it will block the readers (on the data plane) for an extended duration. I think, support
>for RCU is required to solve this issue.
>
>