DPDK patches and discussions
 help / color / mirror / Atom feed
* Re: [dpdk-dev] Why cuckoo based hashing in DPDK library?
@ 2017-09-01 16:15 Andriy Berestovskyy
  2017-09-13 16:49 ` Mcnamara, John
  0 siblings, 1 reply; 3+ messages in thread
From: Andriy Berestovskyy @ 2017-09-01 16:15 UTC (permalink / raw)
  To: Evgeny Agronsky; +Cc: DPDK

Hey Evgeny,
Please see inline.

On Thu, Aug 31, 2017 at 9:35 AM, Evgeny Agronsky
<evgeny.agronsky@gmail.com> wrote:
> I'm basicly asking because of it's poor performance under high

Well, it is not the academic cuckoo hash implementation, so the
performance is not that bad and it also utilizes cache ;)

Please have a look at this paper for more details:
http://www.cs.cmu.edu/~dongz/papers/cuckooswitch.pdf

> with universal hash functions? I'm simply curious, maybe you have some sort
> of benchmarks.

Once someone implement a Hopscotch for DPDK, we could run some benchmarks... ;)
But sure, it would be great to have a faster hash implementation,
since DPDK is all about performance...

Andriy

^ permalink raw reply	[flat|nested] 3+ messages in thread

* Re: [dpdk-dev] Why cuckoo based hashing in DPDK library?
  2017-09-01 16:15 [dpdk-dev] Why cuckoo based hashing in DPDK library? Andriy Berestovskyy
@ 2017-09-13 16:49 ` Mcnamara, John
  0 siblings, 0 replies; 3+ messages in thread
From: Mcnamara, John @ 2017-09-13 16:49 UTC (permalink / raw)
  To: Andriy Berestovskyy, Evgeny Agronsky; +Cc: DPDK



> -----Original Message-----
> From: dev [mailto:dev-bounces@dpdk.org] On Behalf Of Andriy Berestovskyy
> Sent: Friday, September 1, 2017 5:15 PM
> To: Evgeny Agronsky <evgeny.agronsky@gmail.com>
> Cc: DPDK <dev@dpdk.org>
> Subject: Re: [dpdk-dev] Why cuckoo based hashing in DPDK library?
> 
> Hey Evgeny,
> Please see inline.
> 
> On Thu, Aug 31, 2017 at 9:35 AM, Evgeny Agronsky
> <evgeny.agronsky@gmail.com> wrote:
> > I'm basicly asking because of it's poor performance under high
> 
> Well, it is not the academic cuckoo hash implementation, so the
> performance is not that bad and it also utilizes cache ;)
> 
> Please have a look at this paper for more details:
> http://www.cs.cmu.edu/~dongz/papers/cuckooswitch.pdf
> 
> > with universal hash functions? I'm simply curious, maybe you have some
> > sort of benchmarks.
> 
> Once someone implement a Hopscotch for DPDK, we could run some
> benchmarks... ;) But sure, it would be great to have a faster hash
> implementation, since DPDK is all about performance...

Hi,

It might be worth having a generic hash interface in DPDK that other hash algorithms could be inserted under so that comparisons/replacements would be easier.

John

^ permalink raw reply	[flat|nested] 3+ messages in thread

* [dpdk-dev] Why cuckoo based hashing in DPDK library?
@ 2017-08-31  7:35 Evgeny Agronsky
  0 siblings, 0 replies; 3+ messages in thread
From: Evgeny Agronsky @ 2017-08-31  7:35 UTC (permalink / raw)
  To: dev

Hello,

I'm using dpdk lib for various purposes, lately I needed to use a hashmap
for a certain needs and the one I found as part of the library was cuckoo
hashing based hashmap, I'm just wondering is there any reason for cuckoo
hashing? I'm basicly asking because of it's poor performance under high
table loads(and uses 2 hash funcs). Why not Hopscotch Hashing for example
which performs much better under loads, utilizes the cache and works well
with universal hash functions? I'm simply curious, maybe you have some sort
of benchmarks.

Thanks,
Evgeny Agronsky

^ permalink raw reply	[flat|nested] 3+ messages in thread

end of thread, other threads:[~2017-09-13 16:49 UTC | newest]

Thread overview: 3+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2017-09-01 16:15 [dpdk-dev] Why cuckoo based hashing in DPDK library? Andriy Berestovskyy
2017-09-13 16:49 ` Mcnamara, John
  -- strict thread matches above, loose matches on Subject: below --
2017-08-31  7:35 Evgeny Agronsky

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).