Re: [PATCH v7] eal: add seqlock

2022-05-19 Thread Mattias Rönnblom
On 2022-05-15 14:39, Mattias Rönnblom wrote: On 2022-05-15 14:24, Mattias Rönnblom wrote: A sequence lock (seqlock) is a synchronization primitive which allows for data-race free, low-overhead, high-frequency reads, suitable for data structures shared across many cores and which are updated rela

RE: [PATCH v7] eal: add seqlock

2022-05-16 Thread Morten Brørup
> From: Mattias Rönnblom [mailto:hof...@lysator.liu.se] > Sent: Sunday, 15 May 2022 19.54 > > On 2022-05-15 17:19, Morten Brørup wrote: > >> From: Mattias Rönnblom [mailto:mattias.ronnb...@ericsson.com] > >> Sent: Sunday, 15 May 2022 14.40 > >> > >> Two questions remain: > >> > >> 1) Should the se

Re: [PATCH v7] eal: add seqlock

2022-05-15 Thread Mattias Rönnblom
On 2022-05-15 17:19, Morten Brørup wrote: From: Mattias Rönnblom [mailto:mattias.ronnb...@ericsson.com] Sent: Sunday, 15 May 2022 14.40 Two questions remain: 1) Should the seqlock and the seqcount reside in different header files? 2) Is it it good enough to provided only a spinlock-protected se

RE: [PATCH v7] eal: add seqlock

2022-05-15 Thread Morten Brørup
(Resent with Konstantin's new email address.) > From: Mattias Rönnblom [mailto:mattias.ronnb...@ericsson.com] > Sent: Sunday, 15 May 2022 14.40 > > Two questions remain: > > 1) Should the seqlock and the seqcount reside in different header > files? > 2) Is it it good enough to provided only a sp

Recall: [PATCH v7] eal: add seqlock

2022-05-15 Thread Morten Brørup
Morten Brørup would like to recall the message, "[PATCH v7] eal: add seqlock".

RE: [PATCH v7] eal: add seqlock

2022-05-15 Thread Morten Brørup
> From: Mattias Rönnblom [mailto:mattias.ronnb...@ericsson.com] > Sent: Sunday, 15 May 2022 14.40 > > Two questions remain: > > 1) Should the seqlock and the seqcount reside in different header > files? > 2) Is it it good enough to provided only a spinlock-protected seqlock? > > Question 1 I don

Re: [PATCH v7] eal: add seqlock

2022-05-15 Thread Mattias Rönnblom
On 2022-05-15 14:24, Mattias Rönnblom wrote: > A sequence lock (seqlock) is a synchronization primitive which allows > for data-race free, low-overhead, high-frequency reads, suitable for > data structures shared across many cores and which are updated > relatively infrequently. > > A seqlock perm

[PATCH v7] eal: add seqlock

2022-05-15 Thread Mattias Rönnblom
A sequence lock (seqlock) is a synchronization primitive which allows for data-race free, low-overhead, high-frequency reads, suitable for data structures shared across many cores and which are updated relatively infrequently. A seqlock permits multiple parallel readers. A spinlock is used to seri