[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [Qemu-devel] [PATCH v5 12/18] qht: QEMU's fast, resizable and scalab
From: |
Alex Bennée |
Subject: |
Re: [Qemu-devel] [PATCH v5 12/18] qht: QEMU's fast, resizable and scalable Hash Table |
Date: |
Sun, 22 May 2016 09:01:59 +0100 |
User-agent: |
mu4e 0.9.17; emacs 25.0.93.7 |
Emilio G. Cota <address@hidden> writes:
> On Fri, May 20, 2016 at 22:48:11 -0400, Emilio G. Cota wrote:
>> On Sat, May 21, 2016 at 01:13:20 +0300, Sergey Fedorov wrote:
>> > > +static inline
>> > > +void *qht_do_lookup(struct qht_bucket *head, qht_lookup_func_t func,
>> > > + const void *userp, uint32_t hash)
>> > > +{
>> > > + struct qht_bucket *b = head;
>> > > + int i;
>> > > +
>> > > + do {
>> > > + for (i = 0; i < QHT_BUCKET_ENTRIES; i++) {
>> > > + if (atomic_read(&b->hashes[i]) == hash) {
>> > > + void *p = atomic_read(&b->pointers[i]);
>> >
>> > Why do we need this atomic_read() and other (looking a bit inconsistent)
>> > atomic operations on 'b->pointers' and 'b->hash'? if we always have to
>> > access them protected properly by a seqlock together with a spinlock?
>>
>> [ There should be consistency: read accesses use the atomic ops to read,
>> while write accesses have acquired the bucket lock so don't need them.
>> Well, they need care when they write, since there may be concurrent
>> readers. ]
>>
>> I'm using atomic_read but what I really want is ACCESS_ONCE. That is:
>> (1) Make sure that the accesses are done in a single instruction (even
>> though gcc doesn't explicitly guarantee it even to aligned addresses
>> anymore[1])
>> (2) Make sure the pointer value is only read once, and never refetched.
>> This is what comes right after the pointer is read:
>> > + if (likely(p) && likely(func(p, userp))) {
>> > + return p;
>> > + }
>> Refetching the pointer value might result in us passing something
>> a NULL p value to the comparison function (since there may be
>> concurrent updaters!), with an immediate segfault. See [2] for a
>> discussion on this (essentially the compiler assumes that there's
>> only a single thread).
>>
>> Given that even reading a garbled hash is OK (we don't really need (1),
>> since the seqlock will make us retry anyway), I've changed the code to:
>>
>> for (i = 0; i < QHT_BUCKET_ENTRIES; i++) {
>> - if (atomic_read(&b->hashes[i]) == hash) {
>> + if (b->hashes[i] == hash) {
>> + /* make sure the pointer is read only once */
>> void *p = atomic_read(&b->pointers[i]);
>>
>> if (likely(p) && likely(func(p, userp))) {
>>
>> Performance-wise this is the impact after 10 tries for:
>> $ taskset -c 0 tests/qht-bench \
>> -d 5 -n 1 -u 0 -k 4096 -K 4096 -l 4096 -r 4096 -s 4096
>> on my Haswell machine I get, in Mops/s:
>> atomic_read() for all 40.389 +- 0.20888327415622
>> atomic_read(p) only 40.759 +- 0.212835356294224
>> no atomic_read(p) (unsafe) 40.559 +- 0.121422128680622
>>
>> Note that the unsafe version is slightly slower; I guess the CPU is trying
>> to speculate too much and is gaining little from it.
>>
>> [1] "Linux-Kernel Memory Model" by Paul McKenney
>> http://www.open-std.org/jtc1/sc22/wg21/docs/papers/2015/n4374.html
>> [2] https://lwn.net/Articles/508991/
>
> A small update: I just got rid of all the atomic_read/set's that
> apply to the hashes, since retries will take care of possible races.
I guess the potential hash-clash from a partially read or set hash is
handled by the eventual compare against a always valid pointer?
>
> The atomic_read/set's remain only for b->pointers[], for the
> above reasons.
>
> E.
--
Alex Bennée
- [Qemu-devel] [PATCH v5 15/18] qht: add qht-bench, a performance benchmark, (continued)
- [Qemu-devel] [PATCH v5 15/18] qht: add qht-bench, a performance benchmark, Emilio G. Cota, 2016/05/13
- [Qemu-devel] [PATCH v5 14/18] qht: add test program, Emilio G. Cota, 2016/05/13
- [Qemu-devel] [PATCH v5 09/18] tb hash: hash phys_pc, pc, and flags with xxhash, Emilio G. Cota, 2016/05/13
- [Qemu-devel] [PATCH v5 11/18] qdist: add test program, Emilio G. Cota, 2016/05/13
- [Qemu-devel] [PATCH v5 12/18] qht: QEMU's fast, resizable and scalable Hash Table, Emilio G. Cota, 2016/05/13
- Re: [Qemu-devel] [PATCH v5 12/18] qht: QEMU's fast, resizable and scalable Hash Table, Sergey Fedorov, 2016/05/20
- Re: [Qemu-devel] [PATCH v5 12/18] qht: QEMU's fast, resizable and scalable Hash Table, Emilio G. Cota, 2016/05/20
- Re: [Qemu-devel] [PATCH v5 12/18] qht: QEMU's fast, resizable and scalable Hash Table, Emilio G. Cota, 2016/05/21
- Re: [Qemu-devel] [PATCH v5 12/18] qht: QEMU's fast, resizable and scalable Hash Table,
Alex Bennée <=
- Re: [Qemu-devel] [PATCH v5 12/18] qht: QEMU's fast, resizable and scalable Hash Table, Emilio G. Cota, 2016/05/23
- Re: [Qemu-devel] [PATCH v5 12/18] qht: QEMU's fast, resizable and scalable Hash Table, Sergey Fedorov, 2016/05/21
- Re: [Qemu-devel] [PATCH v5 12/18] qht: QEMU's fast, resizable and scalable Hash Table, Sergey Fedorov, 2016/05/23
Re: [Qemu-devel] [PATCH v5 00/18] tb hash improvements, Sergey Fedorov, 2016/05/23