在 2024/11/4 16:13, Dust Li 写道: > On 2024-11-02 14:43:52, Li Qiang wrote: >> >> >> 在 2024/11/1 18:52, Dust Li 写道: >>> On 2024-11-01 16:23:42, liqiang wrote: >>>> connections based on redis-benchmark (test in smc loopback-ism mode): >>> ... >>> ``` >> >> I tested with nginx, the test command is: >> # server >> smc_run nginx >> >> # client >> smc_run wrk -t <2,4,8,16,32,64> -c 200 -H "Connection: close" http://127.0.0.1 >> >> Requests/sec >> --------+---------------+---------------+ >> req/s | without patch | apply patch | >> --------+---------------+---------------+ >> -t 2 |6924.18 |7456.54 | >> --------+---------------+---------------+ >> -t 4 |8731.68 |9660.33 | >> --------+---------------+---------------+ >> -t 8 |11363.22 |13802.08 | >> --------+---------------+---------------+ >> -t 16 |12040.12 |18666.69 | >> --------+---------------+---------------+ >> -t 32 |11460.82 |17017.28 | >> --------+---------------+---------------+ >> -t 64 |11018.65 |14974.80 | >> --------+---------------+---------------+ >> >> Transfer/sec >> --------+---------------+---------------+ >> trans/s | without patch | apply patch | >> --------+---------------+---------------+ >> -t 2 |24.72MB |26.62MB | >> --------+---------------+---------------+ >> -t 4 |31.18MB |34.49MB | >> --------+---------------+---------------+ >> -t 8 |40.57MB |49.28MB | >> --------+---------------+---------------+ >> -t 16 |42.99MB |66.65MB | >> --------+---------------+---------------+ >> -t 32 |40.92MB |60.76MB | >> --------+---------------+---------------+ >> -t 64 |39.34MB |53.47MB | >> --------+---------------+---------------+ >> >>> >>>> >>>> 1. On the current version: >>>> [x.832733] smc_buf_get_slot cost:602 ns, walk 10 buf_descs >>>> [x.832860] smc_buf_get_slot cost:329 ns, walk 12 buf_descs >>>> [x.832999] smc_buf_get_slot cost:479 ns, walk 17 buf_descs >>>> [x.833157] smc_buf_get_slot cost:679 ns, walk 13 buf_descs >>>> ... >>>> [x.045240] smc_buf_get_slot cost:5528 ns, walk 196 buf_descs >>>> [x.045389] smc_buf_get_slot cost:4721 ns, walk 197 buf_descs >>>> [x.045537] smc_buf_get_slot cost:4075 ns, walk 198 buf_descs >>>> [x.046010] smc_buf_get_slot cost:6476 ns, walk 199 buf_descs >>>> >>>> 2. Apply this patch: >>>> [x.180857] smc_buf_get_slot_free cost:75 ns >>>> [x.181001] smc_buf_get_slot_free cost:147 ns >>>> [x.181128] smc_buf_get_slot_free cost:97 ns >>>> [x.181282] smc_buf_get_slot_free cost:132 ns >>>> [x.181451] smc_buf_get_slot_free cost:74 ns >>>> >>>> It can be seen from the data that it takes about 5~6us to traverse 200 >>> >>> Based on your data, I'm afraid the short-lived connection >>> test won't show much benificial. Since the time to complete a >>> SMC-R connection should be several orders of magnitude larger >>> than 100ns. >> >> Sorry, I didn't explain my test data well before. >> >> The main optimized functions of this patch are as follows: >> >> ``` >> struct smc_buf_desc *smc_buf_get_slot(...) >> { >> struct smc_buf_desc *buf_slot; >> down_read(lock); >> list_for_each_entry(buf_slot, buf_list, list) { >> if (cmpxchg(&buf_slot->used, 0, 1) == 0) { >> up_read(lock); >> return buf_slot; >> } >> } >> up_read(lock); >> return NULL; >> } >> ``` >> ... >> >> The optimized code is as follows: >> >> ``` >> static struct smc_buf_desc *smc_buf_get_slot_free(struct llist_head *buf_llist) >> { >> struct smc_buf_desc *buf_free; >> struct llist_node *llnode; >> >> if (llist_empty(buf_llist)) >> return NULL; >> // lock-less link list don't need an lock > ^^^ kernel use /**/ for comments Ok I will change it. :-) > >> llnode = llist_del_first(buf_llist); >> buf_free = llist_entry(llnode, struct smc_buf_desc, llist); > > If 2 CPU both passed the llist_empty() check, only 1 CPU can get llnode, > the other one should be NULL ? Well, what you said makes sense, I think the previous judgment of llist_empty is useless and can be deleted. This function should be changed to: ``` static struct smc_buf_desc *smc_buf_get_slot_free(struct llist_head *buf_llist) { struct smc_buf_desc *buf_free; struct llist_node *llnode; /* lock-less link list don't need an lock */ llnode = llist_del_first(buf_llist); if (llnode == NULL) return NULL; buf_free = llist_entry(llnode, struct smc_buf_desc, llist); WRITE_ONCE(buf_free->used, 1); return buf_free; } ``` If there is only one node left in the linked list, multiple CPUs will compete based on CAS instructions in llist_del_first. In the end, only one consumer will get the node, and other consumers will get the null pointer. Thank you! > >> WRITE_ONCE(buf_free->used, 1); >> return buf_free; >> } >> ``` -- Best regards, Li Qiang
