| Message ID | 20220606065716.270879-2-haoxu.linux@icloud.com (mailing list archive) |
|---|---|
| State | New |
| Headers | show |
| Series | cancel_hash per entry lock | expand |
On 6/6/22 07:57, Hao Xu wrote: > From: Hao Xu <howeyxu@tencent.com> > > Add a new member hash_index in struct io_kiocb to track the req index > in cancel_hash array. This is needed in later patches. > > Signed-off-by: Hao Xu <howeyxu@tencent.com> > --- > io_uring/io_uring_types.h | 1 + > io_uring/poll.c | 4 +++- > 2 files changed, 4 insertions(+), 1 deletion(-) > > diff --git a/io_uring/io_uring_types.h b/io_uring/io_uring_types.h > index 7c22cf35a7e2..2041ee83467d 100644 > --- a/io_uring/io_uring_types.h > +++ b/io_uring/io_uring_types.h > @@ -474,6 +474,7 @@ struct io_kiocb { > u64 extra2; > }; > }; > + unsigned int hash_index; Didn't take a closer look, but can we make rid of it? E.g. computing it again when ejecting a request from the hash? or keep it in struct io_poll? > /* internal polling, see IORING_FEAT_FAST_POLL */ > struct async_poll *apoll; > /* opcode allocated if it needs to store data for async defer */ > diff --git a/io_uring/poll.c b/io_uring/poll.c > index 0df5eca93b16..95e28f32b49c 100644 > --- a/io_uring/poll.c > +++ b/io_uring/poll.c > @@ -74,8 +74,10 @@ static void io_poll_req_insert(struct io_kiocb *req) > { > struct io_ring_ctx *ctx = req->ctx; > struct hlist_head *list; > + u32 index = hash_long(req->cqe.user_data, ctx->cancel_hash_bits); > > - list = &ctx->cancel_hash[hash_long(req->cqe.user_data, ctx->cancel_hash_bits)]; > + req->hash_index = index; > + list = &ctx->cancel_hash[index]; > hlist_add_head(&req->hash_node, list); > } >
On 6/6/22 19:59, Pavel Begunkov wrote: > On 6/6/22 07:57, Hao Xu wrote: >> From: Hao Xu <howeyxu@tencent.com> >> >> Add a new member hash_index in struct io_kiocb to track the req index >> in cancel_hash array. This is needed in later patches. >> >> Signed-off-by: Hao Xu <howeyxu@tencent.com> >> --- >> io_uring/io_uring_types.h | 1 + >> io_uring/poll.c | 4 +++- >> 2 files changed, 4 insertions(+), 1 deletion(-) >> >> diff --git a/io_uring/io_uring_types.h b/io_uring/io_uring_types.h >> index 7c22cf35a7e2..2041ee83467d 100644 >> --- a/io_uring/io_uring_types.h >> +++ b/io_uring/io_uring_types.h >> @@ -474,6 +474,7 @@ struct io_kiocb { >> u64 extra2; >> }; >> }; >> + unsigned int hash_index; > > Didn't take a closer look, but can we make rid of it? > E.g. computing it again when ejecting a request from > the hash? or keep it in struct io_poll? Good point, I prefer moving it to io_poll to computing it again since this patchset is to try to make it faster.
diff --git a/io_uring/io_uring_types.h b/io_uring/io_uring_types.h index 7c22cf35a7e2..2041ee83467d 100644 --- a/io_uring/io_uring_types.h +++ b/io_uring/io_uring_types.h @@ -474,6 +474,7 @@ struct io_kiocb { u64 extra2; }; }; + unsigned int hash_index; /* internal polling, see IORING_FEAT_FAST_POLL */ struct async_poll *apoll; /* opcode allocated if it needs to store data for async defer */ diff --git a/io_uring/poll.c b/io_uring/poll.c index 0df5eca93b16..95e28f32b49c 100644 --- a/io_uring/poll.c +++ b/io_uring/poll.c @@ -74,8 +74,10 @@ static void io_poll_req_insert(struct io_kiocb *req) { struct io_ring_ctx *ctx = req->ctx; struct hlist_head *list; + u32 index = hash_long(req->cqe.user_data, ctx->cancel_hash_bits); - list = &ctx->cancel_hash[hash_long(req->cqe.user_data, ctx->cancel_hash_bits)]; + req->hash_index = index; + list = &ctx->cancel_hash[index]; hlist_add_head(&req->hash_node, list); }