Messages in this thread | | | Subject | Re: [PATCH v7 2/2]: perf record: enable asynchronous trace writing | From | Alexey Budankov <> | Date | Thu, 6 Sep 2018 15:09:19 +0300 |
| |
On 06.09.2018 14:04, Jiri Olsa wrote: > On Wed, Sep 05, 2018 at 10:39:25AM +0300, Alexey Budankov wrote: > > SNIP > >> + } else if (errno != EAGAIN) { >> + cblock->aio_fildes = -1; >> + pr_err("failed to queue perf data, error: %m\n"); >> + break; >> + } >> + } while (1); >> + >> + return rc; >> +} >> + >> +static int record__aio_sync(struct perf_mmap *md) >> +{ > > this is almost identical to record__aio_sync function, > it looks like we should be able to do the sync with > single function.. for both the in-between syncs and > the final one
There is some code duplication here. for()'s loop body at record__aio_complete() could probably be separated to a function and then reused by record__aio_sync(). The rest is not obvious at the moment.
> > jirka >
| |