lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Date:   Thu, 28 Apr 2022 23:23:42 +0200
From:   Bernd Schubert <bernd.schubert@...tmail.fm>
To:     Miklos Szeredi <miklos@...redi.hu>
Cc:     Bernd Schubert <bschubert@....com>,
        Linux-FSDevel <linux-fsdevel@...r.kernel.org>,
        Linux Kernel <linux-kernel@...r.kernel.org>,
        Dharmendra Singh <dsingh@....com>
Subject: Re: RFC fuse waitq latency

Sorry for my late reply, I'm on vacation and family visit this week.

On 4/25/22 10:37, Miklos Szeredi wrote:
> On Fri, 22 Apr 2022 at 17:46, Bernd Schubert <bernd.schubert@...tmail.fm> wrote:
>>
>> [I removed the failing netapp/zufs CCs]
>>
>> On 4/22/22 14:25, Miklos Szeredi wrote:
>>> On Mon, 28 Mar 2022 at 15:21, Bernd Schubert <bschubert@....com> wrote:
>>>>
>>>> I would like to discuss the user thread wake up latency in
>>>> fuse_dev_do_read(). Profiling fuse shows there is room for improvement
>>>> regarding memory copies and splice. The basic profiling with flame graphs
>>>> didn't reveal, though, why fuse is so much
>>>> slower (with an overlay file system) than just accessing the underlying
>>>> file system directly and also didn't reveal why a single threaded fuse
>>>> uses less than 100% cpu, with the application on top of use also using
>>>> less than 100% cpu (simple bonnie++ runs with 1B files).
>>>> So I started to suspect the wait queues and indeed, keeping the thread
>>>> that reads the fuse device for work running for some time gives quite
>>>> some improvements.
>>>
>>> Might be related: I experimented with wake_up_sync() that didn't meet
>>> my expectations.  See this thread:
>>>
>>> https://lore.kernel.org/all/1638780405-38026-1-git-send-email-quic_pragalla@quicinc.com/#r
>>>
>>> Possibly fuse needs some wake up tweaks due to its special scheduling
>>> requirements.
>>
>> Thanks I will look at that as well. I have a patch with spinning and
>> avoid of thread wake  that is almost complete and in my (still limited)
>> testing almost does not take more CPU and improves meta data / bonnie
>> performance in between factor ~1.9 and 3, depending on in which
>> performance mode the cpu is.
>>
>> https://github.com/aakefbs/linux/commits/v5.17-fuse-scheduling3
>>
>> Missing is just another option for wake-queue-size trigger and handling
>> of signals. Should be ready once I'm done with my other work.
> 
> Trying to understand what is being optimized here...  does the
> following correctly describe your use case?
> 
> - an I/O thread is submitting synchronous requests (direct I/O?)
> 
> - the fuse thread always goes to sleep, because the request queue is
> empty (there's always a single request on the queue)
> 
> - with this change the fuse thread spins for a jiffy before going to
> sleep, and by that time the I/O thread will submit a new sync request.
> 
> - the I/O thread does not spin while the the fuse thread is processing
> the request, so it still goes to sleep.


Yes, this describes it well. We basically noticed weird effects with 
multiple fuse threads when you had asked for benchmarks of the atomic 
create/open patches. In our HPC world the standard for such benchmarks 
is to use mdtest, but for simplicity I personally prefer bonnie++, like 
"bonnie++ -s0 -n10:1:1:10 -d <dest-path>"

Initial results were rather confusing, as reduced number of requests 
could result in lower performance. So I started to investigate and found 
a number of issues

1) passthrough_ll is using a single linked list to store inodes, we 
later switched to passthrough_hp which uses a C++ map to avoid the O(N) 
inode search

2) limiting the number of threads in libfuse using the max_idle_threads 
variable caused additional high cpu usage - there was permanent pthread 
creation/destruction. I have submitted patches for that (additional 
difficulty is to fix the API to avoid uninitialized struct members in 
libfuse3)

3) There is some overhead with splice for small requests like meta data. 
Even though the libfuse already tries to use splice for larger requests 
only. But unless disabled it still does a splice system call for the 
request header - enough to introduce a perf penalty. I have some very 
experimental patches for that as well, although it got much more 
difficult than I had initially hoped for. With these patches applied I 
started to profile the system with flame graphs and noticed that 
performance is much lower than it could be explained by the fuse cpu 
overhead.

4) Figured out about the waitq overhead. In the mean time I'm rather 
surprised about the zufs results - benchmarks had been done with at 
least  n-application thread >= 2 x n-zufs threads? Using thread spinning 
might avoid the issue, but with request queue per core in worst case all 
system cores might go a bit into spinning mode - at least not idea for 
embedded systems. And also not ideal for power consumption on laptops or 
phones and neither for HPC systems where systems are supposed to be busy 
to do calculations.

4.1) A sub problem of the waitq is the sleep condition - it checks if 
there are no pending requests - threads on different cores randomly wake 
up, even with avoided explicit thread wake as in my patches.

Right now I'm at a point where I see that my patches help to improve 
performance, but I'm not totally happy with the solution myself. That is 
basically where I believe that a SQ/CQ approach would give better 
performance and should/might avoid additional complexity.  At a minimum 
the request queue (SQ) spinning could be totally controlled/handled in 
user space.
Just need to find the time to code it...


Bernd

Powered by blists - more mailing lists