From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-wi0-f172.google.com (mail-wi0-f172.google.com [209.85.212.172]) by dpdk.org (Postfix) with ESMTP id E43534A63 for ; Fri, 5 Jun 2015 17:24:57 +0200 (CEST) Received: by wiam3 with SMTP id m3so22880735wia.1 for ; Fri, 05 Jun 2015 08:24:57 -0700 (PDT) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20130820; h=x-gm-message-state:mime-version:in-reply-to:references:date :message-id:subject:from:to:cc:content-type; bh=uTlIcYWtz2jRU70Bt8XsKLRoMGfKvjqbtHMOWN5amps=; b=jtz9Ucvmw/07SRVHZiqQNiboTAA7rDo1OpeRnRU+t1kMhww21urCGXPG060aHeZVir TEMZl3qaO5tqRkTZm7hcmUDVBJBV4rSjNmRbhgb68baBfOglWctRaTUpTxrnngRjUSrj keqP4BrcFHcsk/7gcon1lKHtoZL2JRP80w7rnl7uiylgcX6JenrYk9WCFagqBVR/r/LU puE/5QGTSBYIszr5Ox6BdKe41bJ3/9f3F5i27P3RY51+s4UWM5a68lou+36zFtZtnQD3 m+37rp3e0Y2gM04ms4G0lHey+7/BWE0HFq5XL+24RwFiNCzzObPBhQ7/q1Ze12xsJbvP T+ow== X-Gm-Message-State: ALoCoQnAmP+b1YsNsTc94SACOgJ4r6EAeyeWIN5hesDS9pKtlJIbB9L524qL7sxR0EdOBIux0gAB MIME-Version: 1.0 X-Received: by 10.194.157.168 with SMTP id wn8mr7215622wjb.79.1433517897789; Fri, 05 Jun 2015 08:24:57 -0700 (PDT) Received: by 10.194.36.193 with HTTP; Fri, 5 Jun 2015 08:24:57 -0700 (PDT) In-Reply-To: <5571BC86.8060909@bisdn.de> References: <5571BC86.8060909@bisdn.de> Date: Fri, 5 Jun 2015 10:24:57 -0500 Message-ID: From: Jay Rolette To: Marc Sune Content-Type: text/plain; charset=UTF-8 X-Content-Filtered-By: Mailman/MimeDel 2.1.15 Cc: DPDK Subject: Re: [dpdk-dev] KNI performance X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: patches and discussions about DPDK List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 05 Jun 2015 15:24:58 -0000 On Fri, Jun 5, 2015 at 10:13 AM, Marc Sune wrote: > > > On 05/06/15 17:06, Jay Rolette wrote: > >> The past few days I've been trying to chase down why operations over KNI >> are so bloody slow. To give you an idea how bad it is, we did a simple >> test >> over an NFS mount: >> >> # Mount over a non-KNI interface (eth0 on vanilla Ubuntu 14.04 LTS) >> $ time $(ls -last -R /mnt/sfs2008 > /dev/null) >> real 11m58.224s >> user 0m10.758s >> sys 0m25.050s >> >> # Reboot to make sure NFS cache is cleared and mount over a KNI interface >> $ time $(ls -last -R /mnt/sfs2008 > /dev/null) >> real 87m36.295s >> user 0m14.552s >> sys 0m25.949s >> >> Packet captures showed a pretty consistent ~4ms delay. Get a READDIRPLUS >> reply from NFS server and the TCP stack on the DPDK/KNI system took about >> 4ms to ACK the reply. It isn't just on ACK packets either. If there was no >> ACK required, there would be a 4ms delay before the next call was sent >> (ACCESS, LOOKUP, another READDIR, etc.). >> >> This is running on top of a real DPDK app, so there are various queues and >> ring-buffers in the path between KNI and the wire, so I started there. >> Long >> story short, worst case, those could only inject ~120us of latency into >> the >> path. >> >> Next stop was KNI itself. Ignoring a few minor optos I found, nothing in >> the code looked like it could account for 4ms of latency. That wasn't >> quite >> right though... >> >> Here's the code for the processing loop in kni_thread_single(): >> >> while (!kthread_should_stop()) { >> down_read(&kni_list_lock); >> for (j = 0; j < KNI_RX_LOOP_NUM; j++) { >> list_for_each_entry(dev, &kni_list_head, list) { >> #ifdef RTE_KNI_VHOST >> kni_chk_vhost_rx(dev); >> #else >> kni_net_rx(dev); >> #endif >> kni_net_poll_resp(dev); >> } >> } >> up_read(&kni_list_lock); >> /* reschedule out for a while */ >> schedule_timeout_interruptible(usecs_to_jiffies( \ >> KNI_KTHREAD_RESCHEDULE_INTERVAL)); >> >> Turns out the 4ms delay is due to the schedule_timeout() call. The code >> specifies a 5us sleep, but the call only guarantees a sleep of *at least* >> the time specified. >> >> The resolution of the sleep is controlled by the timer interrupt rate. If >> you are using a kernel from one of the usual Linux distros, HZ = 250 on >> x86. That works out nicely to a 4ms period. The KNI kernel thread was >> going >> to sleep and frequently not getting woken up for nearly 4ms. >> >> We rebuilt the kernel with HZ = 1000 and things improved considerably: >> >> # Mount over a KNI interface, HZ=1000 >> $ time $(ls -last -R /mnt/sfs2008 > /dev/null) >> >> real 21m8.478s >> user 0m13.824s >> sys 0m18.113s >> >> Still not where I'd like to get it, but much, much better. >> >> Hopefully my pain is your gain and this helps other KNI users. >> > > Jay, > > If you set CONFIG_RTE_KNI_PREEMPT_DEFAULT to 'n' you should see a reduced > latency and delay since there is no preemption (though sacrifices 1 CPU for > the kni kmod): > > http://patchwork.dpdk.org/dev/patchwork/patch/3304/ > > However, KNI is still pretty slow. Even considering that there will always > be at least 1 copy involved, I still think is too slow. I didn't had time > to look closer yet. > > Marc > Hi Marc, Thanks for the pointer to the patch. I did something similar as a test before we started mucking with rebuilding the kernel. Skipping the call to put the KNI kernel thread to sleep improved performance and reduced latency, but oddly enough, it wasn't as fast for the end-app as the HZ=1000 change. Here's what I got on that test: # Mount over "no-sleep" KNI $ time $(ls -last -R /mnt/sfs2008 > /dev/null) real 37m49.004s user 0m23.274s sys 0m9.010s Jay