Google Cloud Platform Blog
Diagnose Service Performance Bottlenecks with Google Cloud Trace Beta
Thursday, January 8, 2015
Here at Google, we understand the importance of having applications run at optimal speed. Awesome performance of your application is critical for
end user satisfaction and retention
. User expectations for application performance are already high and applications with poor performance
risk losing users
. For example,
25% of users abandon a web page if its load time is more than four seconds
and
86% of users delete an application after poor performance
. Ask any developer who has experienced the stress of diagnosing performance issues in production and you will find that it is extremely difficult to isolate the root cause of poor performance when it happens. This is especially true when the sluggish behavior is only seen by a small fraction of your users.
We
introduced
Google Cloud Trace at Google I/O 2014 and gave an in-depth
talk and demo
at Google Cloud Platform Live back in November. Today, we’re announcing the beta release of Google Cloud Trace which is now available to all Google Cloud Platform customers.
With Google Cloud Trace, you can diagnose performance issues in your production application by quickly finding the traces for slow requests and viewing a detailed report of where time is spent in your application while processing these requests. Its trace analysis feature allows you to see the latency distribution for your application, and find the painfully slow requests that may be affecting only a small number of your users. You can also use the trace analysis feature to check if the performance of a new release is better than the previous release.
If you look at the screenshots below, you can get a feel for the type of insight Cloud Trace provides. Figure 1 shows the breakdown of a single request to an application, and where time was spent in processing the request.
Figure 1 - Breakdown of a single request
Cloud Trace can analyze a set of requests to show their latency distribution, percentile latency values with sample traces, and the remote procedure calls that are significant latency bottlenecks.
Figure 2 - Request analysis
Cloud Trace also allows you to compare the latency profiles for an application’s requests from before and after a change is made, such as rolling out a patch. Figure 3 shows the comparison between the before and after requests.
Figure 3 - Comparing requests
To get started with using Cloud Trace for your project, visit your project’s home page in the
Google Developers Console
, select
Monitoring > Traces
in the navigation panel, click on the
Settings
tab, and set
Traces
to
On
. Cloud Trace has very little overhead, so you can safely leave traces enabled for your application without worrying about performance impact. Once traces are enabled for your application, Cloud Trace will start tracing requests received by your application, and continue to do so as you deploy new versions of your application.
Take a look at our
Google Cloud Platform Live talk
, check out our
documentation
, and
try it yourself
-- there’s no set up required. All you need is an application running on App Engine or a Managed VM. We look forward to receiving your
direct feedback
.
-Posted by Pratul Dublish, Product Manager
Alacris helps better match cancer patients with drug therapies using Google Cloud Platform
Wednesday, January 7, 2015
Today's guest post is from Dr. Alexander Kühn, Head of Bioinformatics at
Alacris Theranostics
, a Berlin-based spin-off company of the Max Planck Institute for Molecular Genetics, which uses next generation sequencing and other genomics data through its predictive modeling system
ModCell™
for drug development and personalized medicine in oncology.
Cancer is a complex disease; differences in the genetic make-up of individuals as well as their tumors make every cancer patient unique. Yet, the majority of current medical practice fails to recognize this individuality and treats many patients identically, leading to wide variations in response to therapy. Typically, only 25% of patients benefit from the (often expensive) treatment they are given, with many suffering serious side effects. Even if some progress is visible, cancer drug therapy still seems to be largely based on a trial and error principle.
Computer models have enormous potential to overcome this mismatch for patients as well as for healthcare costs. We at Alacris use computer models based on millions of data points to carry out virtual clinical trials and virtual patient modeling. In order to better match patients to therapies and therapies to patients, Alacris developed the ModCell™ system.
ModCell™ generates a 'Virtual Patient' model for individualized prediction of therapy outcome. First, an individual patient and his or her tumor is analysed on the molecular level. This patient-specific genetic information is subsequently integrated into a cancer model. Thus, the ModCell™ system combines all available molecular information about a patient's disease with the sum of the molecular and mechanistic knowledge about cancer as a whole within a patient-specific tumor model. Using this model, we can simulate the effects of hundreds of different drugs or drug combinations on the patient tumor right on a computer.
We used the ModCell™ system to simulate the effects of about 100 molecular targeted anti-cancer as well as non anti-cancer drugs/compounds on more than 700 different cancer cell lines, originating from 24 diverse tissue types. Molecular data of cancer cell lines were provided by the Cancer Cell Line Encyclopedia (CCLE). For each different cell line available, virtual models comprised of more than 6,000 parameters were generated. The models were employed to predict cell-line specific responses to a range of drugs by simulating a concentration of varying amounts for each compound (detailed description of the simulation approach can be found here). In total, we generated more than 5 million different models, each of which was expected to need up to one minute to be solved numerically and to produce about 500 kB of simulation data. This results in a simulation time of more than 3,000 days, if run on a single core, and more than 2 TB of data. Google Cloud Platform enabled us to handle this enormous simulation workload:
Here’s a breakdown of the steps we took to set up our workload on Google Compute Engine:
Set up a single n1-highmen-8 instance as an SSH gateway
Connected and exported a persistent 1 TB disk with Network File System version 4 (
NFSv4
)
Created 125 VM instances, with a total of 1,000 cores, and connected these to the exported disk
Used open source project
TaskManager
to control and schedule the generated cluster
TaskManager enabled us to execute the job on a single core by distributing each of the 5 million simulation jobs over the whole cluster
TaskManager enabled us to operate at full capacity and in parallel over several days. Results of each simulation were stored on the shared storage disk.
Simulation results are now being used to calculate the inhibition of cell growth, which will be compared to pharmacological profiles available from Cancer Cell Line Encyclopedia (CCLE). Potentially, these results will facilitate identification of cancer-related signal transduction pathways that are not yet covered in the model, and also further our understanding of the functional consequences of mutations at both the molecular pathway and cellular level. Moreover, we will gain insight into drug action at the molecular level and analyze cross-talk and potential redundancies between pathways. Using this information, the ModCell™ system can be expanded and modified, integrating the identified cancer-related signaling pathways and mutations, and additional drug information, such as drug uptake dynamics and drug metabolism.
Use of Google Cloud Platform has made it possible for us to rapidly refine and improve our modeling system, which has become about 10x faster than using the Alacris’ computer cluster (which contains only 100 cores). These improvements will help (a) to optimize personalized cancer therapy by removing some of the risks associated with classical empirically administered treatments and (b) to optimize the predictive power of virtual clinical trials to test drugs before they go into clinical trials. The goal is for this to lead to higher drug approval rates, saving time and a large fraction of the costs associated with clinical trials.
-Posted by Dr. Alexander Kühn, Head of Bioinformatics at Alacris Theranostics
In case you missed it in December: Six customer success stories, three Windows workload wonders, two Dataflow digests, and a Year in Review highlight series
Tuesday, January 6, 2015
The holidays may be over, but we still have some tidbits to share with you to bring you good cheer. Here’re some fun treats of what went down in December.
Google Cloud Platform sent you some holiday cheer...
...and some expanded Windows support
At the beginning of December the Google Cloud Platform team released three new enhancements to Google Compute Engine, making it a great place for customers to run highly performant Windows-based workloads at scale. Learn more about the enhancements
here
.
Making shopping just a little easier
Also just in time for the holidays, we were pleased to
announce
that Google Cloud Platform was validated for compliance with the Payment Card Industry (PCI) Data Security Standards (DSS). The standard enables our customers to hold, process, or exchange cardholder information from any branded credit card on Google Cloud Platform.
Customer treats and feats
We love when our customers have stories they want to share about how they are using Google Cloud Platform. In December we were lucky enough to have several customers share their stories on our blog, including:
Aerospike
- how they hit one million writes per second with Google Compute Engine
Wix
- how they reached high availability with a multiple cloud deployment
dotCloud
- how they provide faster, more reliable PaaS with Google Cloud Platform
Akselos
- how they help MITx’s edX course with complex engineering simulations on Google Compute Engine
RealMassive
- how they transform commercial real estate with powerful data technology
Bayes Impact
- technically not a customer, but a 24-hour hackathon where data scientists leveraged the power of tools such as
Google Compute Engine
and
BigQuery
to quickly chew through terabytes of information looking for ways to make meaningful impacts on people’s lives.
Our Cloud Developer Advocate team said, "Hello World"
We want to make sure our customers are as successful as they can be, so we introduced to you the team that makes this happen. You can find them speaking at events, answering your questions on
Twitter
or simply making themselves available for any questions or feedback you have on Google Cloud Platform. Get to know them by reading their introductions in this
post
.
Digging more into Cloud Dataflow
We announced the availability of
Cloud Dataflow SDK
as open-source, which makes it easier for developers to integrate with our managed service while also forming the basis for porting Cloud Dataflow to other languages and execution environments.
Read on
to find out why we decided to share Cloud Dataflow via open source. You can also check out
this post
on how we used Cloud Dataflow to spatially aggregate NYC taxi locations with the objective of painting the whole picture on a map.
Rewinding 2014 with our Year in Review highlight series
Every year the Google Cloud Platform team contributes to a Year in Review blog series, where we feature a different Googler sharing their highlight from the past year in Cloud Platform. The series just concluded yesterday with Urs’ highlight that
developers nowadays
have it too easy. Other great favorites included a creative
Cloud Platform poem
set to the well known story
“A Visit from St. Nicholas”
and a
reflection
on making open-source #1 through Kubernetes and Google Container Engine.
- Posted by Charlene Lee, Product Marketing Manager
2014 Year In Review: Making it easier for developers
Monday, January 5, 2015
Today’s post is the last installation in our 2014 Google Cloud Platform Year in Review. Every day since the middle of December, we've featured a different Googler sharing their highlight from the past year in Cloud Platform
.
As we end the year, let me observe that developers have it too easy today. Back in the day, we at Google had to build infrastructure with our own bare hands, after walking for hours through three feet of snow with no shoes, uphill, both ways! And once in the datacenter, sweat poured from our faces as we racked up endless stacks of 40-pound servers in sweltering exhaust heat so hot that the sweat drops evaporated before they hit the floor. Those were the days where doubling your capacity meant long days of backbreaking work.
And now you can just lean back, sip your latte, and use the fruits of our hard labor, blood, sweat and tears, and focus on just your idea without worrying about the engine behind your company. You have no idea what a server looks like, and think of adding ten new servers as a single command line to type.
And that’s exactly how it should be -- we’ve been through this pain so you don’t have to go through it. And we know where you want to go, and we’ll be there with you, evolving our platform as quickly as you evolve your ideas. I’m very excited about what Google Cloud Platform will bring in 2015...and I think you’ll be too once you see what we have in store. By the end of the year, whether you develop for an enterprise or for consumers, I hope you’ll agree that the rate of innovation in public clouds has never been higher, and that Google Cloud Platform is driving it. Happy new year!
- Posted by Urs Hölzle, Senior Vice President
2014 Year in Review: Ending Printf Debugging
Sunday, January 4, 2015
Today’s post is the latest installation in our 2014 Google Cloud Platform Year in Review. Every day until early January, we will be featuring a different Googler sharing their highlight from the past year in Cloud Platform.
A highlight for me this year was
demoing Google Cloud Debugger
at Google Cloud Platform Live. Google Cloud Debugger frees you from searching through logs to debug an issue by giving you direct access to the stack and locals of an application running in production with no negative effects on the production application. The audience (live and online) really appreciated the value of the debugger and the
fun demo application, Emojislator
!
Looking forward to saving developers even more time in 2015!
-Posted by Brad Abrams, Product Manager
2014 Year in Review: Enabling the best and brightest startups
Saturday, January 3, 2015
Today’s post is the latest installation in our 2014 Google Cloud Platform Year in Review. Every day until early January, we will be featuring a different Googler sharing their highlight from the past year in Cloud Platform.
On September 12 of this year, we launched Google Cloud Platform for Startups at the Google for Entrepreneurs Global Partner Summit. In the few short months the offer has been available, we have seen tremendous traction with our investor, accelerator, and incubator partners and the companies taking advantage of credits, technical support, and mentoring.
Partners like
TechStars
,
Galvanize
, and
Founder Institute
have nominated hundreds of companies that are building amazing products on top of the Google Cloud Platform and are seeing tremendous growth.
Rabbit
, a
Google Ventures
backed company, is bringing people closer together with video chat and rich content sharing on top of Google Cloud Platform. Founder and CTO, Philippe Clavel says, “Having a strong, consistent network is very important for video communications, and Google Cloud is the best solution out there. We were able to move from our previous provider in just two weeks, and the transition was easy for us and seamless to our users.”
I have been amazed by the quality of companies taking advantage of the offer and the excitement in the community about Google Cloud Platform. To think 2014 was just the beginning!
-Posted by Brian Gorbett, Senior Program Manager
2014 Year in Review: Bringing a team together to help you best
Thursday, January 1, 2015
Today’s post is the latest installation in our 2014 Google Cloud Platform Year in Review. Every day until early January, we will be featuring a different Googler sharing their highlight from the past year in Cloud Platform.
As we close out 2014 and think about all the new technology we've seen our users get access to over the years, we sometimes forget the people who work hard everyday to make it possible. For me, as the head of marketing, my highlight has been growing an organization of people who wake up every morning around the world to delight you, our users. We live to excite, educate, inspire and help.
Happy New Years! And on behalf of all of us, here's to a healthy and wonderful 2015.
- Posted by Brian Goldfarb, Head of Marketing
Don't Miss Next '17
Use promo code NEXT1720 to save $300 off general admission
REGISTER NOW
Free Trial
GCP Blogs
Big Data & Machine Learning
Kubernetes
GCP Japan Blog
Labels
Announcements
56
Big Data & Machine Learning
91
Compute
156
Containers & Kubernetes
36
CRE
7
Customers
90
Developer Tools & Insights
80
Events
34
Infrastructure
24
Management Tools
39
Networking
18
Open Source
105
Partners
63
Pricing
24
Security & Identity
23
Solutions
16
Stackdriver
19
Storage & Databases
111
Weekly Roundups
16
Archive
2017
Feb
Jan
2016
Dec
Nov
Oct
Sep
Aug
Jul
Jun
May
Apr
Mar
Feb
Jan
2015
Dec
Nov
Oct
Sep
Aug
Jul
Jun
May
Apr
Mar
Feb
Jan
2014
Dec
Nov
Oct
Sep
Aug
Jul
Jun
May
Apr
Mar
Feb
Jan
2013
Dec
Nov
Oct
Sep
Aug
Jul
Jun
May
Apr
Mar
Feb
Jan
2012
Dec
Nov
Oct
Sep
Aug
Jul
Jun
May
Apr
Mar
Feb
Jan
2011
Dec
Nov
Oct
Sep
Aug
Jul
Jun
May
Apr
Mar
Feb
Jan
2010
Dec
Oct
Sep
Aug
Jul
Jun
May
Apr
Mar
Feb
Jan
2009
Dec
Nov
Oct
Sep
Aug
Jul
Jun
May
Apr
Mar
Feb
Jan
2008
Dec
Nov
Oct
Sep
Aug
Jul
Jun
May
Apr
Feed
Subscribe by email
Technical questions? Check us out on
Stack Overflow
.
Subscribe to
our monthly newsletter
.
Google
on
Follow @googlecloud
Follow
Follow
Follow