How to achieve high concurrency with spray.io in this Future and Thread.sleep example? - scala

I was trying the following POC to check how to get high concurrency
implicit def executionContext = context.system.dispatchers.lookup("async-futures-dispatcher")
implicit val timeout = 10 seconds
val contestroute = "/contestroute" {
get {
respondWithMediaType(`application/json`) {
dynamic {
onSuccess(
Future {
val start = System.currentTimeMillis()
// np here should be dealt by 200 threads defined below, so why
// overall time takes so long? why doesn't it really utilize all
// threads I have given to it? how to update the code so it
// utilizes the 200 threads?
Thread.sleep(5000)
val status = s"timediff ${System.currentTimeMillis() - start}ms ${Thread.currentThread().getName}"
status
}) { time =>
complete(s"status: $time")
}
}
}
}
}
My config:
async-futures-dispatcher {
# Dispatcher is the name of the event-based dispatcher
type = Dispatcher
# What kind of ExecutionService to use
executor = "thread-pool-executor"
# Configuration for the thread pool
thread-pool-executor {
# minimum number of threads to cap factor-based core number to
core-pool-size-min = 200
# No of core threads ... ceil(available processors * factor)
core-pool-size-factor = 20.0
# maximum number of threads to cap factor-based number to
core-pool-size-max = 200
}
# Throughput defines the maximum number of messages to be
# processed per actor before the thread jumps to the next actor.
# Set to 1 for as fair as possible.
throughput = 100
}
however when I run apache bench like this:
ab -n 200 -c 50 http://LAP:8080/contestroute
Results I get are:
Server Software: Apache-Coyote/1.1
Server Port:erred: 37500 bytes
HTML transferred: 10350 bytes
Requests per second: 4.31 [#/sec] (mean)
Time per request: 34776.278 [ms] (mean)
Time per request: 231.842 [ms] (mean, across all concurrent requests)
Transfer rate: 1.05 [Kbytes/sec] received
Connection Times (ms)
min mean[+/-sd] median max
Connect: 5 406 1021.3 7 3001
Processing: 30132 30466 390.8 30308 31231
Waiting: 30131 30464 391.8 30306 31231
Total: 30140 30872 998.9 30353 33228 8080
Document Path: /contestroute
Document Length: 69 bytes
Concurrency Level: 150
Time taken for tests: 34.776 seconds
Complete requests: 150
Failed requests: 0
Write errors: 0
Non-2xx responses: 150
Total transferred: 37500 bytes
HTML transferred: 10350 bytes
Requests per second: 4.31 [#/sec] (mean)
Time per request: 34776.278 [ms] (mean)
Time per request: 231.842 [ms] (mean, across all concurrent requests)
Transfer rate: 1.05 [Kbytes/sec] received
Connection Times (ms)
min mean[+/-sd] median max
Connect: 5 406 1021.3 7 3001
Processing: 30132 30466 390.8 30308 31231
Waiting: 30131 30464 391.8 30306 31231
Total: 30140 30872 998.9 30353 33228
Am I missing something big? what do I need to change to have my spray and futures utilize all threads i given to it?
(to add i'm running on top of tomcat servlet 3.0)

In your example all spray operations and blocking operations happen in the same context. You need to split 2 contexts:
Also I don't see the reason to use dynamic, I guess just 'complete' should be good.
implicit val timeout = 10.seconds
// Execution Context for blocking ops
val blockingExecutionContext = {
ExecutionContext.fromExecutor(Executors.newFixedThreadPool(2000))
}
// Execution Context for Spray
import context.dispatcher
override def receive: Receive = runRoute(contestroute)
val contestroute = path("contestroute") {
get {
complete {
Future.apply {
val start = System.currentTimeMillis()
// np here should be dealt by 200 threads defined below, so why
// overall time takes so long? why doesn't it really utilize all
// threads I have given to it? how to update the code so it
// utilizes the 200 threads?
Thread.sleep(5000)
val status = s"timediff ${System.currentTimeMillis() - start}ms ${Thread.currentThread().getName}"
status
}(blockingExecutionContext)
}
}
}
After that you can test it with
ab -n 200 -c 200 http://LAP:8080/contestroute
and you'll see that spray will create all 200 threads for blocking operations
Results:
Concurrency Level: 200
Time taken for tests: 5.096 seconds

Related

Twitter Rate Limit for search_all for full archive data

I am using tweepy to get replies to a given user name and filter by since id and until id. I got a rate limit for every three requests. My code is like blow:
q = "to:"+screen_name
reply_ls = []
tweets = client.search_all_tweets(query = q ,
since_id = since_id,
until_id = until_id,
tweet_fields = ['in_reply_to_user_id',\
'author_id','created_at','conversation_id',"referenced_tweets"],
expansions = "referenced_tweets.id" )
Here is the rate limit I got
10%|█████▌ | 10/100 [00:10<01:28, 1.02it/s]Rate limit exceeded. Sleeping for 607 seconds.
13%|███████ | 13/100 [10:20<2:07:02, 87.62s/it]Rate limit exceeded. Sleeping for 898 seconds.
17%|█████████ | 17/100 [25:22<2:37:38, 113.95s/it]Rate limit exceeded. Sleeping for 897 seconds.
23%|████████████▍ | 23/100 [40:26<1:16:23, 59.52s/it]Rate limit exceeded. Sleeping for 894 seconds.
I thought the API allow 300 requests every 15 minutes. But now I can only have three requests every 15 minutes. I don't know is it reasonable?

Spark getting slow as time goes on

I have a scala code that runs on top of spark 2.4.0 to compute the BFS of a graph which is stored in a table as below:
src
dst
isVertex
1
1
1
2
2
1
...
...
...
1
2
0
2
4
0
...
...
...
At some point in the algorithm, I need to update the visited flag of current vertex neighbors. I am doing this by the following code. When I execute the code, it works fine but as time goes on, it becomes slower and slower. It seems that the last nested loop is the problem:
//var vertices = schema(StructType(Seq(StructField("id",IntegerType),StructField("visited", IntegerType),StructField("qOrder",IntegerType))
val neighbours = edges.filter($"src" === start).join(vertices,$"id" === $"dst").filter($"visited" === lit(0))
.select($"dst".as("id")).withColumn("visited", lit(1)).withColumn("qOrder", lit(priorityCounter)).cache()
-----------------------------------------------------------------------
vertices.collect.foreach{x=>
if(!neighbours.filter(col("id")===x(0)).head(1).isEmpty){
vertices = vertices.filter($"id" =!= x(0)).union(neighbours.filter(col("id")===x(0))).cache()
}
}
-----------------------------------------------------------------------
When it becomes slow, it starts giving the following errors and warnings:
2021-06-08 19:55:08,998 [driver-heartbeater] WARN org.apache.spark.executor.Executor - Issue communicating with driver in heartbeater
org.apache.spark.rpc.RpcTimeoutException: Futures timed out after [10 seconds]. This timeout is controlled by spark.executor.heartbeatInterval
Exception in thread "dag-scheduler-event-loop" java.lang.OutOfMemoryError: GC overhead limit exceeded
Does anyone have any idea about the problem?
I have set the spark parameters as follows:
spark.scheduler.listenerbus.eventqueue.capacity 100000000
spark.dynamicAllocation.enabled true
spark.dynamicAllocation.executorIdleTimeout 2m
spark.dynamicAllocation.minExecutors 1
spark.dynamicAllocation.maxExecutors 10000
spark.max.fetch.failures.per.stage 10
spark.rpc.io.serverThreads 64
spark.rpc.askTimeout 600s
spark.driver.memory 32g
spark.executor.memory 32g

haproxy stats: qtime,ctime,rtime,ttime?

Running a web app behind HAProxy 1.6.3-1ubuntu0.1, I'm getting haproxy stats qtime,ctime,rtime,ttime values of 0,0,0,2704.
From the docs (https://www.haproxy.org/download/1.6/doc/management.txt):
58. qtime [..BS]: the average queue time in ms over the 1024 last requests
59. ctime [..BS]: the average connect time in ms over the 1024 last requests
60. rtime [..BS]: the average response time in ms over the 1024 last requests
(0 for TCP)
61. ttime [..BS]: the average total session time in ms over the 1024 last requests
I'm expecting response times in the 0-10ms range. ttime of 2704 milliseconds seems unrealistically high. Is it possible the units are off and this is 2704 microseconds rather than 2704 millseconds?
Secondly, it seems suspicious that ttime isn't even close to qtime+ctime+rtime. Is total response time not the sum of the time to queue, connect, and respond? What is the other time, that is included in total but not queue/connect/response? Why can my response times be <1ms, but my total response times be ~2704 ms?
Here is my full csv stats:
$ curl "http://localhost:9000/haproxy_stats;csv"
# pxname,svname,qcur,qmax,scur,smax,slim,stot,bin,bout,dreq,dresp,ereq,econ,eresp,wretr,wredis,status,weight,act,bck,chkfail,chkdown,lastchg,downtime,qlimit,pid,iid,sid,throttle,lbtot,tracked,type,rate,rate_lim,rate_max,check_status,check_code,check_duration,hrsp_1xx,hrsp_2xx,hrsp_3xx,hrsp_4xx,hrsp_5xx,hrsp_other,hanafail,req_rate,req_rate_max,req_tot,cli_abrt,srv_abrt,comp_in,comp_out,comp_byp,comp_rsp,lastsess,last_chk,last_agt,qtime,ctime,rtime,ttime,
http-in,FRONTEND,,,4707,18646,50000,5284057,209236612829,42137321877,0,0,997514,,,,,OPEN,,,,,,,,,1,2,0,,,,0,4,0,2068,,,,0,578425742,0,997712,22764,1858,,1561,3922,579448076,,,0,0,0,0,,,,,,,,
servers,server1,0,0,0,4337,20000,578546476,209231794363,41950395095,,0,,22861,1754,95914,0,no check,1,1,0,,,,,,1,3,1,,578450562,,2,1561,,6773,,,,0,578425742,0,198,0,0,0,,,,29,1751,,,,,0,,,0,0,0,2704,
servers,BACKEND,0,0,0,5919,5000,578450562,209231794363,41950395095,0,0,,22861,1754,95914,0,UP,1,1,0,,0,320458,0,,1,3,0,,578450562,,1,1561,,3922,,,,0,578425742,0,198,22764,1858,,,,,29,1751,0,0,0,0,0,,,0,0,0,2704,
stats,FRONTEND,,,2,5,2000,5588,639269,8045341,0,0,29,,,,,OPEN,,,,,,,,,1,4,0,,,,0,1,0,5,,,,0,5374,0,29,196,0,,1,5,5600,,,0,0,0,0,,,,,,,,
stats,BACKEND,0,0,0,1,200,196,639269,8045341,0,0,,196,0,0,0,UP,0,0,0,,0,320458,0,,1,4,0,,0,,1,0,,5,,,,0,0,0,0,196,0,,,,,0,0,0,0,0,0,0,,,0,0,0,0,
In haproxy >2 you now get two values n / n which is the max within a sliding window and the average for that window. The max value remains the max across all sample windows until a higher value is found. On 1.8 you only get the average.
Example of haproxy 2 v 1.8. Note these proxies are used very differently and with dramatically different loads.
So looks like the average response times at least since last reboot are 66m and 275ms.
The average is computed as:
data time + cumulative http connections - 1 / cumulative http connections
This might not be a perfect analysis so if anyone has improvements it'd be appreciated. This is meant to show how I came to the answer above so you can use it to gather more insight into the other counters you asked about. Most of this information was gathered from reading stats.c. The counters you asked about are defined here.
unsigned int q_time, c_time, d_time, t_time; /* sums of conn_time, queue_time, data_time, total_time */
unsigned int qtime_max, ctime_max, dtime_max, ttime_max; /* maximum of conn_time, queue_time, data_time, total_time observed */```
The stats page values are built from this code:
if (strcmp(field_str(stats, ST_F_MODE), "http") == 0)
chunk_appendf(out, "<tr><th>- Responses time:</th><td>%s / %s</td><td>ms</td></tr>",
U2H(stats[ST_F_RT_MAX].u.u32), U2H(stats[ST_F_RTIME].u.u32));
chunk_appendf(out, "<tr><th>- Total time:</th><td>%s / %s</td><td>ms</td></tr>",
U2H(stats[ST_F_TT_MAX].u.u32), U2H(stats[ST_F_TTIME].u.u32));
You asked about all the counter but I'll focus on one. As can be seen in the snippit above for "Response time:" ST_F_RT_MAX and ST_F_RTIME are the values displayed on the stats page as n (rtime_max) / n (rtime) respectively. These are defined as follows:
[ST_F_RT_MAX] = { .name = "rtime_max", .desc = "Maximum observed time spent waiting for a server response, in milliseconds (backend/server)" },
[ST_F_RTIME] = { .name = "rtime", .desc = "Time spent waiting for a server response, in milliseconds, averaged over the 1024 last requests (backend/server)" },
These set a "metric" value (among other things) in a case statement further down in the code:
case ST_F_RT_MAX:
metric = mkf_u32(FN_MAX, sv->counters.dtime_max);
break;
case ST_F_RTIME:
metric = mkf_u32(FN_AVG, swrate_avg(sv->counters.d_time, srv_samples_window));
break;
These metric values give us a good look at what the stats page is telling us. The first value in the "Responses time: 0 / 0" ST_F_RT_MAX, is some max value time spent waiting. The second value in "Responses time: 0 / 0" ST_F_RTIME is an average time taken for each connection. These are the max and average taken within a window of time, i.e. however long it takes for you to get 1024 connections.
For example "Responses time: 10000 / 20":
max time spent waiting (max value ever reached including http keepalive time) over the last 1024 connections 10 seconds
average time over the last 1024 connections 20ms
So for all intents and purposes
rtime_max = dtime_max
rtime = swrate_avg(d_time, srv_samples_window)
Which begs the question what is dtime_max d_time and srv_sample_window? These are the data time windows, I couldn't actually figure how these time values are being set, but at face value it's "some time" for the last 1024 connections. As pointed out here keepalive times are included in max totals which is why the numbers are high.
Now that we know ST_F_RT_MAX is a max value and ST_F_RTIME is an average, an average of what?
/* compue time values for later use */
if (selected_field == NULL || *selected_field == ST_F_QTIME ||
*selected_field == ST_F_CTIME || *selected_field == ST_F_RTIME ||
*selected_field == ST_F_TTIME) {
srv_samples_counter = (px->mode == PR_MODE_HTTP) ? sv->counters.p.http.cum_req : sv->counters.cum_lbconn;
if (srv_samples_counter < TIME_STATS_SAMPLES && srv_samples_counter > 0)
srv_samples_window = srv_samples_counter;
}
TIME_STATS_SAMPLES value is defined as
#define TIME_STATS_SAMPLES 512
unsigned int srv_samples_window = TIME_STATS_SAMPLES;
In mode http srv_sample_counter is sv->counters.p.http.cum_req. http.cum_req is defined as ST_F_REQ_TOT.
[ST_F_REQ_TOT] = { .name = "req_tot", .desc = "Total number of HTTP requests processed by this object since the worker process started" },
For example if the value of http.cum_req is 10, then srv_sample_counter will be 10. The sample appears to be the number of successful requests for a given sample window for a given backends server. d_time (data time) is passed as "sum" and is computed as some non-negative value or it's counted as an error. I thought I found the code for how d_time is created but I wasn't sure so I haven't included it.
/* Returns the average sample value for the sum <sum> over a sliding window of
* <n> samples. Better if <n> is a power of two. It must be the same <n> as the
* one used above in all additions.
*/
static inline unsigned int swrate_avg(unsigned int sum, unsigned int n)
{
return (sum + n - 1) / n;
}

MongoDB Concurrency Bottleneck

Too Long; Didn't Read
The question is about a concurrency bottleneck I am experiencing on MongoDB. If I make one query, it takes 1 unit of time to return; if I make 2 concurrent queries, both take 2 units of time to return; generally, if I make n concurrent queries, all of them take n units of time to return. My question is about what can be done to improve Mongo's response times when faced with concurrent queries.
The Setup
I have a m3.medium instance on AWS running a MongoDB 2.6.7 server. A m3.medium has 1 vCPU (1 core of a Xeon E5-2670 v2), 3.75GB and a 4GB SSD.
I have a database with a single collection named user_products. A document in this collection has the following structure:
{ user: <int>, product: <int> }
There are 1000 users and 1000 products and there's a document for every user-product pair, totalizing a million documents.
The collection has an index { user: 1, product: 1 } and my results below are all indexOnly.
The Test
The test was executed from the same machine where MongoDB is running. I am using the benchRun function provided with Mongo. During the tests, no other accesses to MongoDB were being made and the tests only comprise read operations.
For each test, a number of concurrent clients is simulated, each of them making a single query as many times as possible until the test is over. Each test runs for 10 seconds. The concurrency is tested in powers of 2, from 1 to 128 simultaneous clients.
The command to run the tests:
mongo bench.js
Here's the full script (bench.js):
var
seconds = 10,
limit = 1000,
USER_COUNT = 1000,
concurrency,
savedTime,
res,
timediff,
ops,
results,
docsPerSecond,
latencyRatio,
currentLatency,
previousLatency;
ops = [
{
op : "find" ,
ns : "test_user_products.user_products" ,
query : {
user : { "#RAND_INT" : [ 0 , USER_COUNT - 1 ] }
},
limit: limit,
fields: { _id: 0, user: 1, product: 1 }
}
];
for (concurrency = 1; concurrency <= 128; concurrency *= 2) {
savedTime = new Date();
res = benchRun({
parallel: concurrency,
host: "localhost",
seconds: seconds,
ops: ops
});
timediff = new Date() - savedTime;
docsPerSecond = res.query * limit;
currentLatency = res.queryLatencyAverageMicros / 1000;
if (previousLatency) {
latencyRatio = currentLatency / previousLatency;
}
results = [
savedTime.getFullYear() + '-' + (savedTime.getMonth() + 1).toFixed(2) + '-' + savedTime.getDate().toFixed(2),
savedTime.getHours().toFixed(2) + ':' + savedTime.getMinutes().toFixed(2),
concurrency,
res.query,
currentLatency,
timediff / 1000,
seconds,
docsPerSecond,
latencyRatio
];
previousLatency = currentLatency;
print(results.join('\t'));
}
Results
Results are always looking like this (some columns of the output were omitted to facilitate understanding):
concurrency queries/sec avg latency (ms) latency ratio
1 459.6 2.153609008 -
2 460.4 4.319577324 2.005738882
4 457.7 8.670418178 2.007237636
8 455.3 17.4266174 2.00989353
16 450.6 35.55693474 2.040380754
32 429 74.50149883 2.09527338
64 419.2 153.7325095 2.063482104
128 403.1 325.2151235 2.115460969
If only 1 client is active, it is capable of doing about 460 queries per second over the 10 second test. The average response time for a query is about 2 ms.
When 2 clients are concurrently sending queries, the query throughput maintains at about 460 queries per second, showing that Mongo hasn't increased its response throughput. The average latency, on the other hand, literally doubled.
For 4 clients, the pattern continues. Same query throughput, average latency doubles in relation to 2 clients running. The column latency ratio is the ratio between the current and previous test's average latency. See that it always shows the latency doubling.
Update: More CPU Power
I decided to test with different instance types, varying the number of vCPUs and the amount of available RAM. The purpose is to see what happens when you add more CPU power. Instance types tested:
Type vCPUs RAM(GB)
m3.medium 1 3.75
m3.large 2 7.5
m3.xlarge 4 15
m3.2xlarge 8 30
Here are the results:
m3.medium
concurrency queries/sec avg latency (ms) latency ratio
1 459.6 2.153609008 -
2 460.4 4.319577324 2.005738882
4 457.7 8.670418178 2.007237636
8 455.3 17.4266174 2.00989353
16 450.6 35.55693474 2.040380754
32 429 74.50149883 2.09527338
64 419.2 153.7325095 2.063482104
128 403.1 325.2151235 2.115460969
m3.large
concurrency queries/sec avg latency (ms) latency ratio
1 855.5 1.15582069 -
2 947 2.093453854 1.811227185
4 961 4.13864589 1.976946318
8 958.5 8.306435055 2.007041742
16 954.8 16.72530889 2.013536347
32 936.3 34.17121062 2.043083977
64 927.9 69.09198599 2.021935563
128 896.2 143.3052382 2.074122435
m3.xlarge
concurrency queries/sec avg latency (ms) latency ratio
1 807.5 1.226082735 -
2 1529.9 1.294211452 1.055566166
4 1810.5 2.191730848 1.693487447
8 1816.5 4.368602642 1.993220402
16 1805.3 8.791969257 2.01253581
32 1770 17.97939718 2.044979532
64 1759.2 36.2891598 2.018374668
128 1720.7 74.56586511 2.054769676
m3.2xlarge
concurrency queries/sec avg latency (ms) latency ratio
1 836.6 1.185045183 -
2 1585.3 1.250742872 1.055438974
4 2786.4 1.422254414 1.13712774
8 3524.3 2.250554777 1.58238551
16 3536.1 4.489283844 1.994745425
32 3490.7 9.121144097 2.031759277
64 3527 18.14225682 1.989033023
128 3492.9 36.9044113 2.034168718
Starting with the xlarge type, we begin to see it finally handling 2 concurrent queries while keeping the query latency virtually the same (1.29 ms). It doesn't last too long, though, and for 4 clients it again doubles the average latency.
With the 2xlarge type, Mongo is able to keep handling up to 4 concurrent clients without raising the average latency too much. After that, it starts to double again.
The question is: what could be done to improve Mongo's response times with respect to the concurrent queries being made? I expected to see a rise in the query throughput and I did not expect to see it doubling the average latency. It clearly shows Mongo is not being able to parallelize the queries that are arriving.
There's some kind of bottleneck somewhere limiting Mongo, but it certainly doesn't help to keep adding up more CPU power, since the cost will be prohibitive. I don't think memory is an issue here, since my entire test database fits in RAM easily. Is there something else I could try?
You're using a server with 1 core and you're using benchRun. From the benchRun page:
This benchRun command is designed as a QA baseline performance measurement tool; it is not designed to be a "benchmark".
The scaling of the latency with the concurrency numbers is suspiciously exact. Are you sure the calculation is correct? I could believe that the ops/sec/runner was staying the same, with the latency/op also staying the same, as the number of runners grew - and then if you added all the latencies, you would see results like yours.

Spawning more threads than you have in a gevent pool

As I understand it the idea of a pool in gevent is to limit the total number of concurrent requests at any time, to a database or an API or similar.
Say I have code like this where I am spawning more greenlets than I have room for in the Pool:
import gevent.pool
pool = gevent.pool.Pool(50)
jobs = []
for number in xrange(300):
jobs.append(pool.spawn(do_something, number))
total_result = [x.get() for x in jobs]
What is the actual behavior when trying to spawn the 51st request? When is the 51st request handled?
The pool class uses a semaphore to count active greenlets, initialized with size count in the constructor:
class Pool(Group):
def __init__(self, size=None, greenlet_class=None):
if size is not None and size < 1:
raise ValueError('Invalid size for pool (positive integer or None required): %r' % (size, ))
Group.__init__(self)
self.size = size
if greenlet_class is not None:
self.greenlet_class = greenlet_class
if size is None:
self._semaphore = DummySemaphore()
else:
self._semaphore = Semaphore(size)
Every time spawn() is called, it tries to acquire the semaphore:
def spawn(self, *args, **kwargs):
self._semaphore.acquire()
try:
greenlet = self.greenlet_class.spawn(*args, **kwargs)
self.add(greenlet)
except:
self._semaphore.release()
raise
return greenlet
If the pool is full, the called greenlet will thus wait on _semaphore.acquire() call. Semaphore is released whenever any of the greenlets ends execution:
def discard(self, greenlet):
Group.discard(self, greenlet)
self._semaphore.release()
So in your case, I'd expect the 51st request to be handled (or started, to be precise) as soon as any of the first 50 requests is done.