Principles of Computer Systems
Winter 2021
Stanford University
Computer Science Department
Lecturers: Chris Gregg and
Nick Troccoli
scrabbleword-finder
. The source code for this executable—completely unaware it'll be used in a larger networked application—can be found right here.scrabble-word-finder
is implemented using only CS106B techniques—standard file I/O and procedural recursion with simple pruning.cgregg@myth61:$ ./scrabble-word-finder lexical
ace
// many lines omitted for brevity
lei
lex
lexica
lexical
li
lice
lie
lilac
xi
cgregg@myth61:$
cgregg@myth61:$ ./scrabble-word-finder network
en
// many lines omitted for brevity
wonk
wont
wore
work
worn
wort
wot
wren
wrote
cgregg@myth61:$
scrabble-wordfinder
is capable of.
myth54:13133
, we expect http://myth54:13133/lexical
and http://myth54:13133/network
to generate the following JSON payloads:{
"time":0.041775,
"cached": false,
"possibilities": [
'ace',
// several words omitted
'lei',
'lex',
'lexica',
'lexical',
'li',
'lice',
'lie',
'lilac',
'xi'
]
}
{
"time": 0.223399,
"cached": false,
"possibilities": [
'en',
// several words omitted
'wonk',
'wont',
'wore',
'work',
'worn',
'wort',
'wot',
'wren',
'wrote'
]
}
scrabble-word-finder.cc
to build the core of scrabble-word-finder-server.cc
.scrabble-word-finder
already outputs the primary content we need for our payload. We're packaging the payload as JSON instead of plain text, but we can still tap scrabble-word-finder
to generate the collection of formable words.subprocess_t
type and subprocess
function from Assignment 3.struct subprocess_t {
pid_t pid;
int supplyfd;
int ingestfd;
};
subprocess_t subprocess(char *argv[],
bool supplyChildInput, bool ingestChildOutput) throw (SubprocessException);
main
function implementing our server:int main(int argc, char *argv[]) {
unsigned short port = extractPort(argv[1]);
int server = createServerSocket(port);
cout << "Server listening on port " << port << "." << endl;
ThreadPool pool(16);
map<string, vector<string>> cache;
mutex cacheLock;
while (true) {
struct sockaddr_in address;
// used to surface IP address of client
socklen_t size = sizeof(address); // also used to surface client IP address
bzero(&address, size);
int client = accept(server, (struct sockaddr *) &address, &size);
char str[INET_ADDRSTRLEN];
cout << "Received a connection request from "
<< inet_ntop(AF_INET, &address.sin_addr, str, INET_ADDRSTRLEN) << "." << endl;
pool.schedule([client, &cache, &cacheLock] {
publishScrabbleWords(client, cache, cacheLock);
});
}
return 0;
}
accept
are used to surface the IP address of the client.address
, size
, and the inet_ntop
function until the next lecture, when we'll talk more about them. Right now, it's a neat-to-see!ThreadPool
of size 16.publishScrabbleWords
will rely on our subprocess
function to marshal plain text output of scrabble-word-finder into JSON and publish that JSON as the payload of the HTTP response.publishScrabbleWords
and some of its helper functions.publishScrabbleWords
:static void publishScrabbleWords(int client, map<string, vector<string>>& cache,
mutex& cacheLock) {
sockbuf sb(client);
iosockstream ss(&sb);
string letters = getLetters(ss);
sort(letters.begin(), letters.end());
skipHeaders(ss);
struct timeval start;
gettimeofday(&start, NULL); // start the clock
cacheLock.lock();
auto found = cache.find(letters);
cacheLock.unlock(); // release lock immediately, iterator won't be invalidated by competing find calls
bool cached = found != cache.end();
vector<string> formableWords;
if (cached) {
formableWords = found->second;
} else {
const char *command[] = {"./scrabble-word-finder", letters.c_str(), NULL};
subprocess_t sp = subprocess(const_cast<char **>(command), false, true);
pullFormableWords(formableWords, sp.ingestfd);
waitpid(sp.pid, NULL, 0);
lock_guard<mutex> lg(cacheLock);
cache[letters] = formableWords;
}
struct timeval end, duration;
gettimeofday(&end, NULL); // stop the clock, server-computation of formableWords is complete
timersub(&end, &start, &duration);
double time = duration.tv_sec + duration.tv_usec/1000000.0;
ostringstream payload;
constructPayload(formableWords, cached, time, payload);
sendResponse(ss, payload.str());
}
pullFormableWords
and sendResponse
helper functions.static void pullFormableWords(vector<string>& formableWords, int ingestfd) {
stdio_filebuf<char> inbuf(ingestfd, ios::in);
istream is(&inbuf);
while (true) {
string word;
getline(is, word);
if (is.fail()) break;
formableWords.push_back(word);
}
}
static void sendResponse(iosockstream& ss, const string& payload) {
ss << "HTTP/1.1 200 OK\r\n";
ss << "Content-Type: text/javascript; charset=UTF-8\r\n";
ss << "Content-Length: " << payload.size() << "\r\n";
ss << "\r\n";
ss << payload << flush;
}
getLetters
and the constructPayload
helper functions. I omit the implementation of skipHeaders
—you saw it with web-get
—and constructJSONArray
, which you're welcome to view right here.static string getLetters(iosockstream& ss) {
string method, path, protocol;
ss >> method >> path >> protocol;
string rest;
getline(ss, rest);
size_t pos = path.rfind("/");
return pos == string::npos ? path : path.substr(pos + 1);
}
static void constructPayload(const vector<string>& formableWords, bool cached,
double time, ostringstream& payload) {
payload << "{" << endl;
payload << " \"time\":" << time << "," << endl;
payload << " \"cached\": " << boolalpha << cached << "," << endl;
payload << " \"possibilities\": " << constructJSONArray(formableWords, 2) << endl;
payload << "}" << endl;
}
scrabble-word-finder-server
provided a single API call that resembles the types of API calls afforded by Google, Twitter, or Facebook to access search, tweet, or friend-graph data.<!DOCTYPE html>
<html>
<head>
<title>Scrabble Word Finder</title>
</head>
<body>
Server: <input type="text" id="server" name="server">
Port: <input type="text" id="port" name="port"><br>
Letters: <input type="text" id="letters" name="letters"><br>
<input type="submit" value="Submit" onclick="getWords()">
<p>Time:</p><span id="words_time"></span>
<p>Scrabble words:</p>
<div id="scrabble_words"></div>
<script>
function getWords(){
let letters = document.getElementById("letters").value;
let server = document.getElementById("server").value; // should be in the form of "myth64"
let port = document.getElementById("port").value; // should be a number between 0 and 65535
let scrabble_words = fetch("http://"+server+":"+port+"/"+letters,{method:"GET"})
.then(data=>{return data.json()})
.then(res=>{
console.log(res);
document.getElementById("words_time").innerText = res['time']+"sec";
possibilitiesStr = "";
for (var i=0; i < res.possibilities.length; i++) {
possibilitiesStr += res.possibilities[i]+"<br>";
}
document.getElementById("scrabble_words").innerHTML = possibilitiesStr;
})
.catch(error=>console.log(error))
}
</script>
</body>
</html>
www.facebook.com
") to IPv4 address (e.g. "31.13.75.17
") and vice versa. Functions called gethostbyname
and gethostbyaddr
, while technically deprecated, are still so prevalent that you should know how to use them.struct hostent *gethostbyname(const char *name);
struct hostent *gethostbyaddr(const char *addr, int len, int type);
struct hostent
describing some host machine on the Internet.gethostbyname
assumes its argument is a host name (e.g. "www.google.com
").gethostbyaddr
assumes the first argument is a binary representation of an IP address (e.g. not the string "171.64.64.137
", but the base address of a character array with ASCII values of 171, 64, 64, and 137 laid down side by side in network byte order
. For IPv4, the second argument is usually 4 (or rather, sizeof(struct in_addr)
) and the third is typically the AF_INET
constant.struct hostent
record packages all of the information about a particular host:struct in_addr {
unsigned int s_addr // four bytes, stored in network byte order (big endian)
};
struct hostent {
char *h_name;
// official name of host
char **h_aliases;
// NULL-terminated list of aliases
int h_addrtype;
// host address type (typically AF_INET for IPv4)
int h_length;
// address length (typically 4, or sizeof(struct in_addr) for IPv4)
char **h_addr_list; // NULL-terminated list of IP addresses
}; // h_addr_list is really a struct in_addr ** when hostent contains IPv4 addresses
struct in_addr
is a one-field record modeling an IPv4 address.
s_addr
field packs each figure of a dotted quad (e.g. 171.64.64.136) into one of its four bytes. Each of these four numbers numbers can range from 0 up through 255.struct hostent
is used for all IP addresses, not just IPv4 addresses. For non-IPv4 addresses, h_addrtype
, h_length
, and h_addr_list
carry different types of data than they do for IPv4www.facebook.com
", but network communication ultimately works with IP addresses like "31.13.75.17".
gethostbyname
and gethostbyaddr
are used to manage translations between the two.static void publishIPAddressInfo(const string& host) {
struct hostent *he = gethostbyname(host.c_str());
if (he == NULL) { // NULL return value means resolution attempt failed
cout << host << " could not be resolved to an address. Did you mistype it?" << endl;
return;
}
cout << "Official name is \"" << he->h_name << "\"" << endl;
cout << "IP Addresses: " << endl;
struct in_addr **addressList = (struct in_addr **) he->h_addr_list;
while (*addressList != NULL) {
char str[INET_ADDRSTRLEN];
cout << "+ " << inet_ntop(AF_INET, *addressList, str, INET_ADDRSTRLEN) << endl;
addressList++;
}
}
h_addr_list
is typed to be a char *
array, implying it's an array of C strings, perhaps dotted quad IP addresses. However, that's not correct. For IPv4 records, h_addr_list
is an array of struct in_addr *s
.inet_ntop
function places a traditional C string presentation of an IP address into the provided character buffer, and returns the the base address of that buffer.h_addr_list
array until it lands on a NULL
.static void publishIPAddressInfo(const string& host) {
struct hostent *he = gethostbyname(host.c_str());
if (he == NULL) { // NULL return value means resolution attempt failed
cout << host << " could not be resolved to an address. Did you mistype it?" << endl;
return;
}
cout << "Official name is \"" << he->h_name << "\"" << endl;
cout << "IP Addresses: " << endl;
struct in_addr **addressList = (struct in_addr **) he->h_addr_list;
while (*addressList != NULL) {
char str[INET_ADDRSTRLEN];
cout << "+ " << inet_ntop(AF_INET, *addressList, str, INET_ADDRSTRLEN) << endl;
addressList++;
}
}
Hostname Resolution: IPv4
www.yale.edu
is the exception. It looks like Yale relies on a content delivery network called "fastly.net", and www.yale.edu
is catalogued as an alias.myth61$ ./resolve-hostname
Welcome to the IP address resolver!
Enter a host name: www.google.com
Official name is "www.google.com"
IP Addresses:
+ 172.217.5.196
Enter a host name: www.coinbase.com
Official name is "www.coinbase.com"
IP Addresses:
+ 104.16.8.251
+ 104.16.9.251
Enter a host name: www.yale.edu
Official name is "pantheon-systems.map.fastly.net"
IP Addresses:
+ 151.101.198.133
Enter a host name: www.okcupid.com
Official name is "www.okcupid.com"
IP Addresses:
+ 198.41.209.132
+ 198.41.208.133
+ 198.41.209.131
+ 198.41.208.132
+ 198.41.209.133
Enter a host name: www.wikipedia.org
Official name is "dyna.wikimedia.org"
IP Addresses:
+ 198.35.26.96
Enter a host name:
All done!
myth61$
Hostname Resolution: IPv6
A more generic version of gethostbyname
—inventively named gethostbyname2
—can be used to extract IPv6 address information about a hostname.
struct hostent *gethostbyname2(const char *name, int af);
gethostbyname2
: AF_INET
and AF_INET6
.gethostbyname2(host, AF_INET)
is equivalent to a call to gethostbyname(host)
gethostbyname2(host, AF_INET6)
still returns a struct hostent *
, but the struct hostent is populated with different values and types:h_addrtype
field is set to AF_INET6
,h_length
field houses a 16 (or rather, sizeof(struct in6_addr)), andh_addr_list
field is really an array of struct in6_addr
pointers, where each struct in6_addr
looks like this:
struct in6_addr {
u_int8_t s6_addr[16]; // 16 bytes (128 bits), stored in network byte order
};
IPv6
version of the publishIPAddressInfo
we wrote earlier (we call it publishIPv6AddressInfo
).static void publishIPv6AddressInfo(const string& host) {
struct hostent *he = gethostbyname2(host.c_str(), AF_INET6);
if (he == NULL) { // NULL return value means resolution attempt failed
cout << host << " could not be resolved to an address. Did you mistype it?" << endl;
return;
}
cout << "Official name is \"" << he->h_name << "\"" << endl;
cout << "IPv6 Addresses: " << endl;
struct in6_addr **addressList = (struct in6_addr **) he->h_addr_list;
while (*addressList != NULL) {
char str[INET6_ADDRSTRLEN];
cout << "+ " << inet_ntop(AF_INET6, *addressList, str, INET6_ADDRSTRLEN) << endl;
addressList++;
}
}
gethostbyname2
, and notice the explicit use of AF_INET6
, struct in6_addr
, and INET6_ADDRSTRLEN
.Hostname Resolution: IPv6
myth61$ ./resolve-hostname6
Welcome to the IPv6 address resolver!
Enter a host name: www.facebook.com
Official name is "star-mini.c10r.facebook.com"
IPv6 Addresses:
+ 2a03:2880:f10d:83:face:b00c:0:25de
Enter a host name: www.microsoft.com
Official name is "e13678.dscb.akamaiedge.net"
IPv6 Addresses:
+ 2600:1406:3400:784::356e
+ 2600:1406:3400:79a::356e
Enter a host name: www.google.com
Official name is "www.google.com"
IPv6 Addresses:
+ 2607:f8b0:4007:80d::2004
Enter a host name: www.berkeley.edu
Official name is "www-production-1113102805.us-west-2.elb.amazonaws.com"
IPv6 Addresses:
+ 2600:1f14:436:7801:983d:7984:8ffd:2d07
+ 2600:1f14:436:7800:172e:b120:8f2e:f687
Enter a host name: www.stanford.edu
www.stanford.edu could not be resolved to an address. Did you mistype it?
Enter a host name:
All done!
struct sockaddr { // generic socket
unsigned short sa_family; // protocol family for socket
char sa_data[14];
// address data (and defines full size to be 16 bytes)
};
sockaddr_in
is used to model IPv4 address/port pairs.
sin_family
field should always be initialized to be AF_INET
, which is a constant used to be clear that IPv4 addresses are being used. If it feels redundant that a record dedicated to IPv4 needs to store a constant saying everything is IPv4, then stay tuned.sin_port
field stores a port number in network byte (i.e. big endian) order.sockaddr_in
field stores an IPv4 address as a packed, big endian int
, as you saw with gethostbyname
and the struct hostent
.sin_zero
field is generally ignored (though it's often set to store all zeroes). It exists primarily to pad the record up to 16 bytes.struct sockaddr_in { // IPv4 socket address record
unsigned short sin_family;
unsigned short sin_port;
struct in_addr sin_addr;
unsigned char sin_zero[8];
};
struct sockaddr_in6 { // IPv6 socket address record
unsigned short sin6_family;
unsigned short sin6_port;
unsigned int sin6_flowinfo;;
struct in6_addr sin6_addr;
unsigned int sin6_scope_id;
};
sockaddr_in6
is used to model IPv6 address/port pairs.
sin6_family
field should always be set to AF_INET6
. As with the sin_family
field, sin6_family
field occupies the first two bytes of surrounding record.sin6_port
field holds a two-byte, network-byte-ordered port number, just like sin_port does.struct in6_addr
is also wedged in there to manage a 128-bit IPv6 address.sin6_flowinfo
and sin6_scope_id
are beyond the scope of what we need, so we'll ignore them.struct sockaddr { // generic socket
unsigned short sa_family; // protocol family for socket
char sa_data[14];
// address data (and defines full size to be 16 bytes)
};
struct sockaddr_in { // IPv4 socket address record
unsigned short sin_family;
unsigned short sin_port;
struct in_addr sin_addr;
unsigned char sin_zero[8];
};
struct sockaddr_in6 { // IPv6 socket address record
unsigned short sin6_family;
unsigned short sin6_port;
unsigned int sin6_flowinfo;;
struct in6_addr sin6_addr;
unsigned int sin6_scope_id;
};
struct sockaddr
is the best C can do to emulate an abstract base class.
struct sockaddr
, but many system calls will accept parameters of type struct sockaddr *
.struct sockaddr_in
or a struct sockaddr_in6
. The system call relies on the value within the first two bytes—the sa_family
field—to determine what the true record type is.struct sockaddr { // generic socket
unsigned short sa_family; // protocol family for socket
char sa_data[14];
// address data (and defines full size to be 16 bytes)
};
struct sockaddr_in { // IPv4 socket address record
unsigned short sin_family;
unsigned short sin_port;
struct in_addr sin_addr;
unsigned char sin_zero[8];
};
struct sockaddr_in6 { // IPv6 socket address record
unsigned short sin6_family;
unsigned short sin6_port;
unsigned int sin6_flowinfo;;
struct in6_addr sin6_addr;
unsigned int sin6_scope_id;
};
createClientSocket
and createServerSocket
.
createClientSocket
is the easier of the two, so we'll implement that one first. (For simplicity, we'll confine ourselves to an IPv4 world.)gethostbyname
does this for us.socket
system call to do this.
struct sockaddr_in
that packages the host and port number we're interested in connecting to.connect
to do this.createClientSocket
:int createClientSocket(const string& host, unsigned short port) {
struct hostent *he = gethostbyname(host.c_str());
if (he == NULL) return -1;
int s = socket(AF_INET, SOCK_STREAM, 0);
if (s < 0) return -1;
struct sockaddr_in address;
memset(&address, 0, sizeof(address));
address.sin_family = AF_INET;
address.sin_port = htons(port);
// h_addr is #define for h_addr_list[0]
address.sin_addr = *((struct in_addr *)he->h_addr);
if (connect(s, (struct sockaddr *) &address, sizeof(address)) == 0) return s;
close(s);
return -1;
}
Here are a few details about the implementation of createClientSocket
worth calling out:
gethostbyname
first before we call socket
, because we want to confirm the host has a registered IP address—which means it's reachable—before we allocate any system resources.gethostbyname
is intrinsically IPv4. If we wanted to involve IPv6 addresses instead, we would need to use gethostbyname2
.socket
finds, claims, and returns an unused descriptor. AF_INET
configures it to be compatible with an IPv4 address, and SOCK_STREAM
configures it to provide reliable data transport, which basically means the socket will reorder data packets and requests missing or garbled data packets to be resent so as to give the impression that data that is received in the order it's sent.
AF_INET6
had we decided to use IPv6 addresses instead. (Other arguments are possible, but they're less common.)SOCK_DGRAM
had we preferred to collect data packets in the order they just happen to arrive and manage missing and garbled data packets ourselves. (Other arguments are possible, though they're less common.)address
is declared to be of type struct sockaddr_in
, since that's the data type specifically set up to model IPv4 addresses. Had we been dealing with IPv6 addresses, we'd have declared a struct sockaddr_in6
instead.AF_INET
within the sin_family
field, since those two bytes are examined by system calls to determine the type of socket address structure.sin_port
field is, not surprisingly, designed to hold the port of interest. htons
—that's an abbreviation for h
ost-to
-n
etwork-s
hort—is there to ensure the port is stored in network byte order (which is big endian order). On big endian machines, htons
is implemented to return the provided short without modification. On little endian machines (like the myth
s), htons
returns a figure constructed by exchanging the two bytes of the incoming short
. In addition to htons
, Linux also provided htonl
for four-byte long
s, and it also provides ntohs
and ntohl
to restore host byte order from network byte ordered figures.connect
associates the descriptor s
with the host/IP address pair modeled by the supplied struct sockaddr_in *
. The second argument is downcast to a struct sockaddr *
, since connect
needs accept a pointer to any type within the entire struct sockaddr
family, not just struct sockaddr_in
s.
createServerSocket
:int createServerSocket(unsigned short port, int backlog) {
int s = socket(AF_INET, SOCK_STREAM, 0);
if (s < 0) return -1;
struct sockaddr_in address;
memset(&address, 0, sizeof(address));
address.sin_family = AF_INET;
address.sin_addr.s_addr = htonl(INADDR_ANY);
address.sin_port = htons(port);
if (bind(s, (struct sockaddr *)&address, sizeof(address)) == 0 &&
listen(s, backlog) == 0) return s;
close(s);
return -1;
}
Here are a few details about the implementation of createServerSocket
worth calling out:
socket
is precisely the same here as it was in createClientSocket
. It allocates a descriptor and configures it to be a socket descriptor within the AF_INET
namespace.struct sockaddr_in
here is configured in much the same way it was in createClientSocket
, except that the sin_addr.s_addr
field should be set to a local IP address, not a remote one. The constant INADDR_ANY
is used to state that address should represent all local addresses.bind
call simply assigns the set of local IP addresses represented by address
to the provided socket s
. Because we embedded INADDR_ANY
within address
, bind
associates the supplied socket with all local IP addresses. That means once createServerSocket
has done its job, clients can connect to any of the machine's IP addresses via the specified port.listen
call is what converts the socket to be one that's willing to accept connections via accept
. The second argument is a queue size limit, which states how many pending connection requests can accumulate and wait their turn to be accept
ed. If the number of outstanding requests is at the limit, additional requests are simply refused.