Showing
2 changed files
with
34 additions
and
2 deletions
1 | +2012-02-19 18:28:30 +0100 Georg Hopp | ||
2 | + | ||
3 | + * increase writebuffer size a lot. (HEAD, master) | ||
4 | + | ||
5 | +2012-02-19 18:15:55 +0100 Georg Hopp | ||
6 | + | ||
7 | + * fixed the non keep-alive performance issue as well as i lower memory usage by using a single read and write circular buffer for every connection. @TODO: i noticed a server hang while getting large data (my image) with non keep-alive connections. Additionally an incomplete keep-alive request might stop the server now as the lock on the read buffer will not be released. (origin/master, origin/HEAD) | ||
8 | + | ||
9 | +2012-02-19 15:41:48 +0100 Georg Hopp | ||
10 | + | ||
11 | + * another try with the shmen trick...this time use MAP_ANONYMOUS ... as GNU extension. | ||
12 | + | ||
13 | +2012-02-19 14:33:42 +0100 Georg Hopp | ||
14 | + | ||
15 | + * Merge remote branch 'origin/master' | ||
16 | + | ||
17 | +2012-02-19 12:13:52 +0100 Georg Hopp | ||
18 | + | ||
19 | + * added missing header file to repo | ||
20 | + | ||
1 | 2012-02-19 11:35:15 +0100 Georg Hopp | 21 | 2012-02-19 11:35:15 +0100 Georg Hopp |
2 | 22 | ||
3 | - * another try with a shared memory based ringbuffer...this performs well for keep-alive sessions but is much slower without. actually i am not sure why but most likely the shared memory setup is quite expensive. @TODO: make a profiling. (HEAD, ringbuffer) | 23 | + * another try with a shared memory based ringbuffer...this performs well for keep-alive sessions but is much slower without. actually i am not sure why but most likely the shared memory setup is quite expensive. @TODO: make a profiling. |
24 | + | ||
25 | +2012-02-18 21:08:32 +0100 Georg Hopp | ||
26 | + | ||
27 | + * fix inf loop. @TODO: This whole handling has to be cleaned. | ||
28 | + | ||
29 | +2012-02-18 20:50:01 +0100 Georg Hopp | ||
30 | + | ||
31 | + * this change hopefully makes the shm trick work on amd64 | ||
32 | + | ||
33 | +2012-02-18 20:12:27 +0100 Georg Hopp | ||
34 | + | ||
35 | + * lots of changes but primarily change the request parser to use a ringbuffer. The ringbuffer is implemented using the shared memory trick. | ||
4 | 36 | ||
5 | 2012-02-15 12:30:33 +0100 Georg Hopp | 37 | 2012-02-15 12:30:33 +0100 Georg Hopp |
6 | 38 |
@@ -8,7 +8,7 @@ | @@ -8,7 +8,7 @@ | ||
8 | #include "http/response/writer.h" | 8 | #include "http/response/writer.h" |
9 | #include "cbuf.h" | 9 | #include "cbuf.h" |
10 | 10 | ||
11 | -#define RESPONSE_WRITER_MAX_BUF 32768 | 11 | +#define RESPONSE_WRITER_MAX_BUF 131072 |
12 | #define REQUEST_PARSER_BUFFER_MAX 8192 | 12 | #define REQUEST_PARSER_BUFFER_MAX 8192 |
13 | 13 | ||
14 | #ifndef TRUE | 14 | #ifndef TRUE |
Please
register
or
login
to post a comment