[master] 7f4bf4b Update parameters to current source
Tollef Fog Heen
tfheen at varnish-cache.org
Mon Mar 11 08:59:55 CET 2013
commit 7f4bf4bf5433b7469d8b962f3910ca0f572f4ccd
Author: Tollef Fog Heen <tfheen at varnish-software.com>
Date: Mon Mar 11 08:59:53 2013 +0100
Update parameters to current source
diff --git a/doc/sphinx/reference/params.rst b/doc/sphinx/reference/params.rst
index 1f9a486..1ec8f58 100644
--- a/doc/sphinx/reference/params.rst
+++ b/doc/sphinx/reference/params.rst
@@ -1,3 +1,13 @@
+
+.. The following is the autogenerated output from varnishd -x dumprstparam
+
+accept_filter
+ - Units: bool
+ - Default: on
+ - Flags: must_restart
+
+ Enable kernel accept-filters, if supported by the kernel.
+
acceptor_sleep_decay
- Default: 0.900
- Flags: experimental
@@ -46,25 +56,37 @@ between_bytes_timeout
Default timeout between bytes when receiving data from backend. We only wait for this many seconds between bytes before giving up. A value of 0 means it will never time out. VCL can override this default value for each backend request and backend request. This parameter does not apply to pipe.
+busyobj_worker_cache
+ - Units: bool
+ - Default: off
+
+ Cache free busyobj per worker thread.Disable this if you have very high hitrates and wantto save the memory of one busyobj per worker thread.
+
cc_command
- - Default: exec gcc -std=gnu99 -pthread -fpic -shared -Wl,-x -o %o %s
+ - Default: exec gcc -std=gnu99 -g -O2 -pthread -fpic -shared -Wl,-x -o %o %s
- Flags: must_reload
Command used for compiling the C source code to a dlopen(3) loadable object. Any occurrence of %s in the string will be replaced with the source file name, and %o will be replaced with the output file name.
cli_buffer
- Units: bytes
- - Default: 8192
+ - Default: 8k
- Size of buffer for CLI input.
+ Size of buffer for CLI command input.
You may need to increase this if you have big VCL files and use the vcl.inline CLI command.
NB: Must be specified with -p to have effect.
+cli_limit
+ - Units: bytes
+ - Default: 48k
+
+ Maximum size of CLI response. If the response exceeds this limit, the reponse code will be 201 instead of 200 and the last line will indicate the truncation.
+
cli_timeout
- Units: seconds
- Default: 10
- Timeout for the childs replies to CLI requests from the master.
+ Timeout for the childs replies to CLI requests from the mgt_param.
clock_skew
- Units: s
@@ -81,10 +103,26 @@ connect_timeout
critbit_cooloff
- Units: s
- Default: 180.0
- - Flags:
+ - Flags: wizard
How long time the critbit hasher keeps deleted objheads on the cooloff list.
+debug
+ - Default: none
+
+ Enable/Disable various kinds of debugging.
+ none Disable all debugging
+ Use +/- prefix to set/reset individual bits::
+
+ req_state VSL Request state engine
+ workspace VSL Workspace operations
+ waiter VSL Waiter internals
+ waitinglist VSL Waitinglist events
+ syncvsl Make VSL synchronous
+ hashedge Edge cases in Hash
+ vclrel Rapid VCL release
+ lurker VSL Ban lurker
+
default_grace
- Units: seconds
- Default: 10
@@ -106,30 +144,7 @@ default_ttl
The TTL assigned to objects if neither the backend nor the VCL code assigns one.
Objects already cached will not be affected by changes made until they are fetched from the backend again.
- To force an immediate effect at the expense of a total flush of the cache use "ban.url ."
-
-diag_bitmap
- - Units: bitmap
- - Default: 0
-
- Bitmap controlling diagnostics code::
-
- 0x00000001 - CNT_Session states.
- 0x00000002 - workspace debugging.
- 0x00000004 - kqueue debugging.
- 0x00000008 - mutex logging.
- 0x00000010 - mutex contests.
- 0x00000020 - waiting list.
- 0x00000040 - object workspace.
- 0x00001000 - do not core-dump child process.
- 0x00002000 - only short panic message.
- 0x00004000 - panic to stderr.
- 0x00010000 - synchronize shmlog.
- 0x00020000 - synchronous start of persistence.
- 0x00040000 - release VCL early.
- 0x80000000 - do edge-detection on digest.
-
- Use 0x notation and do the bitor in your head :-)
+ To force an immediate effect at the expense of a total flush of the cache use "ban obj.http.date ~ ."
esi_syntax
- Units: bitmap
@@ -150,17 +165,28 @@ expiry_sleep
How long the expiry thread sleeps when there is nothing for it to do.
+feature
+ - Default: none
+
+ Enable/Disable various minor features.
+ none Disable all features.
+ Use +/- prefix to enable/disable individual feature::
+
+ short_panic Short panic message.
+ wait_silo Wait for persistent silo.
+ no_coredump No coredumps.
+
fetch_chunksize
- - Units: kilobytes
- - Default: 128
+ - Units: bytes
+ - Default: 128k
- Flags: experimental
The default chunksize used by fetcher. This should be bigger than the majority of objects with short TTLs.
Internal limits in the storage_file module makes increases above 128kb a dubious idea.
fetch_maxchunksize
- - Units: kilobytes
- - Default: 262144
+ - Units: bytes
+ - Default: 256m
- Flags: experimental
The maximum chunksize we attempt to allocate from storage. Making this too large may cause delays and storage fragmentation.
@@ -172,11 +198,19 @@ first_byte_timeout
Default timeout for receiving first byte from backend. We only wait for this many seconds for the first byte before giving up. A value of 0 means it will never time out. VCL can override this default value for each backend and backend request. This parameter does not apply to pipe.
group
- - Default: magic
+ - Default: nogroup
- Flags: must_restart
The unprivileged group to run as.
+gzip_buffer
+ - Units: bytes
+ - Default: 32k
+ - Flags: experimental
+
+ Size of malloc buffer used for gzip processing.
+ These buffers are used for in-transit data, for instance gunzip'ed data being sent to a client.Making this space to small results in more overhead, writes to sockets etc, making it too big is probably just a waste of memory.
+
gzip_level
- Default: 6
@@ -188,40 +222,14 @@ gzip_memlevel
Gzip memory level 1=slow/least, 9=fast/most compression.
Memory impact is 1=1k, 2=2k, ... 9=256k.
-gzip_stack_buffer
- - Units: Bytes
- - Default: 32768
- - Flags: experimental
-
- Size of stack buffer used for gzip processing.
- The stack buffers are used for in-transit data, for instance gunzip'ed data being sent to a client.Making this space to small results in more overhead, writes to sockets etc, making it too big is probably just a waste of memory.
-
-gzip_tmp_space
- - Default: 0
- - Flags: experimental
-
- Where temporary space for gzip/gunzip is allocated::
-
- 0 - malloc
- 1 - session workspace
- 2 - thread workspace
-
- If you have much gzip/gunzip activity, it may be an advantage to use workspace for these allocations to reduce malloc activity. Be aware that gzip needs 256+KB and gunzip needs 32+KB of workspace (64+KB if ESI processing).
-
-gzip_window
- - Default: 15
-
- Gzip window size 8=least, 15=most compression.
- Memory impact is 8=1k, 9=2k, ... 15=128k.
-
http_gzip_support
- Units: bool
- Default: on
- Flags: experimental
- Enable gzip support. When enabled Varnish will compress uncompressed objects before they are stored in the cache. If a client does not support gzip encoding Varnish will uncompress compressed objects on demand. Varnish will also rewrite the Accept-Encoding header of clients indicating support for gzip to:
+ Enable gzip support. When enabled Varnish will compress uncompressed objects before they are stored in the cache. If a client does not support gzip encoding Varnish will uncompress compressed objects on demand. Varnish will also rewrite the Accept-Encoding header of clients indicating support for gzip to::
- Accept-Encoding: gzip
+ Accept-Encoding: gzip
Clients that do not support gzip will have their Accept-Encoding header removed. For more information on how gzip is implemented please see the chapter on gzip in the Varnish reference.
@@ -229,41 +237,50 @@ http_max_hdr
- Units: header lines
- Default: 64
- Maximum number of HTTP headers we will deal with in client request or backend reponses. Note that the first line occupies five header fields.
- This paramter does not influence storage consumption, objects allocate exact space for the headers they store.
+ Maximum number of HTTP header lines we allow in {req|resp|bereq|beresp}.http (obj.http is autosized to the exact number of headers).
+ Cheap, ~20 bytes, in terms of workspace memory.
+ Note that the first line occupies five header lines.
http_range_support
- Units: bool
- Default: on
- - Flags: experimental
Enable support for HTTP Range headers.
http_req_hdr_len
- Units: bytes
- - Default: 4096
+ - Default: 8k
Maximum length of any HTTP client request header we will allow. The limit is inclusive its continuation lines.
http_req_size
- Units: bytes
- - Default: 32768
+ - Default: 32k
Maximum number of bytes of HTTP client request we will deal with. This is a limit on all bytes up to the double blank line which ends the HTTP request.
The memory for the request is allocated from the client workspace (param: workspace_client) and this parameter limits how much of that the request is allowed to take up.
http_resp_hdr_len
- Units: bytes
- - Default: 4096
+ - Default: 8k
Maximum length of any HTTP backend response header we will allow. The limit is inclusive its continuation lines.
http_resp_size
- Units: bytes
- - Default: 32768
+ - Default: 32k
Maximum number of bytes of HTTP backend resonse we will deal with. This is a limit on all bytes up to the double blank line which ends the HTTP request.
- The memory for the request is allocated from the thread pool workspace (param: thread_pool_workspace) and this parameter limits how much of that the request is allowed to take up.
+ The memory for the request is allocated from the worker workspace (param: thread_pool_workspace) and this parameter limits how much of that the request is allowed to take up.
+
+idle_send_timeout
+ - Units: seconds
+ - Default: 60
+ - Flags: delayed
+
+ Time to wait with no data sent. If no data has been transmitted in this many
+ seconds the session is closed.
+ See setsockopt(2) under SO_SNDTIMEO for more information.
listen_address
- Default: :80
@@ -279,17 +296,12 @@ listen_depth
Listen queue depth.
-log_hashstring
- - Units: bool
- - Default: on
-
- Log the hash string components to shared memory log.
-
log_local_address
- Units: bool
- - Default: off
+ - Default: on
- Log the local address on the TCP connection in the SessionOpen shared memory record.
+ Log the local address on the TCP connection in the SessionOpen VSL record.
+ Disabling this saves a getsockname(2) system call per TCP connection.
lru_interval
- Units: seconds
@@ -314,11 +326,27 @@ max_restarts
nuke_limit
- Units: allocations
- - Default: 10
+ - Default: 50
- Flags: experimental
Maximum number of objects we attempt to nuke in orderto make space for a object body.
+obj_readonly
+ - Units: bool
+ - Default: false
+
+ If set, we do not update obj.hits and obj.lastuse to avoid dirtying VM pages associated with cached objects.
+
+pcre_match_limit
+ - Default: 10000
+
+ The limit for the number of internal matching function calls in a pcre_exec() execution.
+
+pcre_match_limit_recursion
+ - Default: 10000
+
+ The limit for the number of internal matching function recursions in a pcre_exec() execution.
+
ping_interval
- Units: seconds
- Default: 3
@@ -333,21 +361,52 @@ pipe_timeout
Idle timeout for PIPE sessions. If nothing have been received in either direction for this many seconds, the session is closed.
+pool_req
+ - Default: 10,100,10
+
+ Parameters for per worker pool request memory pool.
+ The three numbers are::
+
+ min_pool -- minimum size of free pool.
+ max_pool -- maximum size of free pool.
+ max_age -- max age of free element.
+
+pool_sess
+ - Default: 10,100,10
+
+ Parameters for per worker pool session memory pool.
+ The three numbers are::
+
+ min_pool -- minimum size of free pool.
+ max_pool -- maximum size of free pool.
+ max_age -- max age of free element.
+
+pool_vbc
+ - Default: 10,100,10
+
+ Parameters for backend connection memory pool.
+ The three numbers are::
+
+ min_pool -- minimum size of free pool.
+ max_pool -- maximum size of free pool.
+ max_age -- max age of free element.
+
+pool_vbo
+ - Default: 10,100,10
+
+ Parameters for backend object fetch memory pool.
+ The three numbers are::
+
+ min_pool -- minimum size of free pool.
+ max_pool -- maximum size of free pool.
+ max_age -- max age of free element.
+
prefer_ipv6
- Units: bool
- Default: off
Prefer IPv6 address when connecting to backends which have both IPv4 and IPv6 addresses.
-queue_max
- - Units: %
- - Default: 100
- - Flags: experimental
-
- Percentage permitted queue length.
-
- This sets the ratio of queued requests to worker threads, above which sessions will be dropped instead of queued.
-
rush_exponent
- Units: requests per request
- Default: 3
@@ -365,33 +424,18 @@ saintmode_threshold
send_timeout
- Units: seconds
- - Default: 60
+ - Default: 600
- Flags: delayed
Send timeout for client connections. If the HTTP response hasn't been transmitted in this many
- seconds the session is closed.
+ seconds the session is closed.
See setsockopt(2) under SO_SNDTIMEO for more information.
-sess_timeout
- - Units: seconds
- - Default: 5
-
- Idle timeout for persistent sessions. If a HTTP request has not been received in this many seconds, the session is closed.
-
-session_linger
- - Units: ms
- - Default: 50
- - Flags: experimental
-
- How long time the workerthread lingers on the session to see if a new request appears right away.
- If sessions are reused, as much as half of all reuses happen within the first 100 msec of the previous request completing.
- Setting this too high results in worker threads not doing anything for their keep, setting it too low just means that more sessions take a detour around the waiter.
-
session_max
- Units: sessions
- Default: 100000
- Maximum number of sessions we will allocate before just dropping connections.
+ Maximum number of sessions we will allocate from one pool before just dropping connections.
This is mostly an anti-DoS measure, and setting it plenty high should not hurt, as long as you have the memory for it.
shm_reclen
@@ -401,15 +445,6 @@ shm_reclen
Maximum number of bytes in SHM log record.
Maximum is 65535 bytes.
-shm_workspace
- - Units: bytes
- - Default: 8192
- - Flags: delayed
-
- Bytes of shmlog workspace allocated for worker threads. If too big, it wastes some ram, if too small it causes needless flushes of the SHM workspace.
- These flushes show up in stats as "SHM flushes due to overflow".
- Minimum is 4096 bytes.
-
shortlived
- Units: s
- Default: 10.0
@@ -422,36 +457,58 @@ syslog_cli_traffic
Log all CLI traffic to syslog(LOG_INFO).
-thread_pool_add_delay
- - Units: milliseconds
- - Default: 2
+tcp_keepalive_intvl
+ - Units: seconds
+ - Default: 5
+ - Flags: experimental
- Wait at least this long between creating threads.
+ The number of seconds between TCP keep-alive probes. Note that this setting will only take effect when it is less thanthe system default.
- Setting this too long results in insuffient worker threads.
+tcp_keepalive_probes
+ - Units: probes
+ - Default: 5
+ - Flags: experimental
- Setting this too short increases the risk of worker thread pile-up.
+ The maximum number of TCP keep-alive probes to send before giving up and killing the connection if no response is obtained from the other end. Note that this setting will only take effect when it is less than the system default.
-thread_pool_add_threshold
- - Units: requests
- - Default: 2
+tcp_keepalive_time
+ - Units: seconds
+ - Default: 600
- Flags: experimental
- Overflow threshold for worker thread creation.
+ The number of seconds a connection needs to be idle before TCP begins sending out keep-alive probes. Note that this setting will only take effect when it is less than the system default.
- Setting this too low, will result in excess worker threads, which is generally a bad idea.
+thread_pool_add_delay
+ - Units: seconds
+ - Default: 0
+ - Flags: experimental
- Setting it too high results in insuffient worker threads.
+ Wait at least this long after creating a thread.
+
+ Some (buggy) systems may need a short (sub-second) delay between creating threads.
+ Set this to a few milliseconds if you see the 'threads_failed' counter grow too much.
+
+ Setting this too high results in insuffient worker threads.
+
+thread_pool_destroy_delay
+ - Units: seconds
+ - Default: 1
+ - Flags: delayed, experimental
+
+ Wait this long after destroying a thread.
+
+ This controls the decay of thread pools when idle(-ish).
+
+ Minimum is 0.01 second.
thread_pool_fail_delay
- - Units: milliseconds
- - Default: 200
+ - Units: seconds
+ - Default: 0.2
- Flags: experimental
Wait at least this long after a failed thread creation before trying to create another thread.
- Failure to create a worker thread is often a sign that the end is near, because the process is running out of RAM resources for thread stacks.
- This delay tries to not rush it on needlessly.
+ Failure to create a worker thread is often a sign that the end is near, because the process is running out of some resource. This delay tries to not rush the end on needlessly.
If thread creation failures are a problem, check that thread_pool_max is not too high.
@@ -459,42 +516,34 @@ thread_pool_fail_delay
thread_pool_max
- Units: threads
- - Default: 500
- - Flags: delayed, experimental
+ - Default: 5000
+ - Flags: delayed
The maximum number of worker threads in each pool.
Do not set this higher than you have to, since excess worker threads soak up RAM and CPU and generally just get in the way of getting work done.
+ Minimum is 10 threads.
+
thread_pool_min
- Units: threads
- - Default: 5
- - Flags: delayed, experimental
+ - Default: 100
+ - Flags: delayed
The minimum number of worker threads in each pool.
- Increasing this may help ramp up faster from low load situations where threads have expired.
-
- Minimum is 2 threads.
-
-thread_pool_purge_delay
- - Units: milliseconds
- - Default: 1000
- - Flags: delayed, experimental
-
- Wait this long between purging threads.
-
- This controls the decay of thread pools when idle(-ish).
+ Increasing this may help ramp up faster from low load situations or when threads have expired.
- Minimum is 100 milliseconds.
+ Minimum is 10 threads.
thread_pool_stack
- Units: bytes
- - Default: -1
+ - Default: 48k
- Flags: experimental
Worker thread stack size.
- On 32bit systems you may need to tweak this down to fit many threads into the limited address space.
+ This is likely rounded up to a multiple of 4k by the kernel.
+ The kernel/OS has a lower limit which will be enforced.
thread_pool_timeout
- Units: seconds
@@ -503,16 +552,9 @@ thread_pool_timeout
Thread idle threshold.
- Threads in excess of thread_pool_min, which have been idle for at least this long are candidates for purging.
+ Threads in excess of thread_pool_min, which have been idle for at least this long, will be destroyed.
- Minimum is 1 second.
-
-thread_pool_workspace
- - Units: bytes
- - Default: 65536
- - Flags: delayed
-
- Bytes of HTTP protocol workspace allocated for worker threads. This space must be big enough for the backend request and responses, and response to the client plus any other memory needs in the VCL code.Minimum is 1024 bytes.
+ Minimum is 10 seconds.
thread_pools
- Units: pools
@@ -527,6 +569,14 @@ thread_pools
Can be increased on the fly, but decreases require a restart to take effect.
+thread_queue_limit
+ - Default: 20
+ - Flags: experimental
+
+ Permitted queue length per thread-pool.
+
+ This sets the number of requests we will queue, waiting for an available thread. Above this limit sessions will be dropped instead of queued.
+
thread_stats_rate
- Units: requests
- Default: 10
@@ -535,11 +585,39 @@ thread_stats_rate
Worker threads accumulate statistics, and dump these into the global stats counters if the lock is free when they finish a request.
This parameters defines the maximum number of requests a worker thread may handle, before it is forced to dump its accumulated stats into the global counters.
+timeout_idle
+ - Units: seconds
+ - Default: 5
+
+ Idle timeout for client connections.
+ A connection is considered idle, until we receive a non-white-space character on it.
+
+timeout_linger
+ - Units: seconds
+ - Default: 0.050
+ - Flags: experimental
+
+ How long time the workerthread lingers on an idle session before handing it over to the waiter.
+ When sessions are reused, as much as half of all reuses happen within the first 100 msec of the previous request completing.
+ Setting this too high results in worker threads not doing anything for their keep, setting it too low just means that more sessions take a detour around the waiter.
+
+timeout_req
+ - Units: seconds
+ - Default: 2
+
+ Max time to receive clients request header, measured from first non-white-space character to double CRNL.
+
user
- - Default: magic
+ - Default: nobody
- Flags: must_restart
- The unprivileged user to run as. Setting this will also set "group" to the specified user's primary group.
+ The unprivileged user to run as.
+
+vcc_allow_inline_c
+ - Units: bool
+ - Default: on
+
+ Allow inline C code in VCL.
vcc_err_unref
- Units: bool
@@ -547,28 +625,79 @@ vcc_err_unref
Unreferenced VCL objects result in error.
-vcl_dir
- - Default: /usr/local/etc/varnish
+vcc_unsafe_path
+ - Units: bool
+ - Default: on
- Directory from which relative VCL filenames (vcl.load and include) are opened.
+ Allow '/' in vmod & include paths.
+ Allow 'import ... from ...'.
-vcl_trace
- - Units: bool
- - Default: off
+vcl_dir
+ - Default: /tmp/z/v/etc/varnish
- Trace VCL execution in the shmlog.
- Enabling this will allow you to see the path each request has taken through the VCL program.
- This generates a lot of logrecords so it is off by default.
+ Directory from which relative VCL filenames (vcl.load and include) are opened.
vmod_dir
- - Default: /usr/local/lib/varnish/vmods
+ - Default: /tmp/z/v/lib/varnish/vmods
Directory where VCL modules are to be found.
-waiter
+vsl_buffer
+ - Units: bytes
+ - Default: 4k
+
+ Bytes of (req-/backend-)workspace dedicated to buffering VSL records.
+ At a bare minimum, this must be longer than the longest HTTP header to be logged.
+ Setting this too high costs memory, setting it too low will cause more VSL flushes and likely increase lock-contention on the VSL mutex.
+ Minimum is 1k bytes.
+
+vsl_mask
- Default: default
- - Flags: must_restart, experimental
+
+ Mask individual VSL messages from being logged.
+ default Set default value
+ Use +/- prefixe in front of VSL tag name, to mask/unmask individual VSL messages.
+
+vsl_space
+ - Units: bytes
+ - Default: 80M
+ - Flags: must_restart
+
+ The amount of space to allocate for the VSL fifo buffer in the VSM memory segment. If you make this too small, varnish{ncsa|log} etc will not be able to keep up. Making it too large just costs memory resources.
+
+vsm_space
+ - Units: bytes
+ - Default: 1M
+ - Flags: must_restart
+
+ The amount of space to allocate for stats counters in the VSM memory segment. If you make this too small, some counters will be invisible. Making it too large just costs memory resources.
+
+waiter
+ - Default: platform dependent
+ - Flags: must_restart, wizard
Select the waiter kernel interface.
+workspace_backend
+ - Units: bytes
+ - Default: 64k
+ - Flags: delayed
+
+ Bytes of HTTP protocol workspace for backend HTTP req/resp. If larger than 4k, use a multiple of 4k for VM efficiency.
+
+workspace_client
+ - Units: bytes
+ - Default: 64k
+ - Flags: delayed
+
+ Bytes of HTTP protocol workspace for clients HTTP req/resp. If larger than 4k, use a multiple of 4k for VM efficiency.
+
+workspace_thread
+ - Units: bytes
+ - Default: 2048
+ - Flags: delayed
+
+ Bytes of auxillary workspace per thread.
+ This workspace is used for certain temporary data structures during the operation of a worker thread.
+ One use is for the io-vectors for writing requests and responses to sockets, having too little space will result in more writev(2) system calls, having too much just wastes the space.
More information about the varnish-commit
mailing list