summaryrefslogtreecommitdiff
path: root/ring_rx.c
AgeCommit message (Collapse)AuthorFilesLines
2016-09-29all: fix build on CentOS 6 by checking presence of several macrosYousong Zhou1-0/+4
Protect usage of macros not present in pre-3.x kernels. Signed-off-by: Yousong Zhou <yszhou4tech@gmail.com> Signed-off-by: Tobias Klauser <tklauser@distanz.ch>
2016-04-27ring: Remove unused parameter sock from setup_ring_layout_generic()Tobias Klauser1-1/+1
setup_ring_layout_generic() takes an "int sock" parameter but never uses it. Remove it to prevent -Wunused-parameter warnings. Signed-off-by: Tobias Klauser <tklauser@distanz.ch>
2016-01-27ring: Make needlessly global function join_fanout_group() staticTobias Klauser1-1/+1
This fixes the following sparse warning: ring_rx.c:197:6: warning: symbol 'join_fanout_group' was not declared. Should it be static? Signed-off-by: Tobias Klauser <tklauser@distanz.ch>
2015-11-06ring: Move common ring block_r/frame_nr shrinking to generic functionTobias Klauser1-4/+1
Merge shrinking code duplicated for RX/TX rings into an own generic function. Signed-off-by: Tobias Klauser <tklauser@distanz.ch>
2015-10-29ring: alloc_ring_frames_generic make types size_tDaniel Borkmann1-1/+1
Lets make i and num as size_t, there's no particular reason for them to be int. At least i is used to setup iov_base offsets. Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2015-10-29ring: Move generic code for ring layout setup to own functionTobias Klauser1-15/+2
Initialization of the ring->layout members is the same for RX and TX rings. Instead of duplicating the code in setup_rx_ring_layout() and setup_tx_ring_layout(), create a new function setup_ring_layout_generic() which is called from the former two. Signed-off-by: Tobias Klauser <tklauser@distanz.ch>
2015-08-25netsniff-ng: Show total rx stats for multi pcap modeVadim Kochan1-20/+3
Allow to collect rx stats for multiple pcap mode, by storing them in separated variables before switch to the next pcap file. It allows to have the one approach when dump for single or multiple pcap(s) mode. Signed-off-by: Vadim Kochan <vadim4j@gmail.com> Signed-off-by: Tobias Klauser <tklauser@distanz.ch>
2015-04-21netsniff-ng: add packet fanout supportMichał Purzyński1-1/+18
This work adds packet fanout support to netsniff-ng. Multiple netsniff-ng instances can join the same fanout group with a particular id in order to improve scaling. Based on different fanout disciplines, e.g. distribute to fanout member by packet hash, round-robin, by arrival cpu, by random, by socket rollover (if one members socket queue is full, switch to next one, etc), by hardware queue mapping, traffic can be distributed to one of the fanout members. Moreover, we also allow the user to specify additional aux arguments, e.g. whether to defrag incoming traffic for the fanout group or not, and whether to roll over a socket in case other disciplines than socket rollover have been used. All that is configurable via command line option. Signed-off-by: Michał Purzyński <michalpurzynski1@gmail.com> [ dbkm made some bigger changes to get this upstream ready ] Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2014-08-14netsniff-ng: Protect all access to tpacket v3 structs and constants (this ↵Tobias Klauser1-12/+41
time for real) Commit 0fab564a98d1 ("netsniff-ng: Properly wrap usage of all tpacket v3 structs") took care of protecting _some_ tpacket v3 structures with compile error when building with !HAVE_TPACKET3 (reported by Mike Reeves): > CC ring_rx.c > ring_rx.c: In function 'setup_rx_ring_layout': > ring_rx.c:124: warning: implicit declaration of function 'set_sockopt_tpacket_v3' > ring_rx.c: In function 'sock_rx_net_stats': > ring_rx.c:194: error: field 'k3' has incomplete type > make: *** [netsniff-ng/ring_rx.o] Error 1 Many thanks to Mike for helping me sort out these problems. Reported-by: Mike Reeves <luke@geekempire.com> Signed-off-by: Tobias Klauser <tklauser@distanz.ch>
2014-08-14netsniff-ng: Properly wrap usage of all tpacket v3 structsTobias Klauser1-21/+40
Mike Reeves reports the following compilation error if tpacket v3 is not available: > CC ring_rx.c > ring_rx.c: In function 'alloc_rx_ring_frames': > ring_rx.c:143: error: 'struct ring' has no member named 'layout3' > ring_rx.c:144: error: 'struct ring' has no member named 'layout3' > ring_rx.c: In function 'sock_rx_net_stats': > ring_rx.c:172: error: field 'k3' has incomplete type > make: *** [netsniff-ng/ring_rx.o] Error 1 The layout3 member of struct ring is only available for HAVE_TPACKET3. Thus, wrap all access to it into inline functions defined depending on wheter HAVE_TPACKET3 is defined. Reported-by: Mike Reeves <luke@geekempire.com> Signed-off-by: Tobias Klauser <tklauser@distanz.ch>
2014-08-14netsniff-ng: Clean up HAVE_TPACKET3 #ifdefsTobias Klauser1-10/+13
Instead of having #ifdef HAVE_TPACKET3 spread all over the code, encapsulate the functionality depending on it inside inline functions: the existing is_tpacket_v3() introduced in commit 5bc19d0b84d0 ("netsniff-ng: Only use TPACKET_V3 if HAVE_TPACKET3 is defined") and the newly introduced get_ring_layout_size() to get the ring layout size depending on the tpacket version available and the version actually in use. Signed-off-by: Tobias Klauser <tklauser@distanz.ch>
2014-08-14netsniff-ng: Only use TPACKET_V3 if HAVE_TPACKET3 is definedTobias Klauser1-9/+16
TPACKET_V3 is not defined if tpacket v3 is not available, thus make its use conditional on HAVE_TPACKET3. Wrap the check for TPACKET_V3 in ring_rx in an inline function which always returns false if HAVE_TPACKET3 is not defined. Reported-by: Mike Reeves <luke@geekempire.com> Signed-off-by: Tobias Klauser <tklauser@distanz.ch>
2014-08-14netsniff-ng: Restore tpacket v2 capturingTobias Klauser1-1/+16
Some older systems (e.g. RHEL 6) don't have tpacket v3 available, but only tpacket v2. However, since commit d8cdc6a ("ring: netsniff-ng: migrate capture only to TPACKET_V3") we solely rely on tpacket v3 for capturing packets. This patch restores the possibility to capture using tpacket v2. For now this is just a fallback if the configure script doesn't detect tpacket v3 (and thus HAVE_TPACKET3 isn't set). Thus, on most modern systems this shouldn't change anything and they will continue using tpacket v3. For now this fix contains quite a bit of ugly #ifdefery which should be cleaned up in the future. Fixes #76 Signed-off-by: Tobias Klauser <tklauser@distanz.ch>
2014-05-09ring: Merge common ring_{rx,tx} initialization into own functionTobias Klauser1-10/+13
Instead of having to perform the individual steps to initialize a ring and open coding them in multiple places, provide convenience functions to do all at once. This has the nice side effect of allowing to make most of these *_{rx,tx}_ring() functions static in their respective module. Signed-off-by: Tobias Klauser <tklauser@distanz.ch>
2014-05-03all: Use macros for printf/scanf format specifiersJames McCoy1-4/+5
Any types that are fixed width should use the standard format specifier macros (PRI... for printf-type functions, SCN... for scanf-type functions) to ensure proper data access. Prior to this ifpps was crashing in 32-bit environments due to the following call mvwprintw(screen, (*voff)++, 2, "%s,%s %s (%s%s), t=%lums, cpus=%u%s/%u" " ", uts.release, machine, ifname, drvinf.driver, buff, ms_interval, top_cpus, top_cpus > 0 && top_cpus < cpus ? "+1" : "", cpus); since ms_interval is a uint64_t but %lu expects an unsigned long, which is only 32 bits. Signed-off-by: James McCoy <vega.james@gmail.com> Signed-off-by: Tobias Klauser <tklauser@distanz.ch>
2014-04-30netsniff-ng/ring: Make verbose flag boolTobias Klauser1-1/+1
Change type of verbose flag from int to bool. Signed-off-by: Tobias Klauser <tklauser@distanz.ch>
2014-04-30ring: Consistently use size_t to specify ring sizeTobias Klauser1-2/+2
The mm_len member of struct ring is of type size_t, but in the code paths leading to set it, unsigned int is used. In circumstances where unsigned int is 32 bit and size_t is 64 bit, this could lead to an integer overflow, which causes an improper ring size being mmap()'ed in mmap_ring_generic(). In order to prevent this, consistently use size_t to store the ring size, since this is also what mmap() takes as its `length' parameter. This now allows to specify ring sizes larger than 4 GiB for both netsniff-ng and trafgen (fixes #90). Reported-by: Jon Schipp <jonschipp@gmail.com> Reported-by: Michał Purzyński <michalpurzynski1@gmail.com> Signed-off-by: Tobias Klauser <tklauser@distanz.ch>
2014-04-12built_in: changed to use RUNTIME_PAGE_SIZE instead of PAGE_SIZEChristian Wiese1-2/+2
References: https://github.com/netsniff-ng/netsniff-ng/commit/453f6eb9d79dd5aa2812ef956b22723f0a493086 https://github.com/netsniff-ng/netsniff-ng/pull/112 Signed-off-by: Christian Wiese <chris@opensde.org> Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
2013-12-11trafgen: speedup TX only path by avoiding kernel packet_rcv() callJesper Dangaard Brouer1-1/+1
The tool trafgen is used in a pktgen style transmit only scenario. We discovered a performance bottleneck in the kernel, when running trafgen, where the kernel stalled on a lock in packet_rcv(). This call is unnecessary for trafgen given its transmit only nature. This packet_rcv() call can, easily be avoided by instructing the RAW/PF_PACKET socket, to not listen to any protocols (by passing protocol argument zero, when creating the socket). The performance gain is huge, increasing performance from approx max 2Mpps to 12Mpps, basically causing trafgen to scale with the number of CPUs. Following tests were run on a 2xCPU E5-2650 with Intel 10Gbit/s ixgbe: Trafgen using sendto() syscall via parameter -t0: * # CPUs -- *with* -- *without* packet_rcv() call * 1 CPU == 1,232,244 -- 1,236,144 pkts/sec * 2 CPUs == 1,592,720 -- 2,593,620 pkts/sec * 3 CPUs == 1,635,623 -- 3,692,216 pkts/sec * 4 CPUs == 1,567,768 -- 4,102,866 pkts/sec * 5 CPUs == 1,700,270 -- 5,151,489 pkts/sec * 6 CPUs == 1,762,392 -- 6,124,512 pkts/sec * 7 CPUs == 1,850,139 -- 7,120,496 pkts/sec * 8 CPUs == 1,770,909 -- 8,058,710 pkts/sec * 9 CPUs == 1,721,072 -- 8,963,192 pkts/sec * 10 CPUs == 1,359,157 -- 9,584,535 pkts/sec * 11 CPUs == 1,175,520 -- 10,498,038 pkts/sec * 12 CPUs == 1,075,867 -- 11,189,292 pkts/sec * 13 CPUs == 1,012,602 -- 12,048,836 pkts/sec * [...] * 20 CPUs == 1,030,446 -- 11,202,449 pkts/sec Trafgen using mmap() TX tpacket_v2 (default) * # CPUs -- *with* -- *without* packet_rcv() call * 1 CPU == 920,682 -- 927,984 pkts/sec * 2 CPUs == 1,607,940 -- 2,061,406 pkts/sec * 3 CPUs == 1,668,488 -- 2,979,463 pkts/sec * 4 CPUs == 1,423,066 -- 3,169,565 pkts/sec * 5 CPUs == 1,507,708 -- 3,910,756 pkts/sec * 6 CPUs == 1,555,616 -- 4,625,844 pkts/sec * 7 CPUs == 1,560,961 -- 5,298,441 pkts/sec * 8 CPUs == 1,596,092 -- 6,000,465 pkts/sec * 9 CPUs == 1,575,139 -- 6,722,130 pkts/sec * 10 CPUs == 1,311,676 -- 7,114,202 pkts/sec * 11 CPUs == 1,157,650 -- 7,859,399 pkts/sec * 12 CPUs == 1,060,366 -- 8,491,004 pkts/sec * 13 CPUs == 1,012,956 -- 9,269,761 pkts/sec * [...] * 20 CPUs == 955,716 -- 8,653,947 pkts/sec It is fairly strange that the mmap() version runs slower than the sendto() version. This is likely another performance problem related to mmap() which seems worth fixing. Note, that the mmap() version speed can be improved by reducing the default --ring-size to around 1-2 MiB. But this does not fix general trend with mmap() performance. Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
2013-08-21ring_{rx,tx}: verbose: output version and v3 specific infoDaniel Borkmann1-3/+9
Kevin says: With netsniff-ng 0.5.8-rc2+, when I run the below packet capture session, the output seems to imply that 64K of memory is being allocated per frame, which does not look like what I want since my interface MTU is only 1500. This appears to be severely limiting the number of frames I can fit into my packet capture ring. As TPACKET_V3 is used in capturing to pcap files, frames are written continuously to the ring, thus the above will give a wrong impression to the user. Therefore, output such information in verbose mode differently when TPACKET_V3 is being used, as it works block-wise. Reported-by: Kevin Branch <branchnetconsulting@gmail.com> Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
2013-07-13ring_rx: fix format string sparse warningDaniel Borkmann1-1/+1
Found by sparse: ring_rx.c:155:44: warning: Unknown escape '%' Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
2013-06-25netsniff-ng: tpacketv3: 'fix' packet accounting outputDaniel Borkmann1-2/+3
In netsniff-ng, we use tpacketv3 for capturing-only mode. The issue observed lately is that when using f.e. -n10 or capturing a pcap and then quitting, the pcap or actually seen number of packets are less than what the statistics tell us from getsockopt(2). This is due to the fact that tpacketv3 divides its ring buffer into blocks of frames. Meaning, while we are traversing block n, the kernel already fills up block n+1 and following if new packets arrive. While doing so, it increments packet counters. Thus, when we ^C, we haven't seen those blocks, so the stats tell us mostly a slightly higher result. Fix this by adjusting socket stats printing to this fact. Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
2013-06-03netsniff-ng: v3: fix packet accounting on --numDaniel Borkmann1-0/+25
We need to carry frame_count through multiple calls of walk function to account correctly for --num <pkts>. Also, move socket stats printing into rx ring, since it belongs there. Todo: the kernel socket seems to have a different count that what we see. This needs to be fixed one way or the other. Not yet sure what's causing this. Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
2013-05-31ring_rx: if v3, free it in kernel space during closeDaniel Borkmann1-2/+7
Let this be freed by the kernel during close(2) call in case of v3 otherwise we would get a -EINVAL. Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
2013-05-31ring: netsniff-ng: migrate capture only to TPACKET_V3Daniel Borkmann1-1/+1
Lets migrate capturing to TPACKET_V3, since it will bring a better performance due to fewer page cache misses caused by a higher density of packets, since now they are contigous placed in the ring buffer. It is said that TPACKET_V3 brings the following benefits: *) ~15 - 20% reduction in CPU-usage *) ~20% increase in packet capture rate *) ~2x increase in packet density *) Port aggregation analysis *) Non static frame size to capture entire packet payload Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
2013-05-31ring: setup frame structure for v2/v3 in a generic wayDaniel Borkmann1-2/+14
Prepare TPACKET_V3 for allowing to transparently setting up the frame structure such that we do not need to change much in the netsniff-ng/trafgen code. Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
2013-05-31ring: move duplicate/generic code parts from rx/tx into ring.cDaniel Borkmann1-37/+6
We do not want to maintain duplicate code, so move this into a separate file and name those *_generic() helpers. Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
2013-05-31ring: implement setup of tpacket v3 ringDaniel Borkmann1-3/+7
Implement ring setup routines and structures for TPACKET_V3. Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
2013-05-30ring: setup_{rx,tx}_ring_layout: use bool for jumbo_supportDaniel Borkmann1-1/+1
There's no good reason why we currently waste an 'int' for jumbo_support while this must better be done as 'bool'. Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
2013-05-30ring: prepare setup_rx_ring_layout for support in v2/v3Daniel Borkmann1-5/+13
Prepare setup_rx_ring_layout for both, v2 and v3. Also do some checks during compile time if offsets stay the same as we operate on different union mappings. Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
2013-05-30ring: set_sockopt_tpacket: rename to set_sockopt_tpacket_v2Daniel Borkmann1-1/+1
Rename it to set_sockopt_tpacket_v2 so that we later on can also add other versions and have it clearly stated which one we use. Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
2013-03-28ring: purge timer before we unmap tx ring buffersDaniel Borkmann1-1/+1
If we unmap TX ring buffers and still have timer shots that trigger the kernel to traverse the TX_RING, it can send out random crap in some situations. Prevent this by destroying the timer and flush the TX_RING first in wait mode. Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
2013-03-19ring: first unmap, then destroy ring bufferDaniel Borkmann1-4/+3
In both, the RX_RING and TX_RING we need to unmap first and then destroy the buffer, otherwise, we get a device or resource busy. Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
2013-03-16ring: check return value of setsockoptDaniel Borkmann1-2/+7
If something screws up, which is rather unlikely, but if it happens, let the user know. Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
2013-03-15all: import netsniff-ng 0.5.8-rc0 sourceDaniel Borkmann1-0/+130
We decided to get rid of the old Git history and start a new one for several reasons: *) Allow / enforce only high-quality commits (which was not the case for many commits in the history), have a policy that is more close to the one from the Linux kernel. With high quality commits, we mean code that is logically split into commits and commit messages that are signed-off and have a proper subject and message body. We do not allow automatic Github merges anymore, since they are total bullshit. However, we will either cherry-pick your patches or pull them manually. *) The old archive was about ~27MB for no particular good reason. This basically derived from the bad decision that also some PDF files where stored there. From this moment onwards, no binary objects are allowed to be stored in this repository anymore. The old archive is not wiped away from the Internet. You will still be able to find it, e.g. on git.cryptoism.org etc. Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: Tobias Klauser <tklauser@distanz.ch>
generated by cgit v1.2.3-54-g00ecf (git 2.39.0) at 2024-05-17 15:21:31 +0000