|
Atomicity of load and store instructions in eBPF 5 messages
Hello folks, We have an eBPF program that shares a 64-bits integer with userspace using an array map. The eBPF program only reads the integer while the user-space application only writes it. We know t
Hello folks, We have an eBPF program that shares a 64-bits integer with userspace using an array map. The eBPF program only reads the integer while the user-space application only writes it. We know t
|
By Mauricio Vasquez
·
|
|
bpf_map_delet_elem too slow 2 messages
I use simple prog to get stat from my map type BPF_MAP_TYPE_HASH. An got too slow speed to delete elems from it, lookup elem 100-1000x faster. My code is just while(bpf_map_get_next_key(fd, &key,&next
I use simple prog to get stat from my map type BPF_MAP_TYPE_HASH. An got too slow speed to delete elems from it, lookup elem 100-1000x faster. My code is just while(bpf_map_get_next_key(fd, &key,&next
|
By Иван Иванов
·
|
|
minutes: IO Visor TSC/Dev Meeting
Hi All, Thank you for joining us on the call today. As usual, here are the notes. -Brenden === Discussion === Yonghong: - working on libbpf features - working on btf support in bcc - need to use upstr
Hi All, Thank you for joining us on the call today. As usual, here are the notes. -Brenden === Discussion === Yonghong: - working on libbpf features - working on btf support in bcc - need to use upstr
|
By Brenden Blanco
·
|
|
reminder: IO Visor TSC/Dev Meeting
Please join us tomorrow for our bi-weekly call. As usual, this meeting is open to everybody and completely optional. You might be interested to join if: You want to know what is going on in BPF land Y
Please join us tomorrow for our bi-weekly call. As usual, this meeting is open to everybody and completely optional. You might be interested to join if: You want to know what is going on in BPF land Y
|
By Brenden Blanco
·
|
|
Question about BPF map type BPF_MAP_TYPE_PERCPU_HASH 2 messages
Hi everyone, I am using BPF_MAP_TYPE_HASH in BPF map definition and my program is working as expected. I have read eBPF-map type BPF_MAP_TYPE_PERCPU_HASH allows for lock free uses of hash-tables in eB
Hi everyone, I am using BPF_MAP_TYPE_HASH in BPF map definition and my program is working as expected. I have read eBPF-map type BPF_MAP_TYPE_PERCPU_HASH allows for lock free uses of hash-tables in eB
|
By Raga lahari
·
|
|
minutes: IO Visor TSC/Dev Meeting 2 messages
Hi All, Thanks for dialing in to the call today. Here are notes from the discussion. Thanks, Brenden === Discussion === Alexei: * Spinlock patches being worked on * Proposal to standardize the BPF ELF
Hi All, Thanks for dialing in to the call today. Here are notes from the discussion. Thanks, Brenden === Discussion === Alexei: * Spinlock patches being worked on * Proposal to standardize the BPF ELF
|
By Brenden Blanco
·
|
|
reminder: IO Visor TSC/Dev Meeting
Please join us tomorrow for our bi-weekly call. As usual, this meeting is open to everybody and completely optional. You might be interested to join if: You want to know what is going on in BPF land Y
Please join us tomorrow for our bi-weekly call. As usual, this meeting is open to everybody and completely optional. You might be interested to join if: You want to know what is going on in BPF land Y
|
By Brenden Blanco
·
|
|
minutes: IO Visor TSC/Dev Meeting 2 messages
Hi All, Thanks for joining the call today after a short holiday hiatus. Below are my notes from the call. === Discussion === Brenden * Adopted new project kubectl-trace into github.com/iovisor from th
Hi All, Thanks for joining the call today after a short holiday hiatus. Below are my notes from the call. === Discussion === Brenden * Adopted new project kubectl-trace into github.com/iovisor from th
|
By Brenden Blanco
·
|
|
reminder: IO Visor TSC/Dev Meeting
*** Resuming after a holiday break *** Please join us tomorrow for our bi-weekly call. As usual, this meeting is open to everybody and completely optional. You might be interested to join if: You want
*** Resuming after a holiday break *** Please join us tomorrow for our bi-weekly call. As usual, this meeting is open to everybody and completely optional. You might be interested to join if: You want
|
By Brenden Blanco
·
|
|
Can and should you use very large maps with XDP? 2 messages
Is there anything that can go haywire if an eBPF map gets too big in an XDP program? I am looking into importing a large database of unique IPs (10,000-100,000) into a eBPF hash map in a XDP program t
Is there anything that can go haywire if an eBPF map gets too big in an XDP program? I am looking into importing a large database of unique IPs (10,000-100,000) into a eBPF hash map in a XDP program t
|
By liamkelly17@...
·
|
|
I want to messages from iovisor-dev@lists.iovisor.org
I want to messages from iovisor-dev@...
I want to messages from iovisor-dev@...
|
By 李鹏飞
·
|
|
Simple bpf_map reader prog 3 messages
Can you give link or some code to understand, how can i get data from maps in c. I saw example, but as i begginer in such programming, i can understand map_fd, obj...etc. I create xdp prog, inserted i
Can you give link or some code to understand, how can i get data from maps in c. I saw example, but as i begginer in such programming, i can understand map_fd, obj...etc. I create xdp prog, inserted i
|
By Иван Иванов
·
|
|
Xdpoffload list avaliable devices 2 messages
Yes currently i believe only Netronome NFP based Agilio CX NICs support xdpoffload.
Yes currently i believe only Netronome NFP based Agilio CX NICs support xdpoffload.
|
By Иван Иванов
·
|
|
Unexpectedly high latencies are showed by self-written script (bpf_ktime_get_ns issue?) 4 messages
Hi, everyone! I've written a small script using bcc python lib for qemu block io latency tracing. I attach two uprobes to block_acct_start and block_acct_done. On some servers i can see unexpectedly h
Hi, everyone! I've written a small script using bcc python lib for qemu block io latency tracing. I attach two uprobes to block_acct_start and block_acct_done. On some servers i can see unexpectedly h
|
By Aleksei Zakharov
·
|
|
question about per_cpu maps 4 messages
Dear eBPF community If I understand correctly, per_cpu maps are meant to avoid threading issues, and for example the need to call BPF_XADD to keep counters safe. There is something I am unclear about:
Dear eBPF community If I understand correctly, per_cpu maps are meant to avoid threading issues, and for example the need to call BPF_XADD to keep counters safe. There is something I am unclear about:
|
By Pablo Alvarez
·
|
|
[PATCHv3 RFC 2/3] tests: add AF_XDP netdev test cases.
The patch adds the test framework for OVS using afxdp. Most of the test cases are slightly modified from the existing test cases at system-traffic.at. All the veth creations, ADD_VETH, are replaced by
The patch adds the test framework for OVS using afxdp. Most of the test cases are slightly modified from the existing test cases at system-traffic.at. All the veth creations, ADD_VETH, are replaced by
|
By William Tu
·
|
|
[PATCHv3 RFC 3/3] FIXME: work around the failed cases.
There are still two issues causing some test cases failed. This patch provides an work-around. Signed-off-by: William Tu <u9012063@...> --- lib/dpif-netdev.c | 2 +- tests/system-afxdp-macros.at | 2 ++
There are still two issues causing some test cases failed. This patch provides an work-around. Signed-off-by: William Tu <u9012063@...> --- lib/dpif-netdev.c | 2 +- tests/system-afxdp-macros.at | 2 ++
|
By William Tu
·
|
|
[PATCHv3 RFC 1/3] netdev-afxdp: add new netdev type for AF_XDP
The patch creates a new netdev type called "afxdp" and re-uses some of the AF_XDP API implementation from xdpsock_user.c at linux sample code. By default, it binds a device's queue 0 and uses the gene
The patch creates a new netdev type called "afxdp" and re-uses some of the AF_XDP API implementation from xdpsock_user.c at linux sample code. By default, it binds a device's queue 0 and uses the gene
|
By William Tu
·
|
|
[PATCHv3 RFC 0/3] AF_XDP netdev support for OVS
The patch series introduces AF_XDP support for OVS netdev. AF_XDP is a new address family working together with eBPF. In short, a socket with AF_XDP family can receive and send packets from an eBPF/XD
The patch series introduces AF_XDP support for OVS netdev. AF_XDP is a new address family working together with eBPF. In short, a socket with AF_XDP family can receive and send packets from an eBPF/XD
|
By William Tu
·
|
|
minutes: IO Visor TSC/Dev Meeting
Thanks all for joining in to the call today. As usual, here are my notes. === Discussion === Jiong: Continuing work on jmp32 - some work on verifier side - needs to work on test support - new test mod
Thanks all for joining in to the call today. As usual, here are my notes. === Discussion === Jiong: Continuing work on jmp32 - some work on verifier side - needs to work on test support - new test mod
|
By Brenden Blanco
·
|