Re: [vpp-dev] heap sizes

2021-07-01 Thread Matthew Smith via lists.fd.io
On Thu, Jul 1, 2021 at 10:07 AM Damjan Marion wrote: > > > > On 01.07.2021., at 16:12, Matthew Smith wrote: > > > > > > > > On Thu, Jul 1, 2021 at 6:36 AM Damjan Marion wrote: > > > > > > > On 01.07.2021., at 11:12, Benoit Ganne (bganne) via lists.fd.io > wrote: > > > > > >> Yes, allowing dyna

Re: [vpp-dev] heap sizes

2021-07-01 Thread Damjan Marion via lists.fd.io
> On 01.07.2021., at 16:12, Matthew Smith wrote: > > > > On Thu, Jul 1, 2021 at 6:36 AM Damjan Marion wrote: > > > > On 01.07.2021., at 11:12, Benoit Ganne (bganne) via lists.fd.io > > wrote: > > > >> Yes, allowing dynamic heap growth sounds like it could be better. > >> Alternatively..

Re: [vpp-dev] heap sizes

2021-07-01 Thread Matthew Smith via lists.fd.io
On Thu, Jul 1, 2021 at 6:36 AM Damjan Marion wrote: > > > > On 01.07.2021., at 11:12, Benoit Ganne (bganne) via lists.fd.io cisco@lists.fd.io> wrote: > > > >> Yes, allowing dynamic heap growth sounds like it could be better. > >> Alternatively... if memory allocations could fail and somethin

Re: [vpp-dev] heap sizes

2021-07-01 Thread Damjan Marion via lists.fd.io
> On 01.07.2021., at 11:12, Benoit Ganne (bganne) via lists.fd.io > wrote: > >> Yes, allowing dynamic heap growth sounds like it could be better. >> Alternatively... if memory allocations could fail and something more >> graceful than VPP exiting could occur, that may also be better. E.g. if >

Re: [vpp-dev] heap sizes

2021-07-01 Thread Benoit Ganne (bganne) via lists.fd.io
> Yes, allowing dynamic heap growth sounds like it could be better. > Alternatively... if memory allocations could fail and something more > graceful than VPP exiting could occur, that may also be better. E.g. if > I'm adding a route and try to allocate a counter for it and that fails, it > would b

Re: [vpp-dev] heap sizes

2021-06-30 Thread Matthew Smith via lists.fd.io
On Wed, Jun 30, 2021 at 3:01 AM Benoit Ganne (bganne) wrote: > > What I'm trying to figure out is this: do I need to try and determine a > > formula for the sizes that should be used for main heap and stat segment > > based on X number of routes and Y number of worker threads? Or is there a > > d

Re: [vpp-dev] heap sizes

2021-06-30 Thread Benoit Ganne (bganne) via lists.fd.io
> What I'm trying to figure out is this: do I need to try and determine a > formula for the sizes that should be used for main heap and stat segment > based on X number of routes and Y number of worker threads? Or is there a > downside to just setting the main heap size to 32G (which seems like a >

Re: [vpp-dev] heap sizes

2021-06-29 Thread Matthew Smith via lists.fd.io
Hi Pim, The defaults we use are 96M for stat segment and 1G for main heap (default main heap size). I know these need to scale up as the numbers of routes and/or threads increase. These values can accommodate a million routes or so when running single threaded, but allocations on the stat segment

Re: [vpp-dev] heap sizes

2021-06-28 Thread Pim van Pelt
Hoi Matt, Out of curiosity how large is your heap and stats segment? I ask because running VPP with a large FIB I needed 2G heap size (and I used page size of 2M), and 96M of statsseg: memory { main-heap-size 3G main-heap-page-size 2M } statseg { socket-name /run/vpp/stats.sock size

[vpp-dev] heap sizes

2021-06-28 Thread Matthew Smith via lists.fd.io
Hi all, It's my understanding that when you set the size of the main heap or the stat segment in startup.conf, the size you specify is used to set up virtual address space and the system does not actually allocate that full amount of memory to VPP. I think when VPP tries to read/write addresses wi