wiki:replication_distribution

Version 43 (modified by alain, 4 months ago) (diff)

--

Data replication & distribution policy

The replication / distribution policy of user processes has two goals: enforce locality (as much as possible), and avoid contention (it is the main goal).

  • The read-only segment containing the user code is replicated in all clusters where there is at least one thread using it.
  • The private segment containing the stack for a given thread is placed in the same cluster as the thread using it.
  • The shared segment containing the global data is distributed on all clusters as regularly as possible to avoid contention.
  • The segments dynamically allocated by the mmap() system call are placed as described below.

To actually control data placement on the physical memory banks, the kernel uses the paged virtual memory MMU to map a virtual segment to a given physical memory bank.

This replication / distribution policy is implemented by the Virtual Memory Manager (in the vmm.h and vmm.c files).

A vseg is a contiguous memory zone in the process virtual space, where all adresses in this vseg can be accessed by the process without segmentation violation: if the corresponding is not mapped, the page fault will be handled by the kernel, and a physical page will be dynamically allocated and initialized if required. A vseg always contains an integer number of pages. Depending on its type, a vseg has some specific attributes regarding access rights, replication policy, and distribution policy. The vseg descriptor is defined by the structure vseg_t.

For each process P, the process descriptor is replicated in all clusters containing at least one thread of P, and these clusters are called active clusters. More precisely, the virtual memory manager VMM(P,K) of process P in active cluster K, contains two main structures:

  • The VSL(P,K) is the list of all vsegs registered for process P in cluster K,
  • The GPT(P,K) is the generic page table, defining the actual physical mapping of those vsegs.

1) User segments types and attributes

  • A vseg is public when it can be accessed by any thread T of the process, whatever the cluster running the thread T. It is private when it can only be accessed by the threads running in the cluster containing the physical memory bank where this vseg is mapped. A private vseg is entirely mapped in one single cluster K.
  • For a public vseg, ALMOS-MKH implements a global mapping : In all clusters, a given virtual address is mapped to the same physical address. For a private vseg, ALMOS-MKH implements a local mapping : the same virtual address can be mapped to different physical addresses, in different clusters.
  • A public vseg can be localized (all vseg pages are mapped in the same cluster), or distributed (different pages are mapped on different clusters, using the virtual page number (VPN) least significant bits as distribution key). A private vseg is always localized.

ALMOS-MK defines six vseg types in vseg_type_t:

Type Access Replication Placement Allocation policy in user space
STACK private localized Read Write one physical mapping per thread same cluster as thread using it dynamic (one stack allocator per cluster)
CODE private localized Read Only one physical mapping per cluster same cluster as thread using it static (defined in .elf file)
DATA public distributed Read Write same mapping for all threads distributed on all clusters static (defined in .elf file)
ANON public localized Read Write same mapping for all threads same cluster as calling thread dynamic (one heap allocator per process
FILE public localized Read Write same mapping for all threads same cluster as the file cache dynamic (one heap allocator per process)
REMOTE public localized Read Write same mapping for all threads cluster defined by user dynamic (one heap allocator per process)
  1. CODE : This private vseg contains the user application code. ALMOS-MK creates one CODE vseg per active cluster. For a process P, the CODE vseg is registered in the VSL(P,Z) when the process is created in reference cluster Z. In the other clusters X, the CODE vseg is registered in VSL(P,X) when a page fault is signaled by a thread of P running in cluster X. In each active cluster X, the CODE vseg is localized, and physically mapped in cluster X.
  2. DATA : This vseg contains the user application global data. ALMOS-MK creates one single DATA vseg per process, that is registered in the reference VSL(P,Z) when the process P is created in reference cluster Z. In the other clusters X, the DATA vseg is registered in VSL(P,X) when a page fault is signaled by a thread of P running in cluster X. To avoid contention, this vseg is physically distributed on all clusters, with a page granularity. For each page, the physical mapping is defined by the LSB bits of the page VPN.
  3. STACK : This private vseg contains the execution stack of a thread. For each thread T of process P running in cluster X, ALMOS_MK creates one STACK vseg. This vseg is registered in the VSL(P,X) when the thread descriptor is created in cluster X. To enforce locality, this vseg is physically mapped in cluster X.
  4. ANON : This type of vseg is dynamically created by ALMOS-MK to serve an anonymous mmap() system call executed by a client thread running in a cluster X. The first vseg registration and the physical mapping are done by the reference cluster Z, but the vseg is mapped in the client cluster X.
  5. FILE : This type of vseg is dynamically created by ALMOS-MK to serve a file based mmap() system call executed by a client thread running in a cluster X. The first vseg registration and the physical mapping are done by the reference cluster Z, but the vseg is mapped in cluster Y containing the file cache.
  6. REMOTE : This type of vseg is dynamically created by ALMOS-MK to serve a remote mmap() system call where a client thread running in a cluster X requests to create a new vseg mapped in another cluster Y. The first vseg registration and the physical mapping are done by the reference cluster Z, but the vseg is mapped in cluster Y specified by the user.

The replication of the VSL(P,K) and GPT(P,K) kernel structures creates a coherence problem for the non private vsegs.

  • A VSL(P,K) contains all private vsegs in cluster K, but contains only the public vsegs that have been actually accessed by a thread of P running in cluster K. Only the reference process descriptor stored in the reference cluster Z contains the complete list VSL(P,Z) of all public vsegs for the P process.
  • A GPT(P,K) contains all mapped entries corresponding to private vsegs. For public vsegs, it contains only the entries corresponding to pages that have been accessed by a thread running in cluster K. Only the reference cluster Z contains the complete GPT(P,Z) page table of all mapped entries for process P.

Therefore, the process descriptors - other than the reference one - can be considered as read-only caches. When a given vseg or a given entry in the page table must be removed by the kernel, this modification must be done first in the reference cluster, and broadcast to all other clusters for update.

2) 32 bits virtual space organisation

The virtual address space of an user process P is split in 5 fixed size zones, defined by configuration parameters in https://www-soc.lip6.fr/trac/almos-mkh/browser/trunk/kernel/kernel_config.h. Each zone contains one or several vsegs, as described below.

The kernel zone

It contains the kcode vseg (type KCODE), that must be mapped in all user process to support syscalls. It is located in the lower part of the virtual space, and starts a address 0. Its size cannot be less than a big page size (2 Mbytes for the TSAR architecture), because it will be mapped as one or several big pages.

The utils zone

It contains the two args and envs vsegs, whose sizes are defined by specific configuration parameters.

  • The args vseg (DATA type) contains the process main() arguments.
  • The envs vseg (DATA type) contains the process environment variables.

It is located on top of the kernel zone, and starts at address defined by the CONFIG_VMM_ELF_BASE parameter.

The elf zone

It contains the text (CODE type) and data (DATA type) vsegs, defining the process binary code and global data. The actual vsegs base addresses and sizes are defined in the .elf file and reported in the boot_info_t structure by the boot loader.

The heap zone

It contains all vsegs dynamically allocated / released by the mmap() / munmap() system calls (i.e. FILE / ANON / REMOTE types). It is located on top of the elf zone, and starts at the address defined by the CONFIG_VMM_HEAP_BASE parameter. The VMM defines a specific MMAP allocator for this zone, implementing the buddy algorithm. The mmap( FILE ) syscall maps directly a file in user space. The user level malloc library uses the mmap( ANON ) syscall to allocate virtual memory from the heap and map it in the same cluster as the calling thread. Besides the standard malloc() function, this library implements a non-standard remote_malloc() function, that uses the mmap( REMOTE ) syscall to dynamically allocate virtual memory from the heap, and map it to a remote physical cluster.

The stack zone

It is located on top of the mmap zone and starts at the address defined by the CONFIG_VMM_STACK_BASE parameter. It contains an array of fixed size slots, and each slot contains one stack vseg. The size of a slot is defined by the CONFIG_VMM_STACK_SIZE. In each slot, the first page is not mapped, in order to detect stack overflows. As threads are dynamically created and destroyed, the VMM implements a specific STACK allocator for this zone, using a bitmap vector. As the stack vsegs are private (the same virtual address can have different mappings, depending on the cluster) the number of slots in the stack zone actually defines the max number of threads for given process in a given cluster.